1
00:00:00,100 --> 00:00:10,100
Ping Yu: (on-hold music) Welcome to the Blooms and Beyond podcast, a podcast that uncovers plant health history,

2
00:00:10,260 --> 00:00:12,620
culture, and management through the lens of science.

3
00:00:13,000 --> 00:00:14,000
I'm your host, Ping.

4
00:00:14,340 --> 00:00:15,440
How's everyone doing today?

5
00:00:15,840 --> 00:00:25,060
I am doing great 'cause I'm about to talk to one of my favorite people here and one of the most exciting topics on today's episode, drone application in the,

6
00:00:25,360 --> 00:00:31,440
in green- in the nursery and greenhouse with Dr. James Robbins and Joe Maja.

7
00:00:32,460 --> 00:00:35,760
So I don't wanna steal any more thunder from our speaker today.

8
00:00:35,940 --> 00:00:41,020
Without further ado, here are the conversations with Dr. Joe Maja and James Robbins.

9
00:00:41,180 --> 00:00:42,040
I hope you enjoy.

10
00:00:43,460 --> 00:00:46,740
Good morning, Doctors James Robbins and Joe Maja.

11
00:00:46,880 --> 00:00:48,080
Welcome to the podcast.

12
00:00:48,200 --> 00:00:51,060
But first, let's start off with the introduction.

13
00:00:51,120 --> 00:00:57,059
Can you guys tell us a little bit about who you are and what you do?

14
00:00:57,120 --> 00:00:58,190
Jim Robbins: Yeah, I'll jump in first.

15
00:00:58,200 --> 00:00:59,670
Thanks, Ping, for the invitation.

16
00:01:00,210 --> 00:01:08,640
So Jim Robbins, I'm a retired extension specialist and professor in commercial ornamental horticulture at the University of Arkansas Division of Agriculture.

17
00:01:09,600 --> 00:01:19,920
For over 23 years with the University of Arkansas, provided support for green industry businesses across the state, focusing on nursery production and woody plant

18
00:01:20,000 --> 00:01:20,840
evaluation.

19
00:01:21,400 --> 00:01:31,440
And as we'll get into a deep dive, in about the last 15 years, got very heavily involved with, with drones, thanks to my collaborative

20
00:01:31,620 --> 00:01:36,440
friendship interaction with Dr. Joe Maja, who's our second speaker.

21
00:01:37,960 --> 00:01:39,200
Joe, do you wanna take over from here?

22
00:01:39,620 --> 00:01:41,000
Joe Maja: Hi, I'm Joe Maja.

23
00:01:41,180 --> 00:01:49,360
I'm currently the director of the Center for Applied AI for Sustainable Agriculture at South Carolina State University.

24
00:01:49,400 --> 00:01:59,880
My background is in engineering with a focus on robotics, unmanned aerial systems, remote sensing, and more recently, integrating AI into agricultural applications.

25
00:02:01,000 --> 00:02:04,140
Over the years, my work has evolved beyond just drones.

26
00:02:04,280 --> 00:02:14,340
Uh, we've been working on systems that combine UAVs and ground-based robotics, RFID technologies, and data analytics platform to address real-world challenges in ag,

27
00:02:14,700 --> 00:02:17,280
particularly in nursery and specialty crop production.

28
00:02:17,780 --> 00:02:26,180
So a big part of what I do is taking advanced engineering concepts and translating them into something practical and usable for growers.

29
00:02:26,660 --> 00:02:31,020
And that's really where the collaboration with Jim has been so valuable.

30
00:02:31,060 --> 00:02:36,840
He brings deep expertise in horticulture and production system, and I bring the engineering and systems integration side.

31
00:02:36,860 --> 00:02:44,660
So together, we've been able to develop solutions that are not only technically sound, but also meaningful and applicable in real operations.

32
00:02:44,720 --> 00:02:45,460
Ping Yu: Okay, thank you.

33
00:02:45,560 --> 00:02:56,360
So it's, it's kind of interesting for today's episode because normally we would have only one expert to talk about a certain topic, but today our two speakers, they

34
00:02:56,540 --> 00:02:59,740
come from very different backgrounds.

35
00:03:01,740 --> 00:03:10,940
(on-hold music) But can you tell us a little bit about like for Dr. James Robbins, can you tell us a little bit about like how did you start with horticulture?

36
00:03:11,060 --> 00:03:21,260
Is this something interested, uh, is this something interesting to you when you were a child, and how did you end up-- Can you walk us through, like, your career

37
00:03:21,360 --> 00:03:23,060
journey in horticulture in general?

38
00:03:24,860 --> 00:03:26,860
Jim Robbins: Yeah, I'll give a, a brief background on that.

39
00:03:27,080 --> 00:03:37,320
So I was raised in, uh, Wisconsin, started working at a nursery, a really prominent nursery and garden center in Wisconsin, probably at age fifteen, and just really knew

40
00:03:37,380 --> 00:03:38,520
that I loved plants.

41
00:03:38,780 --> 00:03:47,960
Was fortunate, uh, went to the University of Wisconsin, Madison, had an exceptional undergrad advisor that really recognized my enthusiasm for plants.

42
00:03:48,300 --> 00:03:57,000
Uh, then I was very fortunate, uh, to go on and get a master's with Michael Dirr at his first, uh, few years at the University of Georgia, and at

43
00:03:57,040 --> 00:04:01,980
that time, he was also the, uh, director of the, uh, State Botanical Garden.

44
00:04:02,660 --> 00:04:06,320
And so each of the grad-- the new grad students, we had a role there.

45
00:04:06,740 --> 00:04:18,060
Then went out, uh, but it was just, you know, I look back and I've blessed with great prominent mentors to just, uh, continue feeding my, my, uh, interest

46
00:04:18,079 --> 00:04:19,280
in, in, in plants.

47
00:04:19,480 --> 00:04:24,640
Went out to UC Davis, uh, uh, where I got my PhD in plant physiology.

48
00:04:25,020 --> 00:04:35,240
And then over my professional career, I-- the breakdown is probably like, uh, I had a, a unique mix, nine years in industry, and then the remainder, probably

49
00:04:35,320 --> 00:04:37,980
whatever it is, twenty-three years, in academia.

50
00:04:38,080 --> 00:04:44,200
So kind of a unique opportunity to be on both, both sides of the, uh, both sides of the fence.

51
00:04:45,120 --> 00:04:54,520
Um, real quickly, I, 'cause I think it's very important 'cause you, you mentioned it, it's kinda unique that you've got two speakers and they're from two dis- different disciplines.

52
00:04:54,740 --> 00:05:00,380
I really wanna point this out because, uh, I'm very fortunate and the industry is fortunate.

53
00:05:00,480 --> 00:05:10,540
Back in 2009, I was at a very prominent field nursery in the Pacific Northwest, and they had raised a question about, gosh, is there

54
00:05:10,620 --> 00:05:10,900
a...

55
00:05:11,040 --> 00:05:11,840
Was I aware of a,

56
00:05:13,120 --> 00:05:16,000
a way to automate inventory for nurseries?

57
00:05:16,320 --> 00:05:24,640
And I was just shocked that we really didn't have beyond manual counting, which is really, uh, the prominent method.

58
00:05:24,740 --> 00:05:34,940
So on my return to the University of Arkansas, I talked to my bio and ag engineering colleague, uh, Dharmendra Saraswat, who had just come on board from

59
00:05:34,980 --> 00:05:41,540
the University of Florida, and, uh, his prior major professor, Reza Ehsani.

60
00:05:42,280 --> 00:05:49,700
They had just completed some work looking at kind of inventorying, uh, or looking at parameters of citrus groves, so they could count them.

61
00:05:49,780 --> 00:05:54,480
They could also measure the canopy volume, which would help them predict, uh, yield.

62
00:05:55,816 --> 00:06:03,975
And so at the time, Joe was there, and we all, uh, got together and, uh, with, maybe no funding.

63
00:06:04,036 --> 00:06:07,056
We-- So this is back in 2009.

64
00:06:07,676 --> 00:06:16,056
We went out to this nursery and w-we're using a ground-based method to try to improve inventory and field nurseries.

65
00:06:16,076 --> 00:06:17,916
And so that's the first time I really met Joe.

66
00:06:18,356 --> 00:06:20,256
Uh, we just really hit it off.

67
00:06:20,396 --> 00:06:27,516
I was just-- He's just, uh, brilliant, uh, and just a great, uh, you know, great human being.

68
00:06:27,635 --> 00:06:29,576
So then it was in, uh...

69
00:06:29,716 --> 00:06:34,336
For a variety of reasons, we dropped the ground method in spring of 2010.

70
00:06:34,456 --> 00:06:36,336
So think about that, it's fifteen years ago.

71
00:06:36,456 --> 00:06:37,476
Joe had kind of

72
00:06:39,016 --> 00:06:42,956
caught the early, uh, whiff of these drones being used.

73
00:06:42,996 --> 00:06:44,796
And this-- they were hobbies at this time.

74
00:06:44,976 --> 00:06:47,296
People don't-- uh, can't appreciate.

75
00:06:47,556 --> 00:06:50,816
If, if you're jumping into this today, you're saying, "Gosh, this is a piece of cake.

76
00:06:50,896 --> 00:06:52,916
These are easy to fly, they're inexpensive.

77
00:06:52,976 --> 00:06:57,956
The flight's navigation software is, is, um, you know, wonderful."

78
00:06:58,116 --> 00:07:00,956
But that really didn't exist in 2010.

79
00:07:01,096 --> 00:07:07,156
These were mostly, uh, built kits, and Joe built, uh, quite a few for our various projects.

80
00:07:07,776 --> 00:07:09,096
They were difficult to fly.

81
00:07:09,536 --> 00:07:12,856
Uh, we didn't have the fancy flight navigation software.

82
00:07:12,976 --> 00:07:21,456
But we jumped into this with the thought that maybe we could use drones in this, uh, plant inventory process.

83
00:07:21,736 --> 00:07:26,036
And that really was for any open field application was the thought at that time.

84
00:07:27,076 --> 00:07:30,536
And so over the years, you know, we've, uh, we've worked on that.

85
00:07:30,756 --> 00:07:41,416
I had a great, uh, master's student, uh, Josue Nahum Leiva, who did his master's, uh, project, uh, looking at analyzing,

86
00:07:41,536 --> 00:07:43,316
uh, aerial images for counting.

87
00:07:43,336 --> 00:07:45,856
And that is one approach that can be used.

88
00:07:45,876 --> 00:07:48,376
There's a number of companies that offer that service.

89
00:07:48,496 --> 00:07:49,936
Actually, it's called plant counting.

90
00:07:50,076 --> 00:07:51,776
So that is available.

91
00:07:52,016 --> 00:08:02,396
But then we kind of evolved into, uh, a collaboration with, uh, Tom Fernandez at Michigan State, who is interested in RFID tags, and that ev-- kind of transitioned

92
00:08:02,436 --> 00:08:13,536
into our recent grant-funded project, which is, uh, to try to use RFID tags, um, and either a handheld

93
00:08:13,616 --> 00:08:23,426
or a drone-based, uh, reader to improve, or automate, uh, inventory for, again, uh, for nurseries or, you know, for greenhouses.

94
00:08:24,296 --> 00:08:29,096
And so it's been a, you know, an evolution, uh, you know, o-over, over time.

95
00:08:29,345 --> 00:08:32,016
And, uh, but Joe has been a, a key component.

96
00:08:32,216 --> 00:08:34,256
I, I, I'm not an engineer.

97
00:08:34,496 --> 00:08:35,535
I don't, you know.

98
00:08:35,776 --> 00:08:36,336
And so

99
00:08:37,616 --> 00:08:41,636
I encourage others that are involved in these kind of projects.

100
00:08:41,736 --> 00:08:51,816
I mean, I help Joe kind of understand the production issues, and that helps feed into his, you know, improving his

101
00:08:51,856 --> 00:08:53,956
designs of engineering solutions.

102
00:08:54,196 --> 00:09:03,816
So it's been a wonderful collaboration, and it-- but it's been necessary because we kind of need both components to provide a, a successful, uh, solution.

103
00:09:03,936 --> 00:09:07,516
So with that, I'll, I'll stop and turn it over to Joe.

104
00:09:07,576 --> 00:09:16,096
But again, I, you know, want to point out that, yeah, this has been a, for me, just a blessing to have this serendipitous, uh, run in with Joe back

105
00:09:16,136 --> 00:09:17,236
in 2009.

106
00:09:17,256 --> 00:09:27,216
And then, you know, just the, uh, realization that, you know, we could become a rather a good collaborative, uh, team and, uh, friends over this many years.

107
00:09:27,276 --> 00:09:29,716
So Joe, over, over to you.

108
00:09:29,776 --> 00:09:30,136
Joe Maja: Yes.

109
00:09:30,176 --> 00:09:40,516
From my perspective, those early years around 2009 and 2010 were really about experimentation and trying to solve a very specific problem, uh, inventory

110
00:09:40,596 --> 00:09:41,716
management in nurseries.

111
00:09:42,596 --> 00:09:49,276
So at that time, we initially explored ground-based solutions, thinking that mobile systems could navigate through rows and track plans.

112
00:09:50,436 --> 00:09:54,456
But it didn't take long to realize that scalability was a major limitation.

113
00:09:55,356 --> 00:10:00,816
The environment was too complex, and the effort required just didn't match the efficiency we were hoping to achieve.

114
00:10:00,976 --> 00:10:04,796
So around the same time, I started seeing early drone platforms.

115
00:10:05,056 --> 00:10:09,296
These were not the commercial systems we have today, but more like hobbyist kits.

116
00:10:09,366 --> 00:10:15,595
Still, it was clear that the aerial perspective offered a completely different way to approach the problem.

117
00:10:15,756 --> 00:10:25,476
So what made the collaboration work so well was that Jim helped me understand the operational challenges from a growth perspective, and I could then think about how to design

118
00:10:25,516 --> 00:10:28,876
systems that actually address those challenges in a scalable way.

119
00:10:28,936 --> 00:10:38,985
Ping Yu: Yeah, 'cause I think you guys are a perfect example of how important or how unique the collaboration can be in terms of your professional development and

120
00:10:39,076 --> 00:10:39,596
friendship.

121
00:10:39,636 --> 00:10:49,196
Uh, uh, I know, I know you guys for a long time, and I know y- like, collaboration, like you guys, where the relationship between you two are like something

122
00:10:49,376 --> 00:10:49,816
unique.

123
00:10:49,876 --> 00:10:59,956
And then for right now in agriculture in general, it needs multi-discipline collaboration to make things work, and then you guys are a perfect example

124
00:11:00,036 --> 00:11:00,576
for that.

125
00:11:01,016 --> 00:11:02,976
But Joe, can I ask you this.

126
00:11:03,076 --> 00:11:10,796
Do you know plant or do you cl-- Will you say you're a plant person before you met James?

127
00:11:12,116 --> 00:11:13,416
Joe Maja: Honestly, no.

128
00:11:13,996 --> 00:11:22,696
So I wasn't a plant person before working with James, and my training was purely in engineering, so I approached everything from a systems and problem-solving perspective.

129
00:11:22,996 --> 00:11:30,476
But through the collaboration, I gained a much deeper appreciation for how complex and dynamic nursery systems really are.

130
00:11:30,536 --> 00:11:36,976
So it's not just about plants, it's about logistics, timing, environmental condition, and operational efficiency.

131
00:11:37,316 --> 00:11:47,356
So in many ways, uh, it became a true interdisciplinary experience, and Jim helped me understand the plant and production side, and I helped bring in

132
00:11:47,376 --> 00:11:51,596
the technology, and that combination is really what made the work successful.

133
00:11:52,416 --> 00:12:02,836
Ping Yu: See, that's, that's a unique part, and James kind of introduced you to the plant world while you kind of drag him into the more fun drone project.

134
00:12:02,906 --> 00:12:04,296
So that's, that's very unique.

135
00:12:04,416 --> 00:12:06,436
That, that's what I see here.

136
00:12:07,220 --> 00:12:13,600
Jim Robbins: Uh, but before- Yeah, and I, and, you know, I kind of dragged Joe (laughs) probably unwillingly into this.

137
00:12:14,020 --> 00:12:17,120
I kept, you know, bringing up ideas of, of projects.

138
00:12:17,160 --> 00:12:27,030
Again, because of his expertise, again, as he says, in remote sensing and robotics, I mean, he does a lot of work on ground-based unmanned vehicles and, and aerial, you

139
00:12:27,060 --> 00:12:27,660
know, vehicles.

140
00:12:27,780 --> 00:12:32,040
But, you know, his, his breadth of knowledge and skill set is, is just tremendous.

141
00:12:32,140 --> 00:12:41,260
So we talk about the problems, and then he's just been phenomenal in, you know, coming up with workable, you know, solutions.

142
00:12:41,290 --> 00:12:50,380
And I want to emphasize, you know, since the majority of our work is in outdoor, out nurs- in nursery production things, it, it's very challenging, and I think Joe

143
00:12:50,400 --> 00:12:51,379
would agree with that.

144
00:12:51,460 --> 00:12:54,120
(laughs) You know, we talk about, like, using...

145
00:12:54,180 --> 00:13:04,390
If you wanted to get RFID and inventory in a, a heating/cooled warehouse with a concrete floor and racks that are very uniform and all that kind of stuff, that,

146
00:13:04,460 --> 00:13:06,960
that's well, well-researched.

147
00:13:07,200 --> 00:13:17,280
But boy, when we start running equipment out in agriculture, you know, where you've got dust and dirt and wind and rain and sun, it's,

148
00:13:17,360 --> 00:13:21,320
it's the transfer of knowledge is not as easy.

149
00:13:21,380 --> 00:13:24,570
And so I think people in the industry appreciate that.

150
00:13:24,800 --> 00:13:34,820
If you think of the harvest robotics and the container moving device and the number of iterations where, you know, they needed to look at the difference in container

151
00:13:34,840 --> 00:13:38,200
bed layouts and the types of materials that are used.

152
00:13:38,280 --> 00:13:43,820
But the outdoor environment is very rough on engineered solutions.

153
00:13:43,910 --> 00:13:53,780
And so hopefully people understand and appreciate that it's definitely much more difficult than, say, in a controlled environment situation.

154
00:13:53,840 --> 00:13:54,770
Ping Yu: Yeah, I agree with that.

155
00:13:54,800 --> 00:14:01,480
And I still-- I want to thank you guys for your hard work because what I remember when I was going through some of my slides for one of my

156
00:14:01,520 --> 00:14:11,440
class that I'm teaching, and there was one slide with you, Dr. James Robins, your, uh, your quote was, I think it was based on one of the projects that

157
00:14:11,500 --> 00:14:21,600
you have done back then in maybe 2010, 2012, about your predictory for the future in nursery production was,

158
00:14:21,720 --> 00:14:30,360
like, the automation would be one of the op- pioneering method or two for our industry to kind of involve.

159
00:14:30,480 --> 00:14:39,400
And it's true right now because over the past couple years, I don't know if you guys have noticed that, but in here in Georgia and I know in other

160
00:14:39,460 --> 00:14:49,880
states, not just in the institution perspective, we have hired a lot of people from the, the precision ag, with people who emphasize

161
00:14:49,940 --> 00:14:58,660
more in engineering and focusing on automation and applica- uh, like, advanced technology application in agriculture in general.

162
00:14:58,780 --> 00:15:08,880
So I've seen the trend of making the-- or adapting the more advanced technology into agriculture, which is great

163
00:15:08,980 --> 00:15:15,220
because I think one of the top issues everywhere you go, people will say labor is a top issue.

164
00:15:15,380 --> 00:15:21,859
And using those advanced technology in agriculture would be one of the tools to address the issue.

165
00:15:24,920 --> 00:15:34,380
But before we jump into it, can you j- guys give us, like, for people out there who doesn't know a whole, a whole lot of those advanced technology in,

166
00:15:34,440 --> 00:15:41,600
in agriculture, can you just give us a brief introduction of the UAVs and what type of drones are out there?

167
00:15:42,080 --> 00:15:49,720
I know people, there are personal use for drones just for the hobbies and taking pictures and doing v- vlogs.

168
00:15:50,160 --> 00:15:57,960
But for the commercial use in agriculture in general, I know a lot of nursery and greenhouses growers are trying to adapt more.

169
00:15:58,100 --> 00:16:01,820
Can you just give us a little bit about, like, the big picture out there?

170
00:16:03,080 --> 00:16:03,180
Jim Robbins: Yeah.

171
00:16:03,190 --> 00:16:08,200
And I think the other thing, yeah, one addition to, yeah, there's this terminology which has evolved.

172
00:16:08,240 --> 00:16:18,340
It's, it's-- Joe and I can, again, because we were really at the earliest stages of the explosion of these drones or UAVs, UAS, whatever

173
00:16:18,360 --> 00:16:26,380
you want to call it, in our group, we actually had to-- we came up with several names at that time because we didn't even know how to describe it.

174
00:16:26,409 --> 00:16:31,220
And we had a meeting with FAA early on, and they said, "Oh, don't-- You can't use that word."

175
00:16:31,920 --> 00:16:39,920
And so it's interesting the nomenclature, how even that was not, 15 years ago, was not hard and fast.

176
00:16:40,120 --> 00:16:42,240
It was still a debated point.

177
00:16:42,320 --> 00:16:46,099
So it's just, again, interesting in 15 years to see the evolution over time.

178
00:16:46,460 --> 00:16:53,480
But one thing is, so there are these two names, UAV, unmanned aerial vehicle, or UAS, unmanned aerial system.

179
00:16:53,940 --> 00:17:00,760
So if you've got a sprayer or you've got the payload is a sensor, you might want to call it a system, I guess.

180
00:17:00,800 --> 00:17:04,740
If you're just flying the aircraft, it could just be unmanned aerial vehicle.

181
00:17:05,260 --> 00:17:08,580
And then there's recognized basically two categories.

182
00:17:08,640 --> 00:17:18,740
So a number of years ago, back, I think it's 2016, the FAA finally came up with kind of some very defined regulations related

183
00:17:18,820 --> 00:17:26,180
to UAVs, and so they defined something called the small, so small UAV, small UAS.

184
00:17:26,640 --> 00:17:35,000
And what that meant was when the unit takes off the ground, so it's the aircraft and the payload, if you were to put that on a balance and it

185
00:17:35,060 --> 00:17:39,220
weighed less than 55 pounds, it fits into a category called small.

186
00:17:39,910 --> 00:17:49,980
And so it's important because a lot of the early regulations, there was a lot of detail related to that, and getting licensed in a

187
00:17:50,420 --> 00:17:53,660
SUS application was very, you know, achievable.

188
00:17:54,520 --> 00:17:59,540
It doesn't mean that you can't fly a drone that weighs more than 55 pounds.

189
00:17:59,840 --> 00:18:04,144
It's just- It, you know, it's a more difficult regulation.

190
00:18:04,184 --> 00:18:07,544
So think of your driver's license, you know, just a regular driver's license.

191
00:18:07,564 --> 00:18:13,874
But if you wanted to be a certified CDL, you know, it's a much, much more expensive and involved process.

192
00:18:13,944 --> 00:18:18,454
And the same is true once we jump above 55 pounds.

193
00:18:18,964 --> 00:18:20,924
So that's important for people to know.

194
00:18:20,964 --> 00:18:27,364
And if you're gonna get into spraying, pretty quickly, you're probably gonna jump into that category.

195
00:18:27,724 --> 00:18:38,144
So it just means, it doesn't mean you can't fly, it just means that when you start looking at the regulations, you're gonna need to focus on this specific area

196
00:18:38,224 --> 00:18:40,444
and not the sUAS rules.

197
00:18:41,304 --> 00:18:51,624
So it-- That, that definition of that category of small aircraft was useful because it kind of gave us something firm to work with-

198
00:18:51,984 --> 00:18:53,324
and a lot of flexibility.

199
00:18:53,524 --> 00:19:04,624
But like I said, today with the increased interest in aerial application, or we'll call them spray drones or spreader drones, a lot of these pretty quickly are gonna

200
00:19:04,664 --> 00:19:06,314
default, fall over.

201
00:19:06,364 --> 00:19:09,684
At takeoff, they're gonna weigh mo- likely more than 55 pounds.

202
00:19:09,724 --> 00:19:14,904
So that regulatory thing is just gonna be a little more involved to process.

203
00:19:14,964 --> 00:19:15,204
Joe Maja: Yes.

204
00:19:15,244 --> 00:19:24,204
When we talk about UAVs or drones in agriculture, I usually break them down into two main categories, so multi-rotor and fixed-wing systems.

205
00:19:24,674 --> 00:19:34,804
So multi-rotor drones, like quadcopters or hexacopters, are the most common, and they can hover, very highly maneuverable, and they're well-suited

206
00:19:34,884 --> 00:19:36,824
for operations where precision is important.

207
00:19:37,664 --> 00:19:45,144
So in nursery environments where you have tighter space and more variability, multi-rotors tend to be the preferred option.

208
00:19:45,564 --> 00:19:53,484
Now, fixed-wing, on the other hand, are designed more like airplanes, so they're efficient over large areas and can cover more ground in a single flight.

209
00:19:53,584 --> 00:19:59,844
But they require more space to operate and don't offer the same level of control in confined environments.

210
00:19:59,884 --> 00:20:03,424
Another factor to consider is payload capacity and flight time.

211
00:20:03,904 --> 00:20:13,884
So multi-rotors typically have shorter flight time, but can carry specialized sensors or application system, while fixed-wing platforms prioritize endurance.

212
00:20:14,024 --> 00:20:18,044
So at the end of the day, the choice shouldn't be driven by the platform itself.

213
00:20:18,284 --> 00:20:20,284
It should be driven by the application.

214
00:20:21,024 --> 00:20:27,084
Whether it's imaging, monitoring, or spraying, the key question is what problems are you trying to solve?

215
00:20:27,144 --> 00:20:33,193
Jim Robbins: So, so I think that's very important for, you know, people- Mm-hmm to understand that there's this kind of two, two categories.

216
00:20:33,284 --> 00:20:33,384
Ping Yu: Yeah.

217
00:20:33,444 --> 00:20:43,724
I like your analogy with where your example of comparing the flying a drone versus your, like a driver license, because basically, if you're, if

218
00:20:43,764 --> 00:20:47,304
you have a driver license, you can just drive your own vehicle.

219
00:20:47,344 --> 00:20:57,344
But if you wanna be a, like, bus driver or a more, like a commercial driver or truck driver, you probably need to advance your driver

220
00:20:57,424 --> 00:20:58,624
license te-test.

221
00:20:58,964 --> 00:21:00,644
But spe- Yeah.

222
00:21:00,804 --> 00:21:05,404
Jim Robbins: And this is, that, that designation in this case is simply based on- Yeah weight issue.

223
00:21:05,464 --> 00:21:13,973
So but it, but it just, it's, it's important for people to know that that 55 pounds is something you need to just have floating in your back of your

224
00:21:13,973 --> 00:21:14,744
mind.

225
00:21:15,704 --> 00:21:15,814
Mm-hmm.

226
00:21:15,824 --> 00:21:25,984
Ping Yu: basically (upbeat music) basically speaking, since we're talking about the license, what are the license that needed for, for instance, for the small drone or

227
00:21:26,024 --> 00:21:26,784
a personal?

228
00:21:27,244 --> 00:21:36,224
Jim Robbins: So again, back in, I think I'm correct in saying it was back in 2016 when they rolled out these formal rules, which was very important because we need-- Prior

229
00:21:36,304 --> 00:21:42,624
to that, was kind of the Wild West, and so you need, as these technologies advance, this is very normal.

230
00:21:42,633 --> 00:21:46,883
The technology advances faster than the regulations can keep up.

231
00:21:46,944 --> 00:21:51,684
And so finally, they did come out with these rules, and again, I believe it was 2016.

232
00:21:52,484 --> 00:22:02,744
And at the time, there were, they defined three groups of users, public, so that would, that applied to Joe and I with, with the universities, commercial, and

233
00:22:02,784 --> 00:22:03,664
what was it called, Joe?

234
00:22:03,704 --> 00:22:04,434
Is it private?

235
00:22:04,544 --> 00:22:06,294
What's the, uh, it wasn't consumer.

236
00:22:07,104 --> 00:22:08,464
The hobby, hobby group.

237
00:22:08,804 --> 00:22:11,184
So there were three buckets at that, at that time.

238
00:22:11,424 --> 00:22:14,944
Over time, that's kind of, they've kind of dissolved that.

239
00:22:15,684 --> 00:22:19,504
And now we're, I think we're down to two, I would generally describe.

240
00:22:19,564 --> 00:22:29,604
But there's this Part 107, which is, so more than likely, if you're gonna use this, it's your nursery or greenhouse, you're gonna need

241
00:22:29,744 --> 00:22:35,664
to look up Part 107 and become a certified pilot.

242
00:22:36,204 --> 00:22:41,364
And the process, again, over time, has gotten much easier.

243
00:22:42,184 --> 00:22:48,324
So it's-- But it still is something that you need to complete, not, not really over, overburden.

244
00:22:49,164 --> 00:22:54,284
If you're, and let's probably not even get into the, just the hobbyist use.

245
00:22:54,504 --> 00:23:02,844
Th- Even today, they've gotta take a, a, a minor test just to get certified, and then where they can fly is controlled.

246
00:23:02,884 --> 00:23:10,804
But really, we, the purpose of this podcast should be for people that are gonna more for this commercial use.

247
00:23:11,024 --> 00:23:14,404
So Part 107 is something that, again, you need to write down.

248
00:23:15,044 --> 00:23:21,244
It doesn't matter who you are, whether you're a hobbyist or commercial, you've gotta register your drone.

249
00:23:21,524 --> 00:23:25,864
And that today is very, very easy online process.

250
00:23:25,884 --> 00:23:27,914
Very, just a couple minutes to do it.

251
00:23:28,844 --> 00:23:30,444
Very inexpensive.

252
00:23:30,484 --> 00:23:38,944
And again, I don't, we don't need to get into the weeds on it, but compared to when Joe and I did it, it was a paper process, very, very

253
00:23:39,024 --> 00:23:39,724
difficult.

254
00:23:40,044 --> 00:23:43,924
So things, again, over time have improved for, for everyone.

255
00:23:44,624 --> 00:23:54,724
And then the other licensing, let's say you do, you do have interest in an aerial application, then you're gonna need to also look at the FAA Part 137

256
00:23:54,784 --> 00:23:56,184
Part 137.

257
00:23:56,824 --> 00:24:03,224
And this is necessary for using drones for applying pesticides or agricultural chemicals.

258
00:24:03,304 --> 00:24:10,496
Now, today- It, it's again gotten a little easier 'cause this is kind of a new category, probably two years old, something.

259
00:24:11,176 --> 00:24:17,116
And so you could do it on your own or there are people that you can pay to help you go through.

260
00:24:17,196 --> 00:24:22,376
But there's a lot of detailed paperwork involved in, in going through this process.

261
00:24:22,456 --> 00:24:32,716
So if you're not going to apply any aerial chemicals, then again, really it's the registering your drone and Part 107 that, that you really need to fo-

262
00:24:33,056 --> 00:24:33,596
focus on.

263
00:24:33,656 --> 00:24:41,676
Joe Maja: Yeah, so from a practical standpoint, uh, Part 107 certification is very achievable for most people.

264
00:24:41,776 --> 00:24:50,976
So even without an aviation background, the exam focuses on topics like airspace classification, weather regulations, and operational safety.

265
00:24:51,956 --> 00:24:57,536
Where people tend to struggle is understanding how airspace works and how to operate legally in different environment.

266
00:24:57,596 --> 00:24:59,316
That's usually the biggest hurdle.

267
00:24:59,896 --> 00:25:02,595
But with some focused study, it's manageable.

268
00:25:02,856 --> 00:25:07,756
So Part 137, the other hand, which is required for aerial application, is more complex.

269
00:25:08,536 --> 00:25:15,496
So there's additional regulatory oversight, more paperwork, and in many cases, it involves working with state agencies as well.

270
00:25:15,556 --> 00:25:25,616
So for someone starting out, they usually recommend focusing on Part 107 first, gaining experience, and then exploring Part 137 if they plan to get into spraying operations.

271
00:25:26,116 --> 00:25:32,956
And in some cases, it's worth working with consultants or experienced providers to navigate that process more efficiently.

272
00:25:34,306 --> 00:25:42,696
Ping Yu: (upbeat music) But what-- can you give us a little bit more about, like, what type of drones are out there for people to use for different purposes?

273
00:25:43,016 --> 00:25:48,436
Can you give us a, like a general introduction to different types of drones?

274
00:25:50,256 --> 00:25:52,436
Jim Robbins: Joe, you want me to take, start and then you can add?

275
00:25:52,496 --> 00:25:58,876
Joe Maja: So when I think about drone application in nurseries, I group them into few categories.

276
00:25:59,016 --> 00:26:05,296
You know, imaging and mapping, crop monitoring, spraying, spreading, and inventory or counting systems.

277
00:26:05,766 --> 00:26:15,876
So with imaging, you can have standard RGB cameras, multispectral sensors, thermal sensors, hyperspectral camera, and even LiDAR system, depending

278
00:26:15,916 --> 00:26:17,876
on the level of detail needed.

279
00:26:18,376 --> 00:26:22,756
So one new ones I'd add is that these categories are becoming less distinct.

280
00:26:23,536 --> 00:26:30,756
We're seeing more integrated systems where a single drone platform can support multiple applications depending on the payload and software.

281
00:26:30,876 --> 00:26:39,086
So instead of thinking in isolated categories, it's becoming more about flexible systems that can adapt to different tasks.

282
00:26:40,696 --> 00:26:50,796
Ping Yu: So right now, people are kind of merging the gaps in between categories, and so one would actually function couple different

283
00:26:50,836 --> 00:26:51,396
functions.

284
00:26:51,516 --> 00:26:53,756
Jim Robbins: And one more, Joe, just general photographs.

285
00:26:53,816 --> 00:26:56,056
I mean, I guess we could put that under the imaging.

286
00:26:56,676 --> 00:27:01,376
Yeah, just simple, people wanna get video or photographs for, say, marketing or sales something.

287
00:27:01,416 --> 00:27:11,666
Ping Yu: So, so basically, based on the purpose of the drone application, we can categorize them into, like, general imaging and plant nutrition monitoring, spray drones,

288
00:27:11,896 --> 00:27:17,056
and for, or spreader for granular application and a counting system.

289
00:27:17,236 --> 00:27:20,375
Basically, five or six of those categories.

290
00:27:20,556 --> 00:27:30,576
For all those different purposes of drone application, are the requirements for the license would be similar, or are there different requirements for

291
00:27:30,676 --> 00:27:34,156
different application or different purpose of using the drone?

292
00:27:34,636 --> 00:27:43,756
And what are-- who's the agency they have to work with, just the FAA, or are there any other agency involved in this whole process?

293
00:27:44,376 --> 00:27:54,476
Jim Robbins: In, in simple terms, Ping, anything that deals with flying your aircraft, that is the sole responsibility of the FAA.

294
00:27:55,516 --> 00:28:03,656
But if you are gonna apply some kind of a chemical, then, for example, in the state of Arkansas, the agriculture department, the pest control division,

295
00:28:05,036 --> 00:28:08,516
y- you may, you know, need to have a conversation with them.

296
00:28:08,596 --> 00:28:17,916
So but anything that deals with flying an aircraft in the national airspace, which is what we're talking about, is the sole responsibility of the FAA.

297
00:28:17,976 --> 00:28:18,286
Ping Yu: Okay.

298
00:28:18,656 --> 00:28:18,976
Okay.

299
00:28:19,676 --> 00:28:29,836
And, and so basically, they have to go through all those paperworks to get their licensing, and depending on what purpose that they are using their drone for, for spray

300
00:28:29,876 --> 00:28:37,676
chemicals, for counting, and they might, may or may not have to go through additional steps to finish the whole process.

301
00:28:39,216 --> 00:28:50,176
(upbeat music) But with all those different type of drone application, have you guys seen over the years what would be the most, well,

302
00:28:50,186 --> 00:28:53,066
I guess most used, uh, drone application?

303
00:28:53,166 --> 00:29:03,176
'Cause I know right now, due to the safety or employee safety purpose, a lot of people are trying to use the spray drone a little bit more.

304
00:29:03,216 --> 00:29:12,536
But have you seen the same trend over the years where people are actually using drone basically anywhere they can?

305
00:29:14,516 --> 00:29:22,816
Jim Robbins: Well, so, uh, Joe and I have stuck to a list of five kinda applications that we set out a number of years ago.

306
00:29:23,556 --> 00:29:27,456
And I, I'm sure that somebody could adjust this, but, but here they are.

307
00:29:27,596 --> 00:29:29,976
So first one is, uh, for marketing and sales.

308
00:29:30,796 --> 00:29:38,346
And so this would be using your drone for high-quality imagery, uh, that enhances, you know, m- marketing materials.

309
00:29:39,016 --> 00:29:49,296
And any operation, I don't care how big or small, should have a small unit, probably gonna cost, uh, you

310
00:29:49,556 --> 00:29:51,516
know, no more than five hundred dollars.

311
00:29:51,556 --> 00:29:58,476
I mean, you could certainly get something for less than that, but, uh, that, you know, is durable for, for that purpose.

312
00:29:58,826 --> 00:30:07,476
'Cause I think we all now recognize if you see the importance of aerial images or aerial videos, again, in sales and marketing.

313
00:30:08,056 --> 00:30:13,456
The second is something that we had defined, uh, as asset tracking and management.

314
00:30:13,516 --> 00:30:20,720
And that would be, for example, let's say you're a large, you know, you're a grower, and I'd like to know how much- bark pi-- how big is my bark

315
00:30:20,780 --> 00:30:21,100
pile?

316
00:30:21,220 --> 00:30:22,980
So how much do I have sitting there?

317
00:30:23,340 --> 00:30:26,840
So I can estimate, you know, how many containers I can fill.

318
00:30:27,320 --> 00:30:34,360
So today, using some image processing methods and an aerial i- combined with an aerial image, we can estimate that quite accurately.

319
00:30:34,420 --> 00:30:35,500
So that's a good example.

320
00:30:36,180 --> 00:30:46,540
Um, or let's say, uh, irrigation coverage, or if you're a greenhouse, uh, and you've got retractable roof or you've got gutter connected, uh, houses

321
00:30:46,580 --> 00:30:51,980
and you need to inspect those, uh, structures safely, it's really the only way to go.

322
00:30:52,100 --> 00:30:55,120
And again, this is that same three $500 unit.

323
00:30:55,940 --> 00:31:05,490
Third category that we've talked about is, uh, is plant inventory, and that's the one that right now Joe and I tend to be most focused on.

324
00:31:05,500 --> 00:31:15,940
And that could either be over time, again, we've looked at both, uh, image analysis for counting, but more recently we're laser focused on using RFID tags

325
00:31:16,020 --> 00:31:26,280
combined with either a ground-based handheld unit, or Joe is designing some phenomenal, very small, lightweight, uh, aerial reading

326
00:31:26,460 --> 00:31:29,540
unit that you would attach, uh, to, a drone.

327
00:31:30,100 --> 00:31:34,380
The fourth category is this aerial application, so that you, you could call it spraying.

328
00:31:34,520 --> 00:31:37,660
I, I like to emphasize that it could also be spreading.

329
00:31:37,760 --> 00:31:43,760
So Ping, I mean, in, in Georgia, fire ants is a big issue, and so fire ant bait application.

330
00:31:43,880 --> 00:31:54,310
And really this is a exceptional application of, uh, of a, of a drone because you can lay out the pattern that you want to apply,

331
00:31:54,370 --> 00:31:57,360
and since in bait it doesn't need to be overlapping.

332
00:31:57,980 --> 00:32:01,830
So you can design this course very easily on your screen.

333
00:32:01,900 --> 00:32:08,060
And then, and because these materials tend to be a lower bulk volume, you can carry quite a bit of it.

334
00:32:08,120 --> 00:32:12,960
And so you can apply these materials probably the most efficient way I can think of.

335
00:32:13,160 --> 00:32:15,960
So in the south, southeast, uh, that, that's a great...

336
00:32:16,360 --> 00:32:21,700
And the credit goes to these, uh, desi- these aircraft designers.

337
00:32:21,780 --> 00:32:24,670
Uh, in just the last three years, they've done a remarkable job.

338
00:32:25,240 --> 00:32:35,460
Used to just be a, a sprayer with a liquid tank, and then very easily they design where you can pull the liquid tank out and swap out an interchangeable

339
00:32:35,660 --> 00:32:38,340
granular dry tank with a cyclone spreader.

340
00:32:38,450 --> 00:32:43,500
It's truly amazing how easily you can adapt from a liquid system to a granular system.

341
00:32:44,020 --> 00:32:46,380
And the last thing is, uh, crop monitoring.

342
00:32:46,480 --> 00:32:48,760
Um, and that Joe has referred to that several times.

343
00:32:48,840 --> 00:32:58,310
So that, you know, whether we're looking for water stress, which Joe and I have done some work on, uh, heat stress, weed infestations is, uh, an area, uh, chemical

344
00:32:58,420 --> 00:33:07,160
damage, all of those using remote sensing to try to identify these areas before really the human eye can pick up on it.

345
00:33:07,400 --> 00:33:10,120
Uh, and that, that's not, you think about it, that's not new.

346
00:33:10,200 --> 00:33:14,840
We've been doing this, but with, um, low-flying manned aircraft.

347
00:33:15,060 --> 00:33:21,700
The unique area is that we're now using these small, very maneuverable drones to, to do it.

348
00:33:21,800 --> 00:33:30,320
And the key to the whole success was that the manufacturers of these sensors had to scale these down.

349
00:33:30,400 --> 00:33:35,080
So they had to make them smaller and lightweight, and they've done a phenomenal job.

350
00:33:35,640 --> 00:33:40,520
'Cause again, when you had a manned aircraft, it-- weight or size really wasn't a big issue.

351
00:33:40,640 --> 00:33:46,640
But when you're trying to use one of these small aircraft, particularly weight is a big, big issue.

352
00:33:46,860 --> 00:33:49,620
So they've-- my hats off to these manufacturers.

353
00:33:49,680 --> 00:33:52,760
Within a short period of time, uh, they've done a phenomenal job.

354
00:33:52,840 --> 00:33:55,600
So that's kind of a summary of, of those.

355
00:33:55,620 --> 00:33:58,200
So, uh, with- Joe, do you wanna add to that?

356
00:33:58,260 --> 00:33:58,620
Joe Maja: Yeah.

357
00:33:58,720 --> 00:34:04,920
So I'd just add that in real world operation, these categories often overlap.

358
00:34:04,960 --> 00:34:14,400
So for example, a system designed for crop monitoring might also support inventory tracking or even mapping for irrigation management.

359
00:34:14,760 --> 00:34:17,140
So the value

360
00:34:18,620 --> 00:34:28,900
really comes from integration, uh, being able to use one platform for multiple purposes, you know, rather than, uh, managing separate system

361
00:34:28,980 --> 00:34:29,720
for each task.

362
00:34:29,780 --> 00:34:36,839
So that's where the technology is heading, and it's what makes it more practical for growers.

363
00:34:36,940 --> 00:34:47,160
Ping Yu: So with all those different type of drones that has potential-- well, has been used in nursery or in commercial nurseries, what would you say is the most used

364
00:34:47,220 --> 00:34:51,480
or adapted drone that has been used for right now in nursery settings?

365
00:34:53,460 --> 00:34:58,740
Jim Robbins: So far and away, I, I think it's just for getting simple still images- Okay videos.

366
00:34:59,440 --> 00:35:09,640
Because that's the easiest thing- Yeah Or for, like I said, we, you know, we know of a grower in Texas that used to get up and

367
00:35:09,760 --> 00:35:15,360
have an employee walk in the gutter of gutter connected, you know, structures, and one of them fell.

368
00:35:15,980 --> 00:35:17,200
And so they said, "That's it.

369
00:35:17,280 --> 00:35:18,800
We're not doing this ever again."

370
00:35:19,260 --> 00:35:27,630
So, and we've demonstrated this at nurseries where, I mean, just a very small drone with a, you know, high resolution camera and you can do the same thing, but-

371
00:35:27,680 --> 00:35:28,580
Mm-hmm safely.

372
00:35:29,360 --> 00:35:37,900
So those are two, you know, low-hanging fruit that every single operation should have a small drone for those- And it's not- those expensive.

373
00:35:38,100 --> 00:35:41,130
It's, it's, uh, very affordable for them to do that.

374
00:35:42,260 --> 00:35:42,270
No.

375
00:35:42,300 --> 00:35:42,480
Yeah.

376
00:35:42,820 --> 00:35:43,080
Yeah.

377
00:35:43,840 --> 00:35:45,920
Just very affordable.

378
00:35:46,120 --> 00:35:56,440
But then you start getting into these other things, you know, they're, they're a little more complicated 'cause you've gotta invest in people and technology, whether it's spraying

379
00:35:56,480 --> 00:36:03,080
or whether it's crop monitoring or whether it's, you know, this RFID thing that we're working on.

380
00:36:03,180 --> 00:36:08,200
I mean, I think it's, it's, it's gonna take you, you know, a little more effort, I think- Mm-hmm to jump into those.

381
00:36:08,300 --> 00:36:16,800
Ping Yu: we kind of briefly mentioned, or most of those works that you guys have done are like in nursery settings, but I know that people-- there are researchers out there,

382
00:36:16,920 --> 00:36:20,520
even maybe you guys have done some work in like greenhouse settings.

383
00:36:20,920 --> 00:36:29,120
What are the-- 'cause I know in, in greenhouse it can be a little bit challenging because it's, you know, well, it has advantages and disadvantages, but one of the

384
00:36:29,160 --> 00:36:39,260
disadvantage of working in the greenhouse setting is when you are flying drones- It's like they have a lot of those different structures within the unit, and that can cause

385
00:36:39,360 --> 00:36:40,600
any pro- some problem.

386
00:36:40,700 --> 00:36:49,960
But can you tell us, like, what's the difference, like what are the challenges of using drone in greenhouses versus in nurseries?

387
00:36:50,320 --> 00:37:00,000
Like, what are the two difference if you're flying drones in different scenario, what are the differences or what are the things that you need to adjust?

388
00:37:02,180 --> 00:37:02,260
Jim Robbins: Yeah.

389
00:37:02,280 --> 00:37:04,040
Another thing is just the, it's obvious.

390
00:37:04,300 --> 00:37:12,700
The inf- the physical infrastructure, you know, inside a infrastructure inside a, you know, a greenhouse.

391
00:37:13,060 --> 00:37:23,740
You know, some of these can be fairly wide open, but you're still gonna have posts and columns and suspended things from the infrastructure that these can be extreme

392
00:37:23,800 --> 00:37:25,560
challenges for flying.

393
00:37:26,640 --> 00:37:36,740
Y- you also have to think that inside the greenhouse, a, a lot of these more advanced productions use some kind of a gantry for irrigation

394
00:37:36,800 --> 00:37:46,900
or a pesticide application, and it just makes much more sense just to, if you wanna attach a sensor or something to that same gantry than to be introducing

395
00:37:47,000 --> 00:37:47,960
a, a small drone.

396
00:37:48,260 --> 00:37:55,760
Now, having said that, there are companies that clearly advertise small drone systems for the inside of greenhouses.

397
00:37:55,810 --> 00:37:57,880
So it is, it is reality.

398
00:37:58,660 --> 00:38:08,940
And I will also say that if we flip to the outside, we know of, y- you know, the application of applying, say, shading compound

399
00:38:09,080 --> 00:38:10,760
now using a spray drone.

400
00:38:11,380 --> 00:38:21,420
Again, instead of getting an employee up on the superstructure to apply these materials, the, the no-brainer solution is if you're gonna apply

401
00:38:21,460 --> 00:38:26,040
these, is to use a, use a drone, a spray drone for applying shading materials.

402
00:38:26,300 --> 00:38:33,960
And so that is an accepted norm now in the greenhouse industry, is the, i- is that application.

403
00:38:34,140 --> 00:38:44,270
And again, it's a, it's a much more efficient 'cause you can design the spray pr- pattern precisely, and again, you're not getting an employee up, you know,

404
00:38:44,340 --> 00:38:45,360
off, off the ground.

405
00:38:45,400 --> 00:38:48,280
So it's a much, much safer- Mm-hmm application.

406
00:38:49,240 --> 00:38:54,700
I should also, just a real quick, just jo- joined thought here, but we talk about drones, but if...

407
00:38:55,040 --> 00:39:03,170
I would encourage your listeners, if they're gonna get into this and they've never flown a drone, go ahead and get what we'd call a practice drone.

408
00:39:03,980 --> 00:39:07,840
And, and they could be less than $50 easily.

409
00:39:07,900 --> 00:39:11,460
But the-- I think I- I've heard this multiple times.

410
00:39:11,500 --> 00:39:15,820
People have gone ahead and gotten a pr- Christmas present, a thousand dollar drone.

411
00:39:15,860 --> 00:39:21,240
No experience, they go out, and sure enough, they slam the thing into a house or a tree or something like that.

412
00:39:21,720 --> 00:39:31,780
It's far more digestible to just start out with one of these and get the f- get a sense because just so you get a feel for what, what's involved.

413
00:39:31,860 --> 00:39:37,640
And then, so it- it's, it's a very worthwhile small expense to just get one of these practice drones.

414
00:39:37,700 --> 00:39:44,320
Ping Yu: Well, yeah, I would- If you have no, no, no background in this, it really is, it's, it's essential.

415
00:39:44,440 --> 00:39:44,450
Yeah.

416
00:39:44,460 --> 00:39:47,540
Ping Yu: People would be happy to get a drone as a Christmas gift.

417
00:39:47,900 --> 00:39:56,180
But I was kind of lucky enough to be able to join one of the trips when you guys are doing on-farm trial with a drone in one of the

418
00:39:56,200 --> 00:39:57,440
nurseries in Georgia.

419
00:39:57,860 --> 00:40:03,500
So I was able to see how you guys conducted the trial and the dr- in and of itself.

420
00:40:04,319 --> 00:40:12,460
(gentle music) But can you give us a little bit about, like, what kind of equipment that needed for drone?

421
00:40:12,600 --> 00:40:20,540
I know for different purpose of using the drone, then you may attach different piece into the flying unit.

422
00:40:20,940 --> 00:40:31,000
But can you just give us a little bit more of like the equipment or the components for certain purpose of using drone in a

423
00:40:31,220 --> 00:40:32,500
commercial nursery setting?

424
00:40:32,800 --> 00:40:40,780
Jim Robbins: It's important to point out that more than like-- Let's say that we follow up with Joe and we say, "You're interested in crop monitoring, and you're gonna use some

425
00:40:40,820 --> 00:40:43,400
kind of a three, four-band multispectral sensor."

426
00:40:45,060 --> 00:40:50,000
U- unless you've really got the expertise, more than likely you're gonna pursue a bundle.

427
00:40:50,120 --> 00:40:56,740
In other words, there's companies that have already put the drone, the aircraft together with the sensor.

428
00:40:56,770 --> 00:41:05,720
And the reason I point this out is because, again, I appreciate it because over the years, Joe has done all of this magic for me.

429
00:41:05,880 --> 00:41:11,440
But, you know, think about this, but that sensor would have its likely its own power source.

430
00:41:11,860 --> 00:41:13,460
You have to have a way to trigger it.

431
00:41:13,820 --> 00:41:21,740
I mean, so somehow you'd like to have a trigger that's connected with your remote control, your RC, et cetera.

432
00:41:22,440 --> 00:41:32,330
So there are companies that if you look, you know, will sell you, it's already put together, a specific multispectral sensor with a, with a drone as a all put

433
00:41:32,360 --> 00:41:32,910
together.

434
00:41:32,940 --> 00:41:37,460
So some of this electronic configuration work has already been taken care of.

435
00:41:38,340 --> 00:41:48,660
I, I'm not to say that people couldn't do it, but people forget that you've got to, again, have-- It's more than just attaching this payload

436
00:41:48,700 --> 00:41:49,560
to the underside.

437
00:41:49,600 --> 00:41:54,200
There, there likely has to be some possible communication with the ground.

438
00:41:54,580 --> 00:41:56,540
There has to be a power supply, et cetera.

439
00:41:56,620 --> 00:41:58,980
All these things you have to kind of think through.

440
00:41:59,020 --> 00:42:05,080
And so more than likely, again, you're gonna seek out somebody who's put this together for you.

441
00:42:05,500 --> 00:42:09,100
Same would be, I mean, the example, the extreme example would be a spray drone.

442
00:42:09,180 --> 00:42:19,340
I guess in theory, somebody could buy the actual aircraft, buy the actual spray components, you know, put it together, but it's more likely

443
00:42:19,580 --> 00:42:26,120
99% certain that you're gonna go and somebody's gonna sell you this already packaged, you know, packaged together.

444
00:42:26,840 --> 00:42:32,720
But, you know, for just simple pictures, videos, that kind of stuff, and, and those can be very powerful.

445
00:42:32,840 --> 00:42:42,236
Again, you know, we've done counting- There's-- I talked about the estimating bark pile volume, that can just be done with a regular RGB digital photograph, et cetera.

446
00:42:42,816 --> 00:42:49,795
So, you know, you're talking about a drone with a 4K camera, so somewhere from five hundred to a thousand dollars, something like that.

447
00:42:50,256 --> 00:42:53,396
And you, you, you've got something pretty powerful.

448
00:42:53,496 --> 00:42:54,256
Joe Maja: Absolutely.

449
00:42:54,816 --> 00:43:00,456
Integrating sensors onto drones involves more complexity than it might seem.

450
00:43:00,536 --> 00:43:10,816
So you have to manage power distribution, synchronize data capture, in-flight operation, and ensure that the data is properly stored

451
00:43:10,836 --> 00:43:11,616
and transferred.

452
00:43:11,716 --> 00:43:19,156
So if any of those components are not properly aligned or configured, the system won't function as intended.

453
00:43:19,256 --> 00:43:22,796
So that's why pre-integrated bundles are so important.

454
00:43:22,956 --> 00:43:33,016
Manufacturers have already addressed these challenges, so instead of trying to build a system from scratch, growers can focus on selecting the

455
00:43:33,076 --> 00:43:34,936
right configurations for their needs.

456
00:43:35,076 --> 00:43:43,576
So it reduces risk, saves time, and generally leads to more reliable outcomes.

457
00:43:43,615 --> 00:43:53,716
Ping Yu: (upbeat music) So speaking of the, the images and videos, and those are the things that it's with-- those are the things

458
00:43:53,776 --> 00:43:57,296
that easily can be adapted by anyone who is interested in.

459
00:43:57,836 --> 00:44:07,296
But one of the things that I wanna ask you guys is, so for instance, we, we took the photo, we took the image and, and especially for people who

460
00:44:07,376 --> 00:44:14,876
are looking into using the phone to do, like, plant monitoring or the inventory, what are the...

461
00:44:14,916 --> 00:44:17,416
Like, once you take the photo, you have to kind of

462
00:44:18,796 --> 00:44:20,156
analyze the data.

463
00:44:20,216 --> 00:44:22,416
Well, what we call analyze the data, the image.

464
00:44:22,956 --> 00:44:33,036
What can-- what are the software that they need to have to be able to analyze those images and then get those results

465
00:44:33,156 --> 00:44:38,656
from whatever they're taking, the videos or the picture, and get the data that they wanted?

466
00:44:39,296 --> 00:44:49,396
Can you, can you walk us through and using one of the example e-either with your or the plant monitoring example to kind of give

467
00:44:49,456 --> 00:44:53,716
us a, like, walk through for the imaging analysis?

468
00:44:54,136 --> 00:44:54,836
Jim Robbins: Well, I'll start.

469
00:44:54,896 --> 00:45:00,836
Uh, so I'll just specifically use, uh, Josue Nahum Leiva's master's work on the, uh, on the counting.

470
00:45:01,376 --> 00:45:09,976
And so we purchased soft- image-based analysis software called Feature Analyst, and I assume it's still available.

471
00:45:10,116 --> 00:45:14,496
And then, um, there was another one that he looked at called eCognition.

472
00:45:15,116 --> 00:45:18,616
And there-- So we had to buy a license for that.

473
00:45:18,796 --> 00:45:26,876
We also had to buy, uh, a, a sub-license for ArcGIS, I believe it was.

474
00:45:26,916 --> 00:45:37,036
But the process was we would take still photographs, land the aircraft, then just take the micro SD card out of the drone, uh, stick it into, you know,

475
00:45:37,076 --> 00:45:39,616
your computer, and then download the images.

476
00:45:39,766 --> 00:45:49,836
And then in our case, Josue needed to develop the step-by-step methodology for how to, you know, handle and process

477
00:45:49,876 --> 00:45:52,916
those images, in this case, to give you plant count.

478
00:45:53,316 --> 00:46:03,936
Now, today, the analogy is there are a number, and we've talked about this, and we could provide names, or you can just search for plant inventory software.

479
00:46:03,976 --> 00:46:09,916
So there's a number of companies that offer-- What you do is you would do what I described.

480
00:46:10,016 --> 00:46:18,255
You would take your digital images, land the aircraft, pull the micro SD card, but you would then upload those images to the cloud.

481
00:46:18,796 --> 00:46:26,476
And then you would contact the company and say, "Hey, I've put-- you know, I'd like you to give me a plant count for, for this."

482
00:46:26,976 --> 00:46:31,156
And they will do that and send you back, you know, a res- a result.

483
00:46:31,816 --> 00:46:39,736
Uh, so they're gonna use these software programs to analyze the images for you.

484
00:46:40,786 --> 00:46:50,236
The, the-- A caution, uh, because we've run into this, is, uh, just understand that talk to the company before because you need to describe.

485
00:46:50,266 --> 00:46:56,246
They have tremendous expertise, for example, but have you ever worked with a, you know, a container nursery?

486
00:46:56,516 --> 00:47:03,716
So you'd wanna find out their experience level because it's not perfectly transferable cases.

487
00:47:04,376 --> 00:47:07,476
The other thing is they're likely gonna tell you how many images.

488
00:47:07,776 --> 00:47:12,676
So you and I might think, "Well, I've got a small nursery, and it's a small block, and I only need one, one image."

489
00:47:12,776 --> 00:47:16,376
And I'm gonna predict that the answer is no, that you need, like, eight images.

490
00:47:16,436 --> 00:47:18,236
There's a series that, that is required.

491
00:47:18,276 --> 00:47:27,096
So there, there might be a-- You'll describe your situation, and you'll probably come to an agreement, okay, we need so many, a minimum number of so many images.

492
00:47:27,136 --> 00:47:28,376
So all that would be worked out.

493
00:47:28,566 --> 00:47:37,676
But to simplify, so in theory, you could do this by yourself, buy all the software, learn a technique, but I don't think most people are capable.

494
00:47:37,776 --> 00:47:44,246
So you'd probably, again, wanna use a service to process your image for that specific purpose.

495
00:47:44,336 --> 00:47:53,196
Ping Yu: Uh, in that case, if anyone-- So if someone wants to do something like that and take a imaging and do the analysis, but they don't wanna fly, and they

496
00:47:53,216 --> 00:48:03,266
don't wanna go through any of those process of flying the drone in their operation, can they-- Are there any service or companies that provide the service, say, say, "Hey,

497
00:48:03,616 --> 00:48:10,856
I want you to come over to my property and then fly the drone and then analyze the data and give me the results"?

498
00:48:10,996 --> 00:48:18,876
Are there any service like this so that they don't have- for anyone who wants to do that, they don't have to go through any of the problem, just to

499
00:48:19,136 --> 00:48:20,235
give me what I want.

500
00:48:22,256 --> 00:48:23,156
Jim Robbins: Great question.

501
00:48:23,356 --> 00:48:33,724
So yeah, we should say that for anything described, you Could easily find somebody to come out and fly the drone for whatever sp-

502
00:48:33,844 --> 00:48:37,784
specific purpose you want, whether it's just to collect dig- digital images.

503
00:48:37,824 --> 00:48:40,714
So you could be a totally hands-off process.

504
00:48:41,064 --> 00:48:48,354
Call them up, they'll do it, and then they would coordinate with a, a different company to process, you know, the images for your objectives.

505
00:48:48,364 --> 00:48:49,304
Same for spraying.

506
00:48:49,364 --> 00:48:56,064
You could just say, "Hey, please come out and spray block C tomorrow at, you know, 3:00 PM," or something like that.

507
00:48:56,604 --> 00:49:06,684
I mean, it's so easy if you just search your area to find drone services for any of the specific tasks that we've,

508
00:49:06,944 --> 00:49:07,904
we have talked about.

509
00:49:07,984 --> 00:49:08,964
You can find them.

510
00:49:09,784 --> 00:49:11,124
A- and then, uh, this is a great point.

511
00:49:11,264 --> 00:49:15,844
Joe and I, we, we wrote a elegant fact sheet, extension fact sheet.

512
00:49:15,924 --> 00:49:23,504
It was probably the final one that I wrote, and we wrote it with a agricultural economist at, at the University of Arkansas, Division of Agriculture, Ron Rainey.

513
00:49:24,264 --> 00:49:31,064
And it's, it's, it's really wonderful because what we did is we did exactly what you're describing, Ping.

514
00:49:31,404 --> 00:49:38,424
We gave three different scenarios related to a drone, and we used as the example multispectral imaging.

515
00:49:38,834 --> 00:49:39,164
And we...

516
00:49:39,574 --> 00:49:41,844
Scenario Number 1 is you do everything yourself.

517
00:49:41,924 --> 00:49:46,964
So you go buy the drone, you get licensed, you buy the software that's necessary.

518
00:49:46,984 --> 00:49:48,944
And it, it totals it up.

519
00:49:49,024 --> 00:49:54,824
How much would you invest in year one, and then it, it extrapolates it out over a five-year time y- return.

520
00:49:55,704 --> 00:50:00,724
And then Scenario Number 3 is exactly what you were asking, Ping, which is a great question.

521
00:50:00,734 --> 00:50:04,764
"Hey, we just call somebody up and just come out and do this entirely for us."

522
00:50:04,784 --> 00:50:09,604
And so we, you know, we knew actual figures what somebody would charge for that.

523
00:50:10,084 --> 00:50:13,024
And then we had Scenario Number 2, which is a hybrid.

524
00:50:13,124 --> 00:50:19,644
So we said, okay, kind of what you were s- alluding to, Ping, "Hey, I'm comfortable taking the images.

525
00:50:19,864 --> 00:50:22,124
I'm not comfortable processing the images."

526
00:50:22,324 --> 00:50:24,303
So we extrapolated that.

527
00:50:24,844 --> 00:50:28,764
So when we're done, we could give you a link to that fact sheet that's still available.

528
00:50:29,264 --> 00:50:39,384
And this, it could easily applied, be applied, even though it's for multispectral image analysis, it could be applied to a spray scenario.

529
00:50:39,394 --> 00:50:44,184
You would just have to change some of the categories that are listed.

530
00:50:44,244 --> 00:50:54,344
So the, the type of drone would be different, but it's a wonderful template for businesses to use to help them make a better

531
00:50:55,124 --> 00:50:56,564
business decision.

532
00:50:56,904 --> 00:51:01,224
What's really their, you know, at this point in time, what's the best approach for them?

533
00:51:01,644 --> 00:51:06,524
So we'll give you a, a link to that, but it, it, it's a wonderful example.

534
00:51:06,544 --> 00:51:15,944
And again, it brings out the importance of bringing in the, an economist because Joe and I both have backgrounds in industry and, you know, we can come up with

535
00:51:15,984 --> 00:51:25,584
these crazy academic ideas, but if they're not functionally, you know, gonna be cost-effective, then, you know, this is just, you know, kind of crazy talk.

536
00:51:25,704 --> 00:51:35,704
Ping Yu: So we, we always like to talk about the economics of, of Yeah, that's one of the things that I, that's uphill, he- head on my mind is, okay,

537
00:51:35,924 --> 00:51:41,284
this all sounds great, but if I'm doing it all offhand, how much does it cost?

538
00:51:41,664 --> 00:51:45,364
If I'm going to do it on my own, how much does that cost?

539
00:51:45,444 --> 00:51:49,924
Because the whole process and being, running a nursery can...

540
00:51:49,964 --> 00:51:56,264
There's a million things coming out every day, and I have to delegate the time and effort to do this.

541
00:51:56,364 --> 00:51:57,264
Does it worth it?

542
00:51:57,704 --> 00:51:59,924
Or would it be more

543
00:52:01,164 --> 00:52:05,424
wise to just hand it off to some expert to do the whole thing for me?

544
00:52:06,004 --> 00:52:17,024
Jim Robbins: And- you know, and I'll be quite blunt forward about saying, for example, I am very, very excited long term on the use of spray drones, spreader drones

545
00:52:17,144 --> 00:52:18,624
in the nursery applications.

546
00:52:18,884 --> 00:52:21,054
I really think long term, this is gonna be a game changer.

547
00:52:21,064 --> 00:52:31,204
That's one of the things that- But in tw-- Yeah, in 2025, I think if you're interested in it, easiest thing is to go find a local

548
00:52:31,304 --> 00:52:37,004
company, which shouldn't be that hard to find, and work with them and kind of explore it at this point.

549
00:52:37,624 --> 00:52:47,704
But thinking of the cost of the unit and all of the little details that we're still working out as far as application rates, nozzles, all of the labeling

550
00:52:47,764 --> 00:52:57,744
issues, everything, I would feel more comfortable advising a nursery to work with a commer- uh, an outside firm that's working day-to-day in this.

551
00:52:58,464 --> 00:53:08,984
And then as time evolves, I truly believe that we're gonna, these are gonna be very, very significant in chemical application in nurseries

552
00:53:09,084 --> 00:53:09,684
long term.

553
00:53:09,744 --> 00:53:17,884
Ping Yu: have same-- Well, I have been asked by various growers in Georgia, where, uh, at least they have expressed their interest in

554
00:53:19,304 --> 00:53:24,044
switching to the traditional chemical spray to drone application.

555
00:53:24,154 --> 00:53:27,344
And now it's just they were like, "Oh, should I do this?"

556
00:53:27,384 --> 00:53:36,084
And, but they don't have a whole lot of like, of, well, I guess, available resources to make the decision which way they should go.

557
00:53:36,404 --> 00:53:46,444
(upbeat music) But speaking of that, and can you guys give us like, I know from my own experience in, for a spray application,

558
00:53:46,644 --> 00:53:48,344
you basically have a tank in there.

559
00:53:48,864 --> 00:53:59,344
But you also mentioned there are a possibility or there are other ways to kind of swap the tank and make it the liquid chemical spray

560
00:53:59,404 --> 00:54:02,644
drone into a granular kind of spray.

561
00:54:02,984 --> 00:54:07,784
Can you te- what's the difference, and can you tell us a little bit more on that?

562
00:54:08,444 --> 00:54:15,644
Uh, and are there any available resources where I would think there are firms that can do that?

563
00:54:16,304 --> 00:54:16,844
Jim Robbins: Yeah, there's...

564
00:54:16,924 --> 00:54:18,944
I'm, I'm just using, uh, Arkansas.

565
00:54:19,064 --> 00:54:26,584
I-- Aerial application drone companies now in Arkansas, and shockingly, it's in row crop agriculture.

566
00:54:27,224 --> 00:54:35,764
And they're so busy that my colleagues, uh, again, I'm retired, uh, that are trying to work with these companies to work on specialty crops.

567
00:54:35,804 --> 00:54:43,104
So for example, uh, I just saw a video from applying a, uh, fungicide to pumpkin production.

568
00:54:43,768 --> 00:54:52,628
And think about this, a vining crop, so whether, you know, it was, uh, squash or pumpkins or something like that, there's, there's no rows.

569
00:54:52,748 --> 00:54:55,908
It's just a, a field full of sprawling vines.

570
00:54:55,948 --> 00:55:01,307
And so if you needed to apply something (laughs) over the top of these things.

571
00:55:01,988 --> 00:55:12,108
So what they're doing, these for fee spray aerial application companies to come in and make the application, and then they've

572
00:55:12,128 --> 00:55:15,168
got the spray cards, you know, and they're doing the data collect-

573
00:55:17,448 --> 00:55:20,768
And, so even as a researcher, I think that's the smarter way.

574
00:55:22,808 --> 00:55:25,968
Regulatory hoops, you've, you know, you've, uh, gotta, gotta go through.

575
00:55:26,268 --> 00:55:34,078
By the way, this example of this, this will be the last thing I'm gonna say about it is I couldn't believe it, but it's got an 18 gallon, uh,

576
00:55:34,208 --> 00:55:36,618
liquid tank, which, th- these things are...

577
00:55:37,408 --> 00:55:39,548
Because that's a lot of, that's a lot of weight.

578
00:55:40,248 --> 00:55:44,428
Um, and that's definitely a, not considered in the small, small category.

579
00:55:45,008 --> 00:55:45,428
But again,

580
00:55:47,468 --> 00:55:56,008
in the nursery industry in the south and southeast, uh, application of particularly fire ant bait materials, boy, man, that's a...

581
00:55:56,248 --> 00:55:58,528
To me that's, uh, I'd give that a se-

582
00:56:00,468 --> 00:56:10,408
Because you can define the flight path so precisely, and because it's a lower bulk density, you can carry a lot more.

583
00:56:10,588 --> 00:56:13,648
I, I just think it's a really, uh, great, great way.

584
00:56:13,688 --> 00:56:17,248
And again, credit to the manufacturers, as I say, stated earlier.

585
00:56:18,108 --> 00:56:28,108
It's amazing how, I mean, they just immediately realized that having a very pullout transferable unit from a liquid to a spray application system, I, I

586
00:56:28,188 --> 00:56:30,828
think they've, uh, smoothly they've made that interface.

587
00:56:31,048 --> 00:56:32,928
So Joe, you got any thoughts?

588
00:56:32,968 --> 00:56:33,528
Joe Maja: Yes, Ping.

589
00:56:33,668 --> 00:56:44,708
So from an engineering standpoint, the ability to switch between liquid and granular systems comes down to standardized

590
00:56:44,748 --> 00:56:47,408
interfaces, both mechanical and electrical.

591
00:56:47,508 --> 00:56:56,568
So what's improving now is how efficiently the systems communicate and how precisely they can control the application rate.

592
00:56:57,248 --> 00:57:02,728
So there's still some room for improvement, especially in calibration and, and Ping, consistency.

593
00:57:03,628 --> 00:57:07,468
But I believe the progress has been very significant.

594
00:57:07,528 --> 00:57:17,548
Ping Yu: So basically, whether they are use-- they want, they wanna use the, to spray a liquid chemical or like a granular or weed control product

595
00:57:17,608 --> 00:57:23,828
or anything related, there are products that's available for the growers to choose from, right?

596
00:57:25,128 --> 00:57:25,288
Jim Robbins: Yeah.

597
00:57:25,328 --> 00:57:28,668
There are platforms that are readily available.

598
00:57:28,688 --> 00:57:30,597
And again, let's say all you want is...

599
00:57:31,558 --> 00:57:40,428
They'll just sell you that, and then later you could, you know, buy the liquid application system, which would be a tank, and obviously there'd be...

600
00:57:40,468 --> 00:57:50,528
It would have a traditional, well, boom with nozzles, so the configuration var- So basically, you can buy different kind of components separately

601
00:57:50,568 --> 00:58:00,588
Ping Yu: and they can make sure, but I guess what I'm saying that you have to think is you just make sure all those components are compatible with your drones, right?

602
00:58:00,748 --> 00:58:04,968
Where is this something, is this an issue with some of those products out there?

603
00:58:07,008 --> 00:58:07,228
Jim Robbins: No.

604
00:58:07,508 --> 00:58:16,468
That's, I mean, they're obviously, as long as it's their system, they've designed those payloads, the liquid application system or the granular to work.

605
00:58:16,597 --> 00:58:19,368
Again, remember this ci- circles back to what I said.

606
00:58:19,848 --> 00:58:20,568
Think about this.

607
00:58:20,578 --> 00:58:25,317
They have to give thought about, how am I gonna power both the sprayer or the spreader?

608
00:58:25,478 --> 00:58:34,788
'Cause it's gonna require some kind of battery power, and they can either pull it from the aircraft itself or they can provide most likely a

609
00:58:36,228 --> 00:58:36,708
course.

610
00:58:36,748 --> 00:58:38,448
And then you also have to have a trick.

611
00:58:39,988 --> 00:58:44,828
Actually want this, uh, system to turn on and to turn off.

612
00:58:44,918 --> 00:58:50,868
And so that is all being taken care of, you know, for you, thanks to, you know- Mm-hmm great engineering.

613
00:58:52,468 --> 00:58:59,728
And the other beauty about these new systems, it's absolutely remarkable, is again, the flight navigation software.

614
00:58:59,828 --> 00:59:06,188
To me, that's been the most significant advance in the last ten years, is, um...

615
00:59:06,728 --> 00:59:11,968
So now they've got sprayers that will lift off, go apply.

616
00:59:12,048 --> 00:59:15,068
They'll sense that they're getting low on, on material.

617
00:59:15,268 --> 00:59:16,488
They'll stop spraying.

618
00:59:16,868 --> 00:59:20,388
They'll come back to the starting point where you can refill.

619
00:59:21,008 --> 00:59:25,328
They will then go back to where they stopped and continue along the path.

620
00:59:26,168 --> 00:59:30,368
So th- this kind of a seamless, it's not where,

621
00:59:32,548 --> 00:59:38,248
you know, what's gonna happen and in the flight navigation software.

622
00:59:38,308 --> 00:59:41,228
And the same is true for r- photographs.

623
00:59:41,268 --> 00:59:48,118
You know, you can see in, in advance, okay, if I need to capture images of this area, it's gonna take maybe

624
00:59:50,188 --> 00:59:52,348
say 28 pictures.

625
00:59:52,408 --> 00:59:54,628
What's the length of the flight path?

626
00:59:54,788 --> 00:59:56,248
Is, do I have enough battery?

627
00:59:56,448 --> 01:00:00,788
All of this is now seamlessly thought through for you.

628
01:00:00,848 --> 01:00:07,628
So where, again, circling back 15 years ago, oh my gosh, it was really rudimentary crude.

629
01:00:07,668 --> 01:00:12,048
And again, Joe, you know, did all this stuff in the earliest years.

630
01:00:12,108 --> 01:00:16,348
So credit goes to, you know, Joe and his many years of engineering.

631
01:00:16,748 --> 01:00:25,228
Ping Yu: (upbeat music) So speaking of that, and I know Joe kind of was dragged into horticulture by James.

632
01:00:25,258 --> 01:00:35,008
And, but, uh, I know right now, a lot of times in, for instance, for drone's application in row crop, and it's most, most of the time it's monoculture.

633
01:00:35,188 --> 01:00:44,048
It's, it'll be easier for them to kind of build up the, the, the kit and then just fly and apply whatever they are applying.

634
01:00:44,508 --> 01:00:55,272
But in horticulture in general, we're dealing with thousands of different Type of crops and they have different requirements and they have, some of them might be sens- sensitive,

635
01:00:55,512 --> 01:00:59,092
very sensitive to some certain of the chemical that you're applying.

636
01:00:59,532 --> 01:01:09,812
Would you say this would be one of the challenges, or are there any solutions to address the challenges and make it a little bit more adapted

637
01:01:09,972 --> 01:01:11,932
by the grower or from the...

638
01:01:12,352 --> 01:01:21,932
For any manufacturers out there who wants to do more business with ornamental horticulture, what, what do you think was your experience?

639
01:01:22,052 --> 01:01:26,512
What, what are the things that you, you think need to be addressed in that perspective?

640
01:01:27,752 --> 01:01:31,752
Jim Robbins: I'm gonna jump in here real quick and then let Joe, but just think about this.

641
01:01:31,912 --> 01:01:38,752
If, if you're growing 3,000 acres of soybeans or 3,000 acres of cotton or, you know, a monoculture like that, and you...

642
01:01:40,802 --> 01:01:48,992
It's a heck of a lot easier than if you go to a nursery that's growing 3, 4, 5, 600 different types of crops.

643
01:01:49,912 --> 01:01:53,552
You know, Joe and I have, you know, done work in

644
01:01:55,572 --> 01:01:58,392
several different ornamental crops in containers.

645
01:01:59,252 --> 01:02:01,312
And, you know, I think it's, uh,

646
01:02:02,912 --> 01:02:08,852
thing, but, you know, was what we learned on panicle hydrangea with...

647
01:02:10,812 --> 01:02:11,112
To...

648
01:02:11,832 --> 01:02:13,992
Well, that's the challenge

649
01:02:15,732 --> 01:02:25,852
against us working on this multispectral area, but we, uh, you know, we have a handicap in that we've got a much

650
01:02:25,912 --> 01:02:32,532
larger diversity of crops than someone in row crop where it's thousands of acres of one thing.

651
01:02:32,992 --> 01:02:43,171
And so their, some of their solutions are gonna be achievable sooner than they will be in our, uh, ornamentals area.

652
01:02:44,032 --> 01:02:51,732
And, you know, in a rough sense, maybe we'd be able to find with a thermal sensor maybe that there's some general water sense, uh, water stress before it occurs

653
01:02:51,772 --> 01:02:54,672
or something on a w- diversity of crops.

654
01:02:55,052 --> 01:02:59,581
And I think artificial intelligence, uh, will, will help us long term.

655
01:02:59,652 --> 01:03:02,232
But yeah, it's...

656
01:03:02,262 --> 01:03:07,972
Again, there are so many more cheap ornamentals, um, you know, compared to other situations.

657
01:03:08,312 --> 01:03:09,232
What are your thoughts, Joe?

658
01:03:09,292 --> 01:03:16,112
Joe Maja: So in ornamental system, the challenges comes from, uh, I believe variability.

659
01:03:16,272 --> 01:03:25,292
So each species has its own spectral signature influenced by factors like, you know, leaf structure, pigmentation, and canopy architecture.

660
01:03:26,192 --> 01:03:35,652
So a model that works well for one species or what's called a taxa may not perform well for another taxa.

661
01:03:36,212 --> 01:03:46,132
That makes it much more difficult to apply a single solution across diverse crops, and it requires more advanced data processing and modeling approaches.

662
01:03:46,172 --> 01:03:56,192
Ping Yu: Well, I guess the ornamental with the diverse of plants that we're growing, it's, it's a beauty, but sometimes in this s- scenario it's a, it's a

663
01:03:56,292 --> 01:03:57,092
challenge, too.

664
01:03:57,212 --> 01:04:07,452
But do you think with the involve with the technology down the road, let's say in the next 10 years or 15 years, are there, like, any possibility

665
01:04:07,572 --> 01:04:10,052
of solutions that can help

666
01:04:11,492 --> 01:04:19,632
make it possible, kind of reduce the, or solve the challenges we are facing now with, in terms of the diversity of crops?

667
01:04:19,692 --> 01:04:29,932
And for instance, can we-- Do you think it's possible for people to come up with ideas to use, like, different type of drones

668
01:04:30,032 --> 01:04:36,872
in, like say paniculata, roses, and then Japanese maple, and then go from there?

669
01:04:36,922 --> 01:04:44,712
'Cause that, that can be maybe a little bit more expensive than monoculturing row crops, but do you think it's possible down the road?

670
01:04:44,832 --> 01:04:50,552
Joe Maja: I think the, uh, future solution is

671
01:04:52,292 --> 01:04:56,512
less about different hardware and more about smarter software.

672
01:04:57,532 --> 01:05:04,012
So AI and machine learning will play a key role in adapting to variability across species.

673
01:05:05,052 --> 01:05:14,912
So we're also seeing advancement in hyperspectral sensing and onboard processing, uh, which actually allow more real-time analysis.

674
01:05:15,012 --> 01:05:17,652
So now we have the so-called edge computing.

675
01:05:18,472 --> 01:05:25,092
So the hardware may remain relatively consistent, but the intelligence behind it will continue to evolve.

676
01:05:26,792 --> 01:05:31,822
Ping Yu: (outro music) Conversation like this only happen when you support the show.

677
01:05:32,232 --> 01:05:40,812
For more information and find ways to support us, please go to bandbpod.com, bandbpod.com.

678
01:05:41,352 --> 01:05:46,612
If you like what you are hearing, spread the word and share this podcast with the people you love.

679
01:05:47,132 --> 01:05:52,492
Make sure you hit that, uh, subscription button and give a review for the podcast.

680
01:05:53,112 --> 01:06:02,872
And as always, go check out the show notes to learn more about this topic and other topics we featured on the show at bandbpod.com.

681
01:06:03,252 --> 01:06:04,232
Thank you for listening.

682
01:06:04,412 --> 01:06:07,332
Till the next time, stay healthy and go plants.

683
01:06:10,132 --> 01:06:20,472
(outro music)