The HarvestMoore webpage is in the process of being updated. The page is being expanded to show the progress that has been made in the development and design of the Harvester. We have focused our efforts on the Harvester as opposed to the Automated Pruning feature based on feedback from Washington orchardists, who have expressed a strong desire for an automated apple harvester first.
HarvestMoore is looking for an Ag Manufacturer to work with HM to design a vehicle based on their manufacturing capability.
HarvestMoore has hired Dave Clark, an Instrument & Controls (I&C) Engineer, to develop code for the HarvestMoore AI Fruit Finder. Dave brings over 40 years’ experience in design, testing, operation and maintenance of I&C systems. His project experience includes nuclear reactor safety systems, I&C support of R&D projects, software design and implementation for control systems, Graphical User Interface (GUI) development, Programmable Logic Controller (PLC) and Human Machine Interface (HMI) design. Familiar with multiple computer, PLC, and HMI programming languages; Dave has a BSEE from the University of Idaho.
“This disclosure includes a method for pruning a fruit plant. An exemplary method step includes obtaining an image of the fruit plant that has branches. Next, creating exclusion zones surrounding the branches. then pruning the fruit plant upon the exclusion zones’
18 Claims, 39 Drawing Sheets“
This Patent covers the Pruning of fruit trees including apple trees. This allows for and automated vehicle to prune the apple tree in the spring and with the change out of end effectors harvest the apple in the fall. HarvestMoore is excited to now cover pruning as well as harvesting with the same automated machine.
HM has now developed the Pick Path Software using image Recognition data. The software generates a Pick-Path table for use by the robotic arm controller. If HM cannot get funding to build the robotic arm it will be a very slow year in developing an Automated Apple Harvester.
HM is now working with Ceil Du Cheval Vineyard to use AI Image Recognition to count the grape clusters in the Spring. This will allow Ciel Du Cheval to get an estimate of the number of tons of each variety of grapes expected during the Fall harvest. HM has been funded on a retirement budget. And would like to raise some funds by licensing the patents on the AI Fruit Finder, or obtaining another partner in HarvestMoore LLC.
HarvestMoore LLC (HM) has continued to work on improving image recognition of apple buds during 2022. The biggest issue is HM needs to design and develop a fast light weight robotic arm. We have the image recognition of buds at 96% per apple tree.
HM has now developed the Pick Path Software using image Recognition data. The software generates a Pick-Path table for use by the robotic arm controller.
HM now has seven Patents on various aspects of Tree Fruit Harvesters.
Year 2021 has been a wild and crazy year. We worked improving image recognition. We are happy with our results, and hope to further improve in 2022. We compared IT image recognition to manual bud recognition and we got an average range of 94 percent to 96 percent IT bud recognition on the first 15 trees in row 1 of Block 6 as compared to manually counting the buds. This is an important milestone towards validating our bud recognition concept.
According to a consultant with John Deere, the HarvestMoore AI Fruit Finder must be able to successfully recognize and pick at least 90 percent of the tree fruit in order for the device to be viable as a tool that competes with manual labor in the field.
The two photos shown here are of the same tree, a couple of years apart. The first image shows our 2020 attempts at bud and tree fruit recognition with the yellow squares representing AI bud recognition. The second photo is the same tree, using the improved AI bud recognition we tested last spring at pruning season.
As you can see, our approach is beginning to yield results. We couldn’t be more excited to deliver this technology to an industry which has been pummeled by the impacts of the pandemic over the last year.
While we are still a few years away from having a product to offer in the field, this fall’s findings suggest we are on the right track to deliver technology that will address the labor needs of tree fruit and nut orchardists in the U.S.
The first prototype was a modified backhoe that provided HarvestMoore a significant amount of development data. The biggest problem was the arm was too slow and much to heavy. HarvestMoore researched available robotic arms but no arm would meet the needs for operation in the apple orchards. We applied for a National Science Foundation NSF) Startup Grant to develop and build the necessary robotic arm.
In the mean time, we will be getting the necessary tree images in March of 2022.
Happy New Year from HarvestMoore. It has now been five years since HarvestMoore LLC (HM) was founded. It has been 12 years since I decided to see if I could find apples using remote technology so they could be picked. It was a hobby to challenge my mind during retirement. My first patent was issued January 5th 2016. My hobby then turned into a job. I had hoped to get some Ag business interested in taking the company and the technology that I had developed and run with it. No such luck! Everyone wanted a sure thing and saw accepting an invention for harvesting apples invented by a retired engineer from the nuclear industry as a no sure thing. They wanted to see a machine picking apples, not a series of proof tests which shows each internal system works. Working as an individual with moral support from my retired friends, I decided to fabricate a robotic arm that could find and pick an apple, remove the fruit from the tree and maintain quality. A demonstration was conducted in August 2018. What the demo pointed out was that the level of the recognition needed to be greater and needed to be above 90 percent fruit finds to be viable.
I have now learned more about Artificial Intelligence (AI) and Image Recognition than I ever thought I wanted to know. Much of this happened with the help of a great friend Dave Clark. I also received 5 more patents to further secure the intellectual property. The other item I learned was, “I DO Not want to manage a manufacturing company”. I am looking for a company that can secure funding and has a manufacturing facility to take what HM has developed and move to a production machine. The machine would cost on the order of $230,000 to build and sell for $500,000.
Remember I retired once. The COVID 19 has a way of refocusing where you want to go.
This fall, HarvestMoore, LLC had a significant breakthrough in the company’s efforts to prove our bud recognition technology can “see” 90 percent of the fruit buds on a blooming tree in the spring. While much work remains to validate and recreate the findings, at HarvestMoore we are convinced that this bodes well for the future of the company’s AI Fruit Finder.
According to a consultant with John Deere, HarvestMoore’s AI Fruit Finder concept must be able to successfully recognize and pick roughly 90 percent of the tree fruit in order for the device to be viable as a tool that competes with manual labor in the field.
The two photos shown are of the same tree, a couple of years apart. The first image shows our initial attempts at bud and tree fruit recognition with the yellow squares representing AI bud recognition and the red circles showing buds that were located by human observation. The second photo is the same tree, using the improved AI bud recognition we tested last spring just before pruning season.
The HarvestMoore AI Fruit Find bud recognition software shows promise in finding at least 90 percent of buds on Granny Smith Apple Trees in spring 2020.
As you can see with your own eyes, our approach is beginning to yield results as we approach 2021 and we couldn’t be more excited to deliver this technology to an industry which has been pummeled by the impacts of the pandemic over the last year. While we are still a few years away from having a product to offer in the field, this fall’s findings suggest we are on the right track to deliver technology that will address the labor needs of three fruit and nut orchardists in the U.S.
