Over the Air · 21 Dec 2023 · 18m
Jorge Heraud, VP of Automation and Autonomy at John Deere, explains how the company is leveraging IoT and computer vision to transform agriculture through products like See & Spray and fully autonomous tractors. He details the decision to refine existing herbicide application rather than pursuing unproven technologies like lasers, achieving a 3-5x reduction in chemical usage. Heraud also outlines John Deere's roadmap to a fully autonomous farm by 2030, highlighting the operational advantages of private land environments compared to public roads.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Engineering & simulationmachine learning, computer visionspraying only 20-30% of the field
John Deere trained programs using machine learning and computer vision to recognize weeds via cameras on the See & Spray system, enabling targeted spraying instead of blanket application.
“We use machine learning, we use computer vision. We train the programs that we utilize to recognize the weeds. And when we see a weed. We spray and we spray only that area where the weed is.”
Speaker 1 · Hear it at 3:52
Engineering & simulation3 to 5 times more efficient use of herbicides
The team experimented with various physical weed-killing mechanisms (lasers, flames, Tesla coils, high-pressure water) after developing plant recognition, ultimately selecting herbicides as the most practical solution based on experimental results.
“We tried different technologies. We started with this ability to recognize plants and then try to kill the weeds, but how to kill them and we try with different things and doing using herbicides and using 20% of what you normally use. So a factor of 3 a factor of 5 less than what you normally do.”
Speaker 1 · Hear it at 6:57
large enterprises
Other shows on the same ground, closest first.
Gaurav Bansal, VP of Engineering at Blue River Technology (a subsidiary of John Deere), discusses the integration of IoT, AI, and computer vision in smart farming to address labor shortages and climate challenges. He details the John Deere autonomous tractor, which uses stereo cameras and NVIDIA Jetson GPUs for obstacle detection, and the See & Spray system, which uses real-time computer vision to reduce herbicide usage by up to two-thirds. Bansal also highlights the critical role of connectivity, noting a partnership with Starlink to solve rural coverage gaps, and outlines John Deere's goal of achieving fully autonomous production systems for corn and soybeans by 2030.
Willy Pell, VP of Autonomy at Blue River Technology (acquired by John Deere), explains how the company applied machine learning and computer vision to automate farming, starting with the See & Spray weed management system and expanding to the autonomous John Deere AR tractor. Pell details the strategic decision to use stereo cameras instead of LIDAR due to dust and speed constraints, and describes how the system uses deep learning to detect crops versus weeds, achieving significant herbicide savings. The episode also covers the broader roadmap for autonomous tillage, planting, and grain cart coordination, drawing inspiration from Tesla's data-driven approach to achieve full autonomy in a semi-structured agricultural environment.
Jorge Heraud, VP of Autonomy at John Deere, explains how the company leverages its acquisition of Blue River Technology and Spark AI to deploy Level 4 autonomous tractors, using computer vision and machine learning to enable 'See and Spray' and autonomous tillage while managing rural connectivity challenges. RJ He and Ryan McMichael, technology leaders at Zoox, discuss their purpose-built, steering-wheel-free robotaxi recently deployed on public roads in California, detailing a perception stack that integrates cameras, LIDAR, radar, and thermal imaging to ensure safety through redundancy and diversity. The episode contrasts the agricultural application of autonomy, focused on labor relief and precision, with the urban mobility focus of Zoox, highlighting the technical hurdles of sensor fusion, edge cases, and the critical importance of building a robust safety case for public acceptance.
Lane Arthur, Vice President of Data Applications and Analytics at John Deere, explains how the company leverages IoT, machine learning, and computer vision to revolutionize agricultural operations. He details specific applications such as automated grain quality adjustment in combines and weed-differentiating sprayers, which improve efficiency and sustainability. Arthur also discusses the critical role of connectivity, including rural broadband and 5G, in enabling real-time data exchange and remote machine management during the pandemic.
Chris Padwick, Director of Computer Vision and Machine Learning at Blue River Technology (a John Deere subsidiary), explains the engineering behind the See & Spray system, which uses computer vision to spot-spray herbicide on weeds. He details the massive compute requirements, noting the system uses NVIDIA Xavier and Orin GPUs to achieve 0.3 petaflops of processing power for real-time image classification at 12 mph. Padwick also discusses the critical role of data collection, the acquisition by John Deere for scaling, and the future of autonomous agricultural machinery.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Over the Air. The episode itself belongs to its publisher.