Update on AgTech automation at CNHI

The Robot Report Podcast · 26 Jan 2024 · 1h 30m

AI in practice: 3 real uses of AI described

What this episode covers

Marc Kermisch, Global CDO at CNHI, discusses the company's progression from assisted autonomy to fully autonomous agricultural machinery, highlighting specific applications like grain cart automation, tillage, and spraying. He details CNHI's strategy involving the acquisition of Hemisphere for centimeter-level GNSS positioning and the integration of AI for precision spraying and generative AI for technical support. The episode also covers the critical role of rural connectivity, exemplified by John Deere's partnership with SpaceX, and recaps innovations from CES 2024, including robots from Figure, Unitree, and ZookS.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulation

CNHI used generative AI to answer technician questions about part numbers and repair procedures for specific tractor models, allowing them to access information immediately without consulting manuals or colleagues.

“we've had unbelievable uh, results in using generative AI to solve what I'd call ankle biter problems … being able to open up your phone and say, hey, what's the part number for the filter on the 715 Steiger and having it immediately return an answer.”

Speaker 13 · Hear it at 1:03:18

ManufacturingAugmenta / Raven Techfully commercialized this year

CNHI commercialized a vision-based spraying system that uses on-vehicle AI to identify weeds versus crops in real-time, allowing for precise application of treatment only to weeds.

“the augmenta capability that I talked about in that variable rate spraying and vision-based spraying system. You know, it's fully commercialized this year and we continue to push that out and really grow that.”

Speaker 13 · Hear it at 1:16:16

Engineering & simulationOn-vehicle AI

CNHI integrated edge AI into autonomous tractors to analyze real-time visual inputs for guidance, swath following, and bale quality assessment during harvesting operations.

“You now are able to take real-time inputs and analyze those back against on the edge AI that we've put on your machines to help you control both guidance and or application … as well as the quality and tightness and compaction of the bale of its, you know, in and of itself.”

Speaker 13 · Hear it at 1:03:18

Mentioned

Companies
CNHI, John Deere, SpaceX, Figure, BMW, Tesla, Optaran, AI Robotics, ZookS, Hemisphere, Raven, Augmenta, Unitree, Boston Dynamics
Products
Glide, Starlink

Other shows on the same ground, closest first.

  • IoT For All Podcast · 20m

    Smart Farming: The Role of IoT and AI | John Deere's Gaurav Bansal | Internet of Things Podcast

    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.

  • IoT For All Podcast · 27m

    How IoT and Smart Farming Technology is Revolutionizing Agriculture

    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.

  • Over the Air · 18m

    Digital Transformation: From Tractors to Autonomous Agriculture

    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.

  • Moore's Lobby · 55m

    Getting Out of the Weeds with John Deere's Revolutionary AI Technology

    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.

  • Built 2 Scale · 1h 10m

    They built a 100-mile highway without humans...

    Hosts Scott Wilcox (Scotty.inc) and Matt Parrott (Pez Limited) discuss the rapid evolution of AI and robotics, highlighting China's completion of a 100-mile autonomous highway and the rise of remote physical labor. They analyze the impact of Google Ultra, Perplexity's integration with Samsung, and the potential disruption of traditional education and market research by AI tools like Notebook LM and N8N. The episode concludes with Matt announcing his move to the US to scale his business, emphasizing the necessity of systems and processes for global expansion.

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Robot Report Podcast. The episode itself belongs to its publisher.