Following the machines, people and ideas shaping agriculture. Selected developments, clear context and a link to the original source.
Robotics. Intelligence. Agriculture.
12 stories matching “Computer vision”.
Carbon Robotics introduced LaserWeeder G2 in February 2025, offering multiple working widths and revised lasers, cameras, computing and cooling to extend its tractor-mounted weeding approach across different farm layouts.
The JaetRobi project combines camera-based plant recognition with a precisely positioned blue laser, targeting young weeds close to vegetable crops while researchers address speed and reliability.
Bengaluru-based Niqo Robotics announced plans in March 2026 to expand its crop library, geographic reach and machine configurations, building on precision-weeding operations in India and the United States.
At CES 2022, John Deere presented an autonomous tillage system combining an 8R tractor, a connected chisel plow, stereo cameras and mobile monitoring, with farmer availability planned later that year.
FarmWise introduced Vulcan at World Ag Expo in February 2023, offering computer-vision-guided mechanical weeding in an open cultivator frame, with single-bed and triple-bed versions announced for vegetable growers.
University of León researchers publish annotated field images collected by a ground robot, providing a reusable resource for crop-detection development.
Arkansas graduates won two competitions in Indianapolis, including a strawberry processing prototype combining vision, motion control and safety systems.
A new research paper sets out WildDrone’s drone, ecology and computer-vision programme, including wildlife monitoring at Kenya’s Ol Pejeta Conservancy.
Embrapa-linked research follows cattle body measurements over time, exploring a less disruptive way to identify changes in growth rate.
The OdinsAEye consortium will connect tractor-mounted cameras, weed recognition and farm software, backed by DKK 8.3 million from Innovation Fund Denmark.
USDA’s Digital Agricultural Systems Hub combines crop imagery, machine-learning resources and deployable cameras to help move agricultural computer vision from research into practical field tools.
Cambridge researchers report a major increase in laboratory screening capacity by automating images of plant-parasitic nematodes, with crop applications still a next step.
