Two Russian companies have partnered on an advanced autonomous driving system for agricultural vehicles.
The Rusagro agricultural firm and Moscow startup Cognitive Pilot advertise their joint Cognitive Agro Pilot project as a truly self-piloting system requiring virtually no human intervention.
The technology reduces reliance on sensors and global-positioning systems, feeding input from a single camera to a custom neural network that helps plan ahead and adapt to obstacles like workers on the ground.
Computer vision algorithms analyze camera input to ascertain the types and positions of objects along the way, construct trajectories, and give control commands for needed maneuvers, with an obstacle map compiled around the vehicle.
Cognitive Pilot CEO Olga Uskova said Cognitive Agro allows workers to concentrate "more on managing and controlling other harvesting parameters," and this should lower the cost of grain by 3% to 5%, and reduce losses during harvesting by a factor of two.
From Popular Mechanics
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA