Deere & Company Patent for Autonomous Obstacle Navigation

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted a patent to Deere & Company for an autonomous off-road vehicle system that uses machine learning to navigate obstacles. The system can identify obstructions, determine if they can be ignored, and either continue navigation, stop, or alert a remote operator.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12585277B2 to Deere & Company for a novel machine-learned obstacle navigation system for autonomous off-road vehicles. The patent details a method where the vehicle uses a first machine-learned model to identify obstructions and, if unsuccessful, a second model to determine if the obstruction can be ignored based on its dimensions. This technology aims to enhance the autonomous navigation capabilities of off-road machinery.

While this is a patent grant and not a regulatory rule imposing direct compliance obligations, it signifies technological advancement in autonomous vehicle systems. Companies developing or deploying similar autonomous off-road vehicles, particularly in agriculture or construction, should be aware of this patented technology. The patent's claims, particularly those related to machine learning for obstacle identification and decision-making, could influence future product development and potentially lead to licensing requirements or design considerations to avoid infringement.

Source document (simplified)

← USPTO Patent Grants

Off-road machine-learned obstacle navigation in an autonomous vehicle environment

Grant US12585277B2 Kind: B2 Mar 24, 2026

Assignee

Deere & Company

Inventors

Travis J. Davis

Abstract

An autonomous off-road vehicle, upon encountering an obstruction while navigating a route, can apply a first machine-learned model to identify the obstruction. In the event that the first machine-learned model cannot identify the obstruction, the autonomous off-road vehicle can apply a second machine-learned model configured to determine whether or not the obstruction can be ignored, for instance based on dimensions of the obstruction. If the obstruction can be ignored, the autonomous off-road vehicle can continue navigating the route. If the obstruction cannot be ignored, the autonomous off-road vehicle can modify the route, can stop, can flag the obstruction to a remote human operator, can modify an interface of a human operator to display a notification or a video feed from the vehicle, and the like.

CPC Classifications

G05D 1/0238 G05D 1/0223 G05D 1/0246 G05D 1/249 G05D 1/628 G05D 1/65 G05D 1/0248 G05D 2201/0201 G05D 2201/0202 G05D 1/0088 G05D 1/0214 G05D 1/0221 G06F 18/24 G06N 3/02 G06V 20/58 G06V 20/64 G06V 10/70 G06V 10/82 G06V 20/60 G06K 9/6267 G01S 7/417 B60W 30/0956 G06T 2207/20084 G06T 2207/20081 G06T 2207/30252 G06T 2207/30261 G06T 2207/10028