ALEXANDRIA, Va., Sept. 17 -- United States Patent no. 12,415,540, issued on Sept. 16, was assigned to WAABI Innovation Inc. (Toronto).

"Trajectory value learning for autonomous systems" was invented by Chris Jia Han Zhang (Toronto), Runsheng Guo (Toronto), Wenyuan Zeng (Toronto) and Raquel Urtasun (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "Trajectory value learning for autonomous systems includes generating an environment image from sensor input and processing the environment image through an image neural network to obtain a feature map. Trajectory value learning further includes sampling possible trajectories to obtain a candidate trajectory for an autonomous system, extracting, from the featur...