Systems and methods for predicting vehicle trajectory

US11126185B2 · kind B2 · utility

Assignee

• TOYOTA RESEARCH INSTITUTE, INC. · US

Inventors

• Stephen G. McGill · Broomall, US
• Luke S. Fletcher · Cambridge, US
• Guy Rosman · Newton, US
• Xin Huang · Xi'an, CN

Key dates

• Filing date: Mar 7, 2019
• Grant date: Sep 21, 2021
• Expiry date: Aug 23, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N7/01
• WIPO field: Control
• WIPO sector: Instruments

Abstract

Systems and methods described herein relate to predicting a trajectory of a vehicle. One embodiment generates first and second predicted vehicle trajectories using respective first and second trajectory predictors based, at least in part, on a plurality of inputs including past trajectory information and vehicle sensor data; generates a confidence score for each of the first and second predicted vehicle trajectories using a confidence estimator that includes a first deep neural network, wherein generating the confidence scores includes computing the confidence scores as a function of time within a predetermined temporal horizon; outputs the first and second predicted vehicle trajectories and their respective confidence scores; and controls operation of the vehicle based, at least in part, on one or more of the first predicted vehicle trajectory, the second predicted vehicle trajectory, the confidence score for the first predicted vehicle trajectory, and the confidence score for the second predicted vehicle trajectory.