US 12,246,747 B2
Adaptive and fuel efficient planning and control
Chaozhe He, Clarence Center, NY (US); and Xiaoyu Huang, San Jose, CA (US)
Assigned to PlusAI, Inc., Santa Clara, CA (US)
Filed by PlusAI, Inc., Santa Clara, CA (US)
Filed on May 31, 2023, as Appl. No. 18/204,216.
Prior Publication US 2024/0400086 A1, Dec. 5, 2024
Int. Cl. B60W 60/00 (2020.01); B60W 40/105 (2012.01); B60W 50/06 (2006.01)
CPC B60W 60/001 (2020.02) [B60W 40/105 (2013.01); B60W 50/06 (2013.01); B60W 2520/00 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
based on a machine learning model, determining, by a computing system, a set of regenerable elevation indexes for distances ahead of a vehicle in an environment and speed ranges for the vehicle;
selecting, by the computing system, a highest regenerable elevation index of the set of regenerable elevation indexes determined by the machine learning model;
determining, by the computing system, parameters for the environment based on the highest regenerable elevation index of the set of regenerable elevation indexes;
generating, by the computing system, a speed profile for the environment based on the parameters;
generating, by the computing system, control actions for the vehicle in the environment based on the speed profile; and
causing, by the computing system, control of at least one of braking, acceleration, and steering of the vehicle to generate movement based on the control actions.