US 11,851,062 B2
Physics-informed optimization for autonomous driving systems
David Smith, Sunnyvale, CA (US); and Kevin Yoon, Oakland, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Dec. 9, 2020, as Appl. No. 17/116,314.
Prior Publication US 2022/0176962 A1, Jun. 9, 2022
Int. Cl. B60W 30/18 (2012.01); B60W 60/00 (2020.01); G01C 21/34 (2006.01)
CPC B60W 30/18109 (2013.01) [B60W 60/001 (2020.02); G01C 21/3461 (2013.01); G01C 21/3492 (2013.01); B60W 2510/18 (2013.01); B60W 2710/18 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying, based on grade data of a route of an autonomous vehicle (AV), a segment of the route that has a grade value that meets a threshold grade value;
identifying map data of a road network associated with the route;
responsive to identifying the segment, generating, based on the grade data and physical vehicle data of the AV, driving constraint data for the segment of the route;
embedding the driving constraint data in the map data to generate map data embedded with the driving constraint data;
while the AV is travelling the segment of the route, identifying current environmental sensing data for a portion of the segment of the route, the current environmental sensing data being associated with a position of one or more objects proximate the AV;
causing the AV to generate, based on the map data embedded with the driving constraint data for the segment of the route and the current environmental sensing data associated with the portion of the segment of the route, short time horizon routing data corresponding to the portion of the segment; and
causing the AV to travel the portion of the segment of the route based on the short time horizon routing data.