US 12,393,192 B2
Behavior prediction for railway agents for autonomous driving system
Vishu Goyal, Sunnyvale, CA (US); Stéphane Ross, San Jose, CA (US); and Kai Ding, Santa Clara, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Oct. 26, 2023, as Appl. No. 18/494,997.
Application 18/494,997 is a continuation of application No. 17/089,046, filed on Nov. 4, 2020, granted, now 11,841,704.
Prior Publication US 2024/0126296 A1, Apr. 18, 2024
Int. Cl. G05D 1/02 (2020.01); G05D 1/00 (2006.01); G05D 1/228 (2024.01); G05D 1/617 (2024.01)
CPC G05D 1/0088 (2013.01) [G05D 1/0214 (2013.01); G05D 1/228 (2024.01); G05D 1/617 (2024.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising one or more computing devices configured to:
detect, using a detection system including one or more sensors, a rail agent in a vicinity of an autonomous vehicle, the rail agent being on a track having a geometry;
determine a likelihood for each of one or more probable paths of the rail agent based on each of one or more motion plans of the one or more probable paths, wherein at least one of the one or more probable paths includes a path direction in which the rail agent will probably travel and at least one of the one or more motion plans;
determine a path for the autonomous vehicle based on a most probable path for the rail agent; and
operate the autonomous vehicle based, at least in part, upon the determined path.