US 11,851,086 B2
Using simulations to identify differences between behaviors of manually-driven and autonomous vehicles
Brian Cohen, San Francisco, CA (US); Guillaume Dupre, San Francisco, CA (US); Jared Russell, San Francisco, CA (US); and Eric Schoenfeld, San Francisco, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Jun. 26, 2020, as Appl. No. 16/912,976.
Prior Publication US 2021/0403033 A1, Dec. 30, 2021
Int. Cl. B60W 60/00 (2020.01); G05D 1/00 (2006.01); G01C 21/34 (2006.01); G01C 22/00 (2006.01)
CPC B60W 60/0011 (2020.02) [B60W 60/0013 (2020.02); G01C 21/3407 (2013.01); G01C 21/3453 (2013.01); G01C 22/00 (2013.01); G05D 1/0088 (2013.01); G05D 2201/0213 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for adjusting software used to operate a simulated autonomous vehicle, the method comprising:
retrieving, by one or more processors, log data collected for a manually-driven vehicle driving along a route;
generating, by the one or more processors based on the retrieved log data, a plurality of path segments for a portion of the route, each of the plurality of path segments being defined by a position of the manually-driven vehicle at a start of a time segment and at an end of the time segment;
running, by the one or more processors using first software for autonomous driving, a simulation including the simulated autonomous vehicle that drives along the plurality of path segments to follow a same route as the manually-driven vehicle;
collecting, by the one or more processors, simulation data for the simulated autonomous vehicle;
extracting, by the one or more processors, one or more metrics from the log data collected for the manually-driven vehicle and one or more metrics collected from the simulation data collected for the simulated autonomous vehicle;
computing, by the one or more processors, a first distance traveled by the manually-driven vehicle along the portion of the route within an amount of time based on the one or more metrics extracted from the log data;
computing, by the one or more processors, a second distance traveled by the simulated autonomous vehicle along the portion of the route within the amount of time based on the one or more metrics extracted from the simulated data;
determining, by the one or more processors, a difference between the first distance and the second distance; and
in response to determining the difference, adjusting, by the one or more processors, the first software to operate the simulated autonomous vehicle more similarly to the manually-driven vehicle.