US 11,953,333 B2
Systems and methods for autonomous vehicle performance evaluation
Kumar Hemachandra Chellapilla, Mountain View, CA (US); Emilie Jeanne Anne Danna, Sunnyvale, CA (US); David Tse-Zhou Lu, Menlo Park, CA (US); Sameer Qureshi, Sunnyvale, CA (US); and Alexis Weill, San Francisco, CA (US)
Assigned to Lyft, Inc., San Francisco, CA (US)
Filed by Lyft, Inc., San Francisco, CA (US)
Filed on Dec. 2, 2019, as Appl. No. 16/700,835.
Claims priority of provisional application 62/814,674, filed on Mar. 6, 2019.
Prior Publication US 2020/0284597 A1, Sep. 10, 2020
Int. Cl. G01C 21/34 (2006.01); G06Q 10/02 (2012.01); G06Q 50/30 (2012.01); G07C 5/00 (2006.01); G07C 5/08 (2006.01); G08G 1/00 (2006.01); G08G 1/0968 (2006.01)
CPC G01C 21/3453 (2013.01) [G01C 21/3438 (2013.01); G01C 21/3461 (2013.01); G06Q 10/02 (2013.01); G06Q 50/30 (2013.01); G07C 5/008 (2013.01); G07C 5/0808 (2013.01); G07C 5/085 (2013.01); G08G 1/096833 (2013.01); G08G 1/207 (2013.01); G08G 1/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by a computing system, transportation information associated with a transportation request, the transportation information comprising a pick up location and a drop off location;
determining, by the computing system, a first route associated with the transportation request and a non-autonomous vehicle;
determining, by the computing system, a second route associated with the transportation request and an autonomous vehicle based on an operating design domain (ODD) associated with one or more autonomous vehicles in a fleet of vehicles;
categorizing, by the computing system, disengagements in scenarios associated with the ODD into at least an adverse outcome category and a no adverse outcome category based on expected outcomes determined by simulation of the disengagements;
determining, by the computing system, at least one performance metric associated with the second route based on a weighted average of performance metric values associated with road segments of the second route, wherein the performance metric values are based on the expected outcomes of the disengagements in the adverse outcome category, wherein at least one of the road segments has a default performance metric value determined based on other road segments within a threshold distance of the at least one of the road segments, and wherein the performance metric values are weighted based on frequency by which the road segments were traversed;
selecting, by the computing system, the second route based at least in part on the at least one performance metric and a comparison of the first route and the second route;
assigning, by the computing system, an autonomous vehicle from the fleet of vehicles to the transportation request based on selection of the second route; and
dispatching, by the computing system, the autonomous vehicle to respond to the transportation request based on the assigning.