US 11,814,080 B2
Autonomous driving evaluation using data analysis
Yoshifumi Sakamoto, Shiga-ken (JP); Kentaro Aota, Aichi (JP); John Maxwell Cohn, Richmond, VT (US); and Hardy Groeger, Baden-Wuerttemberg (DE)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Feb. 28, 2020, as Appl. No. 16/804,968.
Prior Publication US 2021/0269061 A1, Sep. 2, 2021
Int. Cl. B60W 60/00 (2020.01); G08G 1/16 (2006.01); G08G 1/01 (2006.01); G05D 1/00 (2006.01); G06F 11/30 (2006.01); G06F 11/36 (2006.01); G06F 11/34 (2006.01)
CPC B60W 60/0015 (2020.02) [G05D 1/0055 (2013.01); G06F 11/3013 (2013.01); G06F 11/3664 (2013.01); G06F 11/3684 (2013.01); G08G 1/0133 (2013.01); G08G 1/0145 (2013.01); G08G 1/166 (2013.01); G06F 11/3457 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer implemented method for evaluating autonomous vehicle safety comprising:
defining criteria for safety of autonomous vehicles in a test space, wherein criteria for safety includes complexity factor based on a number of lanes for a road on the test space;
dividing the test space into an intended test space and an unintended test space, wherein the intended test space includes characterizations for the autonomous vehicle that can be quantified for said criteria for safety, and the unintended test space includes characterizations that are not quantifiable for said criteria for safety wherein not quantifiable for said criteria for safety results from unpredictable vehicle behavior resulting from incorrect artificial intelligence that results in performance not consistent with a vehicle's general performance;
measuring the safety of the autonomous vehicles in the intended test space;
combining the unintended test space into the intended test space; and
evaluating the intended test space including the feedback from the unintended test space using a combined simulation of the peripheral vehicles and autonomous vehicles using random criteria for vehicle location, vehicle velocity and vehicle route to provide the evaluation of autonomous vehicle safety.