US 12,094,270 B2
Identification of corner cases of operating scenarios
Antonia Reiter, Stuttgart (DE); Indrasen Raghupatruni, Hemmingen (DE); Maria Belen Bescos Del Castillo, Moensheim (DE); and Paul Ruhnau, Leonberg-Hoefingen (DE)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Mar. 3, 2022, as Appl. No. 17/686,031.
Claims priority of application No. 10 2021 202 332.0 (DE), filed on Mar. 10, 2021.
Prior Publication US 2022/0292894 A1, Sep. 15, 2022
Int. Cl. G07C 5/08 (2006.01); G06F 16/901 (2019.01); G06F 30/20 (2020.01); G07C 5/00 (2006.01)
CPC G07C 5/0816 (2013.01) [G06F 16/9024 (2019.01); G06F 30/20 (2020.01); G07C 5/008 (2013.01); G07C 5/0841 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A computer-implemented method for identifying corner cases of operating scenarios of vehicles, comprising:
generating one or more time records of sensor data from one or more sensors of a vehicle during at least semi-autonomous operation of the vehicle;
determining one or multiple features for characterizing an operating state of a vehicle based on the one or more time records of sensor data from the one or more sensors of the vehicle;
extracting at least one trace graph relating to the one or to the multiple features from a graph database;
modifying the at least one trace graph, a modified trace graph being generated;
reconstructing a first operating scenario from the trace graph;
reconstructing a second operating scenario from the modified trace graph;
identifying the second operating scenario as a corner case based on the second operating scenario being assessed as new and/or as unknown as compared to the first operating scenario on the basis of a predetermined criterion; and
testing the corner case during the at least semi-autonomous operation of the vehicle.