US 12,221,131 B2
Accident pattern determination apparatus and method
Masataka Mori, Kariya (JP); Kenji Muto, Kariya (JP); Kazuhito Takenaka, Kariya (JP); Daisuke Hirano, Kariya (JP); Suguru Yamazaki, Kariya (JP); Yoshinori Takeuchi, Kariya (JP); and Shun Shimizu, Kariya (JP)
Assigned to DENSO CORPORATION, Kariya (JP)
Filed by DENSO CORPORATION, Kariya (JP)
Filed on Mar. 8, 2021, as Appl. No. 17/194,726.
Claims priority of application No. 2020-041407 (JP), filed on Mar. 10, 2020.
Prior Publication US 2021/0284197 A1, Sep. 16, 2021
Int. Cl. G08G 1/16 (2006.01); B60W 40/04 (2006.01); B60W 40/09 (2012.01); B60W 60/00 (2020.01); G06N 5/02 (2023.01); B60W 40/08 (2012.01)
CPC B60W 60/0015 (2020.02) [B60W 40/04 (2013.01); B60W 40/09 (2013.01); G06N 5/02 (2013.01); G08G 1/16 (2013.01); B60W 2040/0872 (2013.01)] 9 Claims
OG exemplary drawing
 
1. An accident pattern determination apparatus comprising:
a storage storing attributes assigned to a plurality of predefined traffic situations;
an acquirer configured to acquire, for each of vehicle-related accident cases, an accident pattern that is a combination of traffic situations in a respective accident case, from the plurality of predefined traffic situations; and
a determiner configured to determine, for each accident pattern acquired by the acquirer, whether the accident pattern is an accident pattern of high accident risk or an accident pattern of low accident risk for specific vehicles or drivers, based on the accident patterns acquired for the respective accident cases and the attributes assigned to the plurality of predefined traffic situations, wherein
the specific vehicles are autonomous driving vehicles,
the attributes include a first attribute assigned to traffic situations in which autonomous driving will malfunction, and a second attribute assigned to traffic situations that are likely to affect driver's driving, and
the determiner is configured to compare, for each accident pattern including at least one traffic situation assigned the second attribute, a number of accident cases for the accident pattern including the at least one traffic situation assigned the second attribute and a number of accident cases for an accident pattern that shares a common combination of traffic situations not assigned the second attribute with the accident pattern including the at least one traffic situation assigned the second attribute, and thereby determine whether the accident pattern including the at least one traffic situation assigned the second attribute is of high accident risk for the autonomous driving vehicles.