US 11,814,041 B2
Vehicle control device, vehicle control method, and storage medium that performs risk calculation for traffic participant
Misa Komuro, Wako (JP); and Yosuke Sakamoto, Wako (JP)
Assigned to HONDA MOTOR CO., LTD., Tokyo (JP)
Filed by HONDA MOTOR CO., LTD., Tokyo (JP)
Filed on Oct. 15, 2020, as Appl. No. 17/070,969.
Claims priority of application No. 2019-191024 (JP), filed on Oct. 18, 2019.
Prior Publication US 2021/0114589 A1, Apr. 22, 2021
Int. Cl. B60W 30/09 (2012.01); G08G 1/16 (2006.01); B60R 11/04 (2006.01); B60W 10/04 (2006.01); B60W 10/20 (2006.01); B60W 10/18 (2012.01); B60R 11/00 (2006.01)
CPC B60W 30/09 (2013.01) [B60R 11/04 (2013.01); B60W 10/04 (2013.01); B60W 10/18 (2013.01); B60W 10/20 (2013.01); G08G 1/163 (2013.01); B60R 2011/0003 (2013.01); B60W 2420/42 (2013.01); B60W 2554/4047 (2020.02); B60W 2554/4048 (2020.02); B60W 2710/18 (2013.01); B60W 2710/20 (2013.01); B60W 2720/10 (2013.01); B60W 2720/12 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A vehicle control device comprising:
a processor configured to:
recognize a peripheral status of a vehicle including a position of a traffic participant present in a periphery of the vehicle on a basis of an image captured by a camera provided with the vehicle;
estimate a peripheral attention ability of the traffic participant on a basis of the output of the in-vehicle device;
set a risk area associated with the traffic participant on a basis of the peripheral attention ability of the traffic participant, wherein the risk area is determined based on a defined boundary line between a first position at which an index value is zero and a second position at which the index value is not zero, and wherein the index value is a negative value as the traffic participant is being approached by the vehicle, wherein, when a plurality of time-series images of the traffic participant captured by the camera is input, the processor is configured to estimate a peripheral attention ability of the traffic participant by inputting the plurality of time-series images captured by the camera to a learning model that is trained to output information indicating whether the traffic participant is in a state where the peripheral attention ability is reduced; and
based on the risk area associated with the traffic participant and the state where the peripheral attention ability of the traffic participant is reduced, facilitating steering of the vehicle to avoid entry by the vehicle into the risk area.