US 12,115,982 B2
Unmanned device control based on future collision risk
Mingyu Fan, Beijing (CN); Shuwang Xu, Beijing (CN); Dongchun Ren, Beijing (CN); Yanliang Zhu, Beijing (CN); Deheng Qian, Beijing (CN); and Huaxia Xia, Beijing (CN)
Assigned to BEIJING SANKUAI ONLINE TECHNOLOGY CO., LTD, Beijing (CN)
Filed by BEIJING SANKUAI ONLINE TECHNOLOGY CO., LTD, Beijing (CN)
Filed on Mar. 18, 2022, as Appl. No. 17/698,916.
Claims priority of application No. 202110847025.5 (CN), filed on Jul. 27, 2021.
Prior Publication US 2023/0033069 A1, Feb. 2, 2023
Int. Cl. B60W 30/095 (2012.01); B60W 50/00 (2006.01); B60W 60/00 (2020.01); G05D 1/00 (2024.01)
CPC B60W 30/0956 (2013.01) [B60W 50/0097 (2013.01); B60W 60/0027 (2020.02); G05D 1/0214 (2013.01); B60W 2050/0022 (2013.01); B60W 2554/4042 (2020.02)] 15 Claims
OG exemplary drawing
 
1. An unmanned device control method based on a future collision risk, the method comprising:
acquiring sensing data of obstacles around an unmanned device;
determining, for each obstacle and according to the sensing data, at least one traveling track of the obstacle in a future period of time, to be used as a predicted track corresponding to the obstacle;
determining, for each moment in the future period of time and according to the predicted track corresponding to the obstacle, a collision probability that a collision with the obstacle occurs at each position in a target region at the moment, wherein the target region is a region in which the unmanned device is located in the future period of time;
determining, according to the collision probability that the collision with the obstacle occurs at each position in the target region at the moment, a global collision probability that the collision with the obstacle occurs in the entire target region at the moment; and
controlling the unmanned device in the future period of time according to the global collision probability corresponding to each obstacle at each moment,
wherein the determining, for each moment in the future period of time and according to the predicted track corresponding to the obstacle, a collision probability that a collision with the obstacle occurs at each position in a target region at the moment comprises:
determining, for each position in the target region, an overall probability that the obstacle is located at the position in the target region at the moment; and
determining, according to the overall probability that the obstacle is located at the position in the target region at the moment and overall probabilities that other obstacles are located at the position in the target region at the moment, the collision probability that the collision with the obstacle occurs at the position in the target region at the moment; and
wherein the determining, according to the overall probability that the obstacle is located at the position in the target region at the moment and overall probabilities that other obstacles are located at the position in the target region at the moment, the collision probability that the collision with the obstacle occurs at the position at the moment comprises:
determining, for each of other obstacles and according to the overall probability that the obstacle is located at the position in the target region at the moment and the overall probabilities that the other obstacles are located at the position in the target region at the moment, collision probabilities that the other obstacles collide with the obstacle at the position at the moment; and
determining, according to a maximum collision probability of the collision probabilities for each of the other obstacles that could collide with the obstacle, the collision probability that the collision with the obstacle occurs at the position at the moment.