US 12,304,528 B2
Autonomous driving method for avoiding stopped vehicle and apparatus for the same
Kyoung-Wook Min, Sejong-si (KR); and Jae-Hyuck Park, Daejeon (KR)
Assigned to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed by ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed on Jul. 5, 2022, as Appl. No. 17/857,352.
Claims priority of application No. 10-2021-0090173 (KR), filed on Jul. 9, 2021; and application No. 10-2022-0058339 (KR), filed on May 12, 2022.
Prior Publication US 2023/0008458 A1, Jan. 12, 2023
Int. Cl. B60W 60/00 (2020.01); B60W 30/09 (2012.01); B60W 30/095 (2012.01); B60W 30/18 (2012.01); B60W 40/04 (2006.01); G06V 20/58 (2022.01)
CPC B60W 60/0011 (2020.02) [B60W 30/09 (2013.01); B60W 30/0956 (2013.01); B60W 30/18163 (2013.01); B60W 40/04 (2013.01); B60W 60/0015 (2020.02); G06V 20/584 (2022.01); B60W 2420/403 (2013.01); B60W 2554/20 (2020.02); B60W 2556/40 (2020.02)] 12 Claims
OG exemplary drawing
 
8. An autonomous driving control apparatus comprising:
a processor configured to obtain taillight recognition information for a stopped vehicle identified ahead of an autonomous vehicle, determine whether the stopped vehicle is to be avoided in consideration of the taillight recognition information, when it is determined that the stopped vehicle is to be avoided, set an avoidance method in consideration of whether lane returning is to be performed, which is determined based on an autonomous driving task, set an avoidance time point corresponding to the avoidance method, and control the autonomous vehicle to avoid the stopped vehicle by traveling along an avoidance path generated in conformity with the avoidance time point; and
a memory configured to store the taillight recognition information, the avoidance time point, and the avoidance path,
wherein the avoidance method is any one of a first avoidance method for returning to an original lane after avoiding the stopped vehicle and a second avoidance method for performing lane changing while avoiding the stopped vehicle,
wherein:
the first avoidance method avoids the stopped vehicle by generating an avoidance local path at an avoidance time point that is set in consideration of a time to brake to avoid a collision with the stopped vehicle, and
the second avoidance method avoids the stopped vehicle by generating a lane-change local path at a time point for lane changing,
wherein each of the avoidance local path and the lane-change local path is generated in consideration of an available avoidance space and an avoidance direction that are measured using a high-precision lane level map or a drivable space, and
wherein the processor is configured to, when the avoidance method is set to the first avoidance method, deploy a virtual autonomous vehicle having a size identical to a size of the autonomous vehicle in the avoidance available space, generate a virtual lane central line based on a central line of the virtual autonomous vehicle, and generate the avoidance local path for moving from a lane central line corresponding to the original lane to the virtual lane central line.