US 11,940,798 B2
System, method, and computer-readable medium for an autonomous vehicle to pass a bicycle
Michael J. Delp, Ann Arbor, MI (US); Ruijia Feng, Ann Arbor, MI (US); and Shan Bao, Ann Arbor, MI (US)
Assigned to TOYOTA RESEARCH INSTITUTE, INC., Los Altos, CA (US); and The Regents of the University of Michigan, Ann Arbor, MI (US)
Filed by TOYOTA RESEARCH INSTITUTE, INC., Los Altos, CA (US)
Filed on Jul. 6, 2018, as Appl. No. 16/029,270.
Prior Publication US 2020/0012286 A1, Jan. 9, 2020
Int. Cl. G05D 1/02 (2020.01); G01C 21/34 (2006.01); G01C 21/36 (2006.01); G05D 1/00 (2006.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01); G08G 1/16 (2006.01)
CPC G05D 1/0214 (2013.01) [G01C 21/3461 (2013.01); G01C 21/3626 (2013.01); G05D 1/0231 (2013.01); G06V 20/58 (2022.01); G06V 20/588 (2022.01); G08G 1/166 (2013.01); G05D 2201/0213 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A system, comprising:
an imaging device; and
processing circuitry configured to
receive information from the imaging device,
receive information from a positioning system,
identify variables to a left side and a right side of an autonomous vehicle based on the information received from the imaging device,
determine whether the identified variables identify a cyclist passing situation based on the information received from the imaging device, the cyclist passing situation being a situation in which the autonomous vehicle passes the cyclist,
in a case when the cyclist passing situation is not identified based on the information received from the imaging device alone, identify the cyclist passing situation based on the information from the imaging device and the positioning system,
match the cyclist passing situation with real world data collected from vehicles driven by human drivers in corresponding situations, the real world data including a least a safe passing distance relative to the cyclist as determined from data collected from the vehicles driven by the human drivers passing cyclists, and
plan a path of the autonomous vehicle based on the real world data,
wherein the cyclist passing situation is based on the information received from the imaging device includes identifying a centerline as either a solid center line or a dashed center line, and a current weather condition,
the cyclist passing situation being based on the information received from the imaging device includes identifying when the cyclist is traveling in a bike lane, the processing circuitry determining that the cyclist passing situation arises when the cyclist is not traveling in the bike lane, and
the cyclist passing situation and the path of the autonomous vehicle is planned taking into account whether the cyclist is traveling at less than half of a posted speed limit and whether passing is permitted in a no-passing zone when a vehicle travels at less than half of the posted speed limit,
wherein the planned path of the autonomous vehicle is displayed in the autonomous vehicle.