US 12,249,238 B2
Detecting vehicle aperture and/or door state
Mahsa Ghafarianzadeh, San Francisco, CA (US); and Benjamin John Sapp, San Francisco, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Jul. 28, 2023, as Appl. No. 18/227,511.
Application 18/227,511 is a continuation of application No. 17/210,325, filed on Mar. 23, 2021, granted, now 11,763,668.
Application 17/210,325 is a continuation of application No. 15/897,028, filed on Feb. 14, 2018, granted, now 10,955,851, issued on Mar. 23, 2021.
Prior Publication US 2023/0368660 A1, Nov. 16, 2023
Int. Cl. G08G 1/01 (2006.01); B60K 31/00 (2006.01); G05D 1/00 (2024.01); G06F 18/243 (2023.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 20/58 (2022.01); G08G 1/16 (2006.01)
CPC G08G 1/0145 (2013.01) [B60K 31/0008 (2013.01); G05D 1/0221 (2013.01); G06F 18/24323 (2023.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 20/58 (2022.01); G08G 1/165 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving sensor data, captured by an autonomous vehicle, associated with an environment through which the autonomous vehicle is traversing, the sensor data including image data representing a vehicle having at least one of a door or an aperture;
determining, based at least in part on the sensor data associated with the environment, that a portion of the sensor data is associated with the vehicle in the environment;
providing the sensor data to a machine-learning model, wherein the machine-learning model is trained to output a probability that the vehicle is a blocking vehicle based on whether at least one of the door or aperture of the vehicle is open;
receiving, from the machine-learning model, a probability that the vehicle is a blocking vehicle based at least in part on whether at least one of the door or the aperture of the vehicle is open;
determining a trajectory based at least in part on the probability that the vehicle is the blocking vehicle; and
controlling the autonomous vehicle based on the trajectory.