US 12,240,497 B1
Determining intention of bicycles and other person-wide vehicles
Yi-Ting Lin, Foster City, CA (US); Derek Xiang Ma, San Carlos, CA (US); Kenneth Michael Siebert, Redwood City, CA (US); and Oytun Ulutan, Buena Park, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Sep. 21, 2022, as Appl. No. 17/949,566.
Int. Cl. B60W 60/00 (2020.01); B60W 40/04 (2006.01); B60W 50/00 (2006.01); G06V 10/70 (2022.01); G06V 20/58 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01)
CPC B60W 60/0017 (2020.02) [B60W 40/04 (2013.01); B60W 50/0097 (2013.01); B60W 60/00274 (2020.02); G06V 10/70 (2022.01); G06V 20/58 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01); B60W 2420/403 (2013.01); B60W 2554/4026 (2020.02); B60W 2554/4045 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
non-transitory memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform actions including:
receiving, from a first sensor of an autonomous vehicle traversing an environment, first sensor data relating to the environment;
receiving, from a second sensor of the autonomous vehicle that is different to the first sensor, second sensor data, the second sensor data comprising visual data relating to the environment;
identifying, based at least in part on the first sensor data, a single-track vehicle in the environment in the vicinity of the autonomous vehicle;
determining, based at least in part on the first sensor data and the second sensor data, a portion of visual data corresponding to the single-track vehicle;
providing the portion of the visual data as an input to a machine-learned model trained to determine a predicted turning action of single-track vehicles;
receiving, from the machine-learned model, a predicted turning action for the single-track vehicle based at least in part on the portion of the visual data; and
controlling the autonomous vehicle based at least in part on the predicted turning action.