US 11,726,492 B2
Collision avoidance perception system
James William Vaisey Philbin, Palo Alto, CA (US); Cooper Stokes Sloan, San Francisco, CA (US); Noureldin Ehab Hendy, West Lafayette, IN (US); Nicholas George Charchut, Santa Monica, CA (US); and Chuang Wang, Sunnyvale, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Apr. 14, 2020, as Appl. No. 16/848,834.
Application 16/848,834 is a continuation in part of application No. 16/591,518, filed on Oct. 2, 2019.
Prior Publication US 2021/0101624 A1, Apr. 8, 2021
Int. Cl. G05D 1/02 (2020.01); B60W 60/00 (2020.01); B60W 30/095 (2012.01); G06V 10/764 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01)
CPC G05D 1/0274 (2013.01) [B60W 30/0956 (2013.01); B60W 60/0016 (2020.02); B60W 60/00272 (2020.02); B60W 60/00276 (2020.02); G06V 10/764 (2022.01); G06V 10/803 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
a memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving spatial data associated with a first sensor type;
receiving image data associated with an image sensor;
determining, based at least in part on the spatial data and using a first machine-learned model trained to determine occupancy maps from only spatial data, a first current occupancy map and a first predicted occupancy map;
determining, based at least in part on the image data and using a second machine-learned model trained to determine occupancy maps from only image data, a second current occupancy map and a second predicted occupancy map;
combining the first current occupancy map and the second current occupancy map into a data structure indicating whether a portion of an environment is occupied or unoccupied at a current time;
combining the first predicted occupancy map and the second predicted occupancy map into the data structure indicating whether the portion of the environment is occupied or unoccupied at a future time; and
controlling an autonomous vehicle based at least in part on the data structure.