US 12,080,044 B2
Prediction sampling techniques
Gowtham Garimella, Dublin, CA (US); Marin Kobilarov, Baltimore, MD (US); Andres Guillermo Morales Morales, San Francisco, CA (US); Ethan Miller Pronovost, San Mateo, CA (US); Kai Zhenyu Wang, Foster City, CA (US); and Xiaosi Zeng, San Mateo, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Nov. 24, 2021, as Appl. No. 17/535,396.
Prior Publication US 2023/0162470 A1, May 25, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/44 (2022.01); B60W 60/00 (2020.01); G06F 16/901 (2019.01); G06V 10/422 (2022.01); G06V 10/764 (2022.01)
CPC G06V 10/454 (2022.01) [B60W 60/0027 (2020.02); G06F 16/9024 (2019.01); G06V 10/422 (2022.01); G06V 10/764 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving sensor data from a sensor associated with a vehicle in an environment, the environment including an object;
determining, based at least in part on the sensor data, a first feature associated with one of the object or the vehicle;
determining, based at least in part on map data associated with the environment, a second feature associated with the environment;
determining, based on the first feature and the second feature, a graph node of a Graph Neural Network (GNN);
determining, based at least in part on inferencing the GNN, first output representing distribution data associated with the graph node, the distribution data including predicted positions for the object or the vehicle in the environment;
determining a sampling technique for sampling the distribution data based at least in part on at least one of a classification type of the graph node, the predicted positions of the distribution data, a distribution type of the distribution data, or an input associated with the distribution data;
determining a first predicted position of the object or the vehicle based at least in part on the sampling technique; and
controlling the vehicle based at least in part on the first predicted position.