US 11,842,530 B2
Systems and methods for latent distribution modeling for scene-consistent motion forecasting
Sergio Casas, Toronto (CA); Cole Christian Gulino, Pittsburgh, PA (US); Shun Da Suo, Toronto (CA); Katie Z. Luo, Sunnyvale, CA (US); Renjie Liao, Toronto (CA); and Raquel Urtasun, Toronto (CA)
Assigned to UATC, LLC, Mountain View, CA (US)
Filed by UATC, LLC, San Francisco, CA (US)
Filed on Jan. 15, 2021, as Appl. No. 17/150,995.
Claims priority of provisional application 63/119,981, filed on Dec. 1, 2020.
Claims priority of provisional application 62/985,862, filed on Mar. 5, 2020.
Prior Publication US 2021/0276595 A1, Sep. 9, 2021
Int. Cl. G06V 10/82 (2022.01); B60W 60/00 (2020.01); G08G 1/16 (2006.01); G05D 1/02 (2020.01); G06V 20/58 (2022.01); G06F 18/2137 (2023.01); G06V 30/19 (2022.01); G06V 30/24 (2022.01)
CPC G06V 10/82 (2022.01) [B60W 60/0027 (2020.02); G05D 1/0212 (2013.01); G06F 18/2137 (2023.01); G06V 20/58 (2022.01); G06V 30/19173 (2022.01); G08G 1/166 (2013.01); G06V 30/2504 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining scene-consistent motion forecasts from sensor data, the method comprising:
obtaining, by a computing system comprising one or more computing devices, scene data comprising one or more actor features;
providing, by the computing system, the scene data to a latent prior model, the latent prior model configured to generate scene latent data in response to receipt of scene data, the scene latent data comprising a latent distribution that is partitioned into one or more latent variables, wherein the one or more latent variables encode unobserved dynamics relative to a respective actor feature of the one or more actor features;
obtaining, by the computing system, the scene latent data from the latent prior model;
sampling, by the computing system, latent sample data from the scene latent data;
providing, by the computing system, the latent sample data to a decoder model, the decoder model configured to decode the latent sample data into a motion forecast comprising one or more predicted trajectories of the one or more actor features; and
receiving, by the computing system, the motion forecast comprising one or more predicted trajectories of the one or more actor features from the decoder model;
providing, by the computing system, the one or more predicted trajectories to a motion planning model configured to generate a motion plan for an autonomous vehicle based at least in part on the one or more predicted trajectories; and
implementing, by the computing system, the motion plan to control the autonomous vehicle.