US 11,734,832 B1
Prediction on top-down scenes based on object motion
Andres Guillermo Morales Morales, San Francisco, CA (US); Marin Kobilarov, Baltimore, MD (US); Gowtham Garimella, Dublin, CA (US); and Kai Zhenyu Wang, Foster City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Feb. 2, 2022, as Appl. No. 17/649,690.
Application 17/649,690 is a continuation of application No. 16/719,780, filed on Dec. 18, 2019, granted, now 11,276,179.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); G06T 7/20 (2017.01); G06T 11/20 (2006.01); G06T 7/70 (2017.01); G05D 1/02 (2020.01); G06V 20/58 (2022.01); G06V 30/262 (2022.01); G06N 3/045 (2023.01)
CPC G06T 7/20 (2013.01) [G05D 1/0221 (2013.01); G05D 1/0231 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/70 (2017.01); G06T 11/20 (2013.01); G06V 20/58 (2022.01); G06V 30/274 (2022.01); G05D 2201/0213 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30261 (2013.01); G06T 2210/12 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving data associated with an object in an environment;
generating, based at least in part on the data, an image representing a top-down view of the environment;
inputting the image into a machine learned model trained to determine a trajectory template based at least in part on an unsupervised learning algorithm; and
receiving, from the machine learned model, the trajectory template, wherein the trajectory template is indicative of a predicted trajectory associated with the object.