US 12,337,485 B2
Trajectory optimization using neural networks
Haoran Tang, Emeryville, CA (US); Xi Chen, Emeryville, CA (US); Yan Duan, Emeryville, CA (US); Nikhil Mishra, Irvine, CA (US); Shiyao Wu, Emeryville, CA (US); Maximilian Sieb, Emeryville, CA (US); and Yide Shentu, Berkeley, CA (US)
Assigned to Embodied Intelligence Inc., Emeryville, CA (US)
Filed by Embodied Intelligence Inc., Emeryville, CA (US)
Filed on Jun. 24, 2024, as Appl. No. 18/751,576.
Application 18/751,576 is a continuation of application No. 17/193,870, filed on Mar. 5, 2021, granted, now 12,049,010.
Claims priority of provisional application 62/985,978, filed on Mar. 6, 2020.
Prior Publication US 2024/0342909 A1, Oct. 17, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. B25J 9/16 (2006.01); B25J 5/00 (2006.01); B65G 61/00 (2006.01); G06N 3/08 (2023.01); G05D 1/00 (2024.01); G05D 1/227 (2024.01)
CPC B25J 9/1666 (2013.01) [B25J 9/1605 (2013.01); B25J 9/161 (2013.01); B25J 9/163 (2013.01); B25J 9/1664 (2013.01); B65G 61/00 (2013.01); G06N 3/08 (2013.01); B25J 5/007 (2013.01); B25J 9/1697 (2013.01); G05B 2219/40499 (2013.01); G05B 2219/40519 (2013.01); G05D 1/0088 (2013.01); G05D 1/227 (2024.01)] 20 Claims
OG exemplary drawing
 
1. A trajectory optimization method for a robotic system, the method comprising:
identifying a task for the robotic system, wherein the task comprises one or more requirements;
providing one or more details related to the task to a machine learning model, the machine learning model comprising a neural network trained to generate geometric trajectories for the robotic system that satisfy provided kinematic constraints and provided task constraints, wherein:
the machine learning model determines an optimal trajectory for the robotic system to follow when performing the task that satisfies the one or more requirements; and
the one or more details related to the task comprise a starting point and an ending point, but not a trajectory between the starting point and the ending point;
receiving an output from the machine learning model, wherein the output comprises the optimal trajectory, the optimal trajectory comprising a geometric path determined by the machine learning model; and
directing the robotic system to complete the task via the optimal trajectory.