Trajectory optimization using neural networks

US12179363B2 · kind B2 · utility

Assignee

• Embodied Intelligence Inc. · US

Inventors

• Haoran Tang · Emeryville, US
• Xi Chen · Annandale, US
• Yan Duan · Berkeley, US
• Nikhil Mishra · Irvine, US
• Shiyao Wu · Emeryville, US
• Maximilian Sieb · Emeryville, US
• Yide Shentu · Berkeley, US

Key dates

• Filing date: Mar 5, 2021
• Grant date: Dec 31, 2024
• Expiry date: Dec 28, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N5/04
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Various embodiments of the technology described herein generally relate to systems and methods for trajectory optimization with machine learning techniques. More specifically, certain embodiments relate to using neural networks to quickly predict optimized robotic arm trajectories in a variety of scenarios. Systems and methods described herein use deep neural networks to quickly predict optimized robotic arm trajectories according to certain constraints. Optimization, in accordance with some embodiments of the present technology, may include optimizing trajectory geometry and dynamics while satisfying a number of constraints, including staying collision-free, and minimizing the time it takes to complete the task.