ROBOT CONTROL USING ACTION IMAGES AND A CRITICAL NETWORK
Patent Information
- Application Number
- DE602020053381
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2020-05-28
- Filing Date
- 2020-09-15
- Publication Date
- 2025-06-25
- Estimated Expiration
- 2040-09-15
AI Technical Summary
Existing robotic systems face challenges in efficiently training critic networks for robotic tasks, particularly in grasping and manipulation, due to the need for extensive real-world data and the difficulty in generalizing from simulated to real-world environments.
The use of action images representing candidate poses of robotic components, processed by a trained critic network, to determine the probability of task success, allowing for training based largely on simulated data and enabling high success rates in real-world scenarios.
This approach enables high success rates for robotic tasks, such as grasping, even with disparate objects and environments, by leveraging simulated data and reducing the need for extensive real-world training, thus improving efficiency and effectiveness.