Learning Getting-Up Policies for Real-World Humanoid Robots
robust to variations in initial configuration and terrains.We find these innovations enable a real-world G1 humanoid robot to get up from two main situations that we considered: a) lying face up and b) lying face down, both tested on flat, deformable, slippery surfaces and slopes (e.g., sloppy grass and snowfield).
Authors
- Runpei Dong
- Xialin He
- Saurabh Gupta (ORCID: https://orcid.org/0000-0002-1195-9028)
- Zixuan Chen (ORCID: https://orcid.org/0009-0004-1240-8764)
Publication Details
- Published
- 2025-06-21
- DOI
- https://doi.org/10.15607/rss.2025.xxi.063
- Citations
- 4
- Primary Topic
- Reinforcement Learning in Robotics
- Type
- article
- Field-Weighted Citation Impact
- 9.92