ETH Zurich trains robotic hand to walk on its five fingers across 14 surfaces
burny_tech · x · 2026-09-28
ETH Zurich researchers used reinforcement learning to train a robotic hand to walk on its five fingers, with onboard power, sensing, and computation.
- The hand can crawl, steer, recover from falls, and adapt its locomotion across 14 indoor and outdoor surfaces including carpet, tile, asphalt, grass, and gravel.
- It can also press keyboard keys while supporting its own weight, and use overhead visual feedback to push objects toward target locations.
More from Embodied
- Builder brings a physical Codex Pet to San Francisco for OpenAI Dev Day — paw_lean · 2026-09-28
- Researchers debate GPT-6 Astra: a generalist VLA that could beat custom VLAs — YouJiacheng · 2026-09-28
- Eric Jang: now is the window to test OSS models on robotics before the gap closes — ericjang11 · 2026-09-28
- 10 NeurIPS 2026 robotics papers to watch: VLA inference and long-horizon tasks — shaohua0116 · 2026-09-28
- Claude Opus 5 Shows Creative Tool-Regrasp Skills in Robot Manipulation Tasks — ericjang11 · 2026-09-28
- GPT-6 Astra unlocks agentic real2sim: vision models as tools to turn room video into interactive sims — ericjang11 · 2026-09-28