robotics
The Robot Finds the Hole With Its Eyes Closed
A proprioception-only policy learned insertion, gear meshing and threading without cameras, force sensors or tactile arrays.
Summary
A proprioception-only policy learned insertion, gear meshing and threading without cameras, force sensors or tactile arrays.
Precise assembly is usually treated as a vision or force-sensing problem. These policies observe only a short history of joint positions, velocities and prior actions while the fixture, part pose and grasp are hidden. Trained entirely in simulation across randomized parts and contacts, they learned peg insertion, gear meshing and nut threading. The peg policy transferred to a real robot without additional training and inserted differently shaped pegs in 73 percent of trials. In matched simulation tests, the blind policies generalized better to unseen shapes and sizes than visual policies, though they could be slower. The result argues that a robot's own joints can provide a useful contact signal, not that external sensing is unnecessary in production assembly.
Why it matters
A proprioception-only policy learned insertion, gear meshing and threading without cameras, force sensors or tactile arrays.
Limits and context
- These policies observe only a short history of joint positions, velocities and prior actions while the fixture, part pose and grasp are hidden.
- The result argues that a robot's own joints can provide a useful contact signal, not that external sensing is unnecessary in production assembly.
Key claims
A proprioception-only policy learned insertion, gear meshing and threading without cameras, force sensors or tactile arrays.
Qualification: These policies observe only a short history of joint positions, velocities and prior actions while the fixture, part pose and grasp are hidden.
Evidence: source-2026-10-19-003
Sources
- arXiv preprint 2610.23849, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.