Blind robot policies go far: error feedback and contact exploration are the key enablers
_krishna_murthy · x · 2026-11-01
krishnamurthy highlights that blind robot policies can get surprisingly far, with two key enablers: proxy tactile input from the error between commanded and achieved joint angles, and contact-exploring behaviors emerging from blind RL experts. These policies implicitly measure force/torque info; the open question is whether true tactile sensing unlocks qualitatively distinct behaviors, robustness, and speed.
Related event: Blind Robot Policies Outperform Expectations, Sparking Controller Debate(4 posts)→
More from Embodied
- mink 1.4.0 released with new Elastic Constraints feature for robot control — kevin_zakka · 2026-11-01
- Naval predicts 4-passenger drones will eventually end commercial air travel, with a long interregnum ahead — naval · 2026-11-01
- Meta Quest game scans your real room and turns it into a haunted house — Scobleizer · 2026-11-01
- RoboAuto: Robot Program Search With Multi-Level Physical Understanding — DJiafei · 2026-11-01
- Developer dresses robot 'Bob' as a ghost to hand out Halloween candy — chrismatthieu · 2026-11-01
- GRASP authors compare with SuperMimic: extracting more optimization signal from sim experience — hankyang94 · 2026-11-01