Robotics team fixes jitter by counting executed actions instead of wall-clock time
DominiqueCAPaul · x · 2026-07-21
A robotics policy implementation got a major stability fix: the team says 37 of 40 rollouts succeeded after fixing jittery motion.
What went wrong
They were estimating how many actions had been executed during policy inference using wall-clock time (⌈inferencelatency × fps⌉). That approximation was wrong and caused jumps between action chunks.
What changed
They now count the actual executed actions and remove exactly those from the next chunk, which fixed the motion jitter.
The quoted result also says the policy is already strong enough to reach 88% success on actuator unboxing.
More from Embodied
- ReViV reconstructs egocentric 4D viewer-and-scene dynamics from one monocular video — ethz-vlg · 2026-07-21
- Neuracore pitches a one-loop platform for robotics data, training, and deployment — stepjamUK · 2026-07-21
- Humanoid robots are moving from labs into public culture — Olivier__OG · 2026-07-21
- WAIC panel says world models still lack consensus on routes, metrics, and deployment — 量子位 · 2026-07-21
- Polymarket puts Tesla’s California robotaxi launch odds at 16% this year — Polymarket · 2026-07-21
- Tesla expands robotaxi service to Orlando and Tampa — Polymarket · 2026-07-21