NeuralActuator Wins RSS System Award and Goes Open Source
MIT_CSAIL · x · 2026-07-16
NeuralActuator has won the RSS 2026 Outstanding Systems Paper Award.
The author announced that the project is now fully open-sourced, including the code, pre-trained checkpoints, datasets, data collection pipeline, and hardware setup instructions. The repository also contains additional experimental and technical details not included in the paper, such as residual torque modeling and different approaches to implicitly/explicitly coupling external force estimation with differentiable simulation.
The team is continuously collecting actuator data across different platforms and welcomes data contributions and collaborations.
Related event: MIT and Amazon Introduce NeuralActuator for Sensorless Force Sensing(3 posts)→
More from Embodied
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27
- StackChan robot performs an AI-generated skit, orchestrated by Hermes Agent via JSON script — alexcovo_eth · 2026-10-27
- Full teardown of Zomotor linear actuator for humanoid robots — MarwaEldiwiny · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27