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)→

Original post →

More from Embodied

Embodied channel →