NeuralActuator: Sensorless Force Perception
MIT_CSAIL · x · 2026-07-15
MIT CSAIL highlights a robotics study accepted by RSS 2026, named NeuralActuator.
This work introduces a neural actuator model to jointly predict three types of information:
- 扭矩: Modeling the nonlinear, time-varying current-to-torque relationship in low-cost servos
- 外部接触力: Sensing external forces without torque or tactile sensors
- 电机状态: Determining the current operating region of each motor
The authors note they have expanded coverage to more robots, including LeRobot-S101 and Franka Panda, and released quick demo videos with further details to follow.
Related event: MIT and Amazon Introduce NeuralActuator for Sensorless Force Sensing(3 posts)→
More from Embodied
- AI researchers guessed robots wouldn't outrun humans until 2034 — it already happened — ben_j_todd · 2026-10-26
- Shanghai AI Lab-led team releases 100-hour egocentric wearable dataset for humanoid training — ChuckDBrooks · 2026-10-26
- RealSense D585 Pro AI-Powered 3D Stereo Depth Camera Unboxed for Physical AI — chrismatthieu · 2026-10-26
- Physical world agent swarm demo shared on X — pduan · 2026-10-26
- Scoble shares his full list of AI wearable recording mics — best ones 'yet to come' — Scobleizer · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26