FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning
This work enables force-aware teleoperation and policy learning on commodity robot arms without additional sensors, addressing a practical bottleneck for low-cost robotics.
The paper introduces NEXT, a data-driven method that estimates external joint torques without dedicated force sensors, training in 1 minute from 10 minutes of free-motion data. Combined with FIRST, a force-informed resampling strategy for behavior cloning, it improves policy learning by over 17% in task progress across five long-horizon tasks.
Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates external joint torques without needing any dedicated force sensors. NEXT trains in 1 minute from only 10 minutes of free-motion data, yet achieves estimates comparable to dedicated joint-torque sensors. NEXT enables force-feedback teleoperation on low-cost arms and improves policy learning through Force-Informed Re-Sampling Training (FIRST), which up-samples pre-contact and contact segments during behavior cloning. Across five long-horizon tasks, FIRST outperforms prior force-aware policies by over 17% in task progress. Together, NEXT and FIRST bring force-aware teleoperation and policy learning to off-the-shelf robots without additional sensing hardware. Video results and code are available at https://jasonjzliu.com/factr2