mlsanityData to 14 Oct 2026

FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning

arXiv 2606.12406 ↗First posted 10 Jun 2026cs.RO cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

31 of 48 references.

References · 31

  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  3. 2025DINOv3cited by 1,414
  4. 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 782
  5. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 671
  6. 2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretrainingcited by 399
  7. 2020Critic Regularized Regressioncited by 275
  8. 2023GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulatorscited by 189
  9. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 134
  10. 2025Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulationcited by 108
  11. 2025ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulationcited by 91
  12. 2024Vision Language Models are In-Context Value Learnerscited by 90
19 more
  1. 2024Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learningcited by 47
  2. 2025SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulationcited by 42
  3. 2025Robot Data Curation with Mutual Information Estimatorscited by 37
  4. 2024ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulationcited by 36
  5. 2025FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learningcited by 34
  6. 2024FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulationcited by 33
  7. 2025DataMIL: Selecting Data for Robot Imitation Learning with Datamodelscited by 28
  8. 2024Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformercited by 27
  9. 2025CUPID: Curating Data your Robot Loves with Influence Functionscited by 23
  10. 2025Curating Demonstrations using Online Experiencecited by 18
  11. 2024Learning Variable Compliance Control From a Few Demonstrations for Bimanual Robot with Haptic Feedback Teleoperation Systemcited by 13
  12. 2025FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Taskscited by 7
  13. 2025CoinFT: A Coin-Sized, Capacitive 6-Axis Force Torque Sensor for Robotic Applicationscited by 5
  14. 2020Contact Localization for Robot Arms in Motion without Torque Sensingcited by 3
  15. 2022End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Controlcited by 2
  16. 2024Loss Function Considering Dead Zone for Neural Networkscited by 2
  17. 2024Cycloidal Quasi-Direct Drive Actuator Designs with Learning-based Torque Estimation for Legged Roboticscited by 2
  18. 2025Design and Experimental Validation of Sensorless 4-Channel Bilateral Teleoperation for Low-Cost Manipulatorscited by 2
  19. 2026A Soft Wrist with Anisotropic and Selectable Stiffness for Robust Robot Learning in Contact-rich Manipulationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulationcited by 3
  2. 2026Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learningcited by 1