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

• URL: http://arxiv.org/abs/2606.12406v1
• Date: Wed, 10 Jun 2026 17:59:35 GMT
• Title: FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning
• Abstract summary: Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost.<n>We present Neural External Torque Estimation (torque), a data-driven method that estimates external joint torques without needing any dedicated force sensors.<n>Next enables force-aware teleoperation on low-cost arms and improves policy learning through Force-Informed Re-Sampling Training.
• Score: 54.93624123794711
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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

Related papers

• A Disturbance in the Force: Force Actuation on the RAVEN II Surgical Robot with Parallel Motor-Cable Units [3.2434623519843906]
  A parallel motor-cable system is developed for haptic feedback in surgical robots.<n> Cables with controllable tension connected to the robot end-effector can provide the desired external force.<n>Preliminary experiments suggest an accuracy of force actuation with errors less than 1 N.
  arXiv  Detail & Related papers  (2026-08-06T18:27:58Z)
• FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation [66.22092641373067]
  FTP-1 is the first generalist foundation tactile policy pretrained to acquire transferable tactile manipulation abilities.<n>It supports varied tactile inputs, including image-, array-, and state-based signals.<n>It learns tactile skills that transfer beyond the sensors seen during pretraining.
  arXiv  Detail & Related papers  (2026-06-11T09:30:09Z)
• ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation [75.39847750457626]
  ForceVLA2, an end-to-end vision-language-action framework, equips robots with hybrid force-position control and explicit force awareness.<n>To support learning and evaluation, we construct ForceVLA2-Dataset, containing 1,000 trajectories over 5 contact-rich tasks.<n>Experiments show that ForceVLA2 substantially improves success rates and reliability in contact-rich manipulation.
  arXiv  Detail & Related papers  (2026-03-16T12:03:58Z)
• UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors [51.88112610411651]
  We propose a novel unified tactile representation learning framework that learns a shared latent force space across diverse tactile sensors.<n>UniForce reduces cross-sensor domain shift by jointly modeling inverse dynamics (image-to-force) and forward dynamics (force-to-image)<n>To avoid reliance on expensive external force/torque (F/T) sensors, we exploit static equilibrium and collect force-paired data via direct sensor--object--sensor interactions.
  arXiv  Detail & Related papers  (2026-02-01T11:03:01Z)
• Feel the Force: Contact-Driven Learning from Humans [52.36160086934298]
  Controlling fine-grained forces during manipulation remains a core challenge in robotics.<n>We present FeelTheForce, a robot learning system that models human tactile behavior to learn force-sensitive manipulation.<n>Our approach grounds robust low-level force control in scalable human supervision, achieving a 77% success rate across 5 force-sensitive manipulation tasks.
  arXiv  Detail & Related papers  (2025-06-02T17:57:52Z)
• FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning [70.65987250853311]
  force feedback is readily available in most robot arms, but not commonly used in teleoperation and policy learning.<n>We present a low-cost, intuitive, bilateral teleoperation setup that relays external forces of the follower arm back to the teacher arm.<n>We then introduce FACTR, a policy learning method that employs a curriculum which corrupts the visual input with decreasing intensity throughout training.
  arXiv  Detail & Related papers  (2025-02-24T18:59:07Z)
• Proprioceptive External Torque Learning for Floating Base Robot and its Applications to Humanoid Locomotion [17.384713355349476]
  This paper introduces a method for learning external joint torque solely using proprioceptive sensors (encoders and IMUs) for a floating base robot. Real robot experiments demonstrate that the network can estimate the external torque and contact wrench with significantly smaller errors. The study also validates that the estimated contact wrench can be utilized for zero moment point (ZMP) feedback control.
  arXiv  Detail & Related papers  (2023-09-08T05:33:56Z)
• Fine Robotic Manipulation without Force/Torque Sensor [9.908082209033612]
  A typical 6-axis Force/Torque (F/T) sensor is mounted between the robot's wrist and the end-effector in order to measure the forces exerted by the environment onto the robot (the external wrench) Although a typical 6-axis F/T sensor can provide highly accurate measurements, it is expensive and vulnerable to drift and external impacts. Existing methods aiming at estimating the external wrench using only the robot's internal signals are limited in scope. We present a Neural Network based method and argue that by devoting particular attention to the training data structure, it is possible to accurately estimate the
  arXiv  Detail & Related papers  (2023-01-31T05:06:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.