mlsanityData to 14 Oct 2026

FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Tasks

arXiv 2509.17053 ↗First posted 21 Sep 2025cs.ROcited by 7

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Many contact-rich manipulation tasks require precise force regulation. However, most imitation learning (IL) policies remain position-centric and lack explicit force awareness, and adding force/torque sensors to collaborative robot arms is often costly and requires additional hardware design. To overcome these issues, we propose FILIC, a Force-guided Imitation Learning framework with impedance torque control. FILIC integrates a Transformer-based IL policy with an impedance controller in a dual-loop structure, enabling compliant force-informed, force-executed manipulation. For robots without force/torque sensors, we introduce a cost-effective end-effector force estimator using joint torque measurements through analytical Jacobian-based inversion while compensating with model-predicted torques from a digital twin. Experiments show that FILIC significantly outperforms vision-only and joint-torque-based methods, achieving safer, more compliant, and adaptable contact-rich manipulation. The source code is available at https://github.com/OpenGHz/mujoco-wrench-estimator.git.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 24 of its 42 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

24 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation4 Mar
  2. 2024ALOHA Unleashed: A Simple Recipe for Robot Dexterity17 Oct
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
  4. 2022A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies1 Aug

Other references · 20

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  3. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  4. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  5. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  6. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  7. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  8. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 146
  9. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 123
  10. 2024Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Controlcited by 41
  11. 2019Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assemblycited by 39
  12. 2025FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learningcited by 34
8 more
  1. 2025TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Modelscited by 32
  2. 2024TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulationcited by 23
  3. 2024Natural Language Can Help Bridge the Sim2Real Gapcited by 21
  4. 2023Dexterous In-Hand Manipulation of Slender Cylindrical Objects through Deep Reinforcement Learning with Tactile Sensingcited by 14
  5. 2025Robotic Compliant Object Prying Using Diffusion Policy Guided by Vision and Force Observationscited by 10
  6. 2021SCAPE: Learning Stiffness Control from Augmented Position Control Experiencescited by 4
  7. 2025Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Taskscited by 3
  8. 2024Admittance Visuomotor Policy Learning for General-Purpose Contact-Rich Manipulationscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learningcited by 2
  2. 2026Enabling Dynamic Tracking in Vision-Language-Action Models via Time-Discrete and Time-Continuous Velocity Feedforwardcited by 1
  3. 2026Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learningcited by 1
  4. 2026CR-VLA-Force: Learning Control-aware Compliance VLA Model for Robust Contact-rich Robotic Manipulationcited by 1
  5. 2026Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futurescited by 0
  6. 2026Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulationcited by 0
  7. 2026Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
  2. 2024ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation
  3. 2026Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control
  4. 2026Impedance Cloning: Learning Equilibrium Point Parameters for Contact-Rich Manipulation ↗
  5. 2025FTACT: Force Torque aware Action Chunking Transformer for Pick-and-Reorient Bottle Task
  6. 2025DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation
  7. 2026Contact-Aware Imitation Learning Through Contact Factorization
  8. 2026VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations