mlsanityData to 14 Oct 2026

VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich Manipulation

arXiv 2605.29564 ↗First posted 28 May 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that complements robot proprioception. However, vision-enabled policies tend to overfit to the visual conditions seen during training, limiting their robustness and transferability. We present a human-in-the-loop RL framework that employs teacher-student distillation to achieve robust performance across multiple task variants, trained entirely in the real world without requiring domain randomization or data augmentation. A vision-enabled teacher distills its knowledge into a vision-free student that relies solely on pose, twist, and wrench sensing, combining fast training with strong task generalization. On the real-world NIST assembly benchmark board, our approach achieves 95% overall success after approximately 50 minutes of training on 3 representative tasks, including robust generalization to 8 unseen task variants. Fine-tuning with distillation achieves full success on the most challenging task. We demonstrate that the resulting policies outperform baselines in both robustness and adaptability. Page: https://tuwien-asl.github.io/VE2VF/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 35 of its 39 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

35 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning18 Nov
  2. 2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning13 Dec
  3. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning29 Oct
  4. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes7 Aug
  5. 2024Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist28 Feb

Other references · 30

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  6. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  7. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  8. 2023Efficient Online Reinforcement Learning with Offline Datacited by 363
  9. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 266
  10. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  11. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 100
  12. 2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 90
18 more
  1. 2025MuJoCo Playgroundcited by 78
  2. 2022See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulationcited by 68
  3. 2024TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correctioncited by 59
  4. 2023IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Realitycited by 53
  5. 2021Dynamic Movement Primitives in Robotics: A Tutorial Surveycited by 47
  6. 2022Visuo-Tactile Transformers for Manipulationcited by 47
  7. 2025FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learningcited by 34
  8. 2024Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulationcited by 33
  9. 2020Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigationcited by 32
  10. 2020Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulationcited by 28
  11. 2024AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometriescited by 26
  12. 2025VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulationcited by 25
  13. 2022Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Roboticscited by 24
  14. 2024FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertaintycited by 23
  15. 2025A Survey on Imitation Learning for Contact-Rich Tasks in Roboticscited by 14
  16. 2025SRSA: Skill Retrieval and Adaptation for Robotic Assembly Taskscited by 11
  17. 2025Factorizing Diffusion Policies for Observation Modality Prioritizationcited by 3
  18. 2024Visuotactile-Based Learning for Insertion with Compliant Handscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation
  2. 2026SymVD: Symmetric Vision Language Action Distillation for Robot Manipulation
  3. 2023Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks
  4. 2025ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
  5. 2022How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation
  6. 2026CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning
  7. 2025Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
  8. 2025Zero-Shot Visual Generalization in Robot Manipulation