mlsanityData to 7 Oct 2026

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation

arXiv 2503.02881 ↗First posted 4 Mar 2025cs.RO cs.AI cs.LGcited by 103

On the map: Diffusion models → Diffusion and flow policies for robotics

also in 1 more
Abstract (arXiv)

Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces; however, this remains challenging for robots. Existing visual imitation learning (IL) approaches rely on action chunking to model complex behaviors, which lacks the ability to respond instantly to real-time tactile feedback during the chunk execution. Furthermore, most teleoperation systems struggle to provide fine-grained tactile / force feedback, which limits the range of tasks that can be performed. To address these challenges, we introduce TactAR, a low-cost teleoperation system that provides real-time tactile feedback through Augmented Reality (AR), along with Reactive Diffusion Policy (RDP), a novel slow-fast visual-tactile imitation learning algorithm for learning contact-rich manipulation skills. RDP employs a two-level hierarchy: (1) a slow latent diffusion policy for predicting high-level action chunks in latent space at low frequency, (2) a fast asymmetric tokenizer for closed-loop tactile feedback control at high frequency. This design enables both complex trajectory modeling and quick reactive behavior within a unified framework. Through extensive evaluation across three challenging contact-rich tasks, RDP significantly improves performance compared to state-of-the-art visual IL baselines. Furthermore, experiments show that RDP is applicable across different tactile / force sensors. Code and videos are available on https://reactive-diffusion-policy.github.io.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 45 of its 72 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

45 of 72 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Learning Diffusion Policies from Demonstrations For Compliant Contact-rich Manipulation25 Oct
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 43

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  7. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  8. 2023GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulatorscited by 180
  9. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  10. 2020DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulationcited by 164
  11. 2023AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation Systemcited by 136
  12. 2024Learning Visuotactile Skills with Two Multifingered Handscited by 71
31 more
  1. 2024Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learningcited by 69
  2. 2024OPEN TEACH: A Versatile Teleoperation System for Robotic Manipulationcited by 67
  3. 20243D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensingcited by 67
  4. 2023Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensingcited by 51
  5. 2023AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wildcited by 46
  6. 2025Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Groundingcited by 40
  7. 2021GelSlim3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Fingercited by 39
  8. 2024ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulationcited by 36
  9. 2024Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Controlcited by 36
  10. 2021ReSkin: versatile, replaceable, lasting tactile skinscited by 33
  11. 2023See to Touch: Learning Tactile Dexterity through Visual Incentivescited by 33
  12. 2024FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulationcited by 32
  13. 2023MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulationcited by 30
  14. 2024Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformercited by 27
  15. 2024AnySkin: Plug-and-play Skin Sensing for Robotic Touchcited by 22
  16. 2020Soft-Bubble grippers for robust and perceptive manipulationcited by 18
  17. 2024RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packingcited by 18
  18. 20239DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimationcited by 16
  19. 2024Learning Variable Compliance Control From a Few Demonstrations for Bimanual Robot with Haptic Feedback Teleoperation Systemcited by 13
  20. 2024Learning Precise, Contact-Rich Manipulation through Uncalibrated Tactile Skinscited by 11
  21. 2024MORPHeus: a Multimodal One-armed Robot-assisted Peeling System with Human Users In-the-loopcited by 10
  22. 2022DTact: A Vision-Based Tactile Sensor that Measures High-Resolution 3D Geometry Directly from Darknesscited by 8
  23. 2024CushSense: Soft, Stretchable, and Comfortable Tactile-Sensing Skin for Physical Human-Robot Interactioncited by 7
  24. 2024Tactile-Driven Non-Prehensile Object Manipulation via Extrinsic Contact Mode Controlcited by 6
  25. 2024Built Different: Tactile Perception to Overcome Cross-Embodiment Capability Differences in Collaborative Manipulationcited by 6
  26. 2018Deformation Capture via Soft and Stretchable Sensor Arrayscited by 5
  27. 2023Precise Robotic Needle-Threading with Tactile Perception and Reinforcement Learningcited by 5
  28. 2024GelSlim 4.0: Focusing on Touch and Reproducibilitycited by 4
  29. 2019Effective Estimation of Contact Force and Torque for Vision-based Tactile Sensor with Helmholtz-Hodge Decompositioncited by 2
  30. 2024An Electromagnetism-Inspired Method for Estimating In-Grasp Torque from Visuotactile Sensorscited by 1
  31. 2024ALPHA-α and Bi-ACT Are All You Need: Importance of Position and Force Information/Control for Imitation Learning of Unimanual and Bimanual Robotic Manipulation with Low-Cost Systemcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 31; 2026: 72.

103 papers.

Sort:

By area:

  1. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  2. 2026AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routingcited by 41
  3. 2025VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedbackcited by 37
  4. 2025OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensingcited by 37
  5. 2025TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Modelscited by 30
  6. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  7. 2025Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Grippercited by 29
  8. 2025Embodied AI: From LLMs to World Modelscited by 23
  9. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 22
  10. 2025Dense Policy: Bidirectional Autoregressive Learning of Actionscited by 19
  11. 2026TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulationcited by 17
  12. 2026Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulationcited by 17
38 more
  1. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  2. 2025Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulationcited by 16
  3. 2025Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalizationcited by 16
  4. 2025Vidarc: Embodied Video Diffusion Model for Closed-loop Controlcited by 15
  5. 2026FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulationcited by 15
  6. 2025Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulationcited by 14
  7. 2026FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulationcited by 14
  8. 2026VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAscited by 14
  9. 2025VGGT-DP: Generalizable Robot Control via Vision Foundation Modelscited by 11
  10. 2026AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perceptioncited by 11
  11. 2025VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuningcited by 10
  12. 2026T-Rex: Tactile-Reactive Dexterous Manipulationcited by 10
  13. 2025MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoningcited by 9
  14. 2026AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Modelscited by 9
  15. 2026Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attentioncited by 9
  16. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 8
  17. 2025End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collectioncited by 8
  18. 2025ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learningcited by 8
  19. 2026CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuningcited by 7
  20. 2025FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Taskscited by 6
  21. 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulationcited by 6
  22. 2026ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matchingcited by 5
  23. 2025On the Importance of Tactile Sensing for Imitation Learning: A Case Study on Robotic Match Lightingcited by 4
  24. 2025InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphscited by 4
  25. 2025Delay-Aware Diffusion Policy: Bridging the Observation-Execution Gap in Dynamic Taskscited by 4
  26. 2026Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategycited by 4
  27. 2026SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulationcited by 4
  28. 2026UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Modelscited by 4
  29. 2026Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulationcited by 4
  30. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challengescited by 3
  31. 2025Multimodal Diffusion Forcing for Forceful Manipulationcited by 3
  32. 2026DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adaptercited by 3
  33. 2026Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policycited by 3
  34. 2026RoboPocket: Improve Robot Policies Instantly with Your Phonecited by 3
  35. 2026Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLAcited by 3
  36. 2026LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imaginationcited by 3
  37. 2026ContactWorld: What Representations Matter for Vision-Tactile Latent World Models in Contact-Rich Manipulationcited by 3
  38. 2026Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injectioncited by 3

50 most cited of 103 All 103 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation
  2. 2026TacCoRL: Integrating Tactile Feedback into VLA via Simulation
  3. 2026N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation
  4. 2026PEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile Manipulation
  5. 2025Tactile-Conditioned Diffusion Policy for Force-Aware Robotic Manipulation
  6. 2026Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation
  7. 2026TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance
  8. 2026VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation