mlsanityData to 7 Oct 2026

Generalizable Humanoid Manipulation with 3D Diffusion Policies

arXiv 2410.10803 ↗First posted 14 Oct 2024cs.RO cs.CV cs.LGcited by 49

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

Abstract (arXiv)

Humanoid robots capable of autonomous operation in diverse environments have long been a goal for roboticists. However, autonomous manipulation by humanoid robots has largely been restricted to one specific scene, primarily due to the difficulty of acquiring generalizable skills and the expensiveness of in-the-wild humanoid robot data. In this work, we build a real-world robotic system to address this challenging problem. Our system is mainly an integration of 1) a whole-upper-body robotic teleoperation system to acquire human-like robot data, 2) a 25-DoF humanoid robot platform with a height-adjustable cart and a 3D LiDAR sensor, and 3) an improved 3D Diffusion Policy learning algorithm for humanoid robots to learn from noisy human data. We run more than 2000 episodes of policy rollouts on the real robot for rigorous policy evaluation. Empowered by this system, we show that using only data collected in one single scene and with only onboard computing, a full-sized humanoid robot can autonomously perform skills in diverse real-world scenarios. Videos are available at https://humanoid-manipulation.github.io .

Key facts. Cited by 49 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 30 of its 44 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

30 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Equivariant Diffusion Policy1 Jul
  2. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning1 Jul
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 27

  1. 2020Denoising Diffusion Implicit Modelscited by 9,655
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  5. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  6. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  7. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 167
  8. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
  9. 2024DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulationcited by 149
  10. 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 137
  11. 2023AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation Systemcited by 136
  12. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
15 more
  1. 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
  2. 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 112
  3. 2024Learning Visuotactile Skills with Two Multifingered Handscited by 71
  4. 2024Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learningcited by 69
  5. 2024Humanoid Parkour Learningcited by 66
  6. 2024Humanoid Locomotion as Next Token Predictioncited by 63
  7. 2022On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baselinecited by 55
  8. 2023Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperationcited by 49
  9. 2024Robot Utility Models: General Policies for Zero-Shot Deployment in New Environmentscited by 43
  10. 2024RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effectivecited by 41
  11. 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 38
  12. 2024Twisting Lids Off with Two Handscited by 36
  13. 2024Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learningcited by 36
  14. 2024View-Invariant Policy Learning via Zero-Shot Novel View Synthesiscited by 35
  15. 2024ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperationcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 21; 2026: 28.

49 papers.

Sort:

By area:

  1. 2025TWIST: Teleoperated Whole-Body Imitation Systemcited by 86
  2. 2025ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learningcited by 34
  3. 2025From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priorscited by 25
  4. 2025OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformercited by 17
  5. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  6. 2025StereoVLA: Enhancing Vision-Language-Action Models with Stereo Visioncited by 16
  7. 2025H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learningcited by 13
  8. 2025HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoningcited by 12
  9. 2025Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robotscited by 11
  10. 2026Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrationscited by 11
  11. 2026HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulationcited by 10
  12. 2025SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulationcited by 9
37 more
  1. 2025UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policiescited by 9
  2. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 8
  3. 2025OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulationcited by 7
  4. 2025Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robotscited by 5
  5. 2025D2PPO: Diffusion Policy Policy Optimization with Dispersive Losscited by 5
  6. 2025R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulationcited by 4
  7. 2025Learning Human-Humanoid Coordination for Collaborative Object Carryingcited by 4
  8. 2025FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generationcited by 4
  9. 2025Coordinated Humanoid Manipulation with Choice Policiescited by 4
  10. 2026From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillationcited by 4
  11. 2025UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation Learningcited by 3
  12. 2026PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generationcited by 3
  13. 2025TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learningcited by 2
  14. 2026A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Controlcited by 2
  15. 2026CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulationcited by 2
  16. 2026FAR-Dex: Few-shot Data Augmentation and Adaptive Residual Policy Refinement for Dexterous Manipulationcited by 2
  17. 2026Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulationcited by 2
  18. 2026R3DP: Real-Time 3D-Aware Policy for Embodied Manipulationcited by 2
  19. 2026Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priorscited by 2
  20. 2026Fourier Features Let Agents Learn High Precision Policies with Imitation Learningcited by 2
  21. 2026Structured 4D Latent Predictive Model for Robot Planningcited by 2
  22. 2026SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulationcited by 2
  23. 2026Lifting Embodied World Models for Planning and Controlcited by 1
  24. 2026CUBic: Coordinated Unified Bimanual Perception and Control Frameworkcited by 1
  25. 2026MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulationcited by 1
  26. 2026KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulationcited by 1
  27. 2026ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotioncited by 1
  28. 2026Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulationcited by 1
  29. 2026HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RLcited by 1
  30. 2026UNIC: Learning Unified Multimodal Extrinsic Contact Estimationcited by 0
  31. 2026TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objectscited by 0
  32. 2026Active Stereo-Camera Outperforms Multi-Sensor Setup in ACT Imitation Learning for Humanoid Manipulationcited by 0
  33. 2026Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Datacited by 0
  34. 2026DexPIE: Stable Dexterous Policy Improvement from Real-World Experiencecited by 0
  35. 2026Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentationcited by 0
  36. 2026Dynamics-Aware Meta-Imitation for Generalization to Unseen Robotic Manipulationcited by 0
  37. 2026EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
  2. 2025DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation
  3. 2026SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation
  4. 2025TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System
  5. 2024The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control
  6. 2025Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning
  7. 2026HumDex: Humanoid Dexterous Manipulation Made Easy
  8. 2026AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation