mlsanityData to 14 Oct 2026

GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation

arXiv 2508.09960 ↗First posted 13 Aug 2025cs.RO cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

The creation of human-like humanoid robots is hindered by a fundamental fragmentation: data processing and learning algorithms are rarely universal across different robot morphologies. This paper introduces the Generalized Behavior Cloning (GBC) framework, a comprehensive and unified solution designed to solve this end-to-end challenge. GBC establishes a complete pathway from human motion to robot action through three synergistic innovations. First, an adaptive data pipeline leverages a differentiable IK network to automatically retarget any human MoCap data to any humanoid. Building on this foundation, our novel DAgger-MMPPO algorithm with its MMTransformer architecture learns robust, high-fidelity imitation policies. To complete the ecosystem, the entire framework is delivered as an efficient, open-source platform based on Isaac Lab, empowering the community to deploy the full workflow via simple configuration scripts. We validate the power and generality of GBC by training policies on multiple heterogeneous humanoids, demonstrating excellent performance and transfer to novel motions. This work establishes the first practical and unified pathway for creating truly generalized humanoid controllers.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 50 of its 87 references that are in the map. First posted on arXiv 13 Aug 2025.

Builds on

50 of 87 references.

References · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  8. 2020End-to-End Object Detection with Transformerscited by 7,414
  9. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  10. 2016Generative Adversarial Imitation Learningcited by 1,597
  11. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  12. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
38 more
  1. 2019Root Mean Square Layer Normalizationcited by 1,480
  2. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  3. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  4. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  5. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  6. 2015Policy Distillationcited by 440
  7. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  8. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  9. 2021Robust Motion In-betweeningcited by 229
  10. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 227
  11. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 206
  12. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 198
  13. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 189
  14. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  15. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 185
  16. 2024Behavior Generation with Latent Actionscited by 160
  17. 2019Distilling Task-Specific Knowledge from BERT into Simple Neural Networkscited by 153
  18. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
  19. 2024Expressive Whole-Body Control for Humanoid Robotscited by 139
  20. 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 130
  21. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 122
  22. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 112
  23. 2025TWIST: Teleoperated Whole-Body Imitation Systemcited by 101
  24. 2020Unpaired Motion Style Transfer from Video to Animationcited by 94
  25. 2025HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpitcited by 76
  26. 2018Learning Symmetric and Low-energy Locomotioncited by 61
  27. 2024WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contactscited by 61
  28. 2024Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfercited by 53
  29. 2023Teleoperation of Humanoid Robots: A Surveycited by 34
  30. 2024Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policiescited by 30
  31. 2019How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?cited by 25
  32. 2019Whole-Body Geometric Retargeting for Humanoid Robotscited by 20
  33. 2024HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoidcited by 19
  34. 2023ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Spacecited by 12
  35. 2020Dynamic Movement Primitive based Motion Retargeting for Dual-Arm Sign Language Motionscited by 6
  36. 2021Self-Supervised Motion Retargeting with Safety Guaranteecited by 6
  37. 2024AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Modelscited by 3
  38. 2024Unsupervised Neural Motion Retargeting for Humanoid Teleoperationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robotcited by 0