mlsanityData to 7 Oct 2026

PDP: Physics-Based Character Animation via Diffusion Policy

arXiv 2406.00960 ↗First posted 3 Jun 2024cs.GR cs.ROcited by 30

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

Abstract (arXiv)

Generating diverse and realistic human motion that can physically interact with an environment remains a challenging research area in character animation. Meanwhile, diffusion-based methods, as proposed by the robotics community, have demonstrated the ability to capture highly diverse and multi-modal skills. However, naively training a diffusion policy often results in unstable motions for high-frequency, under-actuated control tasks like bipedal locomotion due to rapidly accumulating compounding errors, pushing the agent away from optimal training trajectories. The key idea lies in using RL policies not just for providing optimal trajectories but for providing corrective actions in sub-optimal states, giving the policy a chance to correct for errors caused by environmental stimulus, model errors, or numerical errors in simulation. Our method, Physics-Based Character Animation via Diffusion Policy (PDP), combines reinforcement learning (RL) and behavior cloning (BC) to create a robust diffusion policy for physics-based character animation. We demonstrate PDP on perturbation recovery, universal motion tracking, and physics-based text-to-motion synthesis.

Key facts. Cited by 30 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 23 of its 48 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

23 of 48 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  6. 2022Human Motion Diffusion Modelcited by 1,062
  7. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  8. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  9. 2016The KIT Motion-Language Datasetcited by 334
  10. 2022EDGE: Editable Dance Generation From Musiccited by 284
  11. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 198
  12. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 153
10 more
  1. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 109
  2. 2018Neural probabilistic motor primitives for humanoid controlcited by 96
  3. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  4. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 58
  5. 2024DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasetscited by 47
  6. 2020UniCon: Universal Neural Controller For Physics-based Character Motioncited by 39
  7. 2023Neural Categorical Priors for Physics-Based Character Controlcited by 37
  8. 2022ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characterscited by 21
  9. 2023Diffusion Co-Policy for Synergistic Human-Robot Collaborative Taskscited by 15
  10. 2023Learning Bipedal Walking for Humanoids with Current Feedbackcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 15.

30 papers.

Sort:

By area:

  1. 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusioncited by 128
  2. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 103
  3. 2025Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Controlcited by 27
  4. 2025UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Controlcited by 24
  5. 2025From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidancecited by 17
  6. 2024Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimickingcited by 14
  7. 2025SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Controlcited by 14
  8. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  9. 2026InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactionscited by 10
  10. 2025SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Controlcited by 7
  11. 2025StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Datacited by 5
  12. 2025From Generated Human Videos to Physically Plausible Robot Trajectoriescited by 5
18 more
  1. 2025InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphscited by 4
  2. 2026SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Controlcited by 4
  3. 2025Diffusion-based Planning with Learned Viability Filterscited by 2
  4. 2025RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characterscited by 1
  5. 2026Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Controlcited by 1
  6. 2026MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Controlcited by 1
  7. 2026GPC: Large-Scale Generative Pretraining for Transferable Motor Controlcited by 1
  8. 2025From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Controlcited by 0
  9. 2026SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillationcited by 0
  10. 2026FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesiscited by 0
  11. 2026EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcingcited by 0
  12. 2026NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Controlcited by 0
  13. 2026Recovering Physically Plausible Human-Object Interactions from Monocular Videoscited by 0
  14. 2026Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physicscited by 0
  15. 2026In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physicscited by 0
  16. 2026Progressively Learning Heterogeneous Skills in a Unified Latent Spacecited by 0
  17. 2026LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interactioncited by 0
  18. 2026PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Scalable Motion In-betweening via Diffusion and Physics-Based Character Adaptation
  2. 2026PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
  3. 2023InsActor: Instruction-driven Physics-based Characters
  4. 2024Taming Diffusion Probabilistic Models for Character Control
  5. 2026ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
  6. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Models
  7. 2025No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts
  8. 2026REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning