mlsanityData to 14 Oct 2026

OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion

arXiv 2609.20566 ↗First posted 17 Sep 2026cs.RO cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Animal demonstrations provide quadruped robots with natural and distinctive gait styles that are difficult to specify through hand-crafted rewards. However, their narrow directional coverage leaves little style-consistent supervision for backward, lateral, and turning commands. We present OmniMimic, a training framework that turns directionally limited animal demonstrations into a single multi-gait policy over target per-axis velocity ranges. OmniMimic first combines temporal reversal, constrained dynamics completion, and sagittal reflection to construct robot-specific kinematic and physical supervision beyond the observed directions. It then expands commands progressively from the demonstrated velocity distribution toward the target per-axis bounds, and uses a shared actor with soft-gated, gait-specialized residual experts to balance reusable locomotion skills with gait-specific corrections. Across four gaits in simulation, OmniMimic reduces mean foot-position RMSE at forward and backward reference velocities by 12.9% and velocity-tracking RMSE on a uniform Cartesian command grid by 63.1%, compared with the matched APEX baseline. The project page is at https://OmniMimic.github.io.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

30 of 41 references.

References · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  3. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  4. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  5. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  6. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  7. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  8. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  9. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 89
  10. 2020Multi-expert learning of adaptive legged locomotioncited by 67
  11. 2022Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learningcited by 37
  12. 2023Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Modelscited by 37
18 more
  1. 2024Leveraging Symmetry in RL-based Legged Locomotion Controlcited by 25
  2. 2023Generalized Animal Imitator: Agile Locomotion with Versatile Motion Priorcited by 19
  3. 2025SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Controlcited by 15
  4. 2024Morphological Symmetries in Roboticscited by 13
  5. 2024A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewardscited by 12
  6. 2024Spatio-Temporal Motion Retargeting for Quadruped Robotscited by 8
  7. 2024Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotioncited by 8
  8. 2025Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotioncited by 8
  9. 2023DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policiescited by 7
  10. 2024Learning to Adapt through Bio-Inspired Gait Strategies for Versatile Quadruped Locomotioncited by 6
  11. 2025Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobilitycited by 5
  12. 2024MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environmentscited by 3
  13. 2025APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robotscited by 2
  14. 2026ReActor: Reinforcement Learning for Physics-Aware Motion Retargetingcited by 2
  15. 2026Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priorscited by 2
  16. 2025Walk Like Dogs: Learning Steerable Imitation Controllers for Legged Robots from Unlabeled Motion Datacited by 1
  17. 2026ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotioncited by 1
  18. 2026Agile perceptive multi-skill locomotion for quadrupedal robots in the wildcited by 1

Built on by

Not cited yet.