mlsanityData to 7 Oct 2026

Integrating Controllable Motion Skills from Demonstrations

arXiv 2408.03018 ↗First posted 6 Aug 2024cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The expanding applications of legged robots require their mastery of versatile motion skills. Correspondingly, researchers must address the challenge of integrating multiple diverse motion skills into controllers. While existing reinforcement learning (RL)-based approaches have achieved notable success in multi-skill integration for legged robots, these methods often require intricate reward engineering or are restricted to integrating a predefined set of motion skills constrained by specific task objectives, resulting in limited flexibility. In this work, we introduce a flexible multi-skill integration framework named Controllable Skills Integration (CSI). CSI enables the integration of a diverse set of motion skills with varying styles into a single policy without the need for complex reward tuning. Furthermore, in a hierarchical control manner, the trained low-level policy can be coupled with a high-level Natural Language Inference (NLI) module to enable preliminary language-directed skill control. Our experiments demonstrate that CSI can flexibly integrate a diverse array of motion skills more comprehensively and facilitate the transitions between different skills. Additionally, CSI exhibits good scalability as the number of motion skills to be integrated increases significantly.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 6 Aug 2024.

Builds on

32 of 44 references.

References · 32

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2017Neural Discrete Representation Learningcited by 4,650
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2016Generative Adversarial Imitation Learningcited by 1,576
  7. 2022Human Motion Diffusion Modelcited by 1,062
  8. 2016Least Squares Generative Adversarial Networkscited by 1,000
  9. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  10. 2018Which Training Methods for GANs do actually Converge?cited by 672
  11. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  12. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
20 more
  1. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  2. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  3. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  4. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 154
  5. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  6. 2021Goal-Conditioned Reinforcement Learning with Imagined Subgoalscited by 129
  7. 2023Robot Parkour Learningcited by 115
  8. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
  9. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 91
  10. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  11. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characterscited by 53
  12. 2023Neural Categorical Priors for Physics-Based Character Controlcited by 37
  13. 2022Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrationscited by 30
  14. 2023Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Modelscited by 30
  15. 2022Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learningcited by 23
  16. 2023HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitationcited by 23
  17. 2021DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learningcited by 15
  18. 2023Learning Terrain-Adaptive Locomotion with Agile Behaviors by Imitating Animalscited by 8
  19. 2023Learning Robust, Agile, Natural Legged Locomotion Skills in the Wildcited by 7
  20. 2020NimbRo-OP2X: Affordable Adult-sized 3D-printed Open-Source Humanoid Robot for Researchcited by 1

Built on by

Not cited yet.