mlsanityData to 7 Oct 2026

Towards Embodiment Scaling Laws in Robot Locomotion

arXiv 2505.05753 ↗First posted 9 May 2025cs.RO cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodiment scaling laws, the hypothesis that increasing the number of training embodiments improves generalization to unseen ones, using robot locomotion as a test bed. We procedurally generate ~1,000 embodiments with topological, geometric, and joint-level kinematic variations, and train policies on random subsets. We observe positive scaling trends supporting the hypothesis, and find that embodiment scaling enables substantially broader generalization than data scaling on fixed embodiments. Our best policy, trained on the full dataset, transfers zero-shot to novel embodiments in simulation and the real world, including the Unitree Go2 and H1. These results represent a step toward general embodied intelligence, with relevance to adaptive control for configurable robots, morphology co-design, and beyond.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 88 of its 119 references that are in the map. First posted on arXiv 9 May 2025.

Builds on

88 of 119 references.

References · 88

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2023Segment Anythingcited by 8,158
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2020Scaling Laws for Neural Language Modelscited by 6,411
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  11. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  12. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
38 more
  1. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  5. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  6. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  7. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  8. 2021Scaling Vision Transformerscited by 993
  9. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  10. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  11. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  12. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  13. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  14. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  15. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  16. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  17. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  18. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  19. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 277
  20. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 268
  21. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  22. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  23. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  24. 2022GNM: A General Navigation Model to Drive Any Robotcited by 161
  25. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 144
  26. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
  27. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  28. 2023Extreme Parkour with Legged Robotscited by 120
  29. 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
  30. 2023Robot Parkour Learningcited by 115
  31. 2020One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Controlcited by 114
  32. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
  33. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  34. 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 101
  35. 2023On Bringing Robots Homecited by 101
  36. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 101
  37. 2022MetaMorph: Learning Universal Controllers with Transformerscited by 78
  38. 2022Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trialscited by 78

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 9.

12 papers.

  1. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  2. 2026SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulationcited by 10
  3. 2026Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotioncited by 3
  4. 2025Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomizationcited by 2
  5. 2026Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Controlcited by 2
  6. 2025Flexible Locomotion Learning with Diffusion Model Predictive Controlcited by 1
  7. 2025GenDexHand: Generative Simulation for Dexterous Handscited by 1
  8. 2026Shape Your Body: Value Gradients for Multi-Embodiment Robot Designcited by 1
  9. 2026Rapid Embodiment Adaptation for Quadrupedal Locomotioncited by 1
  10. 2026Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Controlcited by 0
  11. 2026Teach and Grow: An Agent-Centered Architecture for General Robot Learningcited by 0
  12. 2026Intelligence Across Embodimentscited by 0