ISSN 3083-4471 API Registry JSON Sitemap
TIRAS Transactions on Intelligent Robotics and Autonomous Systems An open access journal of Kaggleyes Academy
TIRAS > Vol. 1, No. 2 (August 2026) > KAGG:2608.00006
Vol. 1, No. 2 (August 2026) — Article KAGG:2608.00006

Cross-Embodiment Transfer of Local Navigation Skills via Configuration Randomization

Authors: Sakura Ishikawa, Kenji Watanabe, Daichi Mori, Aiko Tanaka

Legged Systems Group, The University of Tokyo, Tokyo, Japan

[Received 2026-07-29; accepted 2026-08-09; published online 2026-08-12]

Abstract:

Local navigation skills learned for one quadruped transfer poorly to another, because leg length, payload, and sensor placement change what the robot perceives and which motions it can execute. This paper extends configuration randomization from low-level locomotion to the skill level. A single local navigation policy is trained in simulation with the AgniNav configuration descriptor, augmented with leg length and payload mass, as an explicit input, while the configuration parameters are sampled from the envelope spanned by a robot fleet. The descriptor modulates the policy through feature-wise affine conditioning and scales its velocity limits. Each new embodiment is adapted with a few hundred rollout episodes by a fine-tune that updates only the conditioning and output layers and is anchored to the pretrained policy by a KL penalty. In Isaac Lab, with a fleet of four quadruped morphologies (leg lengths 0.42 to 0.58 m, payloads 0 to 12 kg, sensor heights 0.35 to 0.55 m), 20 navigation scenarios, and 5 seeds, the method reaches 82.6 percent success on held-out morphologies outside the training support, compared with 73.1 percent for morphology-specific training and 77.8 percent for per-morphology fine-tuning from scratch, and reaches 90 percent of its final success after 420 fine-tune episodes on average, compared with 481 and 455. Ablations identify the configuration descriptor and payload randomization as the most consequential components. The gains come with a smaller clearance margin, and success drops to 74.1 percent when leg length is extrapolated by 22 percent.

Journal: Transactions on Intelligent Robotics and Autonomous Systems (TIRAS)
Volume / Issue: Vol. 1, No. 2 (August 2026)
Article ID: KAGG:2608.00006
DOI: 10.5803/kagg.2608.00006
Received: 2026-07-29
Accepted: 2026-08-09
Published online: 2026-08-12
License: CC BY 4.0

References (40)

  1. J. Hwangbo, J. Lee, A. Dosovitskiy, D. Bellicoso, V. Tsounis, V. Koltun, and M. Hutter. Learning Agile and Dynamic Motor Skills for Legged Robots. arXiv:1901.08652, 2019. arXiv:1901.08652
  2. J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter. Learning Quadrupedal Locomotion over Challenging Terrain. arXiv:2010.11251, 2020. arXiv:2010.11251
  3. T. Miki, J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter. Learning Robust Perceptive Locomotion for Quadrupedal Robots in the Wild. arXiv:2201.08117, 2022. arXiv:2201.08117
  4. N. Rudin, D. Hoeller, P. Reist, and M. Hutter. Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning. arXiv:2109.11978, 2021. arXiv:2109.11978
  5. D. Hoeller, L. Wellhausen, F. Farshidian, and M. Hutter. Learning a State Representation and Navigation in Cluttered and Dynamic Environments. arXiv:2103.04351, 2021. arXiv:2103.04351
  6. N. Rudin, D. Hoeller, M. Bjelonic, and M. Hutter. Advanced Skills by Learning Locomotion and Local Navigation End-to-End. arXiv:2209.12827, 2022. arXiv:2209.12827
  7. D. Hoeller, N. Rudin, D. Sako, and M. Hutter. ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots. arXiv:2306.14874, 2023. arXiv:2306.14874
  8. T. Zang, S. Cheng, H. Huang, S. Wang, and W. Zhang. AgniNav: Configuration-Driven Cross-Embodiment Local Planning for Robot Navigation. arXiv:2606.10903, 2026. arXiv:2606.10903
  9. J. Tobin, R. Fong, A. Ray, J. Schneider, W. Zaremba, and P. Abbeel. Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World. arXiv:1703.06907, 2017. arXiv:1703.06907
  10. X. B. Peng, M. Andrychowicz, W. Zaremba, and P. Abbeel. Sim-to-Real Transfer of Robotic Control with Dynamics Randomization. arXiv:1710.06537, 2017. arXiv:1710.06537
  11. OpenAI, I. Akkaya et al.. Solving Rubik's Cube with a Robot Hand. arXiv:1910.07113, 2019. arXiv:1910.07113
  12. G. Feng et al.. GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots. arXiv:2209.05309, 2022. arXiv:2209.05309
  13. N. Bohlinger, G. Czechmanowski, M. Krupka, P. Kicki, K. Walas, J. Peters, and D. Tateo. One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion. arXiv:2409.06366, 2024. arXiv:2409.06366
  14. E. Perez, F. Strub, H. de Vries, V. Dumoulin, and A. Courville. FiLM: Visual Reasoning with a General Conditioning Layer. arXiv:1709.07871, 2017. arXiv:1709.07871
  15. Z. Zhuang, Z. Fu, J. Wang, C. Atkeson, S. Schwertfeger, C. Finn, and H. Zhao. Robot Parkour Learning. arXiv:2309.05665, 2023. arXiv:2309.05665
  16. X. Cheng, K. Shi, A. Agarwal, and D. Pathak. Extreme Parkour with Legged Robots. arXiv:2309.14341, 2023. arXiv:2309.14341
  17. J. Truong, D. Yarats, T. Li, F. Meier, S. Chernova, D. Batra, and A. Rai. Learning Navigation Skills for Legged Robots with Learned Robot Embeddings. arXiv:2011.12255, 2020. arXiv:2011.12255
  18. W. Yu, J. Tan, C. K. Liu, and G. Turk. Preparing for the Unknown: Learning a Universal Policy with Online System Identification. arXiv:1702.02453, 2017. arXiv:1702.02453
  19. A. Kumar, Z. Fu, D. Pathak, and J. Malik. RMA: Rapid Motor Adaptation for Legged Robots. arXiv:2107.04034, 2021. arXiv:2107.04034
  20. C. Finn, P. Abbeel, and S. Levine. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. arXiv:1703.03400, 2017. arXiv:1703.03400
  21. D. Shah, A. Sridhar, A. Bhorkar, N. Hirose, and S. Levine. GNM: A General Navigation Model to Drive Any Robot. arXiv:2210.03370, 2022. arXiv:2210.03370
  22. D. Shah, A. Sridhar, N. Dashora, K. Stachowicz, K. Black, N. Hirose, and S. Levine. ViNT: A Foundation Model for Visual Navigation. arXiv:2306.14846, 2023. arXiv:2306.14846
  23. A. Sridhar, D. Shah, C. Glossop, and S. Levine. NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration. arXiv:2310.07896, 2023. arXiv:2310.07896
  24. A. Eftekhar et al.. The One RING: a Robotic Indoor Navigation Generalist. arXiv:2412.14401, 2024. arXiv:2412.14401
  25. J. Zhang et al.. Embodied Navigation Foundation Model. arXiv:2509.12129, 2025. arXiv:2509.12129
  26. J. Zhang, Y. Du, X. Guo, S. Sun, X. Liu, Y. Sun, G. Lu, W. Sui, and J. Li. EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness. arXiv:2607.19880, 2026. arXiv:2607.19880
  27. Open X-Embodiment Collaboration et al.. Open X-Embodiment: Robotic Learning Datasets and RT-X Models. arXiv:2310.08864, 2023. arXiv:2310.08864
  28. T. Chen, A. Murali, and A. Gupta. Hardware Conditioned Policies for Multi-Robot Transfer Learning. arXiv:1811.09864, 2018. arXiv:1811.09864
  29. W. Huang, I. Mordatch, and D. Pathak. One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control. arXiv:2007.04976, 2020. arXiv:2007.04976
  30. R. Doshi, H. Walke, O. Mees, S. Dasari, and S. Levine. Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation. arXiv:2408.11812, 2024. arXiv:2408.11812
  31. H. Xi, M. Tan, X. Zhang, S. Cheng, S. Wang, Y. Gu, X. Shen, and W. Zhang. CeRLP: A Cross-embodiment Robot Local Planning Framework for Visual Navigation. arXiv:2603.19602, 2026. arXiv:2603.19602
  32. J. Hu, S. Yuan, G. C. R. Bethala, A. Tzes, and Y. Fang. Learning Adaptive Safety Margins for Visual Navigation. arXiv:2607.18200, 2026. arXiv:2607.18200
  33. V. Makoviychuk et al.. Isaac Gym: High Performance GPU-Based Physics Simulation for Robot Learning. arXiv:2108.10470, 2021. arXiv:2108.10470
  34. M. Mittal et al.. Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments. arXiv:2301.04195, 2023. arXiv:2301.04195
  35. A. Kadian et al.. Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance? arXiv:1912.06321, 2019. arXiv:1912.06321
  36. J. Truong, M. Rudolph, N. H. Yokoyama, S. Chernova, D. Batra, and A. Rai. Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation. arXiv:2207.10821, 2022. arXiv:2207.10821
  37. P. Anderson et al.. On Evaluation of Embodied Navigation Agents. arXiv:1807.06757, 2018. arXiv:1807.06757
  38. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov. Proximal Policy Optimization Algorithms. arXiv:1707.06347, 2017. arXiv:1707.06347
  39. J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel. High-Dimensional Continuous Control Using Generalized Advantage Estimation. arXiv:1506.02438, 2015. arXiv:1506.02438
  40. L. Pinto, M. Andrychowicz, P. Welinder, W. Zaremba, and P. Abbeel. Asymmetric Actor Critic for Image-Based Robot Learning. arXiv:1710.06542, 2017. arXiv:1710.06542
Cite this article Sakura Ishikawa, Kenji Watanabe, Daichi Mori, Aiko Tanaka, "Cross-Embodiment Transfer of Local Navigation Skills via Configuration Randomization," Transactions on Intelligent Robotics and Autonomous Systems, 2026, vol. 1, no. 2, KAGG:2608.00006. DOI: 10.5803/kagg.2608.00006.