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. 1 (July 2026) > KAGG:2607.00005
Vol. 1, No. 1 (July 2026) — Article KAGG:2607.00005

Cross-Embodiment Distillation of Local Navigation Planners from Humanoid to Quadruped Teams

Authors: Yifan Chen, Zhiyuan Wang, Haoran Liu, Xiaotong Zhang

Robotics and Autonomous Systems Lab, Shanghai Jiao Tong University, Shanghai, China

[Received 2026-07-07; accepted 2026-07-18; published online 2026-07-21]

Abstract:

Configuration-driven local planners such as AgniNav can serve several robot embodiments from a single planning stack, but the full planner is too expensive for the onboard computers of commodity quadrupeds. This preprint presents a cross-embodiment distillation pipeline in which a configuration-driven teacher planner generates local navigation trajectories in a shared, body-normalized configuration space, and a compact onboard student policy is distilled from these trajectories with an explicit embodiment descriptor as input. Training combines on-policy data aggregation, a finite-difference consistency regularizer that aligns the sensitivity of the student to descriptor changes with that of the teacher, and a held-out embodiment split used for model selection. The pipeline is evaluated in Isaac Lab with a Unitree Go2 and a 12-DoF H1-class humanoid over 20 indoor-outdoor transition scenes, 5 seeds, and 50 episodes per scene and seed, and onboard on a Go2 whose Jetson Orin computer runs the student. The distilled student reaches 90.4 percent navigation success, compared with 81.5 percent for a per-embodiment oracle teacher and 82.3 percent for a student without embodiment conditioning, with a teacher parity score of 93.1 percent and an onboard decision latency of 8.2 ms. Its mean path clearance margin of 18.7 cm is, however, the smallest among the compared methods. Ablations show drops of 11.3 to 15.3 percentage points when the descriptor input, the consistency regularizer, or the held-out split is removed. Recorded failures include reduced clearance on a steep entry ramp and degraded success under descriptor dropout.

Journal: Transactions on Intelligent Robotics and Autonomous Systems (TIRAS)
Volume / Issue: Vol. 1, No. 1 (July 2026)
Article ID: KAGG:2607.00005
DOI: 10.5803/kagg.2607.00005
Received: 2026-07-07
Accepted: 2026-07-18
Published online: 2026-07-21
License: CC BY 4.0

References (45)

  1. 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
  2. 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
  3. 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
  4. X. Xiao, B. Liu, G. Warnell, and P. Stone. Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey. arXiv:2011.13112, 2020. arXiv:2011.13112
  5. 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
  6. 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
  7. 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
  8. A. Eftekhar et al.. The One RING: a Robotic Indoor Navigation Generalist. arXiv:2412.14401, 2024. arXiv:2412.14401
  9. J. Zhang et al.. Embodied Navigation Foundation Model. arXiv:2509.12129, 2025. arXiv:2509.12129
  10. J. Yang, C. Glossop, A. Bhorkar, D. Shah, Q. Vuong, C. Finn, D. Sadigh, and S. Levine. Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation. arXiv:2402.19432, 2024. arXiv:2402.19432
  11. 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
  12. Open X-Embodiment Collaboration. Open X-Embodiment: Robotic Learning Datasets and RT-X Models. arXiv:2310.08864, 2023. arXiv:2310.08864
  13. T. Chen, A. Murali, and A. Gupta. Hardware Conditioned Policies for Multi-Robot Transfer Learning. arXiv:1811.09864, 2018. arXiv:1811.09864
  14. 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
  15. A. Gupta, L. Fan, S. Ganguli, and L. Fei-Fei. MetaMorph: Learning Universal Controllers with Transformers. arXiv:2203.11931, 2022. arXiv:2203.11931
  16. G. Feng et al.. GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots. arXiv:2209.05309, 2022. arXiv:2209.05309
  17. M. Shafiee, G. Bellegarda, and A. Ijspeert. ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots. arXiv:2310.10486, 2023. arXiv:2310.10486
  18. A. Kumar, Z. Fu, D. Pathak, and J. Malik. RMA: Rapid Motor Adaptation for Legged Robots. arXiv:2107.04034, 2021. arXiv:2107.04034
  19. G. Hinton, O. Vinyals, and J. Dean. Distilling the Knowledge in a Neural Network. arXiv:1503.02531, 2015. arXiv:1503.02531
  20. A. A. Rusu et al.. Policy Distillation. arXiv:1511.06295, 2015. arXiv:1511.06295
  21. S. Ross, G. J. Gordon, and J. A. Bagnell. A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning. arXiv:1011.0686, 2010. arXiv:1011.0686
  22. Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. Theodorou, and B. Boots. Agile Autonomous Driving using End-to-End Deep Imitation Learning. arXiv:1709.07174, 2017. arXiv:1709.07174
  23. D. Chen, B. Zhou, V. Koltun, and P. Krähenbühl. Learning by Cheating. arXiv:1912.12294, 2019. arXiv:1912.12294
  24. E. Kaufmann, A. Loquercio, R. Ranftl, M. Müller, V. Koltun, and D. Scaramuzza. Deep Drone Acrobatics. arXiv:2006.05768, 2020. arXiv:2006.05768
  25. A. Loquercio, E. Kaufmann, R. Ranftl, M. Müller, V. Koltun, and D. Scaramuzza. Learning High-Speed Flight in the Wild. arXiv:2110.05113, 2021. arXiv:2110.05113
  26. J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter. Learning Quadrupedal Locomotion over Challenging Terrain. arXiv:2010.11251, 2020. arXiv:2010.11251
  27. 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
  28. W. M. Czarnecki, S. Osindero, M. Jaderberg, G. Swirszcz, and R. Pascanu. Sobolev Training for Neural Networks. arXiv:1706.04859, 2017. arXiv:1706.04859
  29. 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
  30. 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
  31. 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
  32. D. Hoeller, N. Rudin, D. Sako, and M. Hutter. ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots. arXiv:2306.14874, 2023. arXiv:2306.14874
  33. X. Cheng, K. Shi, A. Agarwal, and D. Pathak. Extreme Parkour with Legged Robots. arXiv:2309.14341, 2023. arXiv:2309.14341
  34. Z. Zhuang et al.. Robot Parkour Learning. arXiv:2309.05665, 2023. arXiv:2309.05665
  35. F. Jenelten, J. He, F. Farshidian, and M. Hutter. DTC: Deep Tracking Control. arXiv:2309.15462, 2023. arXiv:2309.15462
  36. I. Radosavovic, T. Xiao, B. Zhang, T. Darrell, J. Malik, and K. Sreenath. Real-World Humanoid Locomotion with Reinforcement Learning. arXiv:2303.03381, 2023. arXiv:2303.03381
  37. X. Gu, Y.-J. Wang, and J. Chen. Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer. arXiv:2404.05695, 2024. arXiv:2404.05695
  38. V. Makoviychuk et al.. Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning. arXiv:2108.10470, 2021. arXiv:2108.10470
  39. M. Mittal et al.. Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments. arXiv:2301.04195, 2023. arXiv:2301.04195
  40. 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
  41. 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
  42. A. Kadian et al.. Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance? arXiv:1912.06321, 2019. arXiv:1912.06321
  43. G. Williams, A. Aldrich, and E. Theodorou. Model Predictive Path Integral Control using Covariance Variable Importance Sampling. arXiv:1509.01149, 2015. arXiv:1509.01149
  44. A. D. Ames, S. Coogan, M. Egerstedt, G. Notomista, K. Sreenath, and P. Tabuada. Control Barrier Functions: Theory and Applications. arXiv:1903.11199, 2019. arXiv:1903.11199
  45. 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
Cite this article Yifan Chen, Zhiyuan Wang, Haoran Liu, Xiaotong Zhang, "Cross-Embodiment Distillation of Local Navigation Planners from Humanoid to Quadruped Teams," Transactions on Intelligent Robotics and Autonomous Systems, 2026, vol. 1, no. 1, KAGG:2607.00005. DOI: 10.5803/kagg.2607.00005.