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. 3 (September 2026) > KAGG:2609.00002
Vol. 1, No. 3 (September 2026) — Article KAGG:2609.00002

Distilling Cross-Embodiment Planners into Onboard-Deployable Policies

Authors: Rongxin Guo, Xiaotong Zhang, Yifan Chen, Daichi Mori

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

[Received 2026-08-20; accepted 2026-08-31; published online 2026-09-03]

Abstract:

Configuration-driven cross-embodiment local planners such as AgniNav allow a single planning stack to serve robots with different body geometry, sensing, and velocity limits, but they pay for this generality with full configuration-space sampling at every replan. On an embedded computer this cost is prohibitive: the full planner requires 41 ms per decision offline, and throttling it onboard degrades agreement with its unthrottled output. This paper distills such a planner into a configuration-conditioned onboard policy through trajectory-level imitation. The teacher produces local trajectories over configuration states; the student maps an observation and a configuration descriptor directly to the next body-motion primitive from a velocity-normalized library. Training combines a soft-target imitation term with a consistency regularizer that penalizes, under perturbed range observations, probability mass on primitives that diverge geometrically from the teacher decision. Because the student remains conditioned on the descriptor, one deployed network serves multiple embodiments. In Isaac Lab experiments with a Unitree Go2 across 18 scenes and 5 seeds, with the student running at 100 Hz on an onboard Orin, the distilled policy reaches a p95 decision latency of 7.8 ms, a teacher parity of 94.3 percent, and a success rate of 91.7 percent, compared with 8.7 ms, 84.2 percent, and 86.3 percent for the throttled full planner. Transfer to a B2-class morphology in simulation retains 89.6 percent parity, and at 10 percent range dropout the regularizer preserves 88.1 percent parity versus 79.4 percent without it.

Journal: Transactions on Intelligent Robotics and Autonomous Systems (TIRAS)
Volume / Issue: Vol. 1, No. 3 (September 2026)
Article ID: KAGG:2609.00002
DOI: 10.5803/kagg.2609.00002
Received: 2026-08-20
Accepted: 2026-08-31
Published online: 2026-09-03
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. 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
  4. 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
  5. 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
  6. D. Chen, B. Zhou, V. Koltun, and P. Krähenbühl. Learning by Cheating. arXiv:1912.12294, 2019. arXiv:1912.12294
  7. 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
  8. J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter. Learning Quadrupedal Locomotion over Challenging Terrain. arXiv:2010.11251, 2020. arXiv:2010.11251
  9. 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
  10. A. Eftekhar et al. The One RING: a Robotic Indoor Navigation Generalist. arXiv:2412.14401, 2024. arXiv:2412.14401
  11. J. Zhang et al. Embodied Navigation Foundation Model. arXiv:2509.12129, 2025. arXiv:2509.12129
  12. 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
  13. 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
  14. A. Gupta, L. Fan, S. Ganguli, and L. Fei-Fei. MetaMorph: Learning Universal Controllers with Transformers. arXiv:2203.11931, 2022. arXiv:2203.11931
  15. G. Feng, H. Zhang, Z. Li, X. B. Peng, B. Basireddy, L. Yue, Z. Song, L. Yang, Y. Liu, K. Sreenath, and S. Levine. GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots. arXiv:2209.05309, 2022. arXiv:2209.05309
  16. M. Shafiee, G. Bellegarda, and A. Ijspeert. ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots. arXiv:2310.10486, 2023. arXiv:2310.10486
  17. 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
  18. G. Hinton, O. Vinyals, and J. Dean. Distilling the Knowledge in a Neural Network. arXiv:1503.02531, 2015. arXiv:1503.02531
  19. A. A. Rusu, S. G. Colmenarejo, C. Gulcehre, G. Desjardins, J. Kirkpatrick, R. Pascanu, V. Mnih, K. Kavukcuoglu, and R. Hadsell. Policy Distillation. arXiv:1511.06295, 2015. arXiv:1511.06295
  20. W. M. Czarnecki, R. Pascanu, S. Osindero, S. M. Jayakumar, G. Swirszcz, and M. Jaderberg. Distilling Policy Distillation. arXiv:1902.02186, 2019. arXiv:1902.02186
  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, 2011. arXiv:1011.0686
  22. S. Levine, C. Finn, T. Darrell, and P. Abbeel. End-to-End Training of Deep Visuomotor Policies. arXiv:1504.00702, 2015. arXiv:1504.00702
  23. T. Zhang, G. Kahn, S. Levine, and P. Abbeel. Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search. arXiv:1509.06791, 2015. arXiv:1509.06791
  24. 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
  25. E. Kaufmann, A. Loquercio, R. Ranftl, M. Müller, V. Koltun, and D. Scaramuzza. Deep Drone Acrobatics. arXiv:2006.05768, 2020. arXiv:2006.05768
  26. 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
  27. A. Kumar, Z. Fu, D. Pathak, and J. Malik. RMA: Rapid Motor Adaptation for Legged Robots. arXiv:2107.04034, 2021. arXiv:2107.04034
  28. A. Agarwal, A. Kumar, J. Malik, and D. Pathak. Legged Locomotion in Challenging Terrains using Egocentric Vision. arXiv:2211.07638, 2022. arXiv:2211.07638
  29. 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
  30. X. Cheng, K. Shi, A. Agarwal, and D. Pathak. Extreme Parkour with Legged Robots. arXiv:2309.14341, 2023. arXiv:2309.14341
  31. M. Pfeiffer, M. Schaeuble, J. Nieto, R. Siegwart, and C. Cadena. From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots. arXiv:1609.07910, 2016. arXiv:1609.07910
  32. 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
  33. X. Xiao, B. Liu, G. Warnell, J. Fink, and P. Stone. APPLD: Adaptive Planner Parameter Learning from Demonstration. arXiv:2004.00116, 2020. arXiv:2004.00116
  34. G. Williams, A. Aldrich, and E. Theodorou. Model Predictive Path Integral Control using Covariance Variable Importance Sampling. arXiv:1509.01149, 2015. arXiv:1509.01149
  35. 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
  36. 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
  37. 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
  38. L. Wellhausen and M. Hutter. ArtPlanner: Robust Legged Robot Navigation in the Field. arXiv:2303.01420, 2023. arXiv:2303.01420
  39. J. Lee, M. Bjelonic, A. Reske, L. Wellhausen, T. Miki, and M. Hutter. Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots. arXiv:2405.01792, 2024. arXiv:2405.01792
  40. C. Chi, S. Feng, Y. Du, Z. Xu, E. Cousineau, B. Burchfiel, and S. Song. Diffusion Policy: Visuomotor Policy Learning via Action Diffusion. arXiv:2303.04137, 2023. arXiv:2303.04137
  41. 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
  42. V. Makoviychuk et al. Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning. arXiv:2108.10470, 2021. arXiv:2108.10470
  43. M. Mittal et al. Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments. arXiv:2301.04195, 2023. arXiv:2301.04195
  44. 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
  45. A. Kadian et al. Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance? arXiv:1912.06321, 2019. arXiv:1912.06321
Cite this article Rongxin Guo, Xiaotong Zhang, Yifan Chen, Daichi Mori, "Distilling Cross-Embodiment Planners into Onboard-Deployable Policies," Transactions on Intelligent Robotics and Autonomous Systems, 2026, vol. 1, no. 3, KAGG:2609.00002. DOI: 10.5803/kagg.2609.00002.