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:2607.00002
Vol. 1, No. 1 (July 2026) — Article KAGG:2607.00002

Terrain-Aware Velocity Command Smoothing for Quadruped Navigation over Unstructured Ground

Authors: Tomas Keller, Priya Raghunathan, Hana Sato

Advanced Robotics Group, Toyota Research Institute, Palo Alto, CA, USA

[Received 2026-07-02; accepted 2026-07-13; published online 2026-07-16]

Abstract:

Local planners for legged robots emit velocity commands without regard for what the locomotion controller can smoothly realize. On unstructured ground this mismatch produces command chatter, degrades tracking, wastes energy, and triggers premature obstacle reactions. This paper presents a terrain-aware, differentiable command-smoothing layer placed between a configuration-driven local planner in the AgniNav style and an opaque quadruped velocity interface. The layer solves a short-horizon smoothing problem whose weights are scheduled by an online terrain-difficulty estimate, and it predicts realized motion with an interface model that is initialized by GAUGE-style active calibration and updated online. Its parameters are trained end-to-end in simulation through implicit differentiation, and its prediction of the realizable motion is fed back to the planner so that collision checking follows the motion the robot is expected to execute. The approach is evaluated in an Isaac Lab deformable-terrain suite with five terrain classes and in field trials with a Unitree B2 over gravel, exposed roots, and graded slopes at 1.0 to 2.5 m/s. Compared with unsmoothed planner output, it reduces command RMS from 9.8 to 9.1 cm/s and 95th-percentile tracking error from 14.7 to 14.2 cm, raises success rate from 86.0 to 91.5 percent, lowers an energy proxy from 1519 to 1385 J/km, and increases mean speed from 1.48 to 1.68 m/s. It also outperforms a fixed gain scheduler and a GAUGE-calibrated fixed-gain smoother. Ablations and recorded failure cases show which components matter and where the approach remains fragile.

Journal: Transactions on Intelligent Robotics and Autonomous Systems (TIRAS)
Volume / Issue: Vol. 1, No. 1 (July 2026)
Article ID: KAGG:2607.00002
DOI: 10.5803/kagg.2607.00002
Received: 2026-07-02
Accepted: 2026-07-13
Published online: 2026-07-16
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. Science Robotics, 2019. arXiv:1901.08652. arXiv:1901.08652
  2. J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter. Learning Quadrupedal Locomotion over Challenging Terrain. Science Robotics, 2020. arXiv:2010.11251. 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. Science Robotics, 2022. arXiv:2201.08117. arXiv:2201.08117
  4. A. Kumar, Z. Fu, D. Pathak, and J. Malik. RMA: Rapid Motor Adaptation for Legged Robots. Robotics: Science and Systems, 2021. arXiv:2107.04034. arXiv:2107.04034
  5. 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
  6. X. Xiao, B. Liu, G. Warnell, and P. Stone. Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey. Autonomous Robots, 2022. arXiv:2011.13112. arXiv:2011.13112
  7. T. Zang, H. Huang, S. Cheng, and W. Zhang. GAUGE: Planner-Conditioned Active Calibration of Opaque Quadruped Velocity Interfaces. arXiv:2607.02841, 2026. arXiv:2607.02841
  8. N. Rudin, D. Hoeller, P. Reist, and M. Hutter. Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning. Conference on Robot Learning, 2021. arXiv:2109.11978. arXiv:2109.11978
  9. G. Ji, J. Mun, H. Kim, and J. Hwangbo. Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion. IEEE Robotics and Automation Letters, 2022. arXiv:2202.05481. arXiv:2202.05481
  10. G. B. Margolis, G. Yang, K. Paigwar, T. Chen, and P. Agrawal. Rapid Locomotion via Reinforcement Learning. Robotics: Science and Systems, 2022. arXiv:2205.02824. arXiv:2205.02824
  11. G. B. Margolis and P. Agrawal. Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior. Conference on Robot Learning, 2022. arXiv:2212.03238. arXiv:2212.03238
  12. Z. Fu, A. Kumar, J. Malik, and D. Pathak. Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots. Conference on Robot Learning, 2021. arXiv:2111.01674. arXiv:2111.01674
  13. Y. Yang, T. Zhang, E. Coumans, J. Tan, and B. Boots. Fast and Efficient Locomotion via Learned Gait Transitions. Conference on Robot Learning, 2021. arXiv:2104.04644. arXiv:2104.04644
  14. A. Agarwal, A. Kumar, J. Malik, and D. Pathak. Legged Locomotion in Challenging Terrains using Egocentric Vision. Conference on Robot Learning, 2022. arXiv:2211.07638. arXiv:2211.07638
  15. X. Cheng, K. Shi, A. Agarwal, and D. Pathak. Extreme Parkour with Legged Robots. IEEE International Conference on Robotics and Automation, 2024. arXiv:2309.14341. arXiv:2309.14341
  16. Z. Zhuang, Z. Fu, J. Wang, C. Atkeson, S. Schwertfeger, C. Finn, and H. Zhao. Robot Parkour Learning. Conference on Robot Learning, 2023. arXiv:2309.05665. arXiv:2309.05665
  17. D. Kim, J. Di Carlo, B. Katz, G. Bledt, and S. Kim. Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Control. arXiv:1909.06586, 2019. arXiv:1909.06586
  18. S. Gangapurwala, M. Geisert, R. Orsolino, M. Fallon, and I. Havoutis. RLOC: Terrain-Aware Legged Locomotion Using Reinforcement Learning and Optimal Control. IEEE Transactions on Robotics, 2022. arXiv:2012.03094. arXiv:2012.03094
  19. N. Rudin, D. Hoeller, M. Bjelonic, and M. Hutter. Advanced Skills by Learning Locomotion and Local Navigation End-to-End. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022. arXiv:2209.12827. arXiv:2209.12827
  20. D. Hoeller, L. Wellhausen, F. Farshidian, and M. Hutter. Learning a State Representation and Navigation in Cluttered and Dynamic Environments. IEEE Robotics and Automation Letters, 2021. arXiv:2103.04351. arXiv:2103.04351
  21. 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. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021. arXiv:2011.12255. arXiv:2011.12255
  22. J. Frey, M. Mattamala, N. Chebrolu, C. Cadena, M. Fallon, and M. Hutter. Fast Traversability Estimation for Wild Visual Navigation. Robotics: Science and Systems, 2023. arXiv:2305.08510. arXiv:2305.08510
  23. D. D. Fan, K. Otsu, Y. Kubo, A. Dixit, J. Burdick, and A. Agha-mohammadi. STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation. Robotics: Science and Systems, 2021. arXiv:2103.02828. arXiv:2103.02828
  24. G. Kahn, P. Abbeel, and S. Levine. BADGR: An Autonomous Self-Supervised Learning-Based Navigation System. IEEE Robotics and Automation Letters, 2021. arXiv:2002.05700. arXiv:2002.05700
  25. D. Shah, A. Sridhar, A. Bhorkar, N. Hirose, and S. Levine. GNM: A General Navigation Model to Drive Any Robot. IEEE International Conference on Robotics and Automation, 2023. arXiv:2210.03370. arXiv:2210.03370
  26. G. Williams, A. Aldrich, and E. A. Theodorou. Model Predictive Path Integral Control using Covariance Variable Importance Sampling. arXiv:1509.01149, 2015. arXiv:1509.01149
  27. X. Xiao, J. Biswas, and P. Stone. Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain. IEEE Robotics and Automation Letters, 2021. arXiv:2102.12667. arXiv:2102.12667
  28. H. Karnan, K. S. Sikand, P. Atreya, S. Rabiee, X. Xiao, G. Warnell, P. Stone, and J. Biswas. VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022. arXiv:2203.15983. arXiv:2203.15983
  29. B. Amos and J. Z. Kolter. OptNet: Differentiable Optimization as a Layer in Neural Networks. International Conference on Machine Learning, 2017. arXiv:1703.00443. arXiv:1703.00443
  30. B. Amos, I. D. J. Rodriguez, J. Sacks, B. Boots, and J. Z. Kolter. Differentiable MPC for End-to-end Planning and Control. Advances in Neural Information Processing Systems, 2018. arXiv:1810.13400. arXiv:1810.13400
  31. A. Agrawal, B. Amos, S. Barratt, S. Boyd, S. Diamond, and J. Z. Kolter. Differentiable Convex Optimization Layers. Advances in Neural Information Processing Systems, 2019. arXiv:1910.12430. arXiv:1910.12430
  32. A. D. Ames, S. Coogan, M. Egerstedt, G. Notomista, K. Sreenath, and P. Tabuada. Control Barrier Functions: Theory and Applications. European Control Conference, 2019. arXiv:1903.11199. arXiv:1903.11199
  33. K. P. Wabersich and M. N. Zeilinger. Linear Model Predictive Safety Certification for Learning-Based Control. IEEE Conference on Decision and Control, 2018. arXiv:1803.08552. arXiv:1803.08552
  34. F. Berkenkamp, M. Turchetta, A. P. Schoellig, and A. Krause. Safe Model-based Reinforcement Learning with Stability Guarantees. Advances in Neural Information Processing Systems, 2017. arXiv:1705.08551. arXiv:1705.08551
  35. V. Makoviychuk, L. Wawrzyniak, Y. Guo, M. Lu, K. Storey, M. Macklin, D. Hoeller, N. Rudin, A. Allshire, A. Handa, and G. State. Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning. NeurIPS Datasets and Benchmarks Track, 2021. arXiv:2108.10470. arXiv:2108.10470
  36. M. Mittal, C. Yu, Q. Yu, J. Liu, N. Rudin, D. Hoeller, J. L. Yuan, R. Singh, Y. Guo, H. Mazhar, A. Mandlekar, B. Babich, G. State, M. Hutter, and A. Garg. Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments. IEEE Robotics and Automation Letters, 2023. arXiv:2301.04195. arXiv:2301.04195
  37. 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. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017. arXiv:1703.06907. arXiv:1703.06907
  38. X. B. Peng, M. Andrychowicz, W. Zaremba, and P. Abbeel. Sim-to-Real Transfer of Robotic Control with Dynamics Randomization. IEEE International Conference on Robotics and Automation, 2018. arXiv:1710.06537. arXiv:1710.06537
  39. J. Tan, T. Zhang, E. Coumans, A. Iscen, Y. Bai, D. Hafner, S. Bohez, and V. Vanhoucke. Sim-to-Real: Learning Agile Locomotion For Quadruped Robots. Robotics: Science and Systems, 2018. arXiv:1804.10332. arXiv:1804.10332
  40. A. Kadian, J. Truong, A. Gokaslan, A. Clegg, E. Wijmans, S. Lee, M. Savva, S. Chernova, and D. Batra. Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance? IEEE Robotics and Automation Letters, 2020. arXiv:1912.06321. arXiv:1912.06321
Cite this article Tomas Keller, Priya Raghunathan, Hana Sato, "Terrain-Aware Velocity Command Smoothing for Quadruped Navigation over Unstructured Ground," Transactions on Intelligent Robotics and Autonomous Systems, 2026, vol. 1, no. 1, KAGG:2607.00002. DOI: 10.5803/kagg.2607.00002.