{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:38:19Z","timestamp":1773329899508,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127448","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulation"],"prefix":"10.1109","author":[{"given":"Jing Yuan","family":"Luo","sequence":"first","affiliation":[{"name":"ETH Zurich,Switzerland"}]},{"given":"Yunlong","family":"Song","sequence":"additional","affiliation":[{"name":"University of Zurich,Switzerland"}]},{"given":"Victor","family":"Klemm","sequence":"additional","affiliation":[{"name":"ETH Zurich,Switzerland"}]},{"given":"Fan","family":"Shi","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Davide","family":"Scaramuzza","sequence":"additional","affiliation":[{"name":"University of Zurich,Switzerland"}]},{"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"ETH Zurich,Switzerland"}]}],"member":"263","reference":[{"issue":"62","key":"ref1","first-page":"eabk2822","volume":"7","author":"Miki","journal-title":"Learning robust perceptive locomotion for quadrupedal robots in the wild"},{"key":"ref2","first-page":"11443","article-title":"Extreme Parkour with Legged Robots","volume-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","author":"Cheng"},{"key":"ref3","first-page":"20668","article-title":"Do Differentiable Simulators Give Better Policy Gradients?","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Suh"},{"key":"ref4","author":"Mnih","journal-title":"Playing Atari with Deep Reinforcement Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"ref6","first-page":"91","article-title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","volume-title":"Proceedings of the 5th Conference on Robot Learning","author":"Rudin"},{"key":"ref7","volume-title":"Proximal Policy Optimization Algorithms","author":"Schulman"},{"key":"ref8","volume-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","author":"Schulman"},{"key":"ref9","first-page":"1861","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.059","article-title":"Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion","volume-title":"Proceedings of Robotics: Science and Systems","author":"He"},{"key":"ref11","first-page":"1349","article-title":"Training Efficient Controllers via Analytic Policy Gradient","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"Wiedemann"},{"key":"ref12","article-title":"Accelerated Policy Learning with Parallel Differentiable Simulation","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR 2022)","author":"Xu"},{"key":"ref13","volume-title":"Brax - A Differentiable Physics Engine for Large Scale Rigid Body Simulation","author":"Freeman"},{"key":"ref14","first-page":"276","article-title":"Rethinking Optimization with Differentiable Simulation from a Global Perspective","volume-title":"Proceedings of The 6th Conference on Robot Learning","author":"Antonova"},{"key":"ref15","volume-title":"Residual Policy Learning","author":"Silver"},{"key":"ref16","first-page":"6023","article-title":"Residual Reinforcement Learning for Robot Control","volume-title":"2019 International Conference on Robotics and Automation (ICRA)","author":"Johannink"},{"key":"ref17","volume-title":"Gradients are Not All You Need","author":"Metz"},{"key":"ref18","volume-title":"Emergence of Locomotion Behaviours in Rich Environments","author":"Heess"},{"issue":"47","key":"ref19","volume":"5","author":"Lee","year":"2010","journal-title":"Learning Quadrupedal Locomotion over Challenging Terrain"},{"issue":"4","key":"ref20","first-page":"12547","volume":"7","author":"Bellegarda","journal-title":"CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adh5401"},{"key":"ref22","first-page":"7805","article-title":"PODS: Policy Optimization via Differentiable Simulation","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Mora"},{"key":"ref23","volume-title":"Back to Newton\u2019s Laws: Learning Vision-based Agile Flight via Differentiable Physics","author":"Zhang"},{"key":"ref24","volume-title":"Learning Quadrupedal Locomotion via Differentiable Simulation","author":"Schwarke"},{"key":"ref25","volume-title":"Learning Quadruped Locomotion Using Differentiable Simulation","author":"Song"},{"key":"ref26","article-title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. Conference and Workshop on Neural Information Processing Systems","author":"Makoviychuk"},{"key":"ref27","article-title":"DiffMimic: Efficient Motion Mimicking with Differentiable Physics","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Ren"},{"key":"ref28","first-page":"5026","article-title":"MuJoCo: A physics engine for model-based control","volume-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"Todorov"},{"key":"ref29","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"ref30","first-page":"38","article-title":"ANYmal - a highly mobile and dynamic quadrupedal robot","volume-title":"2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Hutter"},{"key":"ref31","article-title":"Layer Normalization","volume-title":"arXiv.org","author":"Ba"},{"key":"ref32","first-page":"2497","article-title":"Advanced Skills by Learning Locomotion and Local Navigation End-toEnd","volume-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Rudin"},{"issue":"10","key":"ref33","first-page":"101844","volume":"35","author":"Han","journal-title":"An enhanced adaptive 3D path planning algorithm for mobile robots with obstacle buffering and improved Theta* using minimum snap trajectory smoothing"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.082","article-title":"Demonstrating Agile Flight from Pixels without State Estimation","volume-title":"Proceedings of Robotics: Science and Systems. Robotics: Science and Systems Foundation","author":"Geles"},{"key":"ref35","article-title":"Reinforcement learning with augmented data","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201920","author":"Laskin"},{"key":"ref36","article-title":"Adaptive Horizon Actor-Critic for Policy Learning in ContactRich Differentiable Simulation","volume-title":"Proceedings of the Forty-first International Conference on Machine Learning","author":"Georgiev"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127448.pdf?arnumber=11127448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:14:47Z","timestamp":1756880087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127448","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}