{"ID":2825765,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.10723","arxiv_id":"2601.10723","title":"Energy-Efficient Omnidirectional Locomotion for Wheeled Quadrupeds via Predictive Energy-Aware Nominal Gait Selection","abstract":"Wheeled-legged robots combine the efficiency of wheels with the versatility of legs, but face significant energy optimization challenges when navigating diverse environments. In this work, we present a hierarchical control framework that integrates predictive power modeling with residual reinforcement learning to optimize omnidirectional locomotion efficiency for wheeled quadrupedal robots. Our approach employs a novel power prediction network that forecasts energy consumption across different gait patterns over a 1-second horizon, enabling intelligent selection of the most energy-efficient nominal gait. A reinforcement learning policy then generates residual adjustments to this nominal gait, fine-tuning the robot's actions to balance energy efficiency with performance objectives. Comparative analysis shows our method reduces energy consumption by up to 35\\% compared to fixed-gait approaches while maintaining comparable velocity tracking performance. We validate our framework through extensive simulations and real-world experiments on a modified Unitree Go1 platform, demonstrating robust performance even under external disturbances. Videos and implementation details are available at \\href{https://sites.google.com/view/switching-wpg}{https://sites.google.com/view/switching-wpg}.","short_abstract":"Wheeled-legged robots combine the efficiency of wheels with the versatility of legs, but face significant energy optimization challenges when navigating diverse environments. In this work, we present a hierarchical control framework that integrates predictive power modeling with residual reinforcement learning to optim...","url_abs":"https://arxiv.org/abs/2601.10723","url_pdf":"https://arxiv.org/pdf/2601.10723v1","authors":"[\"Xu Yang\",\"Wei Yang\",\"Kaibo He\",\"Bo Yang\",\"Yanan Sui\",\"Yilin Mo\"]","published":"2025-12-23T09:56:35Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Reinforcement Learning\"]","project_urls":"[\"https://sites.google.com/view/switching-wpg\"]","has_code":false,"code_links":[{"ID":605694,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2825765,"paper_url":"https://arxiv.org/abs/2601.10723","paper_title":"Energy-Efficient Omnidirectional Locomotion for Wheeled Quadrupeds via Predictive Energy-Aware Nominal Gait Selection","repo_url":"https://github.com/google/safevalues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":605695,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2825765,"paper_url":"https://arxiv.org/abs/2601.10723","paper_title":"Energy-Efficient Omnidirectional Locomotion for Wheeled Quadrupeds via Predictive Energy-Aware Nominal Gait Selection","repo_url":"https://github.com/xu-yang16/wheeled-quadruped-sim2sim","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}