Efficient and Versatile Quadrupedal Skating: Optimal Co-design via Reinforcement Learning and Bayesian Optimization
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
In this paper, we present a hardware-control co-design approach that enables efficient and versatile roller skating on quadrupedal robots equipped with passive wheels. Passive-wheel skating reduces leg inertia and improves energy efficiency, particularly at high speeds. However, the absence of direct wheel actuation tightly couples mechanical design and control. To unlock the full potential of this modality, we formulate a bilevel optimization framework: an upper-level Bayesian Optimization searches the mechanical design space, while a lower-level Reinforcement Learning trains a motor control policy for each candidate design. The resulting design-policy pairs not only outperform human-engineered baselines, but also exhibit versatile behaviors such as hockey stop (rapid braking by turning sideways to maximize friction) and self-aligning motion (automatic reorientation to improve energy efficiency in the direction of travel), offering the first system-level study of dynamic skating motion on quadrupedal robots.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 35 references that are in the map. First posted on arXiv 19 Mar 2026.
Builds on
12 of 35 references.
References · 12
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2019Learning agile and dynamic motor skills for legged robotscited by 504
- 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
- 2018Reinforcement Learning for Improving Agent Designcited by 56
- 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 55
- 2022GenLoco: Generalized Locomotion Controllers for Quadrupedal Robotscited by 48
- 2024Learning-based legged locomotion; state of the art and future perspectivescited by 23
- 2025LocoFormer: Generalist Locomotion via Long-context Adaptationcited by 20
- 2022Meta Reinforcement Learning for Optimal Design of Legged Robotscited by 13
- 2023Learning-based Design and Control for Quadrupedal Robots with Parallel-Elastic Actuatorscited by 11
- 2018Keep Rollin' - Whole-Body Motion Control and Planning for Wheeled Quadrupedal Robotscited by 8
- 2025CTBC: Contact-Triggered Blind Climbing for Wheeled Bipedal Robots with Instruction Learning and Reinforcement Learningcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot
- 2026SKATER: Synthesized Kinematics for Advanced Traversing Efficiency on a Humanoid Robot via Roller Skate Swizzles
- 2024Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives
- 2025Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning
- 2025Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds ↗
- 2024Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds ↗
- 2023A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning
- 2025Explosive Jumping with Rigid and Articulated Soft Quadrupeds via Example Guided Reinforcement Learning