Quadrupedal Robot Skateboard Mounting via Reverse Curriculum Learning

2025/05/10 by Danil Belov, Artem Erkhov, Belov, Danil +9
Computer Science · Engineering · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Experimental and Theoretical Physics Studies #FOS: Computer and information sciences #FOS: Mathematics #Optimization and Control (math.OC) #Robotic Locomotion and Control #Robotic Path Planning Algorithms #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2505.06561

openalex publication_date 2025/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The aim of this work is to enable quadrupedal robots to mount skateboards using Reverse Curriculum Reinforcement Learning. Although prior work has demonstrated skateboarding for quadrupeds that are already positioned on the board, the initial mounting phase still poses a significant challenge. A goal-oriented methodology was adopted, beginning with the terminal phases of the task and progressively increasing the complexity of the problem definition to approximate the desired objective. The learning process was initiated with the skateboard rigidly fixed within the global coordinate frame and the robot positioned directly above it. Through gradual relaxation of these initial conditions, the learned policy demonstrated robustness to variations in skateboard position and orientation, ultimately exhibiting a successful transfer to scenarios involving a mobile skateboard. The code, trained models, and reproducible examples are available at the following link: https://github.com/dancher00/quadruped-skateboard-mounting

Citations

• Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding
• Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learning
• Quadruped robot traversing 3D complex environments with limited perception
• Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
• Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
• Extreme Parkour with Legged Robots
• DribbleBot: Dynamic Legged Manipulation in the Wild
• Rapid Locomotion via Reinforcement Learning
• Actor-Critic Reinforcement Learning for Control with Stability Guarantee
• Hierarchical Reinforcement Learning for Quadruped Locomotion
• Stanford Doggo: An Open-Source, Quasi-Direct-Drive Quadruped
• Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning
• Reverse Curriculum Generation for Reinforcement Learning

Related

• Learning Visual Quadrupedal Loco-Manipulation from Demonstrations
• Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning
• Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design
• Learning Rapid Turning, Aerial Reorientation, and Balancing using Manipulator as a Tail
• Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives