Quadrupedal Robot Skateboard Mounting via Reverse Curriculum Learning

2025-05-10

AI Summary

This work addresses the challenging task of quadrupedal robot mounting onto a skateboard from standstill. We propose a reverse-curriculum reinforcement learning framework that inverts the conventional easy-to-hard curriculum: starting from the fixed skateboard’s terminal state, we progressively relax constraints on the initial robot state to enable generalization from static to dynamic skateboard scenarios. Integrating rigid-body dynamics simulation, domain randomization, and policy transfer, the learned policy achieves robust mounting onto skateboards placed at arbitrary positions and orientations on a real robot, with zero-shot transfer to free (unconstrained) skateboard conditions. The core contribution is the first formulation of a reverse-curriculum design for robotic locomotion, which significantly enhances generalization across diverse initial states and improves deployment robustness without additional fine-tuning.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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

Problem

• Enable quadrupedal robots to mount skateboards
• Overcome initial mounting phase challenges
• Achieve robustness to skateboard position variations

Innovation

• Reverse Curriculum Reinforcement Learning for mounting
• Gradual relaxation of initial skateboard conditions
• Robust policy transfer to mobile skateboard scenarios