用两阶段强化学习让四足机器人学会爬U型楼梯并迁移到其他楼梯。
Learning Transferability: A Two-Stage Reinforcement Learning Approach for Enhancing Quadruped Robots' Performance in U-Shaped Stair Climbing
- 分两阶段训练：先在虚拟金字塔楼梯学，再迁移到真实U型楼梯。
- 成功实现带防卡顿惩罚的U型楼梯自主攀爬，成功率高。
- 训练出的策略能跨地形迁移，适用于直、L、螺旋楼梯。
四足机器人被广泛应用于建筑施工场景，但自主跨越不同室内楼梯仍是完成施工任务的主要挑战。本项目采用两阶段端到端深度强化学习（RL）方法，优化机器人在U型楼梯上的表现。训练使用的真实机器人模态为Unitree Go2，首先在Isaac Lab的金字塔楼梯地形上进行训练，随后将学到的策略用于真实U型室内楼梯的攀爬。实验结果表明：（1）机器人在带有停顿惩罚条件下成功完成U型楼梯攀爬；（2）从U型楼梯训练所得策略可有效迁移到直线、L型和螺旋楼梯地形，同时其他楼梯模型的策略也能迁移到U型楼梯部署。
原文摘要 · Abstract (English)
Quadruped robots are employed in various scenarios in building construction. However, autonomous stair climbing across different indoor staircases remains a major challenge for robot dogs to complete building construction tasks. In this project, we employed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize a robot's performance on U-shaped stairs. The training robot-dog modality, Unitree Go2, was first trained to climb stairs on Isaac Lab's pyramid-stair terrain, and then to climb a U-shaped indoor staircase using the learned policies. This project explores end-to-end RL methods that enable robot dogs to autonomously climb stairs. The results showed (1) the successful goal reached for robot dogs climbing U-shaped stairs with a stall penalty, and (2) the transferability from the policy trained on U-shaped stairs to deployment on straight, L-shaped, and spiral stair terrains, and transferability from other stair models to deployment on U-shaped terrain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。