论文标题
自动剩余增强学习的多模式的腿部运动框架
Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning
论文作者
论文摘要
虽然四倍的机器人通常具有良好的稳定性和载荷能力，但两足机器人为不同的任务和环境提供了更高水平的灵活性 /适应性。多模式的腿机器人可以两全其美。在本文中，我们提出了一个多模式的运动框架，该框架由手工制作的过渡运动和一个基于学习的两体控制器组成 - 通过一种称为自动化残留增强学习的新型算法学习。该框架旨在赋予双重行走的任意四倍的机器人。特别是，我们1）为四倍的机器人和连续的多模式过渡策略设计一个附加的支撑结构； 2）提出了一种新型的增强学习算法，以用于两体性控制，并在模拟和现实世界中评估它们的性能。实验结果表明，我们提出的算法在模拟方面具有最佳性能，并在现实世界中保持良好的性能。总体而言，我们的多模式机器人可以成功切换到bip和四足动物之间，并以两种模式行走。实验视频和代码可在https://chenaah.github.io/multimodal/上找到。
While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller -- learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes. Experiment videos and code are available at https://chenaah.github.io/multimodal/.
