Selecting Mechanical Parameters of a Monopode Jumping System with Reinforcement Learning

TL;DR

This paper demonstrates that reinforcement learning can effectively optimize mechanical parameters of a monopode jumping system, leading to designs that are optimal within the specified design space, improving legged robot performance.

Contribution

It introduces a reinforcement learning approach to automatically select mechanical parameters for a monopode jumping system, addressing modeling challenges of flexible, nonlinear systems.

Findings

Reinforcement learning successfully identifies optimal design parameters.

Learned designs improve system performance within the given design space.

The method demonstrates potential for automated mechanical parameter selection.

Abstract

Legged systems have many advantages when compared to their wheeled counterparts. For example, they can more easily navigate extreme, uneven terrain. However, there are disadvantages as well, particularly the difficulty seen in modeling the nonlinearities of the system. Research has shown that using flexible components within legged locomotive systems improves performance measures such as efficiency and running velocity. Because of the difficulties encountered in modeling flexible systems, control methods such as reinforcement learning can be used to define control strategies. Furthermore, reinforcement learning can be tasked with learning mechanical parameters of a system to match a control input. It is shown in this work that when deploying reinforcement learning to find design parameters for a pogo-stick jumping system, the designs the agents learn are optimal within the design space provided to the agents.