Structural Optimization of Lightweight Bipedal Robot via SERL

TL;DR

This paper presents the SERL algorithm, combining reinforcement learning and evolutionary methods, to optimize the structure of a lightweight bipedal robot, resulting in improved energy efficiency and performance.

Contribution

It introduces a novel SERL algorithm for structural optimization, enabling automatic design of bipedal robots with superior performance compared to traditional methods.

Findings

SERL effectively optimizes robot structure within complex design spaces.

Wow Orin demonstrates superior energy efficiency and performance.

SERL's practical applicability is validated through experimental comparisons.

Abstract

Designing a bipedal robot is a complex and challenging task, especially when dealing with a multitude of structural parameters. Traditional design methods often rely on human intuition and experience. However, such approaches are time-consuming, labor-intensive, lack theoretical guidance and hard to obtain optimal design results within vast design spaces, thus failing to full exploit the inherent performance potential of robots. In this context, this paper introduces the SERL (Structure Evolution Reinforcement Learning) algorithm, which combines reinforcement learning for locomotion tasks with evolution algorithms. The aim is to identify the optimal parameter combinations within a given multidimensional design space. Through the SERL algorithm, we successfully designed a bipedal robot named Wow Orin, where the optimal leg length are obtained through optimization based on body structure and motor torque. We have experimentally validated the effectiveness of the SERL algorithm, which is capable of optimizing the best structure within specified design space and task conditions. Additionally, to assess the performance gap between our designed robot and the current state-of-the-art robots, we compared Wow Orin with mainstream bipedal robots Cassie and Unitree H1. A series of experimental results demonstrate the Outstanding energy efficiency and performance of Wow Orin, further validating the feasibility of applying the SERL algorithm to practical design.