Leveraging Evolutionary Algorithms for Feasible Hexapod Locomotion Across Uneven Terrain

TL;DR

This paper demonstrates how evolutionary algorithms can be used to develop stable, efficient gait controllers for hexapod robots to traverse uneven terrain, by evolving parameters in simulation that adapt to complex environments.

Contribution

It introduces a method for evolving hexapod gait controllers capable of navigating uneven terrain using evolutionary algorithms in simulation, highlighting critical gait parameters for rough terrain adaptation.

Findings

Multiple successful gait evolutions with specialized leg functions

Identification of critical gait parameters for rough terrain

Effective traversal of complex obstacle courses

Abstract

Optimizing gait stability for legged robots is a difficult problem. Even on level surfaces, effectively traversing across different textures (e.g., carpet) rests on dynamically tuning parameters in multidimensional space. Inspired by biology, evolutionary algorithms (EA) remain an attractive solution for feasibly implementing robotic locomotion with both energetic economy and rapid parameter convergence. Here, we leveraged this class of algorithms to evolve a stable hexapod gait controller capable of traversing uneven terrain and obstacles. Gait parameters were evolved in a rigid body dynamics simulation on an 8 x 3 meter obstacle course comprised of random step field, linear obstacles and inclined surfaces. Using a fitness function that jointly optimized locomotion velocity and stability, we found that multiple successful gait parameter evolutions yielded specialized functionality for each leg. Specific gait parameters were identified as critical to developing a rough terrain gait.