HyperNEAT for Locomotion Control in Modular Robots

Abstract

Abstract. In an application where autonomous robots can amalgamate spontaneously into arbitrary organisms, the individual robots cannot know a priori at which location in an organism they will end up. If the organism is to be controlled autonomously by the constituent robots, an evolutionary algorithm that evolves the controllers can only develop a single genome that will have to suffice for every individual robot. However, the robots should show different behaviour depending on their position in an organism, meaning their phenotype should be different depending on their location. In this paper, we demonstrate a solution for this problem using the HyperNEAT generative encoding technique with differentiated genome expression. We develop controllers for organism locomotion with obstacle avoidance as a proof of concept. Finally, we identify promising directions for further research.

Evolving Reactive Controller for a Modular Robot: Benefits of the Property of State-Switching in Fractal Gene Regulatory Networks

“…In previous reactive controllers for multi-modular robots, e.g. HyperNEAT [6] and Central Pattern Generators (CPG) [11], or single robots ,e.g. Neural Networks (ANN) [20], the proper behavior is achieved by modulating an input part of an ANN to switch between the ordinary and special behaviors based on environmental signals.…”

Online Gait Learning for Modular Robots with Arbitrary Shapes and Sizes

“…CPPN's are used to set the weights of a fixed size neural network called a substrate. Several studies have shown that HyperNEAT is capable of creating efficient gaits for robots [4,20,9]. Another successful approach that has received much attention is based on Central Pattern Generators (CPG).…”

HyperNEAT Versus RL PoWER for Online Gait Learning in Modular Robots

“…A gait control table consist of rows of actuator commands with one column for each actuator, each row also has a condition for the transition to the next row.A second major avenue of research is that of neural networks (NN). In particular for locomotion of robot organisms HyperNEAT is used extensively with several studies showing that HyperNEAT is capable of creating efficient gaits for robots [4,9,20]. HyperNEAT is discussed in more detail in Section 3.…”