Online evolution of robot behaviour
Year: 2012
Type: dissertation
Abstract: In this dissertation, we propose and evaluate two novel approaches to the online synthesis of neural controllers for autonomous robots. The first approach is odNEAT, an online, distributed, and decentralized version of NeuroEvolution of Augmenting Topologies (NEAT). odNEAT is an algorithm for online evolution in groups of embodied agents such as robots. In odNEAT, agents have to solve the same task, either individually or collectively. While previous approaches to online evolution of neural controllers have been limited to the optimization of weights, odNEAT evolves both weights and network topology. We demonstrate odNEAT through a series of simulation-based experiments in which a group of e-puck-like robots must perform an aggregation task. Our results show that robots are capable of evolving effective aggregation strategies and that sustainable behaviours evolve quickly. We show that odNEAT approximates the performance of rtNEAT, a similar but centralized method. We also analyze the contribution of each algorithmic component on the performance through a series of ablation studies. In the second approach, we extend our previous method and combine online evolution of weights and network topology (odNEAT) with neuromodulated learning. We demonstrate our method through a series of experiments in which a group of simulated robots must perform a dynamic concurrent foraging task. In this task, scattered food items periodically change their nutritive value or become poisonous. Our results show that when neuromodulated learning is employed, neural controllers are synthesized faster than by odNEAT alone. We demonstrate that the online evolutionary process is capable of generating controllers that adapt to the periodic task changes. We evaluate the performance both in a single robot setup and in a multirobot setup. An analysis of the evolved networks shows that they are characterized by specialized modulatory neurons that exclusively regulate online learning in the output neurons.
Author: Fernando Goulart da Silva
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2225428591