Search

Neuroevolution is a promising approach for designing artificial neural networks using an evolutionary algorithm. Unlike recent trending methods that rely on gradient-based algorithms, neuroevolution can simultaneously evolve the topology and weights of neural networks. In neuroevolution with topological evolution, handling crossover is challenging because of the competing conventions problem. Mutation-based evolving artificial neural network is an alternative topology and weights neuroevolution approach that omits crossover and uses only mutations for genetic variation. This study enhances the performance of mutation-based evolving artificial neural network in two ways. First, the mutation step size controlling the magnitude of the parameter perturbation is automatically adjusted by a self-adaptive mutation mechanism, enabling a balance between exploration and exploitation during the evolution process. Second, the structural mutation probabilities are automatically adjusted depending on the network size, preventing excessive expansion of the topology. The proposed methods are compared with conventional neuroevolution algorithms using locomotion tasks provided in the OpenAI Gym benchmarks. The results demonstrate that the proposed methods with the self-adaptive mutation mechanism can achieve better performance. In addition, the adjustment of structural mutation probabilities can mitigate topological bloat while maintaining performance.

This study tackles the task of swarm robotics, where robots explore the environment to detect targets. When a robot detects a target, the robot must be connected with a base station via intermediate relay robots for wireless communication. Our previous results confirmed that Lévy flight outperformed the usual random walk for exploration strategy in an indoor environment. This paper investigated the search performance of swarm crawler robots with Lévy flight on target detection problems in large environments through a series of real robots’ experiments. The results suggest that the swarm crawler robots with Lévy flight succeeded in the target’s discovery in the indoor environment with a 100% success rate, and were able to find several targets in a given time in the outdoor environment. Thus, we confirmed that target exploration in a large environment would be possible by crawler robots with Lévy flight and significant variances in the detection rate among the positions to detect the outdoor environment’s target.

The field of multi-robot systems (MRSs), which deals with groups of autonomous robots, is recently attracting much research interest from robotics. MRSs are expected to achieve their tasks that are difficult to be accomplished by an individual robot. In MRSs, reinforcement learning (RL) is one of promising approaches for distributed control of each robot. RL allows participating robots to learn mapping from their states to their actions by rewards or payoffs obtained through interacting with their environment. Theoretically, the environment of MRSs is non-stationary, and therefore rewards or payoffs learning robots receive depend not only on their own actions but also on the action of other robots. From this point of view, an RL method which segments state and action spaces simultaneously and autonomously to extend the adaptability to dynamic environment, named Bayesian-discrimination-function-based Reinforcement Learning (BRL) has been proposed. In order to improve the learning performance of BRL, this paper proposes a technique of selecting either of two state spaces: one is parametric model useful for exploration and the other is non-parametric model for exploitation. The proposed technique is evaluated through computer simulations of a cooperative carrying task with six autonomous mobile robots.