Robot task switching in complex environments

Robots operating in everyday life environments are often required to switch between different tasks. This paper introduces a new method for multiple tasks performance based on multiobjective evolutionary algorithm, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent robot that has to switch properly between three different tasks: (1) protecting another moving robot by following it closely (2) collecting objects scattered in the environment and (3) exploring the environment by moving close to the walls and obstacles. The simulation and experimental results using Cyber Rodent robot show that multiobjective-based evolutionary method can be applied effectively for generating neural networks controlling the robot to perform multiple tasks, simultaneously.