Engineering Online Evolution of Robot Behaviour: (Doctoral Consortium)

Evolutionary computation techniques have been widely studied to automate the synthesis of behavioural control for robots. In online evolution, an evolutionary algorithm is executed on the robots themselves during task execution so as to continuously optimise the robot controllers. Online evolution provides numerous potential benefits, including enabling robots to modify their behaviour in response to changes in the task and in the environment. Current approaches to online evolution on physical robots, however, often require a prohibitively long evolution time and a substantial amount of human experimentation, and have not yet scaled to complex real-world tasks. In this research, we study how to accelerate and scale online evolution to more complex tasks while minimising the amount of human intervention. Our ultimate objective is to enable the realisation of real-world multirobot systems that can effectively learn new behaviours and adapt online to take on dynamic tasks in a timely manner.