Evolutionary robotics: the Sussex approach

We give an overview of evolutionary robotics research at Sussex over the last 5 years. We explain and justify our distinctive approaches to (artiicial) evolution, and to the nature of robot control systems that are evolved. Results are presented from research with evolved controllers for autonomous mobile robots; simulated robots, coevolved animats, real robots with software controllers, and a real robot with a controller directly evolved in hardware. 1 Why Evolutionary Robotics? Humans are naturally evolved creatures, and the selection criteria under which our ancestors were judged did not include the ability to design complex systems | in fact, we are not very good at it. A common and useful trick to overcome our shortcomings is that of Divide and Conquer; a complex problem is decomposed into separate, less daunting, sub-problems. However, the interactions between such sub-problems must be few in number, so that the human designers can temporarily ignore them while solving one sub-problem at a time. When it comes to designing such complex systems as a cognitive control system for a robot, there are at least three major problems. { It is not clear how a robot control system should be decomposed. { Interactions between separate subsystems are not limited to directly visible connecting links between them, but also include interactions mediated via the environment. { As system complexity grows, the number of potential interactions between sub-parts of the system grows exponentially.