Advantages of Multi-Objective Optimisation in Evolutionary Robotics: Survey and Case Studies

The application of multi-objective optimisation to evolutionary robotics has been so far relatively limited. Despite a few examples exist, the benefits of multi-objective optimisation when applied to the design of autonomous robotic systems have not been clearly spelled out and experimentally demonstrated. A survey of the literature on evolutionary robotics shows the lack of systematic studies confronting singleand multi-objective approaches. This paper fills this gap: starting from well-known results in multi-objective optimisation, we discuss how to tackle commonly recognised problems in evolutionary robotics. In particular, we show that multi-objective optimisation (i) allows evolving a more varied set of behaviours by exploring multiple trade-offs of the objectives to optimise, (ii) supports the evolution of the desired behaviour through the introduction of objectives as proxies, (iii) avoids the premature convergence to local optima possibly introduced by multi-component fitness functions, and (iv) solves the bootstrap problem exploiting ancillary objectives to guide evolution in the early phases. We present an experimental demonstration of these benefits in the context of standard case studies in robotics: maze navigation in a single robot domain, flocking in a swarm robotics context, and a strictly collaborative task in collective robotics.