Abstract
The application of multi-objective optimisation to evolutionary robotics is receiving increasing attention. A survey of the literature reveals the different possibilities it offers to improve the automatic design of efficient and adaptive robotic systems, and points to the successful demonstrations available for both task-specific and task-agnostic approaches (i.e., with or without reference to the specific design problem to be tackled). However, the advantages of multi-objective approaches over single-objective ones have not been clearly spelled out and experimentally demonstrated. This paper fills this gap for task-specific approaches: 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 three different case studies: maze navigation in a single robot domain, flocking in a swarm robotics context, and a strictly collaborative task in collective robotics.
Highlights
Artificial evolution is a powerful optimisation tool, and has been successfully applied to the synthesis of behaviours for autonomous robots, as demonstrated in the evolutionary robotics literature [1,2,3,4]
If we look at the comparison with specific values of γ as shown in Fig 6b to 6f, only for γ ! 0.6 the differences fall below 60% in favour of the multi-objective optimisation (MOO) approach for most of the objective space
The choice of γ = 0.5 results in poor performance, with most of the objective space attained by the MOO approach with at least 60% more probability than the single-objective optimisation (SOO) approach
Summary
Artificial evolution is a powerful optimisation tool, and has been successfully applied to the synthesis of behaviours for autonomous robots, as demonstrated in the evolutionary robotics literature [1,2,3,4]. Finding the correct trade-off between possibly conflicting terms is not easy In this case, a multi-objective approach may provide a set of solutions that explore different trade-offs, so that a principled choice can be made a posteriori. This survey highlights the lack of systematic studies that experimentally demonstrate the advantages of MOO, especially for what concerns the problems faced by designers in defining a suitable fitness function. The second case study (Section 4) concerns another classic task: coordinated motion (flocking) with robots having only local perception of their neighbourhood In this case, we show how MOO avoids the convergence to local optima induced by a multiple-components fitness function. The paper is concluded with a discussion of the results and of the future research directions (see Section 6)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
