Evolutionary Robotics: Exploring New Horizons

Abstract

This paper considers the field of Evolutionary Robotics (ER) from the perspective of its potential users: roboticists. The core hypothesis motivating this field of research is discussed, as well as the potential use of ER in a robot design process. Four main aspects of ER are presented: (a) ER as an automatic parameter tuning procedure, which is the most mature application and is used to solve real robotics problem, (b) evolutionary-aided design, which may benefit the designer as an efficient tool to build robotic systems (c) ER for online adaptation, i.e. continuous adaptation to changing environment or robot features and (d) automatic synthesis, which corresponds to the automatic design of a mechatronic device and its control system. Critical issues are also presented as well as current trends and pespectives in ER. A section is devoted to a roboticist's point of view and the last section discusses the current status of the field and makes some suggestions to increase its maturity.

From evolutionary computation to the evolution of things

“…In the future we expect to see increasing interest in applying EAs to embodied/embedded systems: that is, employing evolution in populations where the candidate solutions are controllers or drivers that implement the operational strategy for some situated entities, and are evaluated within the context of some rich dynamic environment; not for what they are, but what they do. Examples include policies for Web-agents, information retrieval strategies, software for machinery and smart devices, and controllers for autonomous robots 86,87 . In such cases the evolved solutions are embedded in entities that exist and act in a 'habitat', the Internet or the physical world, that is too complex and dynamic to be modelled perfectly.…”

Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

“…Similarly, previous work has demonstrated the benefits of maintaining genotypic diversity as a means to boost the quality of evolved behaviors for various ER tasks (Floreano et al, 2008;Doncieux et al, 2011Doncieux et al, , 2015Mouret and Doncieux, 2012). Genotype diversity maintenance is also a well-explored topic in more general evolutionary computation research (Brameier and Banzhaf, 2002;Ekárt and Németh, 2002;Crepinsek et al, 2013;Lehman et al, 2013;Mueller-Bady et al, 2016).…”

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

“…Bio-inspired robots import some ideas from these natural wonders [118-120, 152, 153, 60], with the hope of taking advantage of billion years of evolution. Evolutionary Robotics (ER) [141,60,53,20] follows a close but different path: instead of trying to replicate the result of evolution, why not try to replicate evolution itself? Evolutionary robotics hence proposes to employ evolution-inspired algorithms to design robots or, more often, control systems for robots.…”

“…From the engineering point of view, evolutionary robotics aims to propose an automated engineering process [113,53,20], that is, a process in which engineers write specifications and a computer takes care of the design.…”