Embodied Evolution in Collective Robotics: A Review

Abstract

This article provides an overview of evolutionary robotics techniques applied to online distributed evolution for robot collectives, namely, embodied evolution. It provides a definition of embodied evolution as well as a thorough description of the underlying concepts and mechanisms. This article also presents a comprehensive summary of research published in the field since its inception around the year 2000, providing various perspectives to identify the major trends. In particular, we identify a shift from considering embodied evolution as a parallel search method within small robot collectives (fewer than 10 robots) to embodied evolution as an online distributed learning method for designing collective behaviors in swarm-like collectives. This article concludes with a discussion of applications and open questions, providing a milestone for past and an inspiration for future research.

On an immuno-inspired distributed, embodied action-evolution cum selection algorithm

“…A recent comprehensive paper by Bredeche et al [3] presents a review of the research published since the inception of the term Embodied Evolution . EE involves continuous and online learning in a collective of robots.…”

“…A population of robots learns in a decentralized manner by sharing the controllers evolved among the peer robots. Although there has been a recent surge in papers [3] where EE has been successfully applied, most of the work that cites the use of real robots [11,17,21,22] are constrained to a single controller that can solve relatively simple tasks such as obstacle avoidance and phototaxis. Only recent, a work by Heinerman et al [11] implements a relatively complex task of foraging using a single controller.…”

“…In contrast to traditional ER approaches, the term Embodied Evolution (EE) applies to a collective of robots that autonomously and continuously adapt their behaviour in accordance with the changes in the environment [3]. In EE, robot controllers learn both onboard and online, and continue to do so even when the robots are deployed in an environment, thereby reducing the reality gap [12].…”

“…(2) Distributed Learning: While the encapsulated version of algorithm within one robot seeks and learns to choose the best subcontroller, sharing of these controllers across peers in the collective of robots speeds up the convergence process [3].…”

Embodied Evolution of Self-organised Aggregation by Cultural Propagation

“…Evolutionary swarm robotics is the approach typically used for synthesising collective behaviours for specific experimental settings via off-line parameter tuning [21,32,31]. An approach of on-line parameter tuning is instead represented by embodied evolution [8], whereby parameters controlling the robot behaviour are continuously adapted as a result of the interaction among robots and between robots and environment. Here, the evolutionary process is not driven by an explicit fitness measure that evaluates the quality of the collective behaviour, but emerges implicitly from the dynamics of interaction among the agents [4].…”