Encouraging behavioral diversity in evolutionary robotics: an empirical study.

Evolutionary robotics (ER) aims at automatically designing robots or controllers of robots without having to describe their inner workings. To reach this goal, ER researchers primarily employ phenotypes that can lead to an infinite number of robot behaviors and fitness functions that only reward the achievement of the task-and not how to achieve it. These choices make ER particularly prone to premature convergence. To tackle this problem, several papers recently proposed to explicitly encourage the diversity of the robot behaviors, rather than the diversity of the genotypes as in classic evolutionary optimization. Such an approach avoids the need to compute distances between structures and the pitfalls of the noninjectivity of the phenotype/behavior relation; however, it also introduces new questions: how to compare behavior? should this comparison be task specific? and what is the best way to encourage diversity in this context? In this paper, we review the main published approaches to behavioral diversity and benchmark them in a common framework. We compare each approach on three different tasks and two different genotypes. The results show that fostering behavioral diversity substantially improves the evolutionary process in the investigated experiments, regardless of genotype or task. Among the benchmarked approaches, multi-objective methods were the most efficient and the generic, Hamming-based, behavioral distance was at least as efficient as task specific behavioral metrics.

Artificial evolution of the morphology and kinematics in a flapping-wing mini-UAV.

Birds demonstrate that flapping-wing flight (FWF) is a versatile flight mode, compatible with hovering, forward flight and gliding to save energy. This extended flight domain would be especially useful on mini-UAVs. However, design is challenging because aerodynamic efficiency is conditioned by complex movements of the wings, and because many interactions exist between morphological (wing area, aspect ratio) and kinematic parameters (flapping frequency, stroke amplitude, wing unfolding). Here we used artificial evolution to optimize these morpho-kinematic features on a simulated 1 kg UAV, equipped with wings articulated at the shoulder and wrist. Flight tests were conducted in a dedicated steady aerodynamics simulator. Parameters generating horizontal flight for minimal mechanical power were retained. Results showed that flight at medium speed (10-12 m s(-1)) can be obtained for reasonable mechanical power (20 W kg(-1)), while flight at higher speed (16-20 m s(-1)) implied increased power (30-50 W kg(-1)). Flight at low speed (6-8 m s(-1)) necessitated unrealistic power levels (70-500 W kg(-1)), probably because our simulator neglected unsteady aerodynamics. The underlying adaptation of morphology and kinematics to varying flight speed were compared to available biological data on the flight of birds.