An Experiment in Automatic Design of Robot Swarms

Abstract

Abstract. We present an experiment in automatic design of robot swarms. For the first time in the swarm robotics literature, we perform an objective comparison of multiple design methods: we compare swarms designed by two automatic methods-AutoMoDe-Vanilla and EvoStickwith swarms manually designed by human experts. AutoMoDe-Vanilla and EvoStick have been previously published and tested on two tasks. To evaluate their generality, in this paper we test them without any modification on five new tasks. Besides confirming that AutoMoDe-Vanilla is e↵ective, our results provide new insight into the design of robot swarms. In particular, our results indicate that, at least under the adopted experimental protocol, not only does automatic design su↵er from the reality gap, but also manual design. The results also show that both manual and automatic methods benefit from bias injection. In this work, bias injection consists in restricting the design search space to the combinations of pre-existing modules. The results indicate that bias injection helps to overcome the reality gap, yielding better performing robot swarms.

AutoMoDe-Chocolate: automatic design of control software for robot swarms

“…The empirical studies presented in the paper are unprecedented in the domain of the automatic design of control software for robot swarms-they comprise 350 runs with a swarm of 20 robots; a total of five methods are tested on five tasks. This paper is an extended version of Francesca et al (2014b), which was presented at ANTS 2014. The results of Study A were already contained in Francesca et al (2014b), while the ones of Study B are presented here for the first time.…”

“…This paper is an extended version of Francesca et al (2014b), which was presented at ANTS 2014. The results of Study A were already contained in Francesca et al (2014b), while the ones of Study B are presented here for the first time.…”

A review of swarm robotics tasks

“…Communication can take place using explicit messages [115,116,117,118,119], or implicitly, by sensing the nearby presence and relative position of other robots [106,115,120,121,122,123,124,125,126,127]. Information acquired from nearby robots can be used to implement simple mechanisms of robot avoidance [123], or, more often, to regulate the position and velocity of a robot according to a desired behavior.…”

“…Podury and Sukhatme [121] used potential fields to maximize the area covered by a swarm of robots with defined sensing and communication ranges, with the constraint that each robot must stay within communication range of a minimum number of other robots. In [127], the task of maximizing the area covered by a swarm of connected robots is tackled with an automatic design method using probabilistic finite state machines, where parameters of robot controllers are selected with an optimization algorithm.…”

The Information-Cost-Reward framework for understanding robot swarm foraging

“…Recent experiments have shown that both manual and automated swarm design methodologies significantly benefit from being constrained to a set of possible robot behaviours, as opposed to being open-ended (Francesca et al 2014). Using the ICR framework, we could identify such behaviour sets by studying how different parts of robot control algorithms affect the overall swarm performance.…”