Distributed On-line Learning in Swarm Robotics with Limited Communication Bandwidth

Abstract

This paper presents a new algorithm for distributed on-line evolutionary learning in swarm robotics. The challenge we address is to cope with the limited computation and communication capabilities of low cost robots, which are often used in swarm robotics. In order to do so, the algorithm decouples computation and communication and ensures learning of efficient control policies even when only a limited amount of information can be exchanged between neighbouring robots. We show experimentally that this algorithm is both remarkably robust with respect to its meta-parameter values, and able to adapt automatically to the available communication bandwidth.

The emergence of collective knowledge and cumulative culture in animals, humans and machines

“…The quantity and nature of the information exchanged between robots has an influence on the quality of their behaviour, as well as on the speed of diffusion of these behaviours in the swarm. In particular, the diffusion of a small amount of information allows exploitation of the possible recombinations between different behavioural strategies already present in the population [ 137 ], and presents an advantage with respect to the user-defined objective when compared to a simple imitation by copying [ 14 , 15 ]. Moreover, the way in which the information received by a robot is used has an influence not only on the improvement of performance [ 138 , 139 ], but also on the structure of the population itself, for example by allowing the specialization of subsets of the swarm to accomplish certain specific tasks [ 140 , 141 ].…”

Adaptive phototaxis of a swarm of mobile robots using positive and negative feedback self-alignment

“…The artificial social learning algorithm we use is built on the algorithm introduced in [15], referred to as the HIT algorithm (for Horizontal Information Transfer). It is distributed over the robots, and evolutionary optimization is conducted by passing messages in-between neighbours.…”

Social learning in swarm robotics

“…In this particular example, we use the horizontal information transfer (HIT) algorithm (see [ 31 ] for a full description). With this algorithm, each robot sends a subset of its control parameters along with the current estimation of its performance.…”

“…The interested reader is referred to [ 31 ] for a comprehensive analysis of the effect of transfer and mutation on convergence speed and performance.…”