Conformity and Nonconformity in Collective Robotics: A Case Study

Abstract

In this work, we develop a social behavioral model designed for multi-agent systems for solving the collective sorting task. Experiments show that under this model agents are capable of improving their performance significantly and can achieve better results than conventional swarms of agents lacking communication and social abilities.

A review of swarm robotics tasks

“…Thus, mechanisms of communication between robots are usually not considered in clustering studies. An exception is represented by scenarios where robots have localization capabilities which allow them to build clusters in a "smarter" way: in this case, coordination between robots becomes important, and communication mechanisms (either direct [91] or indirect [92]) play a role in the global clustering dynamics.…”

“…In [91], agreement between robots is achieved by means of direct communication: robots encountering each other exchange their current cluster location, and based on the received information decide probabilistically to switch to a location used by another robot. In [92], no explicit communication is used: instead, robots are able to measure the size of the different clusters being built, and switch their preferred cluster location based on the observed sizes, giving preference to larger clusters.…”

“…Quantitative measures of task execution performance often used to assess the effectiveness of an algorithm include the number of clusters being created [95,97,96,91], the average cluster size [96,100], the size of the largest cluster [95,96,100,91,90], and the time for task completion [95]. Task completion can be defined as the achievement of a condition where there is a single cluster per object type (in scenarios where this can be obtained with a significant probability), or the number and size of clusters is "satisfactory" according to given criteria.…”