Clustering objects with robots that do not compute

On

Abstract

This paper presents a multi-robot solution to the task of object clustering. 

The simplicity of the robots is pushed to the extreme so that

  • each robot can only detect the presence of (but not the distance to) an object or another robot in its direct line of sight
  • the robots are unable to store previous inputs and cannot perform arithmetic computations

Controllers for the robots were synthesised through an evolutionary robotics approach driven by physics-based simulations.

The results show that the problem can be solved even if the robots cannot distinguish between objects and other robots. However, if they are able to make this distinction, the clustering performance is significantly improved.

The controllers have been shown to scale adequately to large numbers of robots and objects. They have also shown to be robust to noise. The sensor/controller solution was implemented on the e-puck robotic system.

Across ten systematic experiments with five robots and 20 objects, on average, 86.5% of the objects were in one cluster after ten minutes.

We believe that the sensor/controller simplicity paves the way for the implementation of multi-robot systems at very small scales, as required, for instance, in nanomedical applications.


Highlight video


Videos of physical experiments

Videos of the ten trials with physical e-puck robots and objects, accelerated to 15 times real time.

Trial 1
Trial 2
Trial 3
Trial 4
Trial 5
Trial 6
Trial 7
Trial 8
Trial 9
Trial 10

Project updates

Natural Robotics Lab: investigating robotic systems inspired by nature, and robotic models of natural systems.

A global reputation

Sheffield is a world top-100 research university with a global reputation for excellence. We're a member of the Russell Group: one of the 24 leading UK universities for research and teaching.