Heuristic approaches for the optimal wiring in large scale robotic skin design

  • Authors:

  • Davide Anghinolfi;Giorgio Cannata;Fulvio Mastrogiovanni;Cristiano Nattero;Massimo Paolucci

  • Affiliations:

  • DIST, Department of Communication, Computer and Systems Science, University of Genova, Via Opera Pia, 13, 16145 Genova, Italy;DIST, Department of Communication, Computer and Systems Science, University of Genova, Via Opera Pia, 13, 16145 Genova, Italy;DIST, Department of Communication, Computer and Systems Science, University of Genova, Via Opera Pia, 13, 16145 Genova, Italy;DIST, Department of Communication, Computer and Systems Science, University of Genova, Via Opera Pia, 13, 16145 Genova, Italy;DIST, Department of Communication, Computer and Systems Science, University of Genova, Via Opera Pia, 13, 16145 Genova, Italy

  • Venue:
  • Computers and Operations Research
  • Year:
  • 2012

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper faces the problem of optimizing the wiring and the connections in a tactile skin for robots. The robotic skin is a device composed of a network of tactile sensors, whose wiring can be very complex: the control of this complexity is a key problem. In the considered robotic skin, skin elements are grouped into skin patches, which output tactile data that have to be read by a micro-controller. The logical connections between the sensors must be defined in order to route signals through the network. A finite set of micro-controllers is given and a set of constraints is imposed on the given assignment and routing. The considered problem has a combinatorial nature and it can be formulated as a Minimum Constrained Spanning Forest problem with costs on arcs that cannot be a priori defined as they are solution-dependent. The problem is NP-hard. The paper introduces a mathematical formulation and then proposes a Multi-Start Heuristic algorithm and an Ant Colony Optimization approach whose effectiveness is evaluated through experimental tests performed on both real and synthetically generated instances.