JRL members to attend EVOSTAR 2019

Members of the JRL Maria Carrillo, Javier Sanchez Cubillo, Miren Nekane Bilbao, Eneko Osaba and Javier Del Ser have recently authored the paper  Trophallaxis, Low-power Vision Sensors and Multi-objective Heuristics for 3D Scene Reconstruction using Swarm Robotics, which has been accepted for presentation in the reputed conference EVOSTAR 2019 (http://www.evostar.org/2019/), in the main track EVOApplications. EVOSTAR 2019 will be held in the Leipzig University of Applied Sciences, Germany. A representative of the JRL will attend the conference to present the work orally.

Here is the abstract of the accepted paper:

A profitable strand of literature has lately capitalized on the exploitation of the collaborative capabilities of robotic swarms for efficiently undertaking diverse tasks without any human intervention, ranging from the blind exploration of devastated areas after massive disasters to mechanical repairs of industrial machinery in hostile environments, among others. However, most contributions reported to date deal only with robotic missions driven by a single task-related metric to be optimized by the robotic swarm (e.g. tardiness to complete the commanded mission), even though other objectives such as energy consumption may conflict with the imposed goal. In this paper multi-objective heuristic solvers are used to command and route a set of robots towards efficiently reconstructing a scene using simple camera sensors and stereo vision processing techniques. The need for resorting to multi-objective heuristics stems, among other modeling and computational aspects, from the consideration of energy efficiency as a second target of the mission plan. In this regard, the modeled scenario also incorporates energy trophallaxis within the swarm, i.e. specific robots capable of recharging other members of the swarm in favor of an increased overall autonomy. A robotic simulation environment is arranged to shed light on the performance of different heuristic algorithms over a realistically emulated physical environment. The obtained results stimulate further research lines aimed at considering decentralized heuristics for the considered problem.