Embodied Evolution for Collective Indoor Surveillance and Location

This work is devoted with the application of a canonical Embodied Evolution algorithm in a collective task in which a fleet of Micro Aerial Vehicles (MAVs) have to survey an indoor scenario. The MAVs need to locate themselves to keep track of their trajectories and to share this information with other robots. This localization is performed using the IMU, artificial landmarks that can be sensed using the onboard camera and the position of other MAVs in sight. The accuracy in the decentralized location of each MAV has been included as a part of the problem to solve. Therefore, the collective control system is in charge of organizing the MAVs in the scenario in order to increase the accuracy of the fleet location, and consequently, the speed at which a new point of interest is reached.

[1]  Martijn C. Schut,et al.  Is situated evolution an alternative for classical evolution? , 2009, 2009 IEEE Congress on Evolutionary Computation.

[2]  Edwin Olson,et al.  AprilTag: A robust and flexible visual fiducial system , 2011, 2011 IEEE International Conference on Robotics and Automation.

[3]  Henrik I. Christensen,et al.  Darwinian embodied evolution of the learning ability for survival , 2011, Adapt. Behav..

[4]  Roland Siegwart,et al.  Introduction to Autonomous Mobile Robots , 2004 .

[5]  Wenguo Liu,et al.  Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents , 2012 .

[6]  Richard J. Duro,et al.  Open-ended evolution as a means to self-organize heterogeneous multi-robot systems in real time , 2010, Robotics Auton. Syst..

[7]  Vijay Kumar,et al.  Autonomous multi-floor indoor navigation with a computationally constrained MAV , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  A. E. Eiben,et al.  On-line evolution of robot controllers by an encapsulated evolution strategy , 2010, IEEE Congress on Evolutionary Computation.

[9]  Amitava Chatterjee,et al.  Vision Based Autonomous Robot Navigation - Algorithms and Implementations , 2012, Studies in Computational Intelligence.

[10]  Richard J. Duro,et al.  Specialization analysis of embodied evolution for robotic collective tasks , 2013, Robotics Auton. Syst..

[11]  Jordan B. Pollack,et al.  Embodied Evolution: Distributing an evolutionary algorithm in a population of robots , 2002, Robotics Auton. Syst..

[12]  Stefano Nolfi,et al.  Cooperative Robotics in Robocup Soccer is Not Just Playing a Game Andrea Bonarini , 2010 .

[13]  Abraham Prieto,et al.  Distributed embodied evolution for collective tasks: parametric analysis of a canonical algorithm , 2013, GECCO '13 Companion.

[14]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[15]  Geoff S. Nitschke.  Neuro-Evolution approaches to collective behavior , 2009, 2009 IEEE Congress on Evolutionary Computation.

[16]  Vincenzo Lippiello,et al.  MAV indoor navigation based on a closed-form solution for absolute scale velocity estimation using Optical Flow and inertial data , 2011, IEEE Conference on Decision and Control and European Control Conference.