Evolving Vision-Based Flying Robots

We describe a new experimental approach whereby an indoor flying robot evolves the ability to navigate in a textured room using only visual information and neuromorphic control. The architecture of a spiking neural circuit, which is connected to the vision system and to the motors, is genetically encoded and evolved on the physical robot without human intervention. The flying robot consists of a small wireless airship equipped with a linear camera and a set of sensors used to measure its performance. Evolved spiking circuits can manage to fly the robot around the room by exploiting a combination of visual features, robot morphology, and interaction dynamics.

[1]  Thomas S Collett,et al.  Using artificial evolution and selection to model insect navigation , 2001, Current Biology.

[2]  N. Franceschini,et al.  From insect vision to robot vision , 1992 .

[3]  Dimitrios Lambrinos,et al.  Cheap Vision-Exploiting Ecological Niche and Morphology , 2000, SOFSEM.

[4]  Heinrich H. Bülthoff,et al.  Insect Inspired Visual Control of Translatory Flight , 2001, ECAL.

[5]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[6]  F. Prinz,et al.  The Mesicopter: A Meso-Scale Flight Vehicle NIAC Phase II Technical Proposal , 1999 .

[7]  Paul F. M. J. Verschure,et al.  A Neural Model of the Fly Visual System Applied to Navigational Tasks , 2002, ICANN.

[8]  R. Siegwart,et al.  Proceedings of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems , 2002 .

[9]  Wulfram Gerstner,et al.  Associative Memory in a Network of 'Biological' Neurons , 1990, NIPS.

[10]  Thomas Netter,et al.  A robotic aircraft that follows terrain using a neuromorphic eye , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  J. Urzelai.  Evolutionary Robotics: Coping with Environmental Change { Category: Evolutionary Robotics (er) { , 2000 .

[12]  Stefano Nolfi,et al.  Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines , 2000 .

[13]  Dario Floreano,et al.  Evolutionary bits'n'spikes , 2002 .

[14]  T.N. Pornsin-Sirirak,et al.  MEMS wing technology for a battery-powered ornithopter , 2000, Proceedings IEEE Thirteenth Annual International Conference on Micro Electro Mechanical Systems (Cat. No.00CH36308).

[15]  Jean-Christophe Zufferey,et al.  Toward indoor flying robots , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Svetha Venkatesh,et al.  Insect inspired behaviours for the autonomous control of mobile robots , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[17]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[18]  H. Bülthoff,et al.  Evolution of the Sensorimotor Control in an Autonomous Agent , 1996 .

[19]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[20]  Ronald S. Fearing,et al.  Wing transmission for a micromechanical flying insect , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[21]  The Mesicopter : A MesoScale Flight Vehicle NIAC Phase I Final Report 1 , .

[22]  Fumiya Iida,et al.  Goal-Directed Navigation of an Autonomous Flying Robot Using Biologically Inspired Cheap Vision , 2001 .

[23]  Inman Harvey,et al.  Seeing the Light: Artiicial Evolution, Real Vision Seeing the Light: Artiicial Evolution, Real Vision , 1994 .