Evolving effective visual tracking through shaping

Shaping is a way in which a human designer can provide assistance to a learning system to enable it to solve problems that would otherwise defeat it. Results are presented showing that shaping can significantly improve the final performance of controllers evolved for a difficult visual tracking task. Controllers are developed in simulation and then transferred to a real robot head.

[1]  Marco Colombetti,et al.  Robot Shaping: An Experiment in Behavior Engineering , 1997 .

[2]  Simon Perkins,et al.  Incremental Aquisition of Complex Visual Behaviour using Genetic Programming and Robot Shaping , 1998 .

[3]  Jean-Arcady Meyer,et al.  Evolving Motion-tracking Behaviour For a Panning Camera Head , 1998 .

[4]  Riccardo Poli,et al.  Parallel Distributed Genetic Programming , 1996 .

[5]  Marco Colombetti,et al.  Robot shaping: developing situated agents through learning , 1992 .

[6]  Nick Jakobi,et al.  Evolving morion-tracking behaviour for a panning camera head , 1998 .

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

[8]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[9]  Gillian M. Hayes,et al.  Robot Shaping --- Principles, Methods and Architectures , 1996 .

[10]  Nick Jakobi,et al.  Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis , 1997, Adapt. Behav..

[11]  S. Perkins,et al.  Evolving robot vision: increasing performance through shaping , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[12]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[13]  Astro Teller,et al.  PADO: Learning Tree Structured Algorithms for Orchestration into an Object Recognition System , 1995 .

[14]  Stefano Nolfi,et al.  Evolving mobile robots in simulated and real environments , 1995 .

[15]  S.J.J. Smith,et al.  Empirical Methods for Artificial Intelligence , 1995 .

[16]  Astro Teller,et al.  Automatically Choosing the Number of Fitness Cases: The Rational Allocation of Trials , 1997 .