Controle Inteligente do Caminhar de Robôs Móveis Utilizando Algoritmos Genéticos e Redes Neurais Artificiais
Resumo
Este artigo descreve o simulador LegGen, que realiza a configuração automática do caminhar em robôs simulados dotados de pernas. No simulador LegGen, algoritmos genéticos são utilizados para a evolução dos parâmetros do caminhar em robôs móveis simulados através da biblioteca de simulação baseada em física Open Dynamics Engine (ODE). Diversos experimentos foram realizados utilizando duas estratégias de controle: (i) um autômato finito; (ii) uma rede neural do tipo Elman. Diversos experimentos estatisticamente válidos foram realizados, que permitiram constatar a superioridade do controlador baseado em redes neurais artificiais na tarefa em questão.Referências
Batavia, P., Pomerleau, D., and Thorpe, C. (1996). Applying advanced learning algorithms to alvinn. Technical Report CMU-RI-TR-96-31, Carnegie Mellon Univ. (CMU), Pittsburgh, PA.
Bekey, G. A. (2005). Autonomous Robots: From Biological Inspiration to Implementation and Control. MIT Press, Cambridge, MA.
Bongard, J. C. and Pfeifer, R. (2002). A method for isolating morphological effects on evolved behaviour. In Proc. 7th Int. Conf. Simulation of Adaptive Behaviour (SAB), pages 305–311, Edinburgh, UK. MIT Press.
Busch, J., Ziegler, J., Aue, C., Ross, A., Sawitzki, D., and Banzhaf, W. (2002). Automatic generation of control programs for walking robots using genetic programming. In Proc. 5th European Conf. Genetic Programming (EuroGP), volume 2278 of LNCS, pages 258–267, Kinsale, Ireland. Springer-Verlag.
Chernova, S. and Veloso, M. (2004). An evolutionary approach to gait learning for four-legged robots. In Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), Sendai, Japan.
Darwin, C. (1859). Origin of Species. John Murray, London, UK.
Dudek, G. and Jenkin, M. (2000). Computational Principles of Mobile Robotics. Cambridge Univ. Press, Cambridge, UK.
Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14:179–211.
Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading, MA.
Golubovic, D. and Hu, H. (2003). Ga-based gait generation of sony quadruped robots. In Proc. 3th IASTED Int. Conf. Artificial Intelligence and Applications (AIA), Benalmadena, Spain.
Haykin, S. (2001). Redes Neurais: Princípios e Prática. Bookman, Porto Alegre, RS, Brazil, 2 edition.
Heinen, M. R. and Osório, F. S. (2006a). Applying genetic algorithms to control gait of physically based simulated robots. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC), Vancouver, Canada. IEEE World Congress on Computational Intelligence (WCCI), IEEE Press.
Heinen, M. R. and Osório, F. S. (2006b). Gait control generation for physically based simulated robots using genetic algorithms. In Schiman, J., Coelho, H., and Rezende, S. O., editors, Proceedings of the International Joint Conference 2006, 10th Ibero-American Conference on AI (IBERAMIA), 18th Brazilian Symposium on AI (SBIA), Lecture Notes in Computer Science, Ribeirão Preto SP, Brazil. Springer-Verlag.
Heinen, M. R. and Osório, F. S. (2006c). Uso de algoritmos genéticos para a configuração automática do caminhar em robôs móveis. In Anais do Encontro de Robótica Inteligente (EnRI), Campo grande, MS, Brazil. UFMS, UCDB.
Heinen, M. R. and Osório, F. S. (2007). Evolving gait control of physically based simulated robots. Revista de Informática Teórica e Aplicada (RITA) – to appear.
Heinen, M. R., Osório, F. S., Heinen, F. J., and Kelber, C. (2006). SEVA3D: Using artificial neural networks to autonomous vehicle parking control. In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada. IEEE World Congress on Computational Intelligence (WCCI), IEEE Press.
Jacob, D., Polani, D., and Nehaniv, C. L. (2005). Legs than can walk: Embodiment-based modular reinforcement learning applied. In Proc. IEEE Int. Symposium on Computational Intelligence in Robotics and Automation (CIRA), pages 365–372, Espoo, Finland.
Knight, R. and Nehmzow, U. (2002). Walking robots a survey and a research proposal. Technical Report CSM-375, Univ. Essex, Essex, UK.
Kohl, N. and Stone, P. (2004). Policy gradient reinforcement learning for fast quadrupedal locomotion. In Proc. IEEE Int. Conf. Robotics and Automation (ICRA), pages 2619– 2624, New Orleans, LA.
Law, A. M. and Kelton, D. W. (2000). Simulation Modeling and Analysis. McGraw-Hill, New York.
Lewis, M. A., Fagg, A. H., and Solidum, A. (1992). Genetic programming approach to the construction of a neural network for control of a walking robot. In Proc. IEEE Int. Conf. Robotics and Automation (ICRA), pages 2618–2623, Nice, France.
McGhee, R. B. (1976). Robot locomotion. Neural Control of Locomotion, pages 237–264.
Medeiros, A. (1998). Introdução à robótica. In Anais do XVII Encontro Nacional de Automática, volume 1, pages 56–65, Natal, RN, Brazil.
Mitchell, M. (1996). An Introduction to Genetic Algorithms. MIT Press, Cambridge, MA.
Mitchell, T. (1997). Machine Learning. McGrall-Hill, New York.
Osório, F. S., Musse, S. R., Vieira, R., Heinen, M. R., and Paiva, D. C. (2006). Increasing Reality in Virtual Reality Applications through Physical and Behavioural Simulation, volume 2, pages 1–45. Springer-Verlag, Berlin, Germany.
Pfeifer, R. and Scheier, C. (1999). Understanding Intelligence. MIT Press, Cambridge, MA.
Raibert, M. H. (1986). Legged Robots That Balance. MIT Press, Cambridge, MA.
Reeve, R. and Hallam, J. (2005). An analysis of neural models for walking control. IEEE Trans. Neural Networks, 16(3):733–742.
Bekey, G. A. (2005). Autonomous Robots: From Biological Inspiration to Implementation and Control. MIT Press, Cambridge, MA.
Bongard, J. C. and Pfeifer, R. (2002). A method for isolating morphological effects on evolved behaviour. In Proc. 7th Int. Conf. Simulation of Adaptive Behaviour (SAB), pages 305–311, Edinburgh, UK. MIT Press.
Busch, J., Ziegler, J., Aue, C., Ross, A., Sawitzki, D., and Banzhaf, W. (2002). Automatic generation of control programs for walking robots using genetic programming. In Proc. 5th European Conf. Genetic Programming (EuroGP), volume 2278 of LNCS, pages 258–267, Kinsale, Ireland. Springer-Verlag.
Chernova, S. and Veloso, M. (2004). An evolutionary approach to gait learning for four-legged robots. In Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), Sendai, Japan.
Darwin, C. (1859). Origin of Species. John Murray, London, UK.
Dudek, G. and Jenkin, M. (2000). Computational Principles of Mobile Robotics. Cambridge Univ. Press, Cambridge, UK.
Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14:179–211.
Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading, MA.
Golubovic, D. and Hu, H. (2003). Ga-based gait generation of sony quadruped robots. In Proc. 3th IASTED Int. Conf. Artificial Intelligence and Applications (AIA), Benalmadena, Spain.
Haykin, S. (2001). Redes Neurais: Princípios e Prática. Bookman, Porto Alegre, RS, Brazil, 2 edition.
Heinen, M. R. and Osório, F. S. (2006a). Applying genetic algorithms to control gait of physically based simulated robots. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC), Vancouver, Canada. IEEE World Congress on Computational Intelligence (WCCI), IEEE Press.
Heinen, M. R. and Osório, F. S. (2006b). Gait control generation for physically based simulated robots using genetic algorithms. In Schiman, J., Coelho, H., and Rezende, S. O., editors, Proceedings of the International Joint Conference 2006, 10th Ibero-American Conference on AI (IBERAMIA), 18th Brazilian Symposium on AI (SBIA), Lecture Notes in Computer Science, Ribeirão Preto SP, Brazil. Springer-Verlag.
Heinen, M. R. and Osório, F. S. (2006c). Uso de algoritmos genéticos para a configuração automática do caminhar em robôs móveis. In Anais do Encontro de Robótica Inteligente (EnRI), Campo grande, MS, Brazil. UFMS, UCDB.
Heinen, M. R. and Osório, F. S. (2007). Evolving gait control of physically based simulated robots. Revista de Informática Teórica e Aplicada (RITA) – to appear.
Heinen, M. R., Osório, F. S., Heinen, F. J., and Kelber, C. (2006). SEVA3D: Using artificial neural networks to autonomous vehicle parking control. In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada. IEEE World Congress on Computational Intelligence (WCCI), IEEE Press.
Jacob, D., Polani, D., and Nehaniv, C. L. (2005). Legs than can walk: Embodiment-based modular reinforcement learning applied. In Proc. IEEE Int. Symposium on Computational Intelligence in Robotics and Automation (CIRA), pages 365–372, Espoo, Finland.
Knight, R. and Nehmzow, U. (2002). Walking robots a survey and a research proposal. Technical Report CSM-375, Univ. Essex, Essex, UK.
Kohl, N. and Stone, P. (2004). Policy gradient reinforcement learning for fast quadrupedal locomotion. In Proc. IEEE Int. Conf. Robotics and Automation (ICRA), pages 2619– 2624, New Orleans, LA.
Law, A. M. and Kelton, D. W. (2000). Simulation Modeling and Analysis. McGraw-Hill, New York.
Lewis, M. A., Fagg, A. H., and Solidum, A. (1992). Genetic programming approach to the construction of a neural network for control of a walking robot. In Proc. IEEE Int. Conf. Robotics and Automation (ICRA), pages 2618–2623, Nice, France.
McGhee, R. B. (1976). Robot locomotion. Neural Control of Locomotion, pages 237–264.
Medeiros, A. (1998). Introdução à robótica. In Anais do XVII Encontro Nacional de Automática, volume 1, pages 56–65, Natal, RN, Brazil.
Mitchell, M. (1996). An Introduction to Genetic Algorithms. MIT Press, Cambridge, MA.
Mitchell, T. (1997). Machine Learning. McGrall-Hill, New York.
Osório, F. S., Musse, S. R., Vieira, R., Heinen, M. R., and Paiva, D. C. (2006). Increasing Reality in Virtual Reality Applications through Physical and Behavioural Simulation, volume 2, pages 1–45. Springer-Verlag, Berlin, Germany.
Pfeifer, R. and Scheier, C. (1999). Understanding Intelligence. MIT Press, Cambridge, MA.
Raibert, M. H. (1986). Legged Robots That Balance. MIT Press, Cambridge, MA.
Reeve, R. and Hallam, J. (2005). An analysis of neural models for walking control. IEEE Trans. Neural Networks, 16(3):733–742.
Publicado
30/06/2007
Como Citar
HEINEN, Milton Roberto; OSÓRIO, Fernando Santos.
Controle Inteligente do Caminhar de Robôs Móveis Utilizando Algoritmos Genéticos e Redes Neurais Artificiais. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 6. , 2007, Rio de Janeiro/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2007
.
p. 952-961.
ISSN 2763-9061.
