A predictive network architecture for a robust and smooth robot docking behavior
Robots and living beings exhibit latencies in their sensorimotor processing due to mechanical and electronic or neural processing delays. A reaction typically occurs to input stimuli of the past. This is critical not only when the environment changes (e.g. moving objects) but also when the agent itself moves. An agent that does not predict while moving may need to remain static between sensory input acquisition and output response to guarantee that the response is appropriate to the percept. We propose a biologically-inspired learning model of predictive sensorimotor integration to compensate for this latency. In this model, an Elman network is developed for sensory prediction and sensory filtering; a Continuous Actor-Critic Learning Automaton (CACLA) is trained for continuous action generation. For a robot docking experiment, this architecture improves the smoothness of the robot’s sensory input and therefore results in a faster and more accurate continuous approach behavior.
KeywordsSensorimotor integration Continuous Actor-Critic Learning Automaton Elman network Sensory prediction
Unable to display preview. Download preview PDF.
- E. Goldstein, Sensation and Perception (Wadsworth Publishing Company, 2010).Google Scholar
- D. MacKay, Nature (1958).Google Scholar
- R. Nijhawan, Nature (1994).Google Scholar
- R. Nijhawan, Nature (1997).Google Scholar
- J. Hirsch and C. Gilbert, The Journal of Neuroscience 11, 1800 (1991).Google Scholar
- L. Natale, F. Nori, G. Sandini, and G. Metta, in IEEE 6th International Conference on Development and Learning, ICDL (2007), pp. 324–329.Google Scholar
- S. Nishide, T. Ogata, J. Tani, K. Komatani, and H. Okuno, Advanced Robotics 22, 527 (2008).Google Scholar
- N. Pradhan, T. Burg, and S. Birchfield, in IEEE American Control Conference, ACC (2011), pp. 4628–4633.Google Scholar
- T. H. Hong, C. Rasmussen, T. Chang, and M. Shneier, in Proc. of SPIE Aeroscience Conference (2002), pp. 311–319.Google Scholar
- J. Zhong, C. Weber, and S. Wermter, Artificial Neural Networks and Machine Learning, ICANN pp. 539–546 (2012).Google Scholar
- T. Klein, J. Jeka, T. Kiemel, and M. Lewis, Biological Cybernetics pp. 1–14 (2012).Google Scholar
- R. Möller, Journal of Theoretical Biology (2012).Google Scholar
- J. Hirel, P. Gaussier, and M. Quoy, in IEEE International Conference on Robotics and Biomimetics, ROBIO (2011), pp. 1627–1632.Google Scholar
- R. Saegusa, F. Nori, G. Sandini, G. Metta, and S. Sakka, in 7th IEEE-RAS International Conference on Humanoid Robots (2007), pp. 102–108.Google Scholar
- N. Navarro-Guerrero, C. Weber, P. Schroeter, and S. Wermter, Robotics and Autonomous Systems (2012).Google Scholar
- Aldebaran, http://www.aldebaran-robotics.com (2009).
- W. Yan, C. Weber, and S. Wermter, in International Joint Conference on Neural Networks, IJCNN (2012), pp. 1–8.Google Scholar
- J. Anderson and L. Schooler, The Oxford Handbook of Memory. (2000).Google Scholar
- O. Khatib, in Proc. IEEE International Conference on Robotics and Automation. (1985), vol. 2, pp. 500–505.Google Scholar