Adaptability of Tacit Learning in Bipedal Locomotion

The capability of adapting to unknown environmental situations is one of the most salient features of biological regulations. This capability is ascribed to the learning mechanisms of biological regulatory systems that are totally different from the current artificial machine-learning paradigm. We consider that all computations in biological regulatory systems result from the spatial and temporal integration of simple and homogeneous computational media such as the activities of neurons in brain and protein-protein interactions in intracellular regulations. Adaptation is the outcome of the local activities of the distributed computational media. To investigate the learning mechanism behind this computational scheme, we proposed a learning method that embodies the features of biological systems, termed tacit learning. In this paper, we elaborate this notion further and applied it to bipedal locomotion of a 36DOF humanoid robot in order to discuss the adaptation capability of tacit learning comparing with that of conventional control architectures and that of human beings. Experiments on walking revealed a remarkably high adaptation capability of tacit learning in terms of gait generation, power consumption and robustness.

[1]  H. Okano,et al.  Mathematical description of gene regulatory units. , 2006, Biophysical journal.

[2]  Takashi Minato,et al.  Analysis of physical human-robot interaction for motor learning with physical help , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[3]  Joshua G. Hale,et al.  Using Humanoid Robots to Study Human Behavior , 2000, IEEE Intell. Syst..

[4]  Andrew L. Kun,et al.  Adaptive dynamic balance of a biped robot using neural networks , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[5]  James L. McClelland,et al.  Autonomous Mental Development by Robots and Animals , 2001, Science.

[6]  Masao Ito,et al.  Long-lasting depression of parallel fiber-Purkinje cell transmission induced by conjunctive stimulation of parallel fibers and climbing fibers in the cerebellar cortex , 1982, Neuroscience Letters.

[7]  M. Asada,et al.  Visual attention by saliency leads cross-modal body representation , 2008, 2008 7th IEEE International Conference on Development and Learning.

[8]  Hidenori Kimura,et al.  Biomimetic Approach to Tacit Learning Based on Compound Control , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Russ Tedrake,et al.  Efficient Bipedal Robots Based on Passive-Dynamic Walkers , 2005, Science.

[10]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[11]  M. Kawato,et al.  A hierarchical neural-network model for control and learning of voluntary movement , 2004, Biological Cybernetics.

[12]  E Paul Zehr,et al.  Training-induced adaptive plasticity in human somatosensory reflex pathways. , 2006, Journal of applied physiology.

[13]  Kenji Doya,et al.  Reinforcement Learning in Continuous Time and Space , 2000, Neural Computation.

[14]  H. Kimura,et al.  Mathematical classification of regulatory logics for compound environmental changes. , 2008, Journal of theoretical biology.

[15]  Hidenori Kimura,et al.  Neural Computation Scheme of Compound Control: Tacit Learning for Bipedal Locomotion , 2008 .

[16]  Hidenori Kimura,et al.  Emergence of bipedal walking through body/environment interactions , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Shengxiang Yang,et al.  Adaptive Primal–Dual Genetic Algorithms in Dynamic Environments , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Jih-Gau Juang,et al.  Fuzzy neural network approaches for robotic gait synthesis , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[19]  Minoru Asada,et al.  Cognitive developmental robotics as a new paradigm for the design of humanoid robots , 2001, Robotics Auton. Syst..

[20]  Katsu Yamane,et al.  Effects of nerve signal transmission delay in somatosensory reflex modeling based on inverse dynamics and optimization , 2010, 2010 IEEE International Conference on Robotics and Automation.

[21]  Jun Morimoto,et al.  Learning CPG-based biped locomotion with a policy gradient method , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[22]  T. Takenaka,et al.  The development of Honda humanoid robot , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[23]  Yasuo Kuniyoshi,et al.  Early motor development from partially ordered neural-body dynamics: experiments with a cortico-spinal-musculo-skeletal model , 2006, Biological Cybernetics.

[24]  P. Norman,et al.  Immunobiology: The immune system in health and disease , 1995 .

[25]  H. Okano,et al.  Stochastic approach to molecular interactions and computational theory of metabolic and genetic regulations. , 2006, Journal of theoretical biology.

[26]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[27]  Minoru Asada,et al.  CB2: A child robot with biomimetic body for cognitive developmental robotics , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[28]  J Schouenborg,et al.  Developmental Adaptation of Rat Nociceptive Withdrawal Reflexes after Neonatal Tendon Transfer , 1997, The Journal of Neuroscience.

[29]  H. Pontzer,et al.  Chimpanzee locomotor energetics and the origin of human bipedalism , 2007, Proceedings of the National Academy of Sciences.

[30]  Masaki Ogino,et al.  Cognitive Developmental Robotics: A Survey , 2009, IEEE Transactions on Autonomous Mental Development.

[31]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[32]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.