The Cognitive Development Learning Model and Its Application in Autonomous Navigation of Mobile Robot

Jianxian Cai

Abstract


In terms of the navigation problem of the mobile robot occurring in unknown environment, based on the cognitive and developmental mechanism of the biology, a cognitive development model for the autonomous learning navigation of the mobile robot is designed. Through autonomous insertion and deletion of neuron nodes in the neural network, the neural network with a dynamically adjusted structure is designed and the biological characteristics of living beings are imitated, thereby obtaining a network scale that matches the application requirements. The thermodynamic process is used to simulate the asymptotic properties of the animals. The cognitive learning algorithm is designed from the Monte Carlo method, the Metropolis algorithm and the annealing algorithm, and it is theoretically proved convergent. Based on the formation of the cognitive development process, the autonomous navigation activities of the mobile robot is under study. The experimental results show that, with the help of the cognitive development model, the robot automatically acquires knowledge and accumulates experience from the environment through cognition and development like animals. And the robot gradually forms, develops and improves the autonomous navigation skills in a self-organized way.


Full Text:

PDF

References


Asada M., MacDorman K.F., Ishiguro H., and et al. (2001). Cognitive developmental robotics as a new paradigm for the design of humanoid robots, Robotics and Autonomous Systems, 37(2-3), 185-193.

Asada M., Hosoda K., Kuniyoshi Y., and et al. (2009). Cognitive developmental robotics: A survey, IEEE Transa.on Autonomous Mental Development, 1(1), 12-34.

Bejan A. (2016). Constructal thermodynamics, International Journal of Heat and Technology, 34(Special 1),1-8.

Chang C., Gaudiano P. (2012). Application of Biological Learning Theories to Mobile Robot Avoidance and Approach Behaviors, Advances in Complex Systems, 1(1), 79-114.

Cherroun L., Boumehraz M. (2013). Fuzzy logic and reinforcement learning based approaches for mobile robot navigation in unknown environment, Mediterranean Journal of Measurement and Control, 9(1),109-117.

Dirafzoon A., Lobaton E. (2013).Topological mapping of unknown environments using an unlocalized robotic swarm, 2013, IEEE International Conference on Intelligent Robots and Systems, Hamburg, Germany, 5545-5551.

Jorgensen W. L. (2000). Perspective on ‘Equation of state calculations by fast computing machines’, Theor Chem Acc, 103(3), 225–227.

Kirkpatrick S., Gelatt C.D., Vecchi M.P. (1983). Optimization by simulated annealing, Science, 220(4598), 671–680.

Korein M. (2013). Scheduling mobile exploration tasks for environment learning, 12th International Conference on Autonomous Agents and Multiagent Systems, Bologna, Italy, 1255-1256.

Lee J.S. (2004). Self-Organizing neural networks by construction and pruning, Ieice Trans. On Information &System, 87-D (11), 2489-2498.

Murphy L., Corke P.(2012). STALKERBOT: Learning to navigate dynamic human environments by following people, Australasian Conference on Robotics and Automation, Victoria University of Wellington, New Zealand, 1-9.

Saarinen J. (2013). Conditional transition maps: Learning motion patterns in dynamic environments, IEEE International Conference on Intelligent Robots and Systems, Hamburg, Germany, 1196-1201.

Wen S.H., ChenX., MaC., and et al. (2015). The Q-learning obstacle avoidance algorithm based on EKF-SLAM for NAO autonomous walking under unknown environments, Robotics and Autonomous Systems, 72(C), 29-36.

Weng J., Mcclelland J., Pentland A., and et al. (2001). Artificial Intelligence: Autonomous Mental Development by Robots and Animals, Science, 291(5504), 599-600.

Xu X. (2010). Reforment learning and approximate dynamic programming, China: Science press, 110-130.

Yang D, Hu R, Ma Z. (2013). Part-load analysis of waste heat recovery system for a 10000TEU container ship, International Journal of Heat and Technology,31(1),121-128.

Yang D., Ma Z. (2012). Conceptual design and performance analysis of waste heat recovery system for intelligent marine diesel engines.International Journal of Heat and Technology, 30(2), 85-92.

Ye C., Yung N. H. C., Wang D. (2003). A fuzzy controller with supervised learning assisted reinforcement learning algorithm for obstacle avoidance, IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics, 33(1), 17-27.

Yu C.C., Wang C.C. (2014). Multi-step learning to search for dynamic environment navigation, Journal of Information Science and Engineering, 30(3), 637-652.

Zeng S., Cherba D. M., Weng J.(2003). Dav developmental humanoid: the control architecture and body, IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Port Island, Kobe, Japan, 974-980.

Zhang Y., Weng J., Huang W. (2005). Auditory learning: A developmental method, IEEE Trans. on Neural Networks, 16(3), 601-616.


Refbacks

  • There are currently no refbacks.


Revista de la Facultad de Ingeniería,

ISSN: 2443-4477; ISSN-L:0798-4065

Edif. del Decanato de la Facultad de Ingeniería,

3º piso, Ciudad Universitaria,

Apartado 50.361, Caracas 1050-A,

Venezuela.

© Universidad Central de Venezuela