Abstract
There has been growing interest in motion planning problems for mobile robots. In this field, the main research is to generate a motion for a specific robot and task without previously acquired motions. However it is too wasteful not to use hard-earned acquired motions for other tasks. Here, we focus on a mechanism of reusing acquired motion knowledge and study a motion planning system able to generate and reuse motion knowledge. In this paper, we adopt a tree-based representation for expressing knowledge of motion, and propose a hierarchical knowledge for realizing a reuse mechanism. We construct a motion planning system using hierarchical knowledge as motion knowledge and using genetic programming as a learning method. We apply a proposed method for the gait generation task of a six-legged locomotion robot and show its availability with computer simulation.
Similar content being viewed by others
References
Chang, H.: A new technique to handle local minimum for imperfect potential field-based motion planning, in: Proc. of 1996 IEEE Internat. Conf. on Robotics and Automation, 1996, pp. 108–112.
Craig, J. J.: Introduction to Robotics, Addison-Wesley, Reading, MA, 1989.
David, J.: Montana, Strongly typed genetic programming, BBN Technical Report #7866, 1994.
Desai, J. P. and Kumar, V.: Nonholonomic motion planning for multiple mobile manipulators, in: Proc. of 1997 IEEE Internat. Conf. on Robotics and Automation, 1997, pp. 3409–3414.
Fikes, R. E., Hart, P. E., and Nilsson, N. J.: Learning and executing generalized robot plans, Artificial Intell. 3(4) (1972), 251–288.
Flash, T. and Hogan, N.: The coordination of arm movements, J. Neurosci. 5 (1985), 1688–1703.
Fujisawa, Y., Hoshino, H., Fukuda, T., Kosuge, K., Muro, E., and Kikuchi, K.: Omnidirectional walking mechanism (1st Report, Control of moving with coordination of actuators), Trans. Japan Soc. Mech. Engrg. C 60(571) (1994), 964–969.
Fukuda, T., Adachi, Y., Hoshino, H., Kosuge, K., Muro, E., Matunaga, I., and Arai, F.: Omnidirectional walking mechanism (2nd Report, Inclination control while walking on rough terrain), Trans. Japan Soc. Mech. Engrg. C 61(589) (1995), 3620–3626.
Fukuda, T., Adachi, Y., Hoshino, H., and Muro, E.: Omnidirectional walking mechanism (3rd Report, Redundancy and trajectory control), Trans. Japan Soc. Mech. Engrg. C 63(607) (1997), 952–959.
Fukuda, T., Adachi, Y., Hoshino, H., Muro, E., and Kurashige, K.: Omnidirectional walking mechanism (redundancy and trajectory control), JSME Int. J. 40(4) (1997), 694–701.
Han, J., Chung, W. K., Youm, Y., and Kim, S. H.: Task-based design of modular robot manipulator using efficient genetic algorithm, in: Proc. of 1997 IEEE Internat. Conf. on Robotics and Automation, 1997, pp. 507–512.
Jung, D. and Gupta, K. K.: Octree-based hierarchical distance maps for collision detection, in: Proc. of 1996 IEEE Internat. Conf. on Robotic and Automation, 1996, pp. 454–459.
Koza, J.: Genetic Programming, on the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, MA, 1992.
Latombe, J. C.: Robot Motion Planning, Kluwer Academic Publishers, 1991.
Oomichi, T., Higuchi,M., and Ohnishi, K.: Design method of multifingered master manipulator with force and tactile feed-back free from operation restriction by mechanism, J. Robotics Soc. Japan 16(7) (1998), 942–950.
Saito, F. and Fukuda, T.: Reinforcement learning for motion control of real robots, JRSJ 13(1) (1995), 82–88.
Schwefel, H. P.: On the Evolution of Evolutionary Computation, IEEE Press, New York, 1994.
Shibata, T., Fukuda, T., Kosuge, K., and Arai, F.: Selfish and coordinative planning for multiple mobile robots by genetic algorithm, in: Proc. of the 31th IEEE Conf. on Decision and Control, Vol. 3, Tucson, 1992, pp. 497–503.
Tsubouchi, T. and Rude, M.: Motion planning for mobile robots in a time-varying environment: A survey, J. Robotics Mechatoronics 8(1) (1996), pp. 15–24.
Warren, C. W.: Fast path planning using modified A method, in: IEEE Internat. Conf. on Robotics and Automation, Vol. 2, 1993, pp. 662–667.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kurashige, K., Fukuda, T. & Hoshino, H. Reusing Primitive and Acquired Motion Knowledge for Gait Generation of a Six-legged Robot Using Genetic Programming. Journal of Intelligent and Robotic Systems 38, 121–134 (2003). https://doi.org/10.1023/A:1026204313001
Issue Date:
DOI: https://doi.org/10.1023/A:1026204313001