Abstract
The purpose of this study is to develop partner robots that can obtain and accumulate human-friendly behaviors. To achieve this purpose, the entire architecture of the robot is designed, based on a concept of structured learning which emphasizes the importance of interactive learning of several modules through interaction with its environment. This paper deals with a trajectory planning method for generating hand-to-hand behaviors of a partner robot by using multiple fuzzy state-value functions, a self-organizing map, and an interactive genetic algorithm. A trajectory for the behavior is generated by an interactive genetic algorithm using human evaluation. In order to reduce human load, human evaluation is estimated by using the fuzzy state-value function. Furthermore, to cope with various situations, a self-organizing map is used for clustering a given task dependent on a human hand position. And then, a fuzzy state-value function is assigned to each output unit of the self-organizing map. The robot can easily obtain and accumulate human-friendly trajectories using a fuzzy state-value function and a knowledge database corresponding to the unit selected in the self-organizing map. Finally, multiple fuzzy state-value functions can estimate a human evaluation model for the hand-to-hand behaviors. Several experimental results show the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Zadeh LA (1965) Fuzzy sets. J Inform Control 8:338–353
Jang J-SR, Sun C-T, Mizutani E (1997) Neuro-fuzzy and soft computing, Prentice-Hall, Inc.
Fogel DB (1995) Evolutionary computation. IEEE Press, New York
Syswerda G (1991) A study of reproduction in generational and steady-state genetic algorithms, In foundations of genetic algorithms. Morgan Kaufmann Publishers, San Mateo
Tani J (1996) Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Trans Syst Man Cybern B 26(3):421–436
Wolpert DM, Kawato M (1998) Multiple paired forward and inverse models for motor control. Neural Netw 11:1317–1329
Xiao J, Michalewicz Z, Zhang L, Trojanowski K (1998) Adaptive evolutionary planner/navigator for mobile robots. IEEE Trans Evol Comput 1(1):18–28
Fukuda T, Kubota N (1999) An intelligent robotic system based on a fuzzy approach. Proc IEEE 87(9):1448–1470
Cliff D, Harvey I, Husbands P (1993) Explorations in evolutionary robotics. Adapt Behav 2:73–110
Nolfi S, Floreano D (2000) Evolutionary robotics: the biology, intelligence, and technology of self-organizing machines. MIT, Cambridge, USA
Takagi H (2001) Interactive evolutionary computation: fusion of the capabilities of EC optimization and human evaluation. Proc IEEE 89(9):1275–1296
Katagami D, Yamada S (2003) Teacher’s load and timing of teaching based on interactive evolutionary robotics. In: Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation, pp 1096–1101
Bertsekas DP, Tsitsiklis JN (1996) Neuro-dynamic programming. Athena Scientific, Belmont, USA
Sutton RS, Barto AG (1998) Reinforcement learning. MIT, Cambridge, USA
Takadama K, Nakasuka S, Shimohara K (2002) Robustness in organizational-learning oriented classifier system. J Soft Comput 6:229–239
Inoue H, Takadama K, Shimohara K, Katai O (2003) Acquisition of a specialty in multi-agent learning - approach from learning classifier system. In: Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation, pp 306–311
Brooks RA (1999) Cambrian intelligence. MIT, Cambridge, USA
Pfeifer R, Scheier C (1999) Understanding intelligence. MIT, Cambridge, USA
Arkin RC (1998) Behavior-based robotics. MIT, Cambridge, USA
Kubota N, Arakawa T, Fukuda T (1998) Trajectory planning and learning of a redundant manipulator with structured intelligence. J Brazilian Comput Soc 4(3):14–26
Kubota N (2003) Intelligent structured learning for a robot based on percieving-acting cycle. Proceedings of the 12 yale workshop on adaptive and learning systems, pp 199–206
Kubota N, Indra AS, Kojima F (2002) Interactive genetic algorithm for trajectory generation of a robot manipulator. In: Proceedings of the 4th Asia-Pacific conference on simulated evolution and learning, pp 146–150
Nojima Y, Kojima F, Kubota N (2003) Trajectory generation for human-friendly behavior of partner robot using fuzzy evaluating interactive genetic algorithm. In: Proceedings of the IEEE international symposium on computational intelligence in robotics and automation, pp 306-311
Paul RP (1981) Robot manipulators; mathematics, programming, and control. MIT, Cambridge, USA
Davidor Y (1991) A genetic algorithm applied to robot trajectory generation. In: Handbook of genetic algorithms, Van Nostrand, Reinhold, pp 144–165
Walter JA, Martinetz TM, Schulten KJ (1991) Industrial robot learns visuo-motor coordination by means of “neural-gas” network. Artif Neural Netw pp 357–364
Latombe H-L (1991) Robot motion planning. Kluwer Academic Publishers, Dordercht
Canny JF (1988) The complexity of robot motion planning. MIT, Cambridge, USA
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69
Kohonen T (1984) Self-organization and associative memory. Springer, Berlin Heidelberg New York
Kubota N, Hisajima D, Kojima F, Fukuda T (2003) Fuzzy and neural computing for communication of a partner robot. J Multiple-Valued Logic Soft-Comput 9(2):221–239
Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer, Berlin Heidelberg New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kubota, N., Nojima, Y., Kojima, F. et al. Multiple fuzzy state-value functions for human evaluation through interactive trajectory planning of a partner robot. Soft Comput 10, 891–901 (2006). https://doi.org/10.1007/s00500-005-0015-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-005-0015-9