메뉴 건너뛰기




Volumn 14, Issue 1, 1994, Pages 57-71

Robot Juggling: Implementation of Memory-Based Learning

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMICS; LEARNING SYSTEMS; OPTIMAL CONTROL SYSTEMS; STATISTICAL METHODS;

EID: 0028374275     PISSN: 1066033X     EISSN: None     Source Type: Journal    
DOI: 10.1109/37.257895     Document Type: Article
Times cited : (175)

References (42)
  • 2
    • 0024867511 scopus 로고
    • Task-level robot learning: Juggling a tennis ball more accurately
    • Scottsdale, AZ
    • E.W. Aboaf, S.M. Drucker, and C.G. Atkeson, “Task-level robot learning: Juggling a tennis ball more accurately,” in Proc. IEEE Int. Conf. Robot. Auto., May 14–19, 1989, Scottsdale, AZ.
    • (1989) Proc. IEEE Int. Conf. Robot. Auto.
    • Aboaf, E.W.1    Drucker, S.M.2    Atkeson, C.G.3
  • 5
    • 84941494078 scopus 로고
    • Memory-based approaches to approximating continuous functions
    • M.I.T. Cambridge, MA
    • C.G. Atkeson, “Memory-based approaches to approximating continuous functions,” AI-Lab and Brain and Cognitive Sciences Dept., M.I.T. Cambridge, MA, 1990.
    • (1990) AI-Lab and Brain and Cognitive Sciences Dept.
    • Atkeson, C.G.1
  • 7
    • 0019624645 scopus 로고
    • Stochastic dynamic programming: Caution and probing
    • Y. Bar-Shalom, “Stochastic dynamic programming: Caution and probing,” IEEE Trans. Auto. Control, vol. AC-26, Oct. 1981.
    • (1981) IEEE Trans. Auto. Control , vol.AC-26
    • Bar-Shalom, Y.1
  • 8
    • 0003787146 scopus 로고
    • Princeton, NJ: Princeton Univ. Press
    • R. Bellman, Dynamic Programming. Princeton, NJ: Princeton Univ. Press, 1957.
    • (1957) Dynamic Programming
    • Bellman, R.1
  • 11
    • 45549110576 scopus 로고
    • Regression by local fitting: Methods, properties, and computational algorithms
    • W.S. Cleveland, S.J. Devlin, and E. Grosse, “Regression by local fitting: Methods, properties, and computational algorithms,” J. Econometrics, vol. 37, pp. 87–114, 1988.
    • (1988) J. Econometrics , vol.37 , pp. 87-114
    • Cleveland, W.S.1    Devlin, S.J.2    Grosse, E.3
  • 14
    • 21144469140 scopus 로고
    • Variable bandwidth and local linear regression smoothers
    • J. Fan and I. Gijbels, “Variable bandwidth and local linear regression smoothers,” Annals Stat., vol. 20, no.4, pp. 2008–2036, 1992.
    • (1992) Annals Stat. , vol.20 , Issue.4 , pp. 2008-2036
    • Fan, J.1    Gijbels, I.2
  • 16
    • 0040537338 scopus 로고
    • Exploiting chaos to predict the future and reduce noise
    • Los Alamos National Laboratory, Los Alamos, NM
    • J.D. Farmer and J.J. Sidorowich, “Exploiting chaos to predict the future and reduce noise,” Tech. Rep. LA-UR-88-901 Los Alamos National Laboratory, Los Alamos, NM, 1988.
    • (1988) Tech. Rep. LA-UR- , pp. 88-901
    • Farmer, J.D.1    Sidorowich, J.J.2
  • 23
    • 79951524852 scopus 로고
    • Choosing a subset regression
    • Amer. Stat. Assoc., Los Angeles, CA
    • C.L. Mallows. “Choosing a subset regression,” presented at Ann. Meet. Amer. Stat. Assoc., Los Angeles, CA, 1966.
    • (1966) presented at Ann. Meet
    • Mallows, C.L.1
  • 25
    • 0003442587 scopus 로고
    • Efficient memory-based learning for robot control
    • Computer Laboratory, University of Cambridge
    • A.W. Moore, “Efficient memory-based learning for robot control,” Ph.D. thesis, Tech. Rep. 229, Computer Laboratory, University of Cambridge, Oct. 1990.
    • (1990) Ph.D. thesis, Tech. Rep , pp. 229
    • Moore, A.W.1
  • 26
    • 84936904589 scopus 로고
    • Knowledge of knowledge and intelligent experimenttion for learning control
    • Seattle, WA
    • A.W. Moore, “Knowledge of knowledge and intelligent experimenttion for learning control,” in Proc. 1991 Int. Joint Conf. Neural Networks, Seattle, WA, 1991.
    • (1991) Proc
    • Moore, A.W.1
  • 27
    • 84936893291 scopus 로고    scopus 로고
    • An investigation of memory-based function approximators for learning control,” submitted for publication
    • H.-G. Müller, Nonparametric Regression Analysis of Longitudinal Data (Lecture Notes in Statistics Series), vol.46. Berlin: Springer, 1988.
    • Moore, A.W.1    Atkeson, C.G.2
  • 30
    • 0004816298 scopus 로고
    • K.S. Narendra and P. Dorato, Eds., Piscataway, NJ: IEEE Press
    • K.S. Narendra and P. Dorato, Eds., Advances in Adaptive Control. Piscataway, NJ: IEEE Press, 1991.
    • (1991) Advances in Adaptive Control
  • 32
    • 0026868185 scopus 로고
    • Distributed real time control of a spatial robot juggler
    • A.A. Rizzi, L.L. Whitcomb, D.E. Koditschek, “Distributed real time control of a spatial robot juggler,” IEEE Comput., vol. 25. no. 5, 1992.
    • (1992) IEEE Comput. , vol.25 , Issue.5
    • Rizzi, A.A.1    Whitcomb, L.L.2    Koditschek, D.E.3
  • 33
    • 0027204405 scopus 로고
    • Open loop stable control strategies for robot juggling
    • S. Schaal and C.G. Atkeson. “Open loop stable control strategies for robot juggling,” in Proc., IEEE Int. Conf. Robot. Auto., Atlanta, GA, 1993, pp. 913-918.
    • (1993) Proc. IEEE Int. Conf. Robot. Auto. , pp. 913-918
    • Schaal, S.1    Atkeson, C.G.2
  • 35
    • 84899182884 scopus 로고
    • Learning passive motor control strategies with genetic algorithms
    • L. Nadel and D. Stein, Eds. Reading, MA: Addison-Wesley
    • S. Schaal, C.G. Atkeson and S. Botros. “What should be learned?” in Proc. Seventh Yale Workshop Adaptiiv and Learning Syst., New Haven, CT, 1992, pp.199-204.
    • (1993) 1992 Lactures in Complex Systems
    • Schaal, S.1    Stemad, D.2
  • 37
    • 0026254768 scopus 로고
    • Ageneral regression neural network
    • D.F. Specht, “Ageneral regression neural network,” IEEE Trans. Neural Networks. Vol. 2. Nov. 1991.
    • (1991) IEEE Trans. Neural Networks , vol.2
    • Specht, D.F.1
  • 38
    • 85132026293 scopus 로고
    • Integrated architectures for leaming, planning, and reacting based on approximating dynamic programming
    • R.S. Sutton, “Integrated architectures for leaming, planning, and reacting based on approximating dynamic programming,” in Proc. Int. Machine Learning Conf., pp. 212-218, 1990.
    • (1990) Proc. Int. Machine Learning Conf. , pp. 212-218
    • Sutton, R.S.1
  • 39
    • 0003411271 scopus 로고
    • Efficient exploration in reinforcement learning
    • Carnegie-Mellon Univ., Pittsburgh, PA
    • S.B. Thrun, “Efficient exploration in reinforcement learning,” Tech. Rep. CMU-CS-92-102. Carnegie-Mellon Univ., Pittsburgh, PA, 1992.
    • (1992) Tech. Rep. CMU-CS-92-102
    • Thrun, S.B.1
  • 40
    • 84916480042 scopus 로고
    • Design and control of a robotic platform for machine learning
    • M.S. thesis, Dept. Mech. Eng., M.I.T., Cambridge, MA
    • G. Van Zyl, “Design and control of a robotic platform for machine learning,” M.S. thesis, Dept. Mech. Eng., M.I.T., Cambridge, MA, 1991.
    • (1991)
    • Van Zyl, G.1
  • 41
    • 0002617598 scopus 로고
    • A completely automatic French curve: Fitting spline functions by cross-validation
    • M.S. thesis, Dept. Mech. Eng., M.I.T., Cambridge, MA
    • G. Wahba and S. Wold, “A completely automatic French curve: Fitting spline functions by cross-validation,” Commun. Stat., vol. 4, no. 1, 1975.
    • (1975) Commun. Stat. , vol.4 , Issue.1
    • Wahba, G.1    Wold, S.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.