We consider the problem of a robot manipulator operating in a noisy work space. The robot is assigned the task of moving fromPi toPf. BecausePi is its initial position, this position can be known fairly accurately. However, becausePf is usu ally obtained as a result of a sensing operation, possibly vision sensing, we assume thatPf is noisy. We propose a so lution to achieve the motion that involves a new learning automaton, called the Discretized Linear Reward-Penalty (DLRP) automaton. The strategy we propose does not involve the computation of any inverse kinematics. Alternatively, an automaton is positioned at each joint of the robot, and by processing repeated noisy observations of Pf the automata operate in parallel to control the motion of the manipulator.
Get full access to this article
View all access options for this article.
References
1.
Arimoto, S., et al. 1985. Learning control theory for dynamical systems . Proc. 24th IEEE Conf. on Decision and Control , pp. 1375-1379.
2.
Arimoto, S., and Takegaki, M.1981. An adaptive trajectory control of manipulators . Int. J. Control34(2):219-230.
3.
Azadivar, F.1987. The effect of joint position errors of industrial robots on their performance in manufacturing operations. IEEE J. Robot. Automat.3(2):109-114.
4.
Brady, M., et al. 1983. Robot Motion: Planning and Control. Cambridge, Mass.: M.I.T. Press.
5.
Brooks, R.A., and Lozano-Pérez, T.1985. A subdivision algorithm in configuration space for findpath with rotation. IEEE Trans. Sys. Man Cybernet.15(2):224-233.
6.
Canny, J.F.1984. Collision detection for moving polyhedra. AI memo 806 . Artificial Intelligence Laboratory, M.I.T.
7.
Chatilla, R.1982(Torsay, France). Path planning and environment learning in a mobile robot system. Proc. European Conf. onArtificial Intelligence.
8.
Chattergy, R.1985. Some heuristics for the navigation of a robot. Int. J. Robot. Res.4(Spring):59-66.
9.
Craig, J.J., Hsu, P., and Sastry, S.S.1986 (San Francisco). Adaptive control of mechanical manipulators. Proc. 1986 IEEE Robotics and Automation Conference, pp. 190-195.
10.
Crowley, J.L.1985. Navigation of an intelligent mobile robot. IEEE J. Robot. Automat.1(1):31-41.
11.
Giralt, G., Sobek, R., and Chatilla, R.1979 (Tokyo). A multilevel planning and navigation system for a mobile robot. Proc. 6th Int. Joint Conf Artificial Intelligence, pp. 335-338.
12.
Gouzenes, L.1984. Strategies for solving collision-free trajectory problems for mobile and manipulator robots. Int. J. Robot. Res.3(Winter):51-65.
13.
Grossman, D.D., Evans, R.C., and Summers, P.D.1985. The value of multiple independent robot arms. Robot. Computer-Integrated Manufact.2:135-142.
14.
Hopcroft, J.E., Schwartz, J.T., and Sharir, M.1984. On the complexity of motion planning for multiple independent objects; PSPACE-hardness of the Waterhouseman's problem. Int. J. Robot. Res.3:76-88.
15.
Iyengar, S.S., et al. 1985a (Miami Beach). Learned navigation paths for a robot in unexplored terrain. Proc. 2nd Conf. Artificial Intelligence Applications and Engineering of Knowledge Based Systems, pp. 148-155.
16.
Iyengar, S.S., et al. 1985b. Robot navigation algorithms using learned spatial graphs. ORNL technical report TM-9782. Oak Ridge National Laboratory, Oak Ridge, Tenn.
17.
Kant, K., and Zucker, S.W.1984. Trajectory planning in time-varying environments; 1:TPP = PPP + VPP. McGill University. Computer Vision and Robotics TR-84-7R. Laboratory, Montreal, Canada.
18.
Koivo, A.J., and Guo, T.1983. Adaptive linear controller for robotic manipulators . IEEE Trans. Automatic Control28:162-170.
19.
Koivo, A.J.1986 (San Francisco). Force-position-velocity control with self-tuning for robotic manipulators. Proc. IEEE Robotics and Automation Conference. pp. 1563-1568.
20.
Kozlov, A.1985. Robotics and Model Share Innovations. SIAM News.18(5). pp. 1, 11.
21.
Lakshmivarahan, S.1981a. Learning algorithms: Theory and applications. Springer-Verlag. New York.*
22.
Lakshmivarahan, S.1979. ∈-Optimal learning algorithms— non-absorbing barrier type. Technical report EECS-7901. School of Electrical Engineering and Computing Sciences, University of Oklahoma, Norman, Oklahoma.*
23.
Lakshmivarahan, S.1981b. Two person decentralized team with incomplete information. App. Math. Computation8:51-78.*
24.
Lakshmivarahan, S., and Thathachar, M.A.L.1973. Absolutely expedient algorithms for stochastic automata. IEEE Trans. Sys. Man Cybernet.3:281-286.*
25.
Lozano-Pérez, T.1983. Spatial planning: A configuration space approach . IEEE Trans. Computers32(2):108-120.
26.
Lozano-Pérez, T., and Wesley, M.A.1979. An algorithm for planning collision-free paths among polyhedral obstacles. C. ACM22(10):560-570.
27.
Miller III, W.T.1987. Sensor-based control of robotic manipulators using a general learning algorithm. IEEE J. Robot. Automat.3(2):157-165.
Narendra, K.S., and Thathachar, M.A.L.1974. Learning automata—a survey. IEEE Trans. Sys. Man Cybernet.4:323-334.*
30.
Narendra, K.S., and Thathachar, M.A.L.1980. On the behaviour of a learning automaton in a changing environment with routing applications. IEEE Trans. Sys. Man Cybernet.10:262-269.*
31.
Narendra, K.S., Wright, E., and Mason, L.G.1977. Applications of learning automata to telephone traffic routing. IEEE Trans. Sys. Man Cybernet.7:785-792.*
32.
Oommen, B.J., and Hansen, E.R.1984. The Asymptotic optimality of discretized linear reward-inaction learning automata. IEEE Trans. Sys. Man Cybernet.14(3):542-545.*
33.
Oommen, B.J., and Thathachar, M.A.L.1985. Multiaction learning automata possessing ergodicity of the mean. Information Sciences35(3):183-198.*
34.
Oommen, B.J.1986b. Absorbing and ergodic discretized two-action learning automata. IEEE Trans. Sys. Man Cybernet.16(2):282-296.*
35.
Oommen, B.J.1986a. A learning automaton solution to the stochastic minimum spanning cycle problem. IEEE Trans. Sys. Man Cybernet.16(4):598-603.*
36.
Oommen, B.J., et al. 1987. Robot navigation in unknown terrains using learned visibility graphs. Part I: The disjoint convex obstacle case. IEEE J. of Robot. Automat.3(6):672-681.
37.
Oommen, B.J., and Christensen, J.P.R.1988. Epsilon-optimal discretized linear reward-penalty learning automata. IEEE Trans. Sys. Man and Cybernetics. 18(3):451-458.*
38.
Oommen, B.J., and Ma, D.C.Y.1987 (New Orleans). Fast object partitioning using stochastic learning automata. Proc. of the 1987 ACM Int. Conf on Research and Development in Information Retrieval, pp. 111-112.*
39.
Rao, S.V.N., et al. 1985. Concurrent algorithms for autonomous robot navigation in an unexplored terrain. Tech. Rep. 85-048, Dept. Computer Science , Louisiana State University, Baton Rouge.
40.
Ross, S.M.1980. Introduction to Probability Models. Academic Press. New York.*
41.
Schwartz, J.T., and Sharir, M.1983. On the piano movers' problem: III. Coordinating the motion of several independent bodies: The special case of circular bodies amidst polygonal barriers. Int. J. Robot. Res.2:46-75.
42.
Schwartz, J.T. and Yap, C-K., Algorithmic and Geometric Aspects of Robotics, Lawrence Erlbaum Associates Publishers, 1987.
43.
Thathachar, M.A.L., and Oommen, B.J.1979. Discretized reward-inaction learning automata. J. Cybernet. and In-format. Sci.1(Spring):24-29.*
44.
Togai, M., and Yamano, O.1986 (San Francisco). Learning control and its optimality. Proc. IEEE Robotics and Automation Conference, pp. 248-253.
45.
Tsetlin, M.L.1961. On the behavior of finite automata in random media . Automat. Telemekh. (USSR)22:1345-1354.*
46.
Tsetlin, M.L.1973. Automaton theory and the modelling of biological systems . New York: Academic Press .
47.
Tsypkin, Y.Z., and Poznyak, A.S.1972. Finite learning automata. Eng. Cybernet.10:478-490.*
48.
Turchen, M.P., and Wong, A.K.C.1985 (Miami Beach). Low level learning for a mobile robot: Environmental model acquisition. Proc. 2nd IEEE Conf. Artificial Intelligence Applications, pp. 156-161.
49.
Udupa, S.M.1977 (Cambridge, Mass.). Collision detection and avoidance in computer controlled manipulators. Proc. 5th Int. Conf. Artificial Intelligence, pp. 737-748.
50.
Varshavskii, V.I., and Vorontsova, I.P.1963. On the behaviour of stochastic automata with variable structure. Automat. Telemekh. (USSR)24:327-333.*
51.
Whitesides, S.1985. Computational geometry and motion planning. In Toussaint, G. (ed.): Computational Geometry . North Holland.
