We consider the problem of a robot manipulator operating in a noisy work space. The robot is assigned the task of moving from Pi to Pf. Because Pi is its initial position, this position can be known fairly accurately. However, because Pf is usu ally obtained as a result of a sensing operation, possibly vision sensing, we assume that Pf 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.

Additional Metadata
Persistent URL dx.doi.org/10.1177/027836499101000205
Journal The International Journal of Robotics Research
Oommen, J, Andrade, N. (Nicte), & Sitharam Iyengar, S. (S.). (1991). Trajectory Planning of Robot Manipulators in Noisy Work Spaces Using Stochastic Automata. The International Journal of Robotics Research, 10(2), 135–148. doi:10.1177/027836499101000205