Trajectory Planning of Robot Manipulators in Noisy Work Spaces Using Stochastic Automata

We consider the problem of a robot manipulator operating in a noisy work space. The robot is assigned the task of moving from P i to P f. Because P i is its initial position, this position can be known fairly accurately. However, because P f is usually obtained as a result of a sensing operation, possibly vision sensing, we assume that P f is noisy. We propose a solution to achieve the motion that involves a new learning automaton, called the Discretized Linear Reward-Penalty (DL RP) 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 P f the automata operate in parallel to control the motion of the manipulator.