On using stochastic automata for trajectory planning of robot manipulators in noisy workspaces

Abstract

The authors consider the problem of a robot manipulator operating in a noisy workspace. The robot is assigned the task of moving from an initial position P/sub i/ to a final position P/sub f/. Since P/sub i/ this position can be known fairly accurately. However, since P/sub f/ is usually obtained as a result of a sensing operation, possibly vision sensing, the authors assume that P/sub f/ is noisy. The authors propose a solution to achieve the motion which involves a learning automaton, called the discretized linear reward-penalty (DL/sub RP/) automaton. Alternatively, an automaton is positioned at each joint of the robot, and by processing repeated noisy observations of P/sub f/ the automata operate in parallel to control the motion of the manipulator. The advantages and the possible disadvantages of the scheme are also discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>