INTEGRATED SENSING FOR CIRCUIT-BOARD INSERTION

To automate tasks like assembly, disassembly, repair and maintenance, the issues arising from environmental uncertainties must be addressed. An integrated sensing approach which addresses uncertainties is presented for two robot systems equipped with multiple sensors. The target tasks involve the insertion of printed circuit boards into cages. Sensors are used to calibrate the robot to the workspace, locate the supply of printed circuit boards and the destination insertion slots. A fingertip lightbeam sensor is used to refine the location information to the precision required for a successful insertion. Two plausible approaches are explored to test some of the sensing concepts. One approach examines blind system sensing strategies; the other examines vision sensing in conjunction with fuzzy reasoning. A controller which is based on fuzzy logic is used to interpret the forces and torques generated by the wrist‐mounted force‐torque sensor during the insertion process. These explorations represent the first steps which lead toward the development of integrated sensing skills to perform generic activities such as insert and locate. Copyright © 1990 Wiley Periodicals, Inc., A Wiley Company