A sensor-based approach for motion in contact in task planning
- 19 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 468-473
- https://doi.org/10.1109/iros.1995.526258
Abstract
A novel approach based on the use of force sensors for motion in contact with uncertainty in task planning is presented. A neural network monitors the force signals measured by a sensor mounted in the robot wrist. This network is able to learn without need of a teacher the different contact states of the system. The method is intended to work properly in complex real-world situations, for which a geometric analytical model may not be feasible, or too difficult. In this paper the authors study the two-dimensional peg-in-hole problem and a real example of a complex insertion task in a flexible manufacturing system.Keywords
This publication has 10 references indexed in Scilit:
- Representation and learning of nonlinear compliance using neural netsIEEE Transactions on Robotics and Automation, 1993
- The self-organizing mapProceedings of the IEEE, 1990
- Planning Multi-Step Error Detection and Recovery StrategiesThe International Journal of Robotics Research, 1990
- Programmed compliance for error corrective assemblyIEEE Transactions on Robotics and Automation, 1990
- Planning Compliant Motion StrategiesThe International Journal of Robotics Research, 1989
- A geometric approach to error detection and recovery for robot motion planning with uncertaintyArtificial Intelligence, 1988
- The Complexity of Fine Motion PlanningThe International Journal of Robotics Research, 1988
- New lower bound techniques for robot motion planning problemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- Automatic Synthesis of Fine-Motion Strategies for RobotsThe International Journal of Robotics Research, 1984
- Sensor-based robotic assembly systems: Research and applications in electronic manufacturingProceedings of the IEEE, 1983