Action-oriented sensor fusion for telesystems

Work in sensor fusion for fully autonomous mobile robots that is expected to be useful for telesystems is discussed. Emphasis is placed on one product of this work, i.e. the sensor fusion effects (SFX) architecture, which can be extended into a control scheme for sensor fusion in telesystems. It can reduce the teleoperator's time in supervising the execution of a telerobot's sensing strategy and adapting that strategy to sensor malfunctions, changes in the environment, and other unanticipated sensing problems. It does this by autonomously monitoring the execution of the sensing strategy and looking for abnormalities. If an abnormality is detected, SFX initiates an exception handling process which tries to repair the sensing strategy autonomously. If that is not possible, the exception handling module gathers as much relevant information as possible and recommends a course of action for the operator. Experiments with sensor data collected from a Sony Hi8 color camcorder, a Pulnix black and white camera, an Inframetrics true infrared camera, Polaroid ultrasonic transducers, and a Hamamatsu ultraviolet light camera on a mobile robot show that SFX can autonomously monitor the execution of a sensing strategy and detect abnormalities.<<ETX>>

[1]  Thomas B. Sheridan,et al.  Human supervisory control of robot systems , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[2]  Hugh Durrant-Whyte,et al.  Integration, coordination, and control of multi-sensor robot systems , 1987 .

[3]  Gregory D. Hager,et al.  Task-Directed Sensor Fusion and Planning , 1990 .

[4]  Robin R. Murphy Control scheme for sensor fusion for navigation of autonomous mobile robots , 1991, Other Conferences.

[5]  Robin R. Murphy,et al.  Sfx: An Architecture For Action-oriented Sensor Fusion , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Steven A. Shafer,et al.  An architecture for sensor fusion in a mobile robot , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[7]  Lawrence W. Stark,et al.  A supervisory telerobotic control system using model-based vision feedback , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[8]  Robin R. Murphy,et al.  State-based sensor fusion for surveillance , 1992, Other Conferences.

[9]  L. F. Pau Behavioral knowledge in sensor/data fusion systems , 1990, J. Field Robotics.