SENSOR EXPLICATION - KNOWLEDGE-BASED ROBOTIC PLAN EXECUTION THROUGH LOGICAL OBJECTS

Complex robot tasks are usually described as high-level goals, with no details on how to achieve them, However, details must be provided to generate primitive commands to control a real robot, A sensor explicat ion concept that makes details explicit from general commands is prese nted, We show how the transformation from high-level goals to primitiv e commands can be performed at execution time and we propose an archit ecture based on reconfigurable objects that contain domain knowledge a nd knowledge about the sensors and actuators available, Our approach i s based on two premises: 1) plan execution is an information gathering process where determining what information is relevant is a great par t of the process; and 2) plan execution requires that many details are made explicit. We show how our approach is used in solving the task o f moving a robot to and through an unknown, and possibly narrow, doorw ay where sonic range data is used to find the doorway, walls, and obst acles, We illustrate the difficulty of such a task using data from a l arge number of experiments we conducted with a real mobile robot, The laboratory results illustrate how the proper application of knowledge in the integration and utilization of sensors and actuators increases the robustness of plan execution.