Learning Continuous Perception-Action Models Through Experience

Autonomous robotic navigation is defined as the task of find-ing a path along which a robot can move safely from a source point to a destination point in a obstacle-ridden terrain and, often, executing the actions to carry out the movement in a real or simulated world. Several methods have been proposed for this task, ranging from high-level planning methods to reactive methods. High-level planning methods use extensive world knowl-edge and inferences about the environment they interact with (see [Fikes el al., 1972; Georgeff, 1987; Maes, 1990; Sacerdoti, 1975]). Knowledge about available actions and their consequences is used to formulate a detailed plan be-fore the actions are actually executed in the world. Such systems can successfully perform the path-finding required by the navigation task, but only ff an accurate and complete representation of the world is available to the system. Con-siderable high-level knowledge is also needed to learn from planning experiences (see, for example, [Hammond, 1989; Minion, 1988; Mostow and Bhatnagar, 1987; Segre, 1988]). Such a representation is usually not available in real-world environments, which are complex and dynamic in nature. To build the necessary representations, a fast and accurate per-ception process is required to reliably map sensory inputs to high-level representations of the world. A second problem with high-level planning is the large amount of processing time required, resulting in significant slowdown and the in. ability to respond immediately to unexpected situations. Situated or reactive control methods have been proposed as an alternative to high-level planning methods (see [Arkin