An algorithm to navigate a point robot through a sequence of destination points amid unknown stationary polygonal obstacles in a two-dimensional terrain is presented. The algorithm implements learning in the course of building a global terrain model by integrating the sensor information obtained during navigation. This global model is used in planning future navigational paths. This approach prevents the robot from making localized detours, and results in better navigation, in an average case, than obtained using algorithms without learning. The proposed algorithms are implemented in the C language on a simulator for a HERMIES-II robot running on an IBM PC.>

In applications of robotics to surveillance and mapping at nuclear facilities the scene to be described is three-dimensional. Using range data a 3-D model of the environment can be built. First, each measured point on the object surface is surrounded by a solid sphere with a radius determined by the range to that point. Then the 3-D shapes of the visible surfaces are obtained by taking the (Boolean) union of the spheres. Using this representation distances to boundary surfaces can be efficiently calculated. This feature is particularly useful for navigation purposes. The efficiency of the proposed approach is illustrated by a simulation of a spherical robot navigating in a 3-D room with static obstacles.