This paper deals with problems of rough terrain perception and mapping for walking robots equipped with inexpensive optical range sensors providing 2D data only. Two different sensing modalities are considered: the structured light sensor, and the Hokuyo URG-04LX laser scanner. Measurement uncertainty in both sensors is taken into account, and different geometric configurations of these sensors on the walking robot are analysed, yielding the configurations that are best for the task of terrain perception. Then, application of the acquired range data in local terrain mapping is presented. The mapping algorithm as well as novel methods for removing map artifacts that result from qualitative errors in range measurements are detailed. Experimental results are provided.
In this paper, we propose a new method for building an environmental map in a self-organizing manner using visual information from a mobile robot. This method is based on a Higher Rank of Self-Organizing Map (SOM ), in which Kohonen’s SOM is extended to create a map of data distributions (set of manifolds). It is expected that the “SOM” is capable of creating an environmental map in a self-organizing manner from visual information, since the set of visual information obtained from each position in the environment forms a manifold at every position. We also show the effectiveness of the proposed method.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.