Detection of Static and Dynamic Obstacles Based on Fuzzy Data Association with Laser Scanner

Aimed at the detection of static and dynamic obstacles in environmental mapping of mobile robot, an unsupervised clustering algorithm is presented to realize feature extraction of obstacles based on the analysis of ranging data obtained from 2D laser scanner. Considering the unknown clustering number in advance, the validation index function is introduced into the self-learning mechanism to determine the accurate clustering number automatically. At the same time, fuzzy logic is integrated into incremental data association of obstacle features to make the static or dynamic obstacles classification decision to reduce the uncertain influence. Using our office as the operating environment to implement the experiment of feature extraction and obstacles classification, the results verify the effectiveness of this approach.