Obstacle avoidance for autonomous land vehicle navigation in indoor environments by quadratic classifier

A vision-based approach to obstacle avoidance for autonomous land vehicle ( ALV) navigation in indoor environments is proposed. The approach is based o n the use of a pattern recognition scheme, the quadratic classifier, to fin d collision-free paths in unknown indoor corridor environments. Obstacles t reated in this study include the walls of the corridor and the objects that appear in the way of ALV navigation in the corridor. Detected obstacles as well as the two sides of the ALV body are considered as patterns, A system atic method for separating these patterns into two classes is proposed. The two pattern classes are used as the input data to design a quadratic class ifier, Finally, the two-dimensional decision boundary of the classifier, wh ich goes through the middle point between the two front vehicle a heels, is taken as a local collision-free path, This approach is implemented on a re al ALV and successful navigations confirm the feasibility of the approach.