Smooth vision-based autonomous land vehicle navigation in indoor environments by person following using sequential pattern recognition

A new approach to autonomous land vehicle (ALV) navigation by the person fo llowing is proposed. This approach is based on sequential pattern recogniti on and computer vision techniques, and maintenance of smoothness for indoor navigation is the main goal. The ALV is guided automatically to follow a p erson who walks in front of the vehicle. The vehicle can be used as an auto nomous handcart, go-cart, buffet car, golf cart, weeder, etc. in various ap plications. Sequential pattern recognition is used to design a classifier f or making decisions about whether the person in front of the vehicle is wal king straight or is too right or too left of the vehicle. Multiple images i n a sequence are used as input to the system. Computer vision techniques ar e used to detect and locate the person in front of the vehicle. By sequenti al pattern recognition, the relation between the location of the person and that of the vehicle is categorized into three classes. Corresponding adjus tments of the direction of the vehicle are computed to achieve smooth navig ation. The approach is implemented on a real ALV, and successful and smooth navigation sessions confirm the feasibility of the approach. (C) 1999 John Wiley & Sons, Inc.