Multisensor data fusion for autonomous vehicle navigation in risky environments

This paper describes a multisensor data-fusion system for driving an autonomous earthwork vehicle operating in a sanitary landfill. The system acquires data from a set of ultrasonic sensors, a laser range finder, and several charge-coupled device cameras, and produces, as output, alarms that indicate potentially dangerous situations, e.g., the presence of fixed or mobile obstacles in the vehicle working area. The proposed system adds to the vehicle important functionalities such as avoiding terrain holes or down slopes or discriminating between heaps of waste to be compacted and other man-made obstacles. Data fusion allows the system´s reliability to be increased and compensation to be made for the inaccuracies and limited operating ranges of individual sensors. Experimental results shows how the system functions both under normal operating conditions and in the presence of dangerous situations. Moreover, the performance of the system in bad environmental situations (e.g., rain, low lighting) have been evaluated.