Combining Conflicting and Confirmatory Information for Map Matching Using Paraconsistent Neural Networks

This paper presents a new method for matching metric maps generated by mobile robots that act cooperatively. This process of information matching makes it possible to perform global map generation from local maps (possibly partial and nonconsistent) provided by individual robots. The method is based on a paraconsistent artificial neural network model that considers as input preprocessed information from measurement data on landmark distances, possibly generated by different sensors in different robots and considering different metrics. The neural network then analyzes these inputs to determine what are the matching belief and contradiction relations among the points of the distinct maps. The algorithm implemented for the neural architecture achieved good results in the reported experiments, that consider combination of information from different linear distance metrics (Euclidean and Manhattan) and angle measurements. As a side effect, it made it possible to determine certainty and contradiction degrees for each map point match analysis, a feature that can be useful for decision making. Equally important is the fact that the considered architecture allows for the combination of information from partial maps acquired in execution time during navigation.