Classification of target primitives with sonar using two non-parametric data fusion methods

In this study, physical models are used to model reflections from target primitives commordy encountered in a mobile robot’s environment. These tcirgets are differentiated by employing a multi-transducer pulse/echo system which relies on both cimplitude and time-of-flight (TOP) data in the feature fusion process, cillowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused for multiple logical soncirs at different geographical sites. Feature data from multiple logical sensors are fused with Dernpster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Using three sensing nodes, improvement in differentiation is 20% without false decision, however, at the cost of additional computation. Simulation results are verified by experiments with real sonar systems. As an alternative method, neural networks are used for incorporating lecirning of identifying pcirameter relations of target primitives. Amplitude and time-of-flight measurements of .‘]1 sensor pairs cire fused with these neural networks. Improvement in differentiation is 72% with 28% false decision at the cost of elapsed time until the network learns these patterns. These two approaches help to overcome the vulnerability of echo amplitude to noise and enable the modeling of non-parametric uncertainty.