Reliability measure assignment to sonar for robust target differentiation

Abstract

This article addresses the use of evidential reasoning and majority voting in multi-sensor decision making for target di erentiation using sonar sensors. Classiÿcation of target primitives which constitute the basic building blocks of typical surfaces in uncluttered robot environments has been considered. Multiple sonar sensors placed at geographically di erent sensing sites make decisions about the target type based on their measurement patterns. Their decisions are combined to reach a group decision through Dempster-Shafer evidential reasoning and majority voting. The sensing nodes view the targets at di erent ranges and angles so that they have di erent degrees of reliability. Proper accounting for these di erent reliabilities has the potential to improve decision making compared to simple uniform treatment of the sensors. Consistency problems arising in majority voting are addressed with a view to achieving high classiÿcation performance. This is done by introducing preference ordering among the possible target types and assigning reliability measures (which essentially serve as weights) to each decision-making node based on the target range and azimuth estimates it makes and the belief values it assigns to possible target types. The results bring substantial improvement over evidential reasoning and simple majority voting by reducing the target misclassiÿcation rate. ?

A 3D simulator for autonomous robotic fish

“…To simplify computation, the sonar sensor is modeled as a wedge. Its cross-section is designed as shown in Fig.6(b) and is based on a real sonar sensor cross-section as shown in (Fig.6(a) [17] ). The sonar's transducer and receiver are viewed as the same point (T/R).…”

Fuzzy clustering and enumeration of target type based on sonar returns

“…) At each step of the scan (for each value of ), four sonar echo signals are acquired. The echo signals are in the form of slightly skewed wave packets [30] (Fig. 5).…”

Comparative analysis of different approaches to target differentiation and localization with sonar

“…At each step of the scan (for each value of ), four sonar echo signals are acquired. The echo signals are in the form of slightly skewed wave packets [13]. Aaa; A bb ; A ab , and A ba denote the peak values of the echo signals, and taa; t bb ; t ab , and t ba denote their TOF delays (extracted by simple thresholding).…”

“…A brief survey of D-S evidential reasoning in classiÿcation problems is provided in Ref. [13]. In this study, the di erent viewpoints of the sensing unit are assigned beliefs using D-S evidential reasoning and they are combined through Dempster's fusion rule.…”

“…Results associated with some of the methods listed above were published in Refs. [12][13][14][15], sometimes in the context of a speciÿc application. This paper presents these results uniformly together with previously unpublished methods and results.…”