Order Statistic Estimation With Application to Tracking in Autonomous Driving

In this work, we study the order statistic estimation and provide a simple solution to lidar bounding box (BB) centroid estimation for an autonomous vehicle. The estimated BB centroid and its uncertainty will be used in object tracking as measurement and measurement noise variance; the latter is commonly not available from the sensor manufacturer, and is needed for data association and target state estimation. The detected and clustered sensor observations for a single target, on one axis, are assumed to have 1) a triangular density or 2) a uniform (rectangular) density. These densities constitute the likelihood function (LF) of the corresponding support (the interval where they are nonzero) boundaries. Estimators are proposed for the LF support boundary parameter estimation and the centroid coordinates are given by the centers of the boundaries. Experiments using real data are carried out to show the performance of the proposed methods for autonomous driving applications. A comparison with the max-min average approach shows the superiority of the proposed algorithm.

Automated summary

In this work, the order statistic estimation and lidar bounding box (BB) centroid estimation for autonomous vehicles are studied. The estimated BB centroid is used as measurement in object tracking, and the estimation of measurement noise variance is proposed due to unavailability from the sensor manufacturer. The performance of the proposed methods is demonstrated through experiments using real data for autonomous driving applications, showing superiority over the max-min average approach.