GM-PHD Filter for Searching and Tracking an Unknown Number of Targets With a Mobile Sensor With Limited FOV

We study the problem of searching for and tracking a collection of moving targets using a robot with a limited field-of-view (FOV) sensor. The actual number of targets present in the environment is not known
a priori
. We propose a search and tracking framework based on the concept of Bayesian random finite sets (RFSs). Specifically, we generalize the Gaussian mixture probability hypothesis density (GM-PHD) filter which was previously applied for tracking problems to allow for simultaneous search and tracking with a limited FOV sensor. The proposed framework can extract individual target tracks as well as estimate the number and the spatial density of targets. We also show how to use the Gaussian process (GP) regression to extract and predict unknown target trajectories in this framework. We demonstrate the efficacy of our techniques through representative simulations and a real data collected from an aerial robot.
Note to Practitioners
—This article is motivated by search-and-rescue operations where a robot with limited field-of-view (FOV) is used to search and track lost targets. This article presents an estimation and planning framework to estimate the position of targets and track them over time. The key feature of the proposed algorithm is that it can deal with an unknown and varying number of targets. The framework can also deal with an unknown motion model for targets which itself can be complex. The algorithm is shown to be robust to a poor initialization and can handle an initial belief which overestimates or underestimates the actual number of targets. The proposed scheme includes various user-defined parameters. It is recommended to tune these parameters
a priori
using simulations for a better performance. Incorporating a multirobot approach into the proposed algorithm and finding a better planning strategy that minimizes the time are potential future works.