GOSPA-Driven Non-Myopic Multi-Sensor Management with Multi-Bernoulli Filtering

TL;DR

This paper introduces a non-myopic multi-sensor management algorithm for multi-target tracking, optimizing sensor actions over time using GOSPA error bounds and Monte Carlo Tree Search.

Contribution

It presents a novel non-myopic sensor management approach based on multi-Bernoulli filtering and GOSPA error minimization, implemented with MCTS for multi-sensor coordination.

Findings

Algorithm effectively minimizes GOSPA error over a future time window.

Sensors coordinate actions to improve multi-target tracking accuracy.

Simulation results demonstrate the benefits of the proposed method.

Abstract

In this paper, we propose a non-myopic sensor management algorithm for multi-target tracking, with multiple sensors operating in the same surveillance area. The algorithm is based on multi-Bernoulli filtering and selects the actions that solve a non-myopic minimisation problem, where the cost function is the mean square generalised optimal sub-pattern assignment (GOSPA) error, over a future time window. For tractability, the sensor management algorithm actually uses an upper bound of the GOSPA error and is implemented via Monte Carlo Tree Search (MCTS). The sensors have the ability to jointly optimise and select their actions with the considerations of all other sensors in the surveillance area. The benefits of the proposed algorithm are analysed via simulations.