Distributed Complementary Fusion for Connected Vehicles

TL;DR

This paper introduces a distributed fusion method for connected vehicles that enhances situation awareness by combining sensor data through consensus, using novel label merging and extended label spaces to improve accuracy and reduce double counting.

Contribution

It proposes a new distributed complementary fusion algorithm with label merging and extended label spaces, improving multi-vehicle situation awareness over standard methods.

Findings

Outperforms standard LMB filter in distributed scenarios

Effectively eliminates double counting through label merging

Enhances robustness with extended label space for sensor identities

Abstract

We present a random finite set-based method for achieving comprehensive situation awareness by each vehicle in a distributed vehicle network. Our solution is designed for labeled multi-Bernoulli filters running in each vehicle. It involves complementary fusion of sensor information locally running through consensus iterations. We introduce a novel label merging algorithm to eliminate double counting. We also extend the label space to incorporate sensor identities. This helps to overcome label inconsistencies. We show that the proposed algorithm is able to outperform the standard LMB filter using a distributed complementary approach with limited fields of view.