Track-to-Track Association for Collective Perception based on Stochastic Optimization

TL;DR

This paper introduces a stochastic optimization-based track-to-track association algorithm for collective perception in autonomous driving, improving accuracy and computational efficiency in multi-vehicle sensor data fusion.

Contribution

It presents a novel stochastic optimization method that models multiple association hypotheses using a multidimensional likelihood, addressing limitations of previous heuristics.

Findings

Effective in Monte Carlo simulations

Performs well in realistic collective perception scenarios

Handles ambiguous association settings efficiently

Abstract

Collective perception is a key aspect for autonomous driving in smart cities as it aims to combine the local environment models of multiple intelligent vehicles in order to overcome sensor limitations. A crucial part of multi-sensor fusion is track-to-track association. Previous works often suffer from high computational complexity or are based on heuristics. We propose an association algorithms based on stochastic optimization, which leverages a multidimensional likelihood incorporating the number of tracks and their spatial distribution and furthermore computes several association hypotheses. We demonstrate the effectiveness of our approach in Monte Carlo simulations and a realistic collective perception scenario computing high-likelihood associations in ambiguous settings.