Diffusion Models for Multi-target Adversarial Tracking

TL;DR

This paper introduces CADENCE, a diffusion-based multi-agent tracking method that improves adversary location predictions in complex pursuit environments, outperforming baseline models in accuracy.

Contribution

The paper presents a novel cross-attention diffusion model with constraint-based sampling for enhanced multi-target tracking in adversarial scenarios.

Findings

Single-target model outperforms baselines in Average Displacement Error

Monte-Carlo sampling estimates trajectory probabilities effectively

Proposed method generates accurate multimodal track hypotheses

Abstract

Target tracking plays a crucial role in real-world scenarios, particularly in drug-trafficking interdiction, where the knowledge of an adversarial target's location is often limited. Improving autonomous tracking systems will enable unmanned aerial, surface, and underwater vehicles to better assist in interdicting smugglers that use manned surface, semi-submersible, and aerial vessels. As unmanned drones proliferate, accurate autonomous target estimation is even more crucial for security and safety. This paper presents Constrained Agent-based Diffusion for Enhanced Multi-Agent Tracking (CADENCE), an approach aimed at generating comprehensive predictions of adversary locations by leveraging past sparse state information. To assess the effectiveness of this approach, we evaluate predictions on single-target and multi-target pursuit environments, employing Monte-Carlo sampling of the diffusion model to estimate the probability associated with each generated trajectory. We propose a novel cross-attention based diffusion model that utilizes constraint-based sampling to generate multimodal track hypotheses. Our single-target model surpasses the performance of all baseline methods on Average Displacement Error (ADE) for predictions across all time horizons.