MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy

TL;DR

MATT-Diff is a diffusion-based control policy enabling a mobile agent to perform active multi-target tracking with multimodal behaviors, balancing exploration and exploitation without prior target knowledge.

Contribution

The paper introduces a novel diffusion model-based policy for multimodal active target tracking that integrates multiple expert behaviors and handles variable target scenarios.

Findings

MATT-Diff outperforms other learning-based methods in tracking accuracy.

The policy demonstrates effective multimodal behavior sourcing from multiple expert planners.

Evaluation in novel environments confirms superior tracking performance.

Abstract

This paper proposes MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy, a control policy for active multi-target tracking using a mobile agent. The policy enables multiple behavior modes for the agent, including exploration, tracking, and target reacquisition, without prior knowledge of the target numbers, states, or dynamics. Effective target tracking demands balancing exploration for undetected or lost targets with exploitation, i.e., uncertainty reduction, of detected but uncertain ones. We generate a demonstration dataset from three expert planners including frontier-based exploration, an uncertainty-based hybrid planner switching between frontier-based exploration and RRT* tracking, and a time-based hybrid planner switching between exploration and target reacquisition based on target detection time. Our control policy utilizes a vision transformer for egocentric map tokenization and an attention mechanism to integrate variable target estimates represented by Gaussian densities. Trained as a diffusion model, the policy learns to generate multimodal action sequences through a denoising process. Evaluations demonstrate MATT-Diff's superior tracking performance against other learning-based baselines in novel environments, as well as its multimodal behavior sourced from the multiple expert planners. Our implementation is available at https://github.com/CINAPSLab/MATT-Diff.