CSAOT: Cooperative Multi-Agent System for Active Object Tracking

TL;DR

This paper introduces CSAOT, a multi-agent deep reinforcement learning system that improves active object tracking by enabling multiple agents on a single device, enhancing robustness and reducing costs.

Contribution

We propose CSAOT, a novel multi-agent system using MADRL and MoE to improve active object tracking performance on a single device, addressing limitations of existing methods.

Findings

Enhanced robustness against occlusions and rapid motion.

Improved tracking duration and accuracy.

Reduced hardware costs by multi-agent operation on one device.

Abstract

Object Tracking is essential for many computer vision applications, such as autonomous navigation, surveillance, and robotics. Unlike Passive Object Tracking (POT), which relies on static camera viewpoints to detect and track objects across consecutive frames, Active Object Tracking (AOT) requires a controller agent to actively adjust its viewpoint to maintain visual contact with a moving target in complex environments. Existing AOT solutions are predominantly single-agent-based, which struggle in dynamic and complex scenarios due to limited information gathering and processing capabilities, often resulting in suboptimal decision-making. Alleviating these limitations necessitates the development of a multi-agent system where different agents perform distinct roles and collaborate to enhance learning and robustness in dynamic and complex environments. Although some multi-agent approaches exist for AOT, they typically rely on external auxiliary agents, which require additional devices, making them costly. In contrast, we introduce the Collaborative System for Active Object Tracking (CSAOT), a method that leverages multi-agent deep reinforcement learning (MADRL) and a Mixture of Experts (MoE) framework to enable multiple agents to operate on a single device, thereby improving tracking performance and reducing costs. Our approach enhances robustness against occlusions and rapid motion while optimizing camera movements to extend tracking duration. We validated the effectiveness of CSAOT on various interactive maps with dynamic and stationary obstacles.