An Informative Planning Framework for Target Tracking and Active Mapping in Dynamic Environments with ASVs

2025-08-20

AI Summary

This work addresses the challenge of actively tracking multiple drifting floating targets in dynamic aquatic environments—where initial positions are unknown and motion is perturbed by wind and currents—using autonomous surface vehicles (ASVs). We propose an information-driven active tracking framework that integrates a spatiotemporal prediction network to model target motion distributions, replaces conventional entropy-reduction objectives with an adaptive planning objective, and jointly optimizes information gain assessment and online path planning. Our key contribution is the first integration of spatiotemporal prediction into information-driven path planning, enabling robust state estimation and proactive sensing for non-stationary drifting targets. Simulation results demonstrate significantly improved tracking accuracy and stability over baseline methods. Field experiments with real ASVs further validate the framework’s practicality and deployability in complex, realistic dynamic water environments.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Mobile robot platforms are increasingly being used to automate information gathering tasks such as environmental monitoring. Efficient target tracking in dynamic environments is critical for applications such as search and rescue and pollutant cleanups. In this letter, we study active mapping of floating targets that drift due to environmental disturbances such as wind and currents. This is a challenging problem as it involves predicting both spatial and temporal variations in the map due to changing conditions. We propose an informative path planning framework to map an arbitrary number of moving targets with initially unknown positions in dynamic environments. A key component of our approach is a spatiotemporal prediction network that predicts target position distributions over time. We propose an adaptive planning objective for target tracking that leverages these predictions. Simulation experiments show that our proposed planning objective improves target tracking performance compared to existing methods that consider only entropy reduction as the planning objective. Finally, we validate our approach in field tests using an autonomous surface vehicle, showcasing its ability to track targets in real-world monitoring scenarios.

Problem

• Tracking drifting targets in dynamic environments with disturbances
• Mapping unknown moving targets using spatiotemporal prediction networks
• Improving target tracking performance with adaptive planning objectives

Innovation

• Spatiotemporal prediction network for target distributions
• Adaptive planning objective leveraging predictions
• Informative path planning for dynamic environments