An Informative Planning Framework for Target Tracking and Active Mapping in Dynamic Environments with ASVs
Sanjeev Kumar Ramkumar Sudha, Marija Popovic, Erlend M. Coates
AI summary
Problem
Tracking freely drifting targets in dynamic marine environments is challenging due to unpredictable spatial and temporal variations, while existing path planning methods often ignore target drift uncertainty over longer time horizons.
Approach
The framework combines dynamic occupancy grid mapping with a novel path planning strategy that uses a spatiotemporal prediction network to forecast target drift and uncertainty based on real-time wind data and map states.
Key results
- Spatiotemporal network accurately forecasts target position distributions over 30-second horizons
- New IPP objective leveraging drift predictions outperforms entropy-only planning in tracking accuracy
- Dynamic occupancy mapping with wind-driven drift compensation improves map fidelity
- Successful real-world field validation on an autonomous surface vehicle tracking drifting buoys
Why it matters
Enables efficient, real-time autonomous monitoring for critical maritime applications like search and rescue and environmental cleanup.
Abstract
Mobile robot platforms are increasingly being used to automate information gathering tasks such as environmental moni- toring. 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 introduce an integrated framework combining dynamic occupancy grid mapping and an informative planning approach to actively map and track freely drifting targets with an autonomous surface vehicle. A key component of our adaptive planning approach is a spatiotemporal prediction network that predicts target position distributions over time. We further propose a planning objective for target tracking that leverages these predictions. Simulation exper- iments show that this 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, showcasing its ability to track targets in real-world monitoring scenarios.