SCOUT: Spatiotemporal Coverage for Optimal Unmanned Tasking
Research Poster Engineering 2025 Graduate ExhibitionPresentation by Xinghao Peng
Copresented by Runsang Liu
Exhibition Number 127
Abstract
Spatiotemporal heterogeneity in demand distribution poses a significant challenge for the deployment and the coverage control in unmanned aerial vehicle (UAV) tasking. Many traditional approaches rely on static or uniform assumptions, neglecting how demand varies across different locations and times, ultimately leading to suboptimal tasking of UAVs. To address this shortcoming, this paper introduces Spatiotemporal Coverage for Optimal Unmanned Tasking (SCOUT), a method that begins by greedily identifying areas with high-demand density and subsequently refines UAV locations through an iterative, gradient-based update. The resulting deployment and coverage control minimizes a weighted cost function that integrates both spatial distances and demand density, thereby enhancing both accessibility and equity for the demand areas. Evaluations in a simulated scenario demonstrate that SCOUT consistently outperforms 3D K-means and weighted Voronoi methods. Implementing a continuous deployment task further underscores the strong potential of the method for dynamic decision support in complex and rapidly changing environments.
Importance
This work introduces the Spatiotemporal Coverage for Optimal Unmanned Tasking (SCOUT) algorithm, designed for UAV deployment and coverage control in environments with spatiotemporal heterogeneity in demand distributions, an aspect often overlooked or oversimplified in existing research. SCOUT strategically initializes UAV placement in high-density regions and iteratively refines their positions through gradient-based updates, ensuring enhanced resource accessibility and balanced demand coverage across multiple regions. Its ability to adapt to dynamic demand makes it not only a UAV control algorithm but also a powerful decision-support tool for emergency response and logistics applications, including wildfire management and medical resource allocation. This research advances autonomous UAV deployment, promoting efficiency, equity, and effectiveness in real-world operations.