Research Analyzer
← Back ICRA 2026

Entropy-Based Incremental Coverage Path Planning for Multi-UAV Persistent Monitoring

Cai Luo, Lijun Wang, Jiucai Jin, Zhenpeng Du, Wang Miao

PDF

AI summary

Key figure (auto-extracted from paper)
The EICPP framework boosts monitoring timeliness by 19–25% over baselines while reducing flight distance and maintaining high coverage for dynamic oil spills.
Multi-UAV monitoring Coverage path planning Oil spill response Information freshness Entropy-based clustering Incremental coverage

Problem

Traditional coverage path planning fails for dynamic, scattered oil spills due to redundant monitoring, unbalanced workloads, and a lack of focus on information timeliness, hindering rapid emergency response.

Approach

The method isolates newly emerged spill areas via contour comparison, applies entropy-weighted clustering for balanced region division, and guides UAV paths to prioritize high-uncertainty regions under endurance constraints.

Key results

  • 19–25% improvement in Drift Information Freshness across simulated spill scales
  • 19.6–24% DIF gain on real-world oil spill datasets
  • Substantial reduction in total flight distance while maintaining ≥90% coverage
  • Novel entropy-based region division and incremental contour mechanism for dynamic environments

Why it matters

Provides a scalable, timeliness-aware monitoring strategy that directly enhances the speed and effectiveness of marine environmental emergency responses.

Abstract

Oil spills continuously affect marine ecosystems and require rapid monitoring for effective emergency response. This letter tackles the problem of persistent monitoring for continuously changing and scattered oil spill regions through Entropy-Based Incremental Coverage Path Planning (EICPP). By using contour comparison between monitoring cycles, an incremental coverage mechanism is first introduced to focus on newly emerged oil spill re- gions. Then, a balanced region division algorithm is incorporated to handle scattered oil spill areas while ensuring equal workload dis- tribution among UAVs. The entropy-based path planning enhances oil spill monitoring effectiveness by Drift Information Freshness (DIF) through prioritizing high-entropy regions under limited UAV resources. We evaluate the robustness and effectiveness of our method across multiple scenarios. Our method demonstrates clear advantages in DIF, achieving 19–25% improvements over strong baselines across different spill scales and about 19.6–24% on real- world oil spill datasets. It also substantially reduces total flight dis- tance while consistently satisfying the 90% coverage requirement.

Index terms

Motion and Path Planning Environment Monitoring and Management Multi-Robot Systems

Related papers