A Resource-Efficient Decentralized Sequential Planner for Spatiotemporal Wildfire Mitigation

TL;DR

This work tackles early wildfire mitigation under partial observability and dynamic fires using a multi-UAV system. It introduces CREDS, a three-phase decentralized framework combining OMS-based search, REDS for local trajectory generation with a novel non-stationary Deadline-Prioritized Mitigation Cost (DPMC), and a conflict-aware consensus mechanism to produce feasible global paths. The key contributions are the DPMC cost formulation, a decentralized sequential spatiotemporal task assignment, and demonstrated high success rates and convergence in Monte Carlo experiments—especially with heterogeneous UAV teams and fire-to-UAV ratios up to five. The approach promises practical impact by enabling rapid, resource-efficient, and scalable wildfire intervention with real-time computation in resource-constrained settings.

Abstract

This paper proposes a Conflict-aware Resource-Efficient Decentralized Sequential planner (CREDS) for early wildfire mitigation using multiple heterogeneous Unmanned Aerial Vehicles (UAVs). Multi-UAV wildfire management scenarios are non-stationary, with spatially clustered dynamically spreading fires, potential pop-up fires, and partial observability due to limited UAV numbers and sensing range. The objective of CREDS is to detect and sequentially mitigate all growing fires as Single-UAV Tasks (SUT), minimizing biodiversity loss through rapid UAV intervention and promoting efficient resource utilization by avoiding complex multi-UAV coordination. CREDS employs a three-phased approach, beginning with fire detection using a search algorithm, followed by local trajectory generation using the auction-based Resource-Efficient Decentralized Sequential planner (REDS), incorporating the novel non-stationary cost function, the Deadline-Prioritized Mitigation Cost (DPMC). Finally, a conflict-aware consensus algorithm resolves conflicts to determine a global trajectory for spatiotemporal mitigation. The performance evaluation of the CREDS for partial and full observability conditions with both heterogeneous and homogeneous UAV teams for different fires-to-UAV ratios demonstrates a $100\%$ success rate for ratios up to $4$ and a high success rate for the critical ratio of $5$, outperforming baselines. Heterogeneous UAV teams outperform homogeneous teams in handling heterogeneous deadlines of SUT mitigation. CREDS exhibits scalability and $100\%$ convergence, demonstrating robustness against potential deadlock assignments, enhancing its success rate compared to the baseline approaches.

Figures (7)

• Figure 1: A wildfire management scenario where multiple UAVs perform search and mitigation of wildfire.
• Figure 2: Schematic diagram of the CREDS for a UAV.
• Figure 3: Box plot of different performance indices for homogeneous team
• Figure 4: Box plot of different performance indices for heterogeneous team
• Figure 5: Percentage of failure vs fire to UAV ratio (a) Variation of quench rate for constant velocity. (b)Variation of velocity for constant quench rate.