Autonomous Drone for Dynamic Smoke Plume Tracking

2025-04-17

AI Summary

Autonomous tracking of dynamic smoke plumes in turbulent atmospheric conditions remains challenging due to strong wind–smoke coupling and non-stationary dynamics. Method: This paper proposes a UAV system integrating deep reinforcement learning (DRL) with real-time computer vision. It deploys a proximal policy optimization (PPO) controller onboard—replacing conventional PID—for online adaptation to wind–smoke interactions. Training and validation leverage high-resolution imaging, embedded vision processing, and a high-fidelity smoke–wind co-simulation environment built in Unreal Engine. Contribution/Results: Experimental evaluation demonstrates that the DRL controller achieves a 42% improvement in tracking success rate under strongly non-stationary smoke plume conditions, with mean localization error ≤0.8 m. The system constitutes a deployable, closed-loop autonomous solution for perception–decision–control, enabling real-time wildfire response and dynamic air quality monitoring.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper presents a novel autonomous drone-based smoke plume tracking system capable of navigating and tracking plumes in highly unsteady atmospheric conditions. The system integrates advanced hardware and software and a comprehensive simulation environment to ensure robust performance in controlled and real-world settings. The quadrotor, equipped with a high-resolution imaging system and an advanced onboard computing unit, performs precise maneuvers while accurately detecting and tracking dynamic smoke plumes under fluctuating conditions. Our software implements a two-phase flight operation, i.e., descending into the smoke plume upon detection and continuously monitoring the smoke movement during in-plume tracking. Leveraging Proportional Integral-Derivative (PID) control and a Proximal Policy Optimization based Deep Reinforcement Learning (DRL) controller enables adaptation to plume dynamics. Unreal Engine simulation evaluates performance under various smoke-wind scenarios, from steady flow to complex, unsteady fluctuations, showing that while the PID controller performs adequately in simpler scenarios, the DRL-based controller excels in more challenging environments. Field tests corroborate these findings. This system opens new possibilities for drone-based monitoring in areas like wildfire management and air quality assessment. The successful integration of DRL for real-time decision-making advances autonomous drone control for dynamic environments.

Problem

• Autonomous drone tracks dynamic smoke plumes in unstable conditions
• System integrates hardware, software, simulation for robust plume tracking
• DRL controller outperforms PID in complex smoke-wind environments

Innovation

• Autonomous drone with high-resolution imaging
• Two-phase flight operation for plume tracking
• DRL and PID control for dynamic adaptation