Information-Guided Safe Reinforcement Learning for Autonomous Gas Source Localization using sUAS
On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control
Abstract (arXiv)
The autonomous localization of fugitive gas emissions using small Unmanned Aircraft Systems (sUAS) constitutes a fundamentally ill-posed inverse problem. In turbulent atmospheric boundary layers, highly intermittent scalar concentration fields violate the assumptions of classical gradient-based navigation, causing data-driven estimators to suffer from severe noise and spurious local minima. To address these challenges, we introduce an Information-Guided Safe Reinforcement Learning framework evaluated within a custom, GPU-accelerated 3D simulation environment coupling an Eulerian wind solver with a Lagrangian puff dispersion model. We identify a critical vulnerability in deterministic information-seeking planners - a Gramian bias where agents act greedily upon flawed early estimates, starving the estimator of spatial diversity. To systematically break this degeneracy, our architecture integrates a classical empirical observability Gramian (EMGR) planner with a learned Soft Actor-Critic (SAC) exploratory policy. A deterministic meta-supervisor actively monitors estimator reliability via Kullback-Leibler (KL) divergence, dynamically blending deterministic exploitation with learned exploration to steer the sUAS into high-information zones. Trained via a progressive curriculum and safeguarded by a strictly enforced Robust Control Barrier Function (RCBF), our RL framework achieves nearly 80% localization success on complex, mobile sources - drastically outperforming classical baselines (~30%) - while ensuring zero safety violations.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 52 references that are in the map. First posted on arXiv 4 Sep 2026.
Builds on
15 of 52 references.
Closest ancestors · 1
Same direction, newest first
Other references · 14
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
- 2019Control Barrier Functions: Theory and Applicationscited by 372
- 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
- 2018Safe Exploration in Continuous Action Spacescited by 247
- 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 161
- 2017Time Limits in Reinforcement Learningcited by 79
- 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 59
- 2016Robustness of Control Barrier Functions for Safety Critical Controlcited by 30
- 2023Vehicular Applications of Koopman Operator Theory -- A Surveycited by 6
- 2019Robust Barrier Functions for a Fully Autonomous, Remotely Accessible Swarm-Robotics Testbedcited by 4
2 more
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Guiding drones by information gain
- 2026Multi-Agent Reinforcement Learning for UAV-Based Chemical Plume Source Localization ↗
- 2024Using reinforcement learning to improve drone-based inference of greenhouse gas fluxes
- 2026CIG-RL: Curiosity-Driven Information-Guided Reinforcement Learning for Source Term Estimation in Uncertain Environments
- 2025Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach
- 2024Navigating the Smog: A Cooperative Multi-Agent RL for Accurate Air Pollution Mapping through Data Assimilation
- 2025Khalasi: Energy-Efficient Navigation for Surface Vehicles in Vortical Flow Fields
- 2026Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling