CIG-RL: Curiosity-Driven Information-Guided Reinforcement Learning for Source Term Estimation in Uncertain Environments
2026-08-31 • Robotics
Robotics
AI summaryⓘ
The authors focus on improving how robots find and identify dangerous gas leaks. They note that current methods either take too long or explore randomly, which makes the process less reliable. To fix this, they created a new system that encourages the robot to explore uncertain situations smartly and learn from less-visited scenarios. Their tests show that this approach works well even with noisy data and real-world challenges. This improvement could help robots search for gas leaks more quickly and accurately.
Source Term EstimationInformation-Theoretic ApproachesDeep Reinforcement LearningBelief StateCuriosity-Driven ExplorationUncertainty-Adaptive RewardActive PerceptionRobustnessNoisy EnvironmentsMobile Sensors
Authors
Junhee Lee, Seunghwan Kim, Hongro Jang, Hyungjin Kim, Hyoungho Park, Changseung Kim, Hyondong Oh
Abstract
Source term estimation (STE), which aims to estimate key properties of the gas source, is essential for identifying hazardous gas releases. Information-theoretic approaches have been adopted for autonomous STE using mobile sensors due to robustness in noisy environments, yet their online action selection incurs substantial computational cost. Deep reinforcement learning (DRL) provides a promising alternative with its fast decision-making capability. In DRL-based STE, the agent selects actions based on belief states of the source term updated from noisy measurement sequences. However, existing methods rely on random exploration or solely on belief uncertainty reduction without an effective exploration strategy in DRL, which can limit policy robustness in noisy environments. To address this, we propose a curiosity-driven information-guided reinforcement learning for robust and efficient STE. The proposed method promotes active exploration of novel belief state transitions that have not been sufficiently explored during training. We further introduce an uncertainty-adaptive active perception reward to guide efficient source search under uncertainty. Simulations under high-noise conditions and real-world experiments demonstrate the robustness and feasibility of the proposed framework, highlighting its potential for practical STE problems.