Unlike the stable gas mixtures often analyzed in lab settings, the gas mixtures in practice may change fast due to the turbulent conditions of the environment, making the detection of gas components challenging. There will be a great safety risk if no fast and accurate detection method. In this paper, an attention-based gated recurrent unit (AGRU) is proposed to solve this problem. It was introduced in detail that the method based on the gated recurrent unit (GRU) and attention mechanism. The component and concentration of the gas mixture were analyzed simultaneously by the dual loss function. The individual gas concentration in the gas mixture was obtained by multi-label coding. It was used to evaluate the performance of the model by accuracy, root mean square error(RMSE), number of model parameters, and floating point of operations(FLOPs). The experiment result showed that the AGRU’s accuracy curve is fluctuating around 97%, and varying the length of response time between 3s and 30s hardly affected the recognition accuracy of gas species. AGRU also has the smallest RMSE of each gas among models. At 3s, AGRU’s FLOPs is smaller than Improved LeNet5, which lays the foundation for the deployment in the embedded. Therefore, our proposed algorithm has a higher detection performance, lower complexity, and excellent robustness to be applicable in various practical applications for fast detection.

Air pollution affects people’s life and health, and controlling air pollution requires the collection of polluting gas information. Unmanned aerial vehicles (UAVs) have been used for environmental detection due to their characteristics. However, the limitation of onboard energy sources of UAVs will limit the coverage of the detection area and the number of gas samples collected, which will affect the assessment of pollution levels. In addition, to truly and completely reflect the distribution of atmospheric pollutants, it is necessary to sample the entire three-dimensional space. This paper proposes a three-dimensional space path planning method suitable for UAV atmospheric environment detection, which can generate a full-coverage path with optimal coverage density under energy constraints. Simulation results show that the proposed method can effectively improve the coverage density compared with other path generation methods. Field experiments show that the proposed method is reliable and accurate in the application of UAV atmospheric environment space detection.

Precise odor source localization in turbulent and sparse environments plays a vital role in enabling robotic systems for hazardous chemical monitoring and effective disaster response. To address this, we propose Cooperative Gravitational-Rényi Infotaxis (CGRInfotaxis), a distributed decision-optimization framework that combines multi-agent collaboration with hybrid cognitive strategy to improve search efficiency and robustness. The method integrates a gravitational potential field for rapid source convergence and Rényi divergence-based probabilistic exploration to handle sparse detections, dynamically balanced via a regulation factor. Particle filtering optimizes posterior probability estimation to autonomously refine search areas while preserving computational efficiency, alongside a distributed interactive-optimization mechanism for real-time decision updates through agent cooperation. The algorithm’s performance is evaluated in scenarios with fixed and randomized odor source locations, as well as with varying numbers of agents. Results demonstrate that CGRInfotaxis achieves a near-100% success rate with high consistency across diverse conditions, outperforming existing methods in stability and adaptability. Increasing the number of agents further enhances search efficiency without compromising reliability. These findings suggest that CGRInfotaxis significantly advances multi-agent odor source localization in turbulent, sparse environments, offering practical utility for real-world applications.