In this paper, an improved APF-GFARRT* (artificial potential field-guided fuzzy adaptive rapidly exploring random trees) algorithm based on APF (artificial potential field) guided sampling and fuzzy adaptive expansion is proposed to solve the problems of weak orientation and low search success rate when randomly expanding nodes using the RRT (rapidly exploring random trees) algorithm for disinfecting robots in the dense environment of disinfection operation. Considering the inherent randomness of tree growth in the RRT* algorithm, a combination of APF with RRT* is introduced to enhance the purposefulness of the sampling process. In addition, in the context of RRT* facing dense and restricted environments such as narrow passages, adaptive step-size adjustment is implemented using fuzzy control. It accelerates the algorithm’s convergence and improves search efficiency in a specific area. The proposed algorithm is validated and analyzed in a specialized environment designed in MATLAB, and comparisons are made with existing path planning algorithms, including RRT, RRT*, and APF-RRT*. Experimental results show the excellent exploration speed of the improved algorithm, reducing the average initial path search time by about 46.52% compared to the other three algorithms. In addition, the improved algorithm exhibits faster convergence, significantly reducing the average iteration count and the average final path cost by about 10.01%. The algorithm’s enhanced adaptability in unique environments is particularly noteworthy, increasing the chances of successfully finding paths and generating more rational and smoother paths than other algorithms. Experimental results validate the proposed algorithm as a practical and feasible solution for similar problems.

In natural language understanding, intent recognition plays a central role in human–computer interaction. However, in elderly-care scenarios, acoustic signals are often affected by atypical speech patterns, slower speaking rates, and environmental noise, making audio information less reliable and reducing the effectiveness of conventional text–audio fusion methods. To address this problem, we propose a prompt-guided and quality-aware text–audio intent recognition framework. Specifically, a χ²-based intent prototype soft prompt is introduced to enhance the semantic representation of text. Then, a residual-free text-guided cross-attention module is designed to refine degraded acoustic features using textual semantics as reliable guidance. In addition, a dynamic fusion gate is developed to adjust the contributions of text and audio based on modality reliability and intent-related information. Experiments on the MIntRec dataset with simulated acoustic degradation show that the proposed model achieves 60.90% accuracy, 60.80% weighted F1, and 57.90% macro-F1, outperforming several competitive baselines. These results indicate that the proposed framework can improve the robustness of intent recognition under challenging acoustic conditions in elderly-oriented interaction scenarios.

Overcoming complex background noise and poor small-target detection in industrial settings, this paper introduces YOLOv8-BBP2, an enhanced YOLOv8 model. To better extract dynamic features, the backbone integrates a BiFormer dual-level routing attention mechanism. Moreover, a learnable Bi-directional Feature Pyramid Network (BiFPN) replaces the standard module, optimizing multi-scale feature integration. A P2 detection head is also added to accurately identify tiny objects, such as early flames and thin smoke. Tested on a custom factory fire dataset, YOLOv8-BBP2 yields 95.231% precision, 94.612% recall, and 89.677% mean average precision (mAP@0.5). These metrics represent respective gains of 3.31%, 4.934%, and 7.451% over the baseline YOLOv8s. Ultimately, with an inference speed of 20 ms per frame, the proposed network ensures highly robust, real-time performance.