The existing SLAM (Simultaneous Localization and Mapping) systems often suffer from increased positioning errors, inaccurate map construction, and challenges in real-time multimodal sensor data fusion in dynamic environments. This paper proposes enhancements to the SLAM system using nonlinear optimal filtering and deep learning to improve adaptability in such conditions. The study employs an Unscented Kalman Filter (UKF) for nonlinear state estimation, while deep feature extraction of environmental images is conducted via Convolutional Neural Networks (CNN). Semantic edge detection integrates Fully Convolutional Networks (FCN) and Canny edge detection techniques. The Extended Kalman Filter (EKF) is utilized for multimodal data fusion to optimize positioning accuracy across vision, lidar, and inertial measurement unit (IMU) sensors. Real-time motion estimation is achieved through an event-based camera combined with an optical flow algorithm, enhancing speed and accuracy in dynamic scenes. Experimental results demonstrate that the proposed SLAM system achieves an absolute trajectory error (ATE) as low as 0.067 m across datasets, with over 90% overlap in constructed maps. The system's average frame processing time is under 90 ms, and it responds within an average of 0.035 s during event-based camera experiments. These results outperform other mainstream SLAM systems, confirming that nonlinear optimal filtering and deep learning significantly enhance positioning accuracy, mapping quality, and real-time performance in complex environments. This study primarily employs simulation-based experiments to validate the proposed SLAM system's performance in dynamic hospital environments. While the results demonstrate high accuracy (e.g., an absolute trajectory error of 0.07 m), future work will include field experiments to further verify the system's robustness in real-world applications.

Facing Gaussian noise from severe rain and haze, we employ multi-scale YOLO v10 for obstacle detection amidst high noise and DDPG (Deep Deterministic Policy Gradient) for enhanced path planning. YOLO v10 is used to annotate obstacles, and different input scales are set to deal with Gaussian noise. Recognition accuracy is optimized using cross entropy loss function. The DDPG algorithm is applied to update the path planning strategy, define the state space of robot position, velocity, and Laser Radar (LiDAR) readings, and output possible movement directions and velocities as action outputs. A reward function is designed to motivate the agent to learn. The weighted average method is used to fuse the visual information of YOLO v10 with LiDAR data. The robot’s status and surrounding environment are tracked through real-time feedback mechanism. The path planning is dynamically adjusted, and an intelligent navigation system is built. The research results show that the average recognition rate of the system for obstacles is 0.95, and the success rate of avoidance under extreme weather conditions of heavy rainfall is 88.0%. The system can effectively cope with various Gaussian noise environments and achieve precise path planning decisions.

Under complex lighting conditions, hospital logistics robots are facing serious challenges in positioning and navigation.The traditional ORB (Oriented FAST and rotated BRIEF) algorithm often has problems such as unstable feature point extraction, poor positioning accuracy, and long navigation path planning time in environments with large lighting changes, which greatly affects the robot's navigation efficiency and accuracy. In this paper, an improved ORB-SLAM3 algorithm is used to improve the navigation performance of the robot in a hospital environment with complex lighting. The improved ORB-SLAM3 algorithm extracts feature points of different scales by constructing an image pyramid to ensure that effective visual information can be stably obtained under different lighting conditions; the strategy of combining adaptive threshold and dual threshold methods is used to optimize the accuracy of feature point extraction, and the feature points are efficiently managed through a four-tree model to ensure the uniform distribution of feature points. These measures significantly improve the quality and matching accuracy of feature point extraction; the algorithm also combines visual and inertial information closely by combining inertial measurement unit data, further enhancing the positioning accuracy and system stability.The experimental results show that in the environment of rapid light changes, the average positioning error, navigation map construction integrity and navigation planning time of the improved ORB-SLAM3 algorithm are 0.26 m, 80% and 7.26 ms, respectively.This achievement not only effectively improves the navigation efficiency of the hospital logistics robot, but also enhances its stability and reliability in an environment with severe lighting changes. It is of great practical significance to improve the level of intelligence of the hospital's internal logistics system.

In multi-hop routing of 5G vehicle network, node movement and link failure often lead to frequent changes in network topology, which in turn cause delay and packet loss problems. A multimodal transmission strategy based on environment perception is proposed in this study to achieve adaptive switching of routing protocols. Vehicle-mounted sensors are used to collect location, speed, network load and traffic density information in real-time. Then, graph sample and aggregation (GraphSAGE) is used to process the network topology and extract node and edge features of the data. The features are input into gated recurrent unit (GRU) for time series modeling to predict the link node movement pattern. Then, ad hoc on-demand distance vector routing (AODV), greedy perimeter stateless routing (GPSR) and dynamic source routing (DSR) are integrated, and the best protocol is automatically selected through the classification and regression trees (CART) algorithm. Finally, a route request packet (RREQ) is generated and broadcast according to the selected routing protocol. After being processed by the intermediate node, the route reply packet (RREP) is returned to the source node to achieve real-time update of the routing table and maintain the link status. The results show that when the number of nodes reaches 1200, the system delay is 146.99 ms; when the average vehicle speed is 30 km/h and the network load is 50 Mbps, the packet loss rate of switching to the DSR protocol is only 0.833%. The method can significantly reduce the real-time delay in multi-hop routing of 5G vehicle network. Clinical trial number: Not applicable.

This study introduces a novel evaluation framework that combines a space-time graph diffusion model (STG-DM) and federated contrastive learning (FedCL) to address collaborative optimization challenges in cross-school education evaluation. This integration enables the creation of a thermodynamically driven space-time diffusion equation and an adaptive graph convolution mechanism, facilitating accurate modeling of the space-time evolution of multimodal educational behaviors. It effectively overcomes the shortcomings of traditional methods, which often suffer from local overfitting and dynamic correlation modeling failures due to data silos. The graph diffusion operator, constrained by non-equilibrium thermodynamic principles, has proven to enhance the prediction accuracy of cross-regional education strategies, reducing the average absolute error (MAE) by 18.7% compared to conventional space-time models. In the context of heterogeneous data distribution across 30 universities, the system successfully reduces the privacy leakage risk (ε) to below 1.5, while simultaneously achieving balanced optimization of cross-school model generalization performance. The lightweight evaluation system developed includes a multimodal real-time analysis engine that enables space-time heatmap rendering and collaborative decision-making for 100,000-level nodes, with a system response delay of less than two seconds. This provides education managers with efficient and reliable data intelligence tools.

Professional translators may resist highly directive AI assistance when it threatens perceived autonomy, authorship, and control. This study introduces the Recursive Control and Alignment Protocol (ReCAP), a reactance-aware framework for interactive machine translation. ReCAP combines a reactance-potential model with a recursive loop of Intent Inference, Reactance-Guided Generation, and Critical Feedback Integration. Its Adversarial Reactance Minimization objective balances translation quality against estimated autonomy costs, and the task-specific Critical Automation Capability Index (CACI) provides an exploratory behavioral summary of critical engagement. In an evaluation with 156 professional translators across four English-based bidirectional language-pair settings, ReCAP achieved a mean COMET × 100 score of 36.8, 2.8 points above QE-guided MT (34.0), the strongest baseline, across five seed-matched runs per method–language-pair configuration. Mixed-effects estimates showed lower reported reactance for ReCAP than QE-guided MT (β = −0.55, 95% CI [−0.71, −0.39]) and higher exploratory CACI scores than CHORUS (β = 0.64, 95% CI [0.44, 0.84]). Post hoc CACI checks remained task-specific and exploratory. These findings support a run-level translation-quality advantage and task-specific human-outcome associations under the evaluated conditions.