Changes in lateral clearance are prone to drastic changes in the driving environment at the entrance and exit of the tunnel, which can cause a driver to become psychologically stressed and deviate from the center of a lane, thus creating a greater security risk. However, most of the existing regulations and studies only focus on the horizontal and vertical alignment of the tunnel entrances and exits, and there are few studies on the influence of lateral clearance on driving behavior. This study hired 15 random subjects to conduct real vehicle tests in eight tunnels on expressways with 3 design speeds by using a CAN-OBD analyzer and steering wheel angle meter. First, in five lateral clearance variation schemes, different speed characteristic indicators and steering wheel angles were selected as the indicators of driving behavior. Second, the interactive influence of the design speed, lateral clearance, operating speed, steering wheel angle, and other indicators were analyzed. Finally, paired t-test analysis and Wilcoxon and Friedman nonparametric tests were used to compare the differences in various indicators among different lateral clearance schemes. The results showed that when the left lateral clearance is 1.5 meters, the operating speed is increased by 3.9, while the standard deviation of speed is small, and the driving performance is higher. When the right lateral clearance is 1.75 and 2.00 meters, the operating speed is not much different. However, the latters speed standard deviation is smaller. By contrast, when the right lateral clearance is up to 2.25m, the operating speed increases by 3.7. However, the speed standard deviation also increases. Different lateral clearances have little effect on the steering wheel angle. The operating speed on the right side is higher and more stable when the design speed is 100km/h. This study provides scientific suggestions for the setting of the lateral clearance of the tunnels.

Mobile inspections conducted by intelligent tunnel robots are instrumental in broadening the inspection reach, economizing on inspection expenditures, and augmenting the operational efficiency of inspections. Despite differences from fixed surveillance, mobile-captured traffic videos have complex backgrounds and device conditions that interfere with accurate traffic event identification, warranting more research. This paper proposes an improved algorithm based on YOLOv9 and DeepSORT for intelligent event detection in edge computing mobile device using the intelligent tunnel robot. The enhancements comprise the integration of the Temporal Shift Module to boost temporal feature recognition and the establishment of logical rules for identifying diverse traffic incidents in mobile video imagery. Experimental results show that our fused algorithm achieves a 93.25% accuracy rate, an inprovement of 1.75% over the baseline. The algorithm is also applicable to inspection vehicles, drones, and autonomous vehicles, effectively enhancing the detection of traffic events and improving traffic safety.