The study focuses on takeover and conflict risk of Level 3 autonomous vehicles(L3-AVs)in highway maintenance areas.Analysis of autonomous vehicle collisions shows that many of them are related to takeover process and ...The study focuses on takeover and conflict risk of Level 3 autonomous vehicles(L3-AVs)in highway maintenance areas.Analysis of autonomous vehicle collisions shows that many of them are related to takeover process and collisions occur more frequently on highways.However,existing studies lack analysis of L3-AV performance in highway maintenance areas.In this study,we investigated the traffic flow and maintenance situation of S68 highway in Zhenjiang City and simulated it in SUMO,then compared the L3-AV takeover details based on length and number of lanes of maintenance area,fitted the prediction of the conflict data using the CatBoost model,and interpreted the prediction results in terms of global and local features by the SHAP theory.The results show that the length of the maintenance area and the number of lanes influence both the initial takeover and the takeover frequency.The relative speed between the L3-AV and the surrounding vehicles plays an important role in the conflict likelihood during traveling in the maintenance area.The findings of this paper are important for optimizing highway maintenance area configurations and developing L3-AV conflict avoidance techniques in specific scenarios.展开更多
Accurate prediction of performance decay law is an important basis for long-term planning of maintenance strategy.The statistical regression prediction model is the most widely employed method to calculate pavement pe...Accurate prediction of performance decay law is an important basis for long-term planning of maintenance strategy.The statistical regression prediction model is the most widely employed method to calculate pavement performance due to its advantages such as the small amount of calculation and good accuracy,but the traditional prediction model seems not applicable to the high maintenance level areas with excellent pavement conditions.In this paper,the service life and the cumulative number of the axle load were determined as the independent variables of prediction models of pavement performance.The pavement condition index(PCI)and rutting depth index(RDI)were selected as maintenance decision control indexes to establish the unified prediction model of PCI and RDI respectively by applying the cosine deterioration equation.Results reveal that the deterioration law of PCI presents an anti-S type or concave type and the deterioration law of RDI shows an obvious concave type.The prediction model proposed in this study added the pavement maintenance standard factor d,which brings the model parameterα(reflecting the road life)and the deterioration equations are more applicable than the traditional standard equations.It is found that the fitting effects of PCI and RDI prediction models with different traffic grades are relatively similar to the actual service state of the pavements.展开更多
基金supported by the National Key R&D Program of China(2023YFB2504400)National Natural Science Foundation of China(52372413,U20A20333,U20A20331,52225212,51905223)。
文摘The study focuses on takeover and conflict risk of Level 3 autonomous vehicles(L3-AVs)in highway maintenance areas.Analysis of autonomous vehicle collisions shows that many of them are related to takeover process and collisions occur more frequently on highways.However,existing studies lack analysis of L3-AV performance in highway maintenance areas.In this study,we investigated the traffic flow and maintenance situation of S68 highway in Zhenjiang City and simulated it in SUMO,then compared the L3-AV takeover details based on length and number of lanes of maintenance area,fitted the prediction of the conflict data using the CatBoost model,and interpreted the prediction results in terms of global and local features by the SHAP theory.The results show that the length of the maintenance area and the number of lanes influence both the initial takeover and the takeover frequency.The relative speed between the L3-AV and the surrounding vehicles plays an important role in the conflict likelihood during traveling in the maintenance area.The findings of this paper are important for optimizing highway maintenance area configurations and developing L3-AV conflict avoidance techniques in specific scenarios.
基金the National Key Research and Development Program of China with Grant No.2018YFB1600100the National Natural Science Foundation of China with Grant No.51978219 and No.51878228.
文摘Accurate prediction of performance decay law is an important basis for long-term planning of maintenance strategy.The statistical regression prediction model is the most widely employed method to calculate pavement performance due to its advantages such as the small amount of calculation and good accuracy,but the traditional prediction model seems not applicable to the high maintenance level areas with excellent pavement conditions.In this paper,the service life and the cumulative number of the axle load were determined as the independent variables of prediction models of pavement performance.The pavement condition index(PCI)and rutting depth index(RDI)were selected as maintenance decision control indexes to establish the unified prediction model of PCI and RDI respectively by applying the cosine deterioration equation.Results reveal that the deterioration law of PCI presents an anti-S type or concave type and the deterioration law of RDI shows an obvious concave type.The prediction model proposed in this study added the pavement maintenance standard factor d,which brings the model parameterα(reflecting the road life)and the deterioration equations are more applicable than the traditional standard equations.It is found that the fitting effects of PCI and RDI prediction models with different traffic grades are relatively similar to the actual service state of the pavements.
