Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potenti...Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions.However,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world applications.In this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway driving.Within this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step.Thus,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events.To construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy.Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data.The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios.The proposed risk assessment framework is promising for real-world applications.展开更多
Despite of modern navigation devices, there are problems in navigation of vessels in waterways due to the geographical structures, disturbances in water, dynamic nature, and heavily environmental influenced sea traffi...Despite of modern navigation devices, there are problems in navigation of vessels in waterways due to the geographical structures, disturbances in water, dynamic nature, and heavily environmental influenced sea traffic. Even though all vessels are equipped with modern navigation devices, the accidents are reported caused by various reasons and mainly by human factor according to investigation. We propose an effective and efficient composition collision risk calculation method for finding the collision probability and avoiding the collision between ships in possible collision situations. The proposed composition collision risk calculation method at ship's position using combination of fuzzy and fuzzy comprehensive evaluation methods. The algorithm is straightforward to implement and is shown to be effective in automatic ship handling for ships involved in complex navigation situations. Experiments are carried out with indigenous data and the results show the effectiveness of the proposed approach.展开更多
In this paper,a new method to calculate collision risk of air-routes,based on variable nominal separation,is proposed. The collision risk model of air-routes,based on the time variable and initial time interval variab...In this paper,a new method to calculate collision risk of air-routes,based on variable nominal separation,is proposed. The collision risk model of air-routes,based on the time variable and initial time interval variable,is given. Because the distance and the collision probability vary with time when the nominal relative speed between aircraft is not zero for a fixed initial time interval,the distance,the variable nominal separation,and the collision probability at any time can be expressed as functions of time and initial time interval. By the probabilistic theory,a model for calculating collision risk is acquired based on initial time interval distribution,flow rates,and the proportion of aircraft type. From the results of calculations,the collision risk can be characterized by the model when the nominal separation changes with time. As well the roles of parameters can be shown more readily.展开更多
There are standard procedures for collecting data on numbers of birds at sites being proposed for wind farm development and evaluating collision risk for each key species. However, methods do not work well for all spe...There are standard procedures for collecting data on numbers of birds at sites being proposed for wind farm development and evaluating collision risk for each key species. However, methods do not work well for all species. Where a local bird population is depleted, empirical data cannot provide estimates of likely collision mortality numbers if that population returns to satisfactory conservation status. Field survey methods are also inadequate for cryptic bird species. Both these problems can be important for evaluation of impacts of proposed wind farms on bird populations protected by the EU Birds Directive. We present an alternative method, based on energy constrained activity budgets and natural history, which permits assessment of likely collision numbers where empirical data are inadequate. Two case studies are presented where this approach has been successfully used to resolve disputed planning applications, one for a hen harrier population where numbers present are much below the population size at designation, and one for a cryptic species (greenshank). Our novel method helps reduce uncertainty in assessments constrained by difficulties in collecting suitable empirical data.展开更多
Wildlife-vehicle collisions(WVCs)with large animals are estimated to cost the USA over 8 billion USD in property damage,tens of thousands of human injuries and nearly 200 human fatalities each year.Most WVCs occur on ...Wildlife-vehicle collisions(WVCs)with large animals are estimated to cost the USA over 8 billion USD in property damage,tens of thousands of human injuries and nearly 200 human fatalities each year.Most WVCs occur on rural roads and are not collected evenly among road segments,leading to imbalanced data.There are a disproportionate number of analysis units that have zero WVC cases when investigating large geographic areas for collision risk.Analysis units with zero WVCs can reduce prediction accuracy and weaken the coefficient estimates of statistical learning models.This study demonstrates that the use of the synthetic minority over-sampling technique(SMOTE)to handle imbalanced WVC data in combination with statistical and machine-learning models improves the ability to determine seasonal WVC risk across the rural highway network in Montana,USA.An array of regularized variables describing landscape,road and traffic were used to develop negative binomial and random forest models to infer WVC rates per 100 million vehicle miles travelled.The random forest model is found to work particularly well with SMOTE-augmented data to improve the prediction accuracy of seasonal WVC risk.SMOTE-augmented data are found to improve accuracy when predicting crash risk across fine-grained grids while retaining the characteristics of the original dataset.The analyses suggest that SMOTE augmentation mitigates data imbalance that is encountered in seasonally divided WVC data.This research provides the basis for future risk-mapping models and can potentially be used to address the low rates of WVCs and other crash types along rural roads.展开更多
为定量识别城市非信控环形交叉口区域内的机动车冲突风险易发生点,降低环形交叉口的事故发生率,本文构建针对非信控环形交叉口机动车冲突风险识别模型。首先,利用无人机采集高精度、连续的多车辆轨迹视频,结合Kinovea视频运动分析软件...为定量识别城市非信控环形交叉口区域内的机动车冲突风险易发生点,降低环形交叉口的事故发生率,本文构建针对非信控环形交叉口机动车冲突风险识别模型。首先,利用无人机采集高精度、连续的多车辆轨迹视频,结合Kinovea视频运动分析软件实现运行车辆状态识别与跟踪,并记录车辆每一帧的运动数据;其次,基于交通冲突识别指标TTC(Time to Collision),提出适应环形交叉口道路线形特征的车辆TTC计算方法,并使用累计频率法确定严重、一般和轻微冲突的阈值分别为1.2,2.8,4.4 s;最后,通过绘制高峰和平峰交通冲突空间异步图,并结合交通冲突数和严重冲突率,对环形交叉口的36个子区段进行交通冲突风险等级评定。研究结果显示:在高峰时段,某一子区段的平均交通冲突发生次数约为15次,严重冲突率为17.45%;在平峰时段,某一子区段的平均交通冲突发生次数约为8次,严重冲突率为8.28%。重度风险区域在高峰时段占比达到50%,而在平峰时段为8.33%,这些重度风险区域主要集中在交织区段。因此,环形交叉口在高峰时段且位于交织区段的情况更易发生交通事故。本文研究成果有助于交通管理部门了解环形交叉口在不同时段和区段上的交通冲突情况和特征,以便采取相应的预警和管理措施。展开更多
基金supported by the proactive SAFEty systems and tools for a constantly UPgrading road environment(SAFE-UP)projectfunding from the European Union’s Horizon 2020 Research and Innovation Program(861570)。
文摘Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions.However,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world applications.In this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway driving.Within this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step.Thus,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events.To construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy.Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data.The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios.The proposed risk assessment framework is promising for real-world applications.
基金supported by ETRI through Maritime Safety & Maritime Traffic Management R&D Program of the MOF/KIMST (2009403, Development of Next Generation VTS for Maritime Safety)supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MEST) (No. 2011-0015009)
文摘Despite of modern navigation devices, there are problems in navigation of vessels in waterways due to the geographical structures, disturbances in water, dynamic nature, and heavily environmental influenced sea traffic. Even though all vessels are equipped with modern navigation devices, the accidents are reported caused by various reasons and mainly by human factor according to investigation. We propose an effective and efficient composition collision risk calculation method for finding the collision probability and avoiding the collision between ships in possible collision situations. The proposed composition collision risk calculation method at ship's position using combination of fuzzy and fuzzy comprehensive evaluation methods. The algorithm is straightforward to implement and is shown to be effective in automatic ship handling for ships involved in complex navigation situations. Experiments are carried out with indigenous data and the results show the effectiveness of the proposed approach.
基金The National Natural Science Foundations(Nos. 60776813 and 60979018)the National Air Traffic Management Research Program ( GKG200802015)the NUAA Research Funding (NS2010184)
文摘In this paper,a new method to calculate collision risk of air-routes,based on variable nominal separation,is proposed. The collision risk model of air-routes,based on the time variable and initial time interval variable,is given. Because the distance and the collision probability vary with time when the nominal relative speed between aircraft is not zero for a fixed initial time interval,the distance,the variable nominal separation,and the collision probability at any time can be expressed as functions of time and initial time interval. By the probabilistic theory,a model for calculating collision risk is acquired based on initial time interval distribution,flow rates,and the proportion of aircraft type. From the results of calculations,the collision risk can be characterized by the model when the nominal separation changes with time. As well the roles of parameters can be shown more readily.
文摘There are standard procedures for collecting data on numbers of birds at sites being proposed for wind farm development and evaluating collision risk for each key species. However, methods do not work well for all species. Where a local bird population is depleted, empirical data cannot provide estimates of likely collision mortality numbers if that population returns to satisfactory conservation status. Field survey methods are also inadequate for cryptic bird species. Both these problems can be important for evaluation of impacts of proposed wind farms on bird populations protected by the EU Birds Directive. We present an alternative method, based on energy constrained activity budgets and natural history, which permits assessment of likely collision numbers where empirical data are inadequate. Two case studies are presented where this approach has been successfully used to resolve disputed planning applications, one for a hen harrier population where numbers present are much below the population size at designation, and one for a cryptic species (greenshank). Our novel method helps reduce uncertainty in assessments constrained by difficulties in collecting suitable empirical data.
文摘Wildlife-vehicle collisions(WVCs)with large animals are estimated to cost the USA over 8 billion USD in property damage,tens of thousands of human injuries and nearly 200 human fatalities each year.Most WVCs occur on rural roads and are not collected evenly among road segments,leading to imbalanced data.There are a disproportionate number of analysis units that have zero WVC cases when investigating large geographic areas for collision risk.Analysis units with zero WVCs can reduce prediction accuracy and weaken the coefficient estimates of statistical learning models.This study demonstrates that the use of the synthetic minority over-sampling technique(SMOTE)to handle imbalanced WVC data in combination with statistical and machine-learning models improves the ability to determine seasonal WVC risk across the rural highway network in Montana,USA.An array of regularized variables describing landscape,road and traffic were used to develop negative binomial and random forest models to infer WVC rates per 100 million vehicle miles travelled.The random forest model is found to work particularly well with SMOTE-augmented data to improve the prediction accuracy of seasonal WVC risk.SMOTE-augmented data are found to improve accuracy when predicting crash risk across fine-grained grids while retaining the characteristics of the original dataset.The analyses suggest that SMOTE augmentation mitigates data imbalance that is encountered in seasonally divided WVC data.This research provides the basis for future risk-mapping models and can potentially be used to address the low rates of WVCs and other crash types along rural roads.
文摘为定量识别城市非信控环形交叉口区域内的机动车冲突风险易发生点,降低环形交叉口的事故发生率,本文构建针对非信控环形交叉口机动车冲突风险识别模型。首先,利用无人机采集高精度、连续的多车辆轨迹视频,结合Kinovea视频运动分析软件实现运行车辆状态识别与跟踪,并记录车辆每一帧的运动数据;其次,基于交通冲突识别指标TTC(Time to Collision),提出适应环形交叉口道路线形特征的车辆TTC计算方法,并使用累计频率法确定严重、一般和轻微冲突的阈值分别为1.2,2.8,4.4 s;最后,通过绘制高峰和平峰交通冲突空间异步图,并结合交通冲突数和严重冲突率,对环形交叉口的36个子区段进行交通冲突风险等级评定。研究结果显示:在高峰时段,某一子区段的平均交通冲突发生次数约为15次,严重冲突率为17.45%;在平峰时段,某一子区段的平均交通冲突发生次数约为8次,严重冲突率为8.28%。重度风险区域在高峰时段占比达到50%,而在平峰时段为8.33%,这些重度风险区域主要集中在交织区段。因此,环形交叉口在高峰时段且位于交织区段的情况更易发生交通事故。本文研究成果有助于交通管理部门了解环形交叉口在不同时段和区段上的交通冲突情况和特征,以便采取相应的预警和管理措施。
