与传统列控系统相比,全自动无人驾驶运营场景更加复杂多变,潜在的危险及致因具有更强的隐蔽性和复杂性,给运营安全带来了新的挑战。针对以上问题,提出一种STAMP(Systems-Theoretic Accident Model and Process)与模型检验相结合的复杂...与传统列控系统相比,全自动无人驾驶运营场景更加复杂多变,潜在的危险及致因具有更强的隐蔽性和复杂性,给运营安全带来了新的挑战。针对以上问题,提出一种STAMP(Systems-Theoretic Accident Model and Process)与模型检验相结合的复杂运营场景安全验证方法。首先,基于STAMP理论构建运营场景分层控制结构模型,辨识潜在的不安全控制行为、分析危险致因和安全约束;其次,定义分层控制结构模型与安全状态机模型间的基本转换规则,基于分层控制结构模型、安全约束和转换规则,构建运营场景安全状态机模型;最后,针对提取的安全约束,利用数据流图建立安全属性验证模型,结合模型检验技术,对运营场景安全状态机模型进行形式化验证。以全自动无人驾驶运营场景中列车自动进站停车为例,对方法进行验证分析。结果表明,当STAMP理论提取的安全约束通过了场景安全状态机模型的验证时,表示在该场景中对应的不安全控制行为没有发生且不导致相应危险。该方法结合系统安全分析与形式化建模验证的优势,降低了运营场景建模的难度,构建的运营场景形式化模型满足系统安全约束,可以作为全自动无人驾驶系统安全设计和安全改进的重要基础。展开更多
With the increasing level of automation of autonomous vehicles,it is important to conduct comprehensive and extensive testing before releasing autonomous vehicles into the market.Traditional public road and closed-fie...With the increasing level of automation of autonomous vehicles,it is important to conduct comprehensive and extensive testing before releasing autonomous vehicles into the market.Traditional public road and closed-field testing failed to meet the requirements of high testing efficiency and scenario coverage.Therefore,scenario-based autonomous vehicle simulation testing has emerged.Many scenarios form the basis of simulation testing.Generating additional scenarios from an existing scenario library is a significant problem.Taking the scenarios of a proceeding vehicle cutting into an adjacent lane on highways as an example,based on an autoencoder and a generative adversarial network(GAN),a method that combines Transformer to capture the features of a long-time series,called SceGAN,is proposed to model and generate scenarios of autonomous vehicles on highways.An evaluation system is established to analyze the reliability of SceGAN using discriminative and predictive scores and further evaluate the effect of scenario generation in terms of similarity and coverage.Experiments showed that compared with TimeGAN and AEGAN,SceGAN is superior in data fidelity and availability,and their similarity increased by 27.22%and 21.39%,respectively.The coverage increased from 79.84%to 93.98%as generated scenarios increased from 2,547 to 50,000,indicating that the proposed method has a strong generalization capability for generating multiple trajectories,providing a basis for generating test scenarios and promoting autonomous vehicle testing.展开更多
To improve the efficiency of safety tests of driver-automation cooperation,a method for generating a scenario library is proposed that considers the probability of scenario occurrence and driver-handling challenges in...To improve the efficiency of safety tests of driver-automation cooperation,a method for generating a scenario library is proposed that considers the probability of scenario occurrence and driver-handling challenges in real driving situations.First,the original scenario data under cut-in conditions stored in a time series are extracted from the scenario data set.Then,a mathematical performance index is used to model the scenario and a significance function in terms of the occurrence frequency of the scenario,and the performance challenge between the driver and the vehicle is established.Next,the important scenario set is extracted from the original scenario set by constructing and optimizing a significance auxiliary function.Finally,the extracted important scenario sets are filtered by using the significance function values of the scenarios to generate a scenario library.Simulation results show that the proposed method for scenario library generation can effectively identify scenarios with potential adventure during driver-automation cooperation and thus accelerate safety tests compared with traditional methods.展开更多
为解决地铁运营延误事件因缺乏合理的结构化情景构建方法而难以形成准确有效的属性知识,来辅助应急调度处置决策、减少主观经验依赖的问题,引入EOC(Element-Object-Consequence)模型,结合人-机-环安全体系和运营延误事件特征,提出了以...为解决地铁运营延误事件因缺乏合理的结构化情景构建方法而难以形成准确有效的属性知识,来辅助应急调度处置决策、减少主观经验依赖的问题,引入EOC(Element-Object-Consequence)模型,结合人-机-环安全体系和运营延误事件特征,提出了以列车运行为主的“要素(Element)-对象(Object)-结果(Consequence)-管理与响应(Management and Response)”情景构建框架,建立了事件情景属性关联分析模型,并设计了辅助决策应用流程。在此基础上,以供电故障引起的运营延误事件为例进行情景构建应用及可视化表达,分析了属性间关联性和敏感性。最后,对新供电故障事件的延误时间进行了预测,并与实际结果进行了对比验证。结果表明,在考虑要素和对象权重相同的前提下,环境要素、线路开通年份、列车最大运营年限对供电故障事件的总关联度影响较大,而新事件的预测延误时间相比实际延误时间的误差在15%以内,验证了结构化情景构建方法在事件影响预测上的可行性。展开更多
无储能动态电压恢复器(dynamic voltage restorer,DVR)作为工程中解决电压暂降问题的常用设备,其实际运行受限于应用场景的参数。为解决上述问题,提出了一种无储能DVR安全运行区域的算法,基于应用场景参数计算无储能DVR的最大补偿能力,...无储能动态电压恢复器(dynamic voltage restorer,DVR)作为工程中解决电压暂降问题的常用设备,其实际运行受限于应用场景的参数。为解决上述问题,提出了一种无储能DVR安全运行区域的算法,基于应用场景参数计算无储能DVR的最大补偿能力,进而规范无储能DVR在工程中的应用。首先,基于线缆、变压器与无储能DVR装置安全补偿范围间的联系,构建了系统的阻抗模型;其次,分析了无储能DVR补偿过程造成的次生压降问题,结合系统过载能力计算无储能DVR装置的安全运行区域。最后,通过仿真分析对安全运行区域计算方法进行验证。结果表明:所提方法在应用场景约束条件下确定了新的无储能DVR安全运行区域,为有效应用无储能DVR提供理论参考。展开更多
Continuous-scale trusted safety efficiency evaluation is crucial for the agile development and robust validation of autonomous vehicle intelligence.While the UN R157 Regulation evaluates automated lane-keeping system(...Continuous-scale trusted safety efficiency evaluation is crucial for the agile development and robust validation of autonomous vehicle intelligence.While the UN R157 Regulation evaluates automated lane-keeping system(ALKS)performance baselines through safe collision plots(SCPs)in various scenario clusters,quantifying the specific ALKS safety efficiency remains challenging.We propose a spectrum quantification approach to evaluate the safety efficiency of autonomous vehicles in cut-in scenarios.First,we collected speed-distance data under different cut-in scenarios and extracted essential spectral features to indicate the vehicle motion parameters during the cut-in process.Second,by utilizing Fourier analysis,a spectral analysis model was built to quantify and analyze the vehicle motion characteristics,providing insights into scenario safety.Finally,we created approximate analytical equations for the normalized disturbance frequencies in the nonlinear response scenarios of autonomous driving systems by combining the SCP with a frequency spectrum analysis model.The results showed that the normalized disturbance frequency in the cut-in scenario was approximately 0.2.When the relative longitudinal distance and speed of the vehicle are the same,if the cut-in speed of the cut-in vehicle is larger,the normalized disturbance frequency is higher,indicating that the cut-in process of the autonomous vehicle is more dangerous and may trigger a collision.展开更多
文摘与传统列控系统相比,全自动无人驾驶运营场景更加复杂多变,潜在的危险及致因具有更强的隐蔽性和复杂性,给运营安全带来了新的挑战。针对以上问题,提出一种STAMP(Systems-Theoretic Accident Model and Process)与模型检验相结合的复杂运营场景安全验证方法。首先,基于STAMP理论构建运营场景分层控制结构模型,辨识潜在的不安全控制行为、分析危险致因和安全约束;其次,定义分层控制结构模型与安全状态机模型间的基本转换规则,基于分层控制结构模型、安全约束和转换规则,构建运营场景安全状态机模型;最后,针对提取的安全约束,利用数据流图建立安全属性验证模型,结合模型检验技术,对运营场景安全状态机模型进行形式化验证。以全自动无人驾驶运营场景中列车自动进站停车为例,对方法进行验证分析。结果表明,当STAMP理论提取的安全约束通过了场景安全状态机模型的验证时,表示在该场景中对应的不安全控制行为没有发生且不导致相应危险。该方法结合系统安全分析与形式化建模验证的优势,降低了运营场景建模的难度,构建的运营场景形式化模型满足系统安全约束,可以作为全自动无人驾驶系统安全设计和安全改进的重要基础。
基金supported by the National Key R&D Program of China(2021YFB2501200)the National Natural Science Foundation of China(52131204)the Shaanxi Province Key Research and Development Program(2022GY-300).
文摘With the increasing level of automation of autonomous vehicles,it is important to conduct comprehensive and extensive testing before releasing autonomous vehicles into the market.Traditional public road and closed-field testing failed to meet the requirements of high testing efficiency and scenario coverage.Therefore,scenario-based autonomous vehicle simulation testing has emerged.Many scenarios form the basis of simulation testing.Generating additional scenarios from an existing scenario library is a significant problem.Taking the scenarios of a proceeding vehicle cutting into an adjacent lane on highways as an example,based on an autoencoder and a generative adversarial network(GAN),a method that combines Transformer to capture the features of a long-time series,called SceGAN,is proposed to model and generate scenarios of autonomous vehicles on highways.An evaluation system is established to analyze the reliability of SceGAN using discriminative and predictive scores and further evaluate the effect of scenario generation in terms of similarity and coverage.Experiments showed that compared with TimeGAN and AEGAN,SceGAN is superior in data fidelity and availability,and their similarity increased by 27.22%and 21.39%,respectively.The coverage increased from 79.84%to 93.98%as generated scenarios increased from 2,547 to 50,000,indicating that the proposed method has a strong generalization capability for generating multiple trajectories,providing a basis for generating test scenarios and promoting autonomous vehicle testing.
基金Major Project of Scientific and Technological Innovation 2030“New Generation Artificial Intelligence”(Grant No.2020AAA0108105)National Nature Science Foundation of China(Grants Nos.62103162 and U19A2069)+1 种基金Jilin Key Research and Development Program(Grant No.20200401088GX)the Jilin Major Science and Technology Projects(Grant No.20200501011GX).
文摘To improve the efficiency of safety tests of driver-automation cooperation,a method for generating a scenario library is proposed that considers the probability of scenario occurrence and driver-handling challenges in real driving situations.First,the original scenario data under cut-in conditions stored in a time series are extracted from the scenario data set.Then,a mathematical performance index is used to model the scenario and a significance function in terms of the occurrence frequency of the scenario,and the performance challenge between the driver and the vehicle is established.Next,the important scenario set is extracted from the original scenario set by constructing and optimizing a significance auxiliary function.Finally,the extracted important scenario sets are filtered by using the significance function values of the scenarios to generate a scenario library.Simulation results show that the proposed method for scenario library generation can effectively identify scenarios with potential adventure during driver-automation cooperation and thus accelerate safety tests compared with traditional methods.
文摘为解决地铁运营延误事件因缺乏合理的结构化情景构建方法而难以形成准确有效的属性知识,来辅助应急调度处置决策、减少主观经验依赖的问题,引入EOC(Element-Object-Consequence)模型,结合人-机-环安全体系和运营延误事件特征,提出了以列车运行为主的“要素(Element)-对象(Object)-结果(Consequence)-管理与响应(Management and Response)”情景构建框架,建立了事件情景属性关联分析模型,并设计了辅助决策应用流程。在此基础上,以供电故障引起的运营延误事件为例进行情景构建应用及可视化表达,分析了属性间关联性和敏感性。最后,对新供电故障事件的延误时间进行了预测,并与实际结果进行了对比验证。结果表明,在考虑要素和对象权重相同的前提下,环境要素、线路开通年份、列车最大运营年限对供电故障事件的总关联度影响较大,而新事件的预测延误时间相比实际延误时间的误差在15%以内,验证了结构化情景构建方法在事件影响预测上的可行性。
文摘无储能动态电压恢复器(dynamic voltage restorer,DVR)作为工程中解决电压暂降问题的常用设备,其实际运行受限于应用场景的参数。为解决上述问题,提出了一种无储能DVR安全运行区域的算法,基于应用场景参数计算无储能DVR的最大补偿能力,进而规范无储能DVR在工程中的应用。首先,基于线缆、变压器与无储能DVR装置安全补偿范围间的联系,构建了系统的阻抗模型;其次,分析了无储能DVR补偿过程造成的次生压降问题,结合系统过载能力计算无储能DVR装置的安全运行区域。最后,通过仿真分析对安全运行区域计算方法进行验证。结果表明:所提方法在应用场景约束条件下确定了新的无储能DVR安全运行区域,为有效应用无储能DVR提供理论参考。
基金the National Key R&D Program of China(Grant No.2021YFB1600403)the National Natural Science Foundation of China(Grant Nos.51805312 and 52172388).
文摘Continuous-scale trusted safety efficiency evaluation is crucial for the agile development and robust validation of autonomous vehicle intelligence.While the UN R157 Regulation evaluates automated lane-keeping system(ALKS)performance baselines through safe collision plots(SCPs)in various scenario clusters,quantifying the specific ALKS safety efficiency remains challenging.We propose a spectrum quantification approach to evaluate the safety efficiency of autonomous vehicles in cut-in scenarios.First,we collected speed-distance data under different cut-in scenarios and extracted essential spectral features to indicate the vehicle motion parameters during the cut-in process.Second,by utilizing Fourier analysis,a spectral analysis model was built to quantify and analyze the vehicle motion characteristics,providing insights into scenario safety.Finally,we created approximate analytical equations for the normalized disturbance frequencies in the nonlinear response scenarios of autonomous driving systems by combining the SCP with a frequency spectrum analysis model.The results showed that the normalized disturbance frequency in the cut-in scenario was approximately 0.2.When the relative longitudinal distance and speed of the vehicle are the same,if the cut-in speed of the cut-in vehicle is larger,the normalized disturbance frequency is higher,indicating that the cut-in process of the autonomous vehicle is more dangerous and may trigger a collision.
