Driverless car,as a direction for future automobile development,greatly improves the efficiency and safety of the traffic system.It’s one of the most popular technical fields.In recent years,driverless car has develo...Driverless car,as a direction for future automobile development,greatly improves the efficiency and safety of the traffic system.It’s one of the most popular technical fields.In recent years,driverless car has developed rapidly.The related development is concerned by governments,businesses,consumers and stakeholders widely,and most of countries have been actively studying this technology.This paper first introduces the current development of driverless car at home and abroad.Besides,the basic technologies of driverless car are briefly analyzed.In addition,the author compares the American government’s attitudes with Chinese government’s attitudes towards driverless car.Specifically,the article makes an analysis of contents of literature and periodicals at home and abroad and policies and documents which have already been published.The analysis shows that there is no great difference between the attitudes of Chinese and American governments.Both of two governments actively support the development of driverless car.Finally,this paper expounds the development direction of the driverless car field in future by dividing into two categories through road conditions:automatic driving on expressways and automatic driving in cities.展开更多
Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar perform...Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle detection.Achieving a balance between accuracy and detection speed is crucial for real-time object detection in real-world road scenes.This paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the background.Secondly,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of themodel.Finally,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid structure.Experimental results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/s.FBPN demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.展开更多
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
文摘Driverless car,as a direction for future automobile development,greatly improves the efficiency and safety of the traffic system.It’s one of the most popular technical fields.In recent years,driverless car has developed rapidly.The related development is concerned by governments,businesses,consumers and stakeholders widely,and most of countries have been actively studying this technology.This paper first introduces the current development of driverless car at home and abroad.Besides,the basic technologies of driverless car are briefly analyzed.In addition,the author compares the American government’s attitudes with Chinese government’s attitudes towards driverless car.Specifically,the article makes an analysis of contents of literature and periodicals at home and abroad and policies and documents which have already been published.The analysis shows that there is no great difference between the attitudes of Chinese and American governments.Both of two governments actively support the development of driverless car.Finally,this paper expounds the development direction of the driverless car field in future by dividing into two categories through road conditions:automatic driving on expressways and automatic driving in cities.
基金funded by Ministry of Science and Technology of the People’s Republic of China,Grant Numbers 2022YFC3800502Chongqing Science and Technology Commission,Grant Number cstc2020jscx-dxwtBX0019,CSTB2022TIAD-KPX0118,cstc2020jscx-cylhX0005 and cstc2021jscx-gksbX0058.
文摘Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle detection.Achieving a balance between accuracy and detection speed is crucial for real-time object detection in real-world road scenes.This paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the background.Secondly,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of themodel.Finally,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid structure.Experimental results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/s.FBPN demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.
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。
