Perception Enhanced Deep Deterministic Policy Gradient for Autonomous Driving in Complex Scenarios

Autonomous driving has witnessed rapid advancement;however,ensuring safe and efficient driving in intricate scenarios remains a critical challenge.In particular,traffic roundabouts bring a set of challenges to autonomous driving due to the unpredictable entry and exit of vehicles,susceptibility to traffic flow bottlenecks,and imperfect data in perceiving environmental information,rendering them a vital issue in the practical application of autonomous driving.To address the traffic challenges,this work focused on complex roundabouts with multi-lane and proposed a Perception EnhancedDeepDeterministic Policy Gradient(PE-DDPG)for AutonomousDriving in the Roundabouts.Specifically,themodel incorporates an enhanced variational autoencoder featuring an integrated spatial attention mechanism alongside the Deep Deterministic Policy Gradient framework,enhancing the vehicle’s capability to comprehend complex roundabout environments and make decisions.Furthermore,the PE-DDPG model combines a dynamic path optimization strategy for roundabout scenarios,effectively mitigating traffic bottlenecks and augmenting throughput efficiency.Extensive experiments were conducted with the collaborative simulation platform of CARLA and SUMO,and the experimental results show that the proposed PE-DDPG outperforms the baseline methods in terms of the convergence capacity of the training process,the smoothness of driving and the traffic efficiency with diverse traffic flow patterns and penetration rates of autonomous vehicles(AVs).Generally,the proposed PE-DDPGmodel could be employed for autonomous driving in complex scenarios with imperfect data.

Roundabout1对大鼠周围神经再生轴突导向的影响

目的:探讨Roundabout1(Robo1)对周围神经再生轴突的导向作用。方法:利用坐骨神经压榨和切断后立即缝合模型,将可溶性Robo1-Fc融合蛋白注入到压榨或缝合部位,形成压榨组和缝合组;以人的Fc蛋白注入上述模型形成两对照组。对术后不同时间点行再生纤维半薄切片、图像分析、步态分析。结果:术后21d两实验组再生纤维数均明显少于对照组;至术后42d,与对照组比较差异无统计学意义。术后14、21d,压榨实验组坐骨神经功能指数(SFI)明显不及压榨对照组。术后14、21d,缝合实验组与缝合对照组比较,SFI差异无统计学意义;而在术后35、42d明显少于缝合对照组。结论:Robo1可能促进周围神经再生并参与调控再生轴突生长方向。

Roundabout4在肿瘤血管新生及细胞迁移中作用的研究进展

视网膜新生血管性疾病是世界范围内最严重的致盲性眼病之一，包括糖尿病视网膜病变、年龄相关性黄斑变性等。近年来普遍认为血管生长因子是调控视网膜内皮细胞增生和新生血管形成的最主要因素。Roundabout 4（Rob04）是近年发现的一种跨膜蛋白，特异性表达于血管生成活跃的内皮细胞表面。目前的研究认为，Rob04能够调控内皮细胞的迁移及血管新生，参与血管生长因子的信号转导途径，在血管稳定性的调节中发挥重要作用。对Rob04的深入研究将有助于揭示视网膜新生血管性疾病的形成机制。就Rob04的分布、结构、配体及在血管发生、内皮细胞迁移中的作用及与眼部相关的基础研究进行综述。

脂多糖对人脐静脉内皮细胞Robo4表达的影响

目的:观察不同浓度脂多糖(LPS)对人脐静脉内皮细胞(HUVECs)Robo4受体表达的作用。方法:体外培养HUVECs,分正常对照组和2个浓度LPS组(正常对照组基础上分别加入终浓度为10μg/m L和100μg/m L LPS),每组重复实验6次。免疫荧光染色及Western blot检测各组细胞Robo4蛋白表达,RT-PCR检测Robo4 m RNA表达。结果:高剂量LPS组HUVECs Robo4蛋白与m RNA表达分别为(0.49±0.08)和(0.23±0.08),较正常对照组(1.35±0.15)和(0.97±0.17)明显下降(P<0.05);低剂量LPS组Robo4蛋白与m RNA表达分别为(0.13±0.13)和(0.94±0.14),较正常对照组均有下降,但差异无统计学意义(P>0.05)。结论:高剂量100μg/m L LPS可下调HUVECs Robo4的表达。

Robo1 RNA干扰慢病毒载体的构建及其基因沉默效应

目的构建Roundabout(Robo1)siRNA慢病毒载体,并在SKOV3卵巢癌细胞中鉴定其转染及基因沉默效果。方法根据GenBank中基因信息,采用干扰序列设计软件设计靶点,制备Robo1DNA片段,在T4DNA连接酶作用下,将线性化的病毒载体GV118与DNA片段制备合成GV118-siRNA目的质粒,转化感受态细胞,对于长出的克隆应用菌落PCR鉴定,再对PCR鉴定阳性的克隆进行测序和对比分析,重组病毒质粒与另外2种辅助包装原件载体质粒通过LipofectamineTM2000共转染293T细胞,培养48h后,收集细胞培养上清液,将病毒浓缩后在293T细胞中测定病毒滴度;并检测病毒载体在工具细胞SKOV3卵巢癌细胞中的转染效率,实时荧光定量PCR(RT-PCR)和Western blot方法检测Robo1siRNA慢病毒对SKOV3中Robo1的干扰作用。结果成功构建Robo1siRNA慢病毒载体GV118-siR-NA,病毒滴度为2×109 TU/mL;用该病毒体外转染SKOV3卵巢癌细胞,当感染复数(MOI)为10时,感染效率大于90%;RT-PCR和Western blot方法检测Robo1基因沉默的效率分别为76.7%、56.0%。结论成功构建了Robo1siR-NA慢病毒载体GV118-siRNA,该病毒载体在体外转染SKOV3卵巢癌细胞的效率较高,且具有显著的基因沉默效果。

用RNA-RNA原位杂交技术研究Robo2在早期鸡胚发育中的表达

目的:探讨Robo2(roundabout homolog 2)在早期鸡胚发育中的表达。方法:利用分子生物学手段,构建Robo2/pSPT18重组质粒,并且制备地高辛标记的Robo2 RNA探针,进而通过RNA-RNA原位杂交技术检测Robo2在早期鸡胚发育中的表达。结果:原条发生前Robo2表达较弱,原条发生后主要表达在原条和神经板。体节期Robo2主要表达在脊索、神经管、体节和血岛部位。冰冻切片后观察到Robo2主要表达在外胚层,而在中胚层和内胚层只有部分表达。结论:阐明了Robo2在早期鸡胚发育中的表达,为进一步研究Robo2在正常生理和病理条件下的功能及作用机制奠定基础。

Slit-Robo细胞信号转导通路研究进展

Slit-Robo细胞信号转导通路调控多种多样的生理功能,不同的下游信号转导途径可产生不同的生理功能。其中最广为人知的功能是介导双侧对称生物体胚胎神经系统发育时的轴突排斥现象。近年来,作为一种在生物体内广泛表达的细胞信号转导通路,Slit-Robo的功能库已大大扩展,与神经发育、血管生成、器官及组织发育以及干细胞的增殖调节等均有关。本文就Slit-Robo细胞信号转导通路目前的研究进展做一综述。

Slit2/Robo1信号通路与肿瘤相关性的研究进展

1988年Rothberg等[1]发现果蝇的中枢神经中线胶质细胞可合成Slit蛋白,其缺乏可导致纵行传导通路和交叉（联合）神经元轴突在中线发生聚集异常.1998年,Kidd等[2]首次提出Roundabout（Robo）蛋白是Slit的受体,为进一步研究Slit蛋白的功能奠定了基础.Slit-Robo通路包括Slit分泌蛋白家族（Slit1、2、3）及其特异性受体（Robo1、2、3、4）,其中Slit2/Robo1信号通路最初发现是与中枢神经系统发育有关。

The CA model for traffic-flow at the grade roundabout crossing

The cellular automaton model is suggested to describe the traffic-flow at the grade roundabout crossing. After the simulation with computer, the fundamental properties of this model have been revealed. Analysing this kind of road structure, this paper transforms the grade roundabout crossing with inner-roundabout-lane and outer-roundabout-lane into a configuration with many bottlenecks. Because of the self-organization, the traffic flow remains unblocked under a certain vehicle density. Some results of the simulation are close to the actual design parameter.

Comparative evaluation of roundabout capacities under heterogeneous traffic conditions

In heterogeneous traffic conditions, roundabout capacity is described by vehicle and driver characteristics which are different from traffic conditions in homogeneous conditions. In the present study, the capacity of the roundabout is determined using various capacity formulas such as gap acceptance models given by Highway Capacity Manual 2010 （US）, German model （2001）; empirical regression models given by TRRL （UK） and weaving models given by IRC： 65-1976 （India）. In addition, microscopic simulation model like VISSIM （PTV Ger- many） is also used to derive capacity values. Unlike the other capacity estimation models, VISSIM is helpful in estimating capacity values using geometric and driver characteristics and it can also simulate heterogeneous traffic condition accurately. Capacity is estimated after calibrating the simulation model （VISSIM） developed for the roundabout. This is achieved by incorporating different vehicle classes to represent the heterogeneous traffic environment, driver gap acceptance, and lane changeparameters. All the required inputs were extracted from the video using semi-automatic data collection methods. Data are used for the estimation of capacity values from dif- ferent methods mentioned above and for the calibration and validation of simulation model. The capacity values esti- mated form various formulas except German model are distinctly different from the field values and they are either overestimating or underestimating. Analysis of these observations reveals that the capacity values from VISSIM and German models are nearly matching with the field capacity.

Delay model of signalized roundabouts

In order to evaluate the service level of roundaboutsintuitively, a new delay model of signalized roundabouts isestablished. According to traffic flow characteristics in thesignalized roundabout, vehicle delays on roundabouts aredivided into two parts： entrance delay and circulating lanedelay. Entrance delay is calculated by the delay model inHCM2010. Circulating lane delay is studied by analyzingconflict behavior in signalized roundabouts, and the delaymodels of traffic flows turning in different directions areestablished based on the motorcade analysis method. Finally,the simulation software Vissim, calibrated with field data, isused to verify the model. The simulation results show that theaverage relative error of the model is 10. 1%, meeting theaccuracy requirements. Therefore, the delay model properlyreflects the operation efficiency of a roundabout, and can thusorovide a scientific basis for the design of control schemes.

Traffic flow of a roundabout crossing with an open boundary condition

This paper presents a cellular automaton traffic flow model with an open boundary condition to describe the traffic flow at a roundabout crossing with an inner roundabout lane and an outer roundabout lane. The simulation results show that the boundary condition, bottlenecks and the self-organization affect the traffic flow at the roundabout crossing. Because of the effect of bottlenecks, jams easily appear on the inner roundabout lane. To improve the capacity of the roundabout system, proper values of the enter probability α and the out probability βcan be chosen.

Roundabout Performance Analysis Using Connected Vehicle Data

There are over 8000 roundabouts in the United States. The current techniques for assessing their performance require field counts to provide inputs to analysis or simulation models. These techniques are labor-intensive and do not scale well. This paper presents a methodology to use connected vehicle (CV) trajectory data to estimate delay and level of service for roundabout approaches by adapting the Purdue Probe Diagram used for traffic signal analytics. By linear referencing vehicle trajectories with a particular movement based on the location and time they exit a roundabout, delay can be calculated. The scalability is demonstrated by applying these techniques to assess over 100 roundabouts in Carmel, IN during the weekday afternoon peak period in July 2021. Over 264,000 trajectories and 3,600,000 GPS points were analyzed to rank over 300 roundabout approaches by delay and summarize in Pareto-sorted graphics and maps. The paper concludes by discussing how these techniques can also be used to analyze queue lengths and origin-destination characteristics at roundabouts. The methodology presented in this study can be used by any agency that wants to assess the performance of all roundabouts in their system.

Roundabout’s Impact on Nearby Businesses

The objective of this study is to determine if installation of roundabouts in a business area or on business corridors can be good for the businesses as well as improve the traffic flow in that area. This objective is achieved by emphasizing on roundabouts located in Kansas cities, particularly Topeka, Kansas. The study concentrates on conducting survey of businesses around the roundabout corridors in different places in the US including Topeka (Kansas), Junction City (Kansas), Newton (Kansas), and Carmel (Indiana). The survey results indicated a positive impact of roundabouts on businesses and traffic movement. Further, as there is no before and after corridor data available for making definite conclusions, a business corridor in Topeka, Kansas is simulated using both SIDRA and VISSIM software to evaluate the impacts of converting several traditional intersections in the corridor to roundabouts. The results from the simulation tasks have showed substantial reductions in vehicle delay and queuing for most of the traffic movements. Therefore, it was concluded that roundabouts on businesses corridor have a positive impact on traffic flows and business.

Calibrating HCM model for roundabout entry capacity under heterogeneous traffic

Roundabout is a channelized intersection where traffic moves around a central island,clockwise for leftside driving and anti-clockwise for right-side driving.Efficiently designed roundabouts can handle traffic very smoothly without causing any delay.The capacity of roundabouts used to be calculated by the weaving theory in India.However,calculation of the entry capacity in the recent literature is based on critical gaps and follow-up times,and the Highway Capacity Manual of US(HCM2010)provides an equation to estimate the entry capacity of a roundabout by using the flow in passenger car unit per hour(PCU/h),critical gaps and follow-up times at the entry section.In order to examine whether the HCM equation applies to Indian traffic condition or not,we collected data from five roundabouts in India in this study.Relevant data were extracted/estimated to calibrate parameters of the HCM equation.The PCU for a vehicle was estimated on the basis of lagging headway and width of the vehicle,and the critical gap value for a vehicle was estimated by minimizing the sum of absolute difference in a gap with respect to the highest rejected and accepted gaps.Results show that the critical gap values obtained under heterogeneous traffic conditions are much lower than those given in the literature for homogeneous traffic conditions.In addition,the modified HCM equation based on the critical gap values was verified using the field data taken during the formation of a continuous and stable queue at the entry of a roundabout.It was found that a multiplicative adjustment factor needs to be calculated for different sizes of roundabouts to ensure the adjusted HCM equation represents well the traffic condition prevailing in developing countries like India.A test conducted at another roundabout validated that the entry capacity estimated from the calibrated and adjusted HCM model was consistent with the field entry capacity,and the calibrated and adjusted HCM model could predict the entry capacity of an approach to a roundabout quite accurately.

Development of a tracking-based system for automated traffic data collection for roundabouts

Traffic data collection is essential for performance assessment, safety improvement and road planning. While automated traffic data collection for highways is relatively mature, that for roundabouts is more challenging due to more complex traffic scenes, data specifications and vehicle behavior. In this paper, the authors propose an automated traffic data collection system dedicated to roundabout scenes. The proposed system has mainly four steps of processing. First, camera calibration is performed for roundabout traffic scenes with a novel circle-based calibration algorithm. Second, the system uses enhanced Mixture of Gaussian algorithm with shaking removal for video segmentation, which can tolerate repeated camera displacements and background movements. Then, Kalman filtering, Kemel-based tracking and overlap-based opti- mization are employed to track vehicles while they are occluded and to derive the complete vehicle trajectories. The resulting vehicle trajectory of each individual vehicle gives the position, size, shape and speed of the vehicle at each time moment. Finally, a data mining algorithm is used to automatically extract the interested traffic data from the vehicle trajectories. The overall traffic data collection system has been implemented in software and runs on regular PC. The total processing time for a 3-hour video is currently 6 h. The automated traffic data collection system can significantly reduce cost and improve efficiency compared to manual data collection. The extracted traffic data have been compared to accurate manual measurements for 29 videos recorded on 29 different days, and an accuracy of more than 90% has been achieved.

Trucks at Roundabouts: A Synthesis Study

Roundabouts in United States and other countries have been proved to be very successful, effective, and a safe traffic control treatment. Roundabouts in the context of regularly expected truck configuration have also been successful for effective roundabout designs;however, there are always some site specific issues for trucks accommodation at roundabouts. Therefore, there is a great need for an informational guide in the form of synthesis report for roundabout designs specific to unique trucking traffic activity. While there are not significant literatures and studies in this subject, there are few studies/reports spread out which address various issues in this subject area. This study attempts to synthesize the research and knowledge of truck accommodation at roundabouts by synthesizing various research studies, reports, and articles;various subject areas such as roundabout designs for trucking activity, roundabout designs and accommodation strategies for specialized trucking activity such as oversized trucks, truck safety at roundabouts, and motor carrier perspective of trucking at roundabouts have been analyzed and relevant knowledge has been synthesized. This synthesis can be useful o researchers, designers, planners, and decision makers to determine effective ways to address specific trucking related issues at a roundabout.

Integrating Roundabouts with Freight Roadway Networks

The demand for freight transportation in the United States has grown rapidly in the past couple of decades;the rate at which the highway capacity is growing is not able to meet the freight-trans- portation needs, resulting in congestion and delay, ultimately affecting the users and the public with increased prices for the goods delivered, unreliable delivery times, and air-pollution concerns. Freight bottlenecks are a major cause of recurring congestion which accounts for about 40% of total vehicle hours of delay in the United States. Intersections for urban freight-roadway networks are one of the major freight bottlenecks and are considered to be a significant contributor for congestion and delay. Improving the efficiency at urban intersections with high truck traffic can address the freight-traffic congestion, leading to optimized goods movement as well as decreased delays, congestion, and emissions, thus enhancing the air quality in and around the communities. With the roundabout intersection control being proven as a safe, operationally efficient, and environment-friendly control treatment, a greater use of roundabouts with urban freight- roadway networks and their feasibility is analyzed in this study. The control for most urban intersections is a signalized treatment;a performance analysis is conducted for selected signalized intersections in urban freight-roadway networks, comparing the intersections by adapting a roundabout control theoretically using SIDRA (signalized and un-signalized intersection design and research aid) Intersection software. Various parameters, such as the intersection’s level of service, the effective intersection capacity, the average control delay, vehicular emissions [carbon dioxide (CO2), hydrocarbons (HC), carbon monoxide (CO), and nitrogen oxides (NOx)], the intersection’s annual delay, and the intersection’s annual cost, are selected for comparison.

Reconstructing a Six-Leg Intersection into Mohave County’s First Roundabout

Mohave County,Arizona maintains a six-leg intersection in the Golden Shores area bisected by an uncontrolled regional County highway,County Route 1,where two STOP-controlled section line local roads converge.The two-lane,rural CR 1 serves commuter and visitor traffic traveling between population centers of Lake Havasu City,AZ and Bullhead City,AZ/Laughlin,NV on the Colorado River and its desert lakes.The intersection features 180 total vehicle-to-vehicle conflict points inclusive of 126 crossing conflicts.This paper presents the County’s technical and administrative approach and techniques in planning and developing the CR 1“Six Points”roundabout given the(1)absence of fatal and incapacitating injury crash history and(2)backdrop of this improvement representing the County’s first roundabout.Project initiation entailed the County securing a Federal share of Highway Safety Improvement Program funding at 100-percent.Project design commenced with a preliminary engineering study to identify,evaluate,and solicit public input on alternative improvement solutions as part of validating the roundabout improvement as superior for traffic operations,community and business function,sitting,and constructability.Public input targeted preference for maintaining CR 1 uninterrupted flow versus interrupted flow introduced under roundabout circulation.This simple decision tree enabled the County to understand existing operational and access conditions important to the public,business owners,and public safety providers for purpose of configuring a roundabout improvement satisfying local motorist and community needs,which stoked stakeholder buy-in on the project.

Investigating the Possibilities of Specific Crash Type at Roundabouts

A comprehensive analysis of road crashes is extremely supportive in identifying existing deficiencies and in proposing new the design strategies. There are several research studies carried out for improving safety at roundabouts with the aim to altering conflict types, reducing the drivers’ speeds and crash severity, and highlighting a considerable differences in the safety performance of individual or group of roundabouts. The main purpose in this study was to explain the correlation between the types of crashes to the geometry of the roundabouts based on data collected from ten top poorly performing roundabouts in Toowoomba, Australia. Preliminary analysis revealed the following as top three types as prominent at these identified roundabouts such as angle crashes (74%), hit-object crashes (13%), and Rear-end crashes (9%). Excess proportion of specific crash method has been used as methodological tool to estimate the potential possibilities for a specific crash type exceeding threshold at each roundabout. Results show that eight out of ten roundabouts were regarded for a particular type of crash but only two roundabouts were viewed for two types of crashes such as angle and hit-object.