Origin-destination trip table estimation based on subarea network OD flow and vehicle trajectory data

Identifying accurate origin-destination (O-D) travel demand is one of the most important and challenging tasks in the transportation planning field. Recently, a wide range of traffic data has been made available. This paper proposes an O-D estimation model using multiple field data. This study takes advantage of emerging technologies – car navigation systems, highway toll collecting systems and link traffic counts – to determine O-D demand. The proposed method is unique since these multiple data are combined to improve the accuracy of O-D estimation for an entire network. We tested our model on a sample network and found great potential for using multiple data as a means of O-D estimation. The errors of a single input data source do not critically affect the model’s overall accuracy, meaning that combining multiple data provides resilience to these errors. It is suggested that the model is a feasible means for more reliable O-D estimation.     

双缸推动型船舶电动舵机的同步控制技术

为解决当前液压伺服操控滞后、精度不足等缺点,提出了基于双交流同步伺服电机的船舶电动舵机操控模式,并给出了实现其一致性操控方法,最后通过采用原理样机操控方法对系统的精确性与有效性进行了验证,结果显示该双摆缸同步操控模式及其一致性控制方法已具备了实船装配的工程基础与工程价值。     

基于车辆轨迹的信号交叉口机非冲突判别

选取长沙市中心区4个典型信号交叉口,利用视频轨迹追踪软件,提取右转机动车与直行非机动车的冲突交通流轨迹数据.以减速、换道等避险行为与可能发生碰撞(距离碰撞点时间小于2 s)为依据,采集机非冲突样本;选择距离碰撞最大时间(MTTC)和冲突时间差(TDTC)作为评价指标,提出一种基于交通流运行轨迹的改进型TTC(Time ...     

盾构推进姿态控制策略研究

为提高盾构施工过程中姿态控制系统的控制精度和控制性能,提出一种盾构推进姿态控制策略。该策略将轨迹自动跟踪控制方法与模糊自适应PID闭环控制算法相结合,通过轨迹、位移、压力等多个闭环反馈实现对各个分区液压缸的速度控制,保证盾构推进轨迹按照设计的隧道轴线运行,并通过电液控制试验平台中的推进系统对提出的策略进行试验验证。结果表明,文章提出的控制策略能够使位移偏差维持在5 mm之内,可以很好地满足施工要求。     

基于多特征融合的行人意图以及行人轨迹预测方法研究

行人作为重要的交通参与者,其行走意图和轨迹预测对智能驾驶汽车的决策规划具有重要意义。基于注意力机制增强的长短时记忆(Long Short-term Memory, LSTM)网络,设计一种多特征融合的行人意图以及行人轨迹预测方法。该方法通过融合行人骨架和头部方向特征,以加强行人运动特征的表达,并将融合特征作为意图预测网络输入,继而得到行人意图;由于行人运动具有不确定性,将行人意图预测类别和历史轨迹坐标的联合向量作为行人轨迹预测网络的输入,以期生成更为精确的轨迹预测结果。此外,在轨迹预测网络中引入注意力机制,以加强LSTM对各个时刻编码向量的有效利用,从而提高网络的行人轨迹预测性能,并基于Daimler数据集进行训练及验证。研究结果表明：所提出的多特征意图预测方法准确率可达96.0%,优于基于骨架单特征的意图预测网络;在预测时域为1 s的情况下,预测轨迹的位置均方根误差为347 mm,相较于恒速度(Constant Velocity, CV)模型、交互多模型(Interacting Multiple Model, IMM)、常规LSTM等基线方法均有明显的提升;在实际场景分析中,提出的方...     

Modeling and simulation of torpedo acoustic homing trajectory with multiple targets

1Introduction Homingtrajectoryisthemostimportantaspectwithin exteriortrajectoryofanacoustichomingtorpedo.Thus,homingtrajectoryshouldreceivemuchattention intorpedotrajectorysimulations.Inthisresearchpro ject,atorpedoacoustichomingtrajectorysimulation progr…     

掺石灰对高液限土击实试验的影响

石灰作为一种有效的外掺剂可以显著降低其液塑限.为了指导施工,保证路基的压实质量,对不同灰剂量的石灰土进行标准击实试验,可得出最大干密度和最佳含水量随灰剂量的变化规律.     

鱼雷跟踪目标深度起伏机理分析及全弹道数学仿真研究

针对鱼雷跟踪目标时的深度起伏现象，从水声传播原理和鱼雷跟踪目标时深度平面的控制原理进行了理论分析，给出了等效声线的建模方法，通过设置工况条件，对鱼雷进行了全弹道数学仿真，得到了与实际情况基本相符的结果，验证了理论分析的正确性。     

INDU网络的解析表达及其一致性计算

INDU网络在区间代数的基础上引入了时间区间的长度，细化了时间区间之间的定性关系，使得时间定性推理的精确性有所提高。本文给出了INDU网络的0维、1维及2维的共计25个解析公式，用解析的方法来刻画INDU网络，并用它来实现INDU网络全局解的一致性计算。     

Dangerous driving behavior detection using video-extracted vehicle trajectory histograms

Dangerous driving behavior detection can be used in video surveillance systems to identify dangerous patterns, such as Abrupt Double Lane Change (ALC), Retrograde Driving (RD), and Illegal U-Turn (IT), for traffic design, traffic management, and law enforcement. The purpose of this study is to develop a detection method of dangerous driving behavior based on video surveillance. First, a novel method named trajectory histogram is proposed. A set of trajectory histograms (e.g., control points histogram and velocity histogram) is constructed to represent vehicle motion. Then, a frequently used feature selection method named Minimum Redundancy and Maximum Relevance (mRMR) is introduced to evaluate the most representative trajectory histograms for dangerous driving behavior detection. In addition, a hybrid algorithm, Particle Swarm Optimization-Support Vector Machine (PSO_SVM), is then developed to identify dangerous driving behavior. To validate the performance and effectiveness of the proposed method, several experiments are conducted. The results show that mRMR is better than other representative methods, namely Conditional Mutual Information Maximization (CMIM), Mutual Information Maximization (MIM), and ReliefF, for evaluating the most representative trajectory histograms. Based on the most representative trajectory histograms, the detection accuracy rate of dangerous driving behavior using PSO_SVM is superior to those of the most frequently used classifiers—Naïve Bayesian Classifier (NBC), k-Nearest Neighbor (kNN), and C4.5 decision tree. In addition, we find that the proposed method outperforms the two common approaches for dangerous driving behavior detection in video surveillance systems. Therefore, the proposed method can be widely applied to detect dangerous driving behavior in video surveillance systems.