Vehicle Motion Prediction at Intersections Based on the Turning Intention and Prior Trajectories Model

Intersections are quite important and complex traffic scenarios,where the future motion of surrounding vehicles is an indispensable reference factor for the decision-making or path planning of autonomous vehicles.Considering that the motion trajectory of a vehicle at an intersection partly obeys the statistical law of historical data once its driving intention is determined,this paper proposes a long short-term memory based(LSTM-based)framework that combines intention prediction and trajectory prediction together.First,we build an intersection prior trajectories model(IPTM)by clustering and statistically analyzing a large number of prior traffic flow trajectories.The prior trajectories model with fitted probabilistic density is used to approximate the distribution of the predicted trajectory,and also serves as a reference for credibility evaluation.Second,we conduct the intention prediction through another LSTM model and regard it as a crucial cue for a trajectory forecast at the early stage.Furthermore,the predicted intention is also a key that is associated with the prior trajectories model.The proposed framework is validated on two publically released datasets,next generation simulation(NGSIM)and INTERACTION.Compared with other prediction methods,our framework is able to sample a trajectory from the estimated distribution,with its accuracy improved by about 20%.Finally,the credibility evaluation,which is based on the prior trajectories model,makes the framework more practical in the real-world applications.

A Statistical Model for Investigating Climatic Trend Turning Points

A two-phase trend model is presented to investigate the turning-point signals of evolution trend in long-term series of a climatic element. Based on nonlinear fitting, the revised model brings out more evident improvement of the linear model proposed by Solow et al. (1987). Both theoretical deduction and case calculation show that our version can search the turning point and period accurately and objectively. In particular it is fit for computer exploring the turning points in long-range records from stations covering a large area, thus avoiding subjective judgement by a usual drawing method.

Adaptive tracking algorithm based on 3D variable turn model

Satisfactory results cannot be obtained when three-dimensional (3D) targets with complex maneuvering characteristics are tracked by the commonly used two-dimensional coordinated turn (2DCT) model. To address the problem of 3D target tracking with strong maneuverability, on the basis of the modified three-dimensional variable turn (3DVT) model, an adaptive tracking algorithm is proposed by combining with the cubature Kalman filter (CKF) in this paper. Through ideology of real-time identification, the parameters of the model are changed to adjust the state transition matrix and the state noise covariance matrix. Therefore, states of the target are matched in real-time to achieve the purpose of adaptive tracking. Finally, four simulations are analyzed in different settings by the Monte Carlo method. All results show that the proposed algorithm can update parameters of the model and identify motion characteristics in real-time when targets tracking also has a better tracking accuracy.

Modelling and Analysis of Turning Motion of a Subsurface Mapping AUV with Split-Hull Design

There is much need for autonomous underwater vehicles(AUVs)for inspection and mapping purposes.Most conventional AUVs use torpedo-shaped single-rigid hull,because of which their manoeuvrability is limited.Moreover,any increase in payload results in a larger hull size and the turning diameter,limiting its operation in constrained areas.As a solution to this problem,we develop M-Hull,a subsurface mapping AUV with a modular-split hull design that provides better manoeuvrability than a conventional torpedo-shaped vehicle.At the same time,it has more agility than an unconventional bio-inspired snake-like vehicle though their designs look similar.This approach makes it a hybrid solution between conventional torpedo-shaped AUVs and unconventional bio-inspired vehicles.We focus on improving the turning diameter during the mapping operation,and hence this paper concentrates on the dynamic aspects of the 2D turning motion of the vehicle.It will provide the relationship between turning speed,thrust,and joint torque requirements for the multi-hull underwater vehicle.Different turning modes are compared to choose an optimum turning configuration,and the critical speed is calculated for the vehicle's safe operation.In the end,the modelling is verified using the experimental data.One can follow the method followed here for the 2D motion analysis of similar underwater vehicles.

Modeling and Simulation of Laser Assisted Turning of Hard Steels

This research work is focused on simulation of laser assisted turning as a new solution for machining of hard steels. A transient, three-dimensional model was developed to predict the temperature distribution of a rotated cylindrical steel workpiece subjected to a localized heating using a moving Gaussian laser beam. In this regard, a User-Defined Function was created to overcome the problem of a moving Gaussian heat source’ definition. This User-Defined Function was compiled into a finite volume software package (Fluent), where three-dimensional single precision solver was used for analysis. Based on this model, simulation of the surface temperature of 32 mm diameter workpiece of AISI51 50H steel was performed as a function of time at a specific distance behind the laser beam spot, which is corresponding to 30° angle from the laser beam. The simulation results were compared with other published data of the same steel type where a close agreement was obtained. The verified model was used for simulation of laser assisted turning of 20 mm diameter workpiece of AISI D2 tool steel. The cutting depth, behind the laser beam, was set at a distance corresponding to 60° angle from the laser beam for having sufficient access for handling both laser head and cutting tool. This cutting depth was studied as a function of different lasers and machining parameters. The results indicated that the optimum parameters for successful laser-assisted turning process of the concerned steels are 800 W laser power, 5 mm laser beam spot diameter, 20 sec preheating time, 0.8 mm/sec laser scanning speed, 300 rpm rotational speed and 0.8 mm/sec feed rate. These parameters ensure easy/successful cutting of 1 mm depth in one pass without deteriorating the properties of the remaining bulk material. It can be deduced that the developed model might provide a useful tool for online process control of different steel types regardless of their physical properties and geometries.

Artificial Neural Networks Based Integrated Predictive Modelling of Quality Characteristics in CNC Turning of Cantilever Bars

The objective of this study is to develop an effective approach for product quality prediction in Computer Numerical Control turning of cantilever bars. A systematic predictive modelling procedure based on experimental investigations, neural network modelling and various statistical analysis tools is designed to produce the most accurate, practical and cost-effective prediction model. The modeling procedure begins by exploring the relationships between cutting parameters known to have an influence on quality characteristics of machined parts, such as dimensional errors, form errors and surface roughness, as well as their sensitivity to the process conditions. Based on these explorations and using numerous statistical tools, the most relevant variables to include in the prediction model are identified and fused using several artificial neural network architectures. An application on CNC turning of cantilever bars demonstrates that the proposed modeling procedure can be effectively and advantageously applied to quality characteristics prediction due to its simplicity, accuracy and efficiency. The experimental validation reveals that the resulting prediction model can correctly predict the quality characteristics of machined parts under variable machining conditions.

A hybrid model of a subminiature helicopter in horizontal turn

A hybrid model of a subminiature helicopter in horizontal turn is presented. This model is based on a mechanism model and its compensated neural network （NN）. First, the nonlinear dynamics of a sub-miniature helicopter is established. Through the linearization of the nonlinear dynamics on a trim point, the linear time-invariant mechanism model in horizontal turn is obtained. Then a diagonal recursive neural network is used to compensate the model error between the mechanism model and the nonlinear model, thus the hybrid model of a subminiature helicopter in horizontal turn is achieved. Simulation results show that the hybrid model has higher accuracy than the mechanism model and the obtained compensated-NN has good generalization capability.

A model for the response of wave directions in slowly turning wind fields

On the basis of the wave energy balance equation, the response model of mean directions of locally wind-generated waves in slowly turning wind fields has been derived. The results show that in a homogeneous field, the time scale of the response is not only related to the rate of wave growth, but also to the directional energy distribution and the angle between the wind direction and the mean wave direction. Furthermore, the law of change in the mean wave direction has been derived. The numerical computations show that the response of wave directions to slowly turning wind directions can be treated as the superposition of the responses of wave directions to a series of sudden small-angle changes of wind directions and the turning rate of the mean wave direction depends on the turning rate and the total turning angles of the wind direction. The response of wave directions is in agreement with the response for a sudden change of wind directions if the change in wind directions is very fast. Based on the normalized rates of wave growth under local winds presented by Wen et al. (1989), a quantitative estimate of the time scale of the response shows that the relationships between the dimensionless time scale and both the dimensionless total wave energy and the dimensionless peak frequency agree fairly well with the observations in comparison with other models.

Turn-Taking Modelinthe Chinese Recruitment Reality show——Belong to You

Based on the theories of conversational analysis proposed by Sacks et al,this paper chooses excerpts of candidates' interview from the Chinese recruitment reality TV show Belong to You in Tianjin TV. Through analyzing the excerpt, how the rules of turn-taking are applied in this program will be demonstrated. And the features of turn-taking strategies used by the host,candidates and bosses will be concluded.

行人过街模拟及车辆右转避障路径规划方法

为解决无信号十字路口右转车辆与同侧过街行人的交互冲突问题,提出一种模拟过街行为的行人过街运动模型,设计了车辆横纵向解耦避障路径规划算法,并进行了仿真实验。使车辆面向动、静态行人时能合理切换避障路径规划策略;同时,将过街运动模型驱动下的行人作为车辆避障对象,以过街模型输出的行人未来轨迹生成车辆纵向速度规划障碍位移—时间区域,从而让行人未来运动状态反馈到车辆避障中。结果表明:本文的行人过街运动模型相对观测值的准确率达到了90%,因此,该模型复现了行人过街过程;能根据行人运动状态切换避障方案,使车辆安全避让过街行人。

基于自航模的某海洋调查船回转性能数值研究

本文针对某海洋调查船在实船海试过程中出现回转横倾角过大问题,采用基于RANS方程的数值模拟技术结合自航模型对其回转性能进行数值模拟,获得了其回转性能预报结果,为了减小该船回转过程中的横倾角,对船底呆木开展改进设计,获得呆木改进设计方案后该船的回转性横倾。通过对比分析可知,改进方案有效降低了回转过程中的横倾角,避免了回转中横倾过大的问题,为该船的顺利交付提供了技术支撑。

信控交叉口借道左转设计的延误优化研究

为准确分析交叉口借道左转设计的左转延误,针对现有的延误模型的不足,建立一个合适的延误优化模型,并提升其设置的科学性。先对逆向车道长度进行优化;再通过分析左转车辆的累计到达驶离曲线,以左转总延误最小为优化目标,建立一种新的考虑预信号延误的优化模型;最后,以长沙市芙蓉中路一个交叉口为实例,进行验证,分析左转到达流率对借道左转设计延误的影响及逆向车道长度对左转车均延误的影响。研究结果表明:左转流率越大,越能充分发挥借道左转设计的优势,该模型的左转延误下降可达59.21%;当左转流量偏低时,预信号位置的延误占比较大,随着左转流量的增大,传统车道和逆向车道的延误占比逐步增加。该研究可以准确评价借道左转设计的实用性和优劣程度,对借道左转设计的推广与应用具有重要意义。

两相位信号交叉口右转车辆礼让行人特征分析

为了提高两相位信号交叉口右转车辆与过街行人的通行安全,构建了基于多元有序Logistic模型的礼让意向模型以寻找影响右转车辆礼让行人意向的因素。在现有研究因素是否对右转车辆礼让行为产生影响的基础上,将右转车辆的礼让方式进一步细分为“软礼让”和“硬礼让”,以“不礼让、硬礼让、软礼让”3种礼让程度作为因变量,选取12个因素作为自变量构建礼让意向模型。为分析不同因素对右转车辆礼让行人意向影响的差异性,构建自变量在礼让模型中的优势比k。结果表明:右转车辆车速、人行横道长度、行人过街规模等因素k值大于1,表明这些因素增加了右转车辆对行人主动实施礼让的意向;行人行走在11~20 m长度的人行横道上会在最大程度上促使右转车辆停车礼让行人。

面向数控车床的切削加工仿真方法

针对现有数控加工仿真系统中存在的加工过程动态仿真效果差、切削加工仿真类型有限以及系统交互性不足等问题,结合加工工件的几何外形和成形特征,采用基于二维边界表示法(B-rep)模型生成算法,实现回转体工件模型的快速生成和更新。在虚拟数控车床上的应用实验表明,该方法能够高效地生成和更新工件模型,满足实时监控的要求。基于布尔运算的二维B-rep多边形切削算法实现了内径加工、外径加工和螺纹加工3种切削类型的加工模拟,提升了系统的仿真能力和灵活性。

面向转向制动工况的制动力动态分配策略

受轮胎侧偏、载荷横移等因素的影响,汽车在转向制动工况下的动力学行为比直线制动更复杂。深入探究该工况下改善汽车循迹能力的制动力分配策略,对于保障行车安全具有重要意义。对此,本文以电子机械制动为载体,进一步研究转向制动工况下的制动力分配策略。首先,以2自由度汽车动力学模型为参考,基于模型预测控制算法求解汽车保持稳定行驶时前和后轴车轮所需的最低侧向力。然后,通过在线求解附着椭圆得出可供各车轮制动的最大纵向力。在此基础上,以最大纵向力为依据进一步计算制动力分配系数,实现制动力优化分配。仿真和试验结果表明:所提出的制动力分配策略能够根据汽车行驶工况、载荷状态和路面附着条件动态调节制动力分配比例,提升了转向制动工况汽车的循迹能力。

基于再生能利用的地铁多车协同折返优化研究

折返站作为影响线路发车上限的重要因素,影响着整条线路的运营效率,也是能量浪费较为严重的地方。因此,有必要在兼顾线路运营效率的前提下减少列车折返运行的能耗。为此,通过提出基于再生制动能量利用的列车折返问题对列车的节能运营进行研究。通过建立底层网络图,构建以列车折返为基础考虑再生制动能量利用的能耗优化模型。为提高模型的求解能力,引入辅助变量将其转变为线性化模型。以上海地铁某折返站作为实例对象,借助Gurobi进行求解并对能耗等数据进行分析,证实模型有效。由该模型得到的折返时刻图在保证折返能力的同时,列车能耗与原始折返方式相比降低了5.74%,为考虑再生制动能量利用的列车折返运营方式提供一定的理论支撑与依据。

考虑右转车干扰的信号交叉口直行车辆轨迹预测

相交道路右转车辆干扰下的直行车辆轨迹扰动现象成为城市道路信号交叉口交通运行的安全隐患,为提高直行车驾驶人对驶入右转车辆的应对能力并做出正确决策,对于直行车辆扰动轨迹的可靠预测至关重要。研究通过将不同状态下的直行车辆轨迹分布特征与相交道路右转车运行信息相关联,在车辆受扰轨迹识别的基础上将碰撞时间(TTC)指标作为输入层加入模型,构建了3层高斯混合-输入输出隐马尔可夫模型(GMM-IOHMM),提出了一种考虑信号交叉口被交道路右转车对本面直行车作用程度的直行车辆受扰轨迹预测方法。实验结果表明:改进模型相比于传统的隐马尔可夫模型(HMM)在模型训练时能够更好地拟合实际的轨迹数据,且相比于传统的时间序列模型,GMM-IOHMM模型的拟合效果取得较大提升;可将TTC≤4.5 s且偏航角大于2.35°作为直行车辆轨迹扰动的判别标准。轨迹预测结果能够更加准确地判断直行车辆与周围车辆发生冲突的可能性,可作为受扰直行车及同行其他车辆辅助驾驶系统设计的重要依据。

考虑坐标耦合的三维变结构多模型机动目标跟踪方法

在3维空间机动目标跟踪过程中,目标运动先验未知和坐标耦合误差会引起运动模型-模式失配,而模型-模式失配会引起状态估计有偏。该文根据目标运动速度正交条件修正状态转移矩阵,利用原始-对偶正则约束空间测量到球面可行域,结合自适应转弯率模型和无迹卡尔曼滤波(UKF),进行模型状态滤波并融合状态估计的一致输出,推导3维变结构多模型无迹卡尔曼滤波(VSMMUKF)算法。实验结果表明,相比多模重要性无迹卡尔曼滤波(MIUKF)算法,VSMMUKF计算量相当,能够更准确地拟合3维空间点目标机动运动。相比于交互多模型最大最小粒子滤波(IMM-MPF)算法,VSMMUKF跟踪固定翼无人机(UAV)的滤波精度提升了2.8%~59.9%,整体算法负担减小了1个数量级。

感应电机匝间短路暂态分析及实用辨识方法

感应电机匝间短路是常见的故障类型,可能引发相间短路或接地短路,严重影响系统稳定性。针对电机匝间短路暂态分析及辨识问题,基于匝间短路模型分析了故障期间定子电流、电磁转矩、转速的暂态特性,研究了不同故障支路电阻与短路绕组系数对短路电流的影响。在此基础上,提出了一种以电流矢量为特征量的匝间短路实用辨识方法,最后通过一台1600 kW感应电机验证了方法的有效性。

1 MHz硅器件LLC-DCX变换器设计与优化

LLC-DCX变换器的软开关特性可以显著降低开关损耗及器件应力,在航空航天等高功率密度要求的场景下,是一种实现母线电压变换以及电气隔离功能的优异拓扑。高功率密度意味着高开关频率,但在这些应用场景下宽禁带器件的应用受到了限制。这里讨论了传统硅器件在高频LLC-DCX变换器中的设计与应用,通过对变换器在死区时间内的等效电路进行时域分析,推导得到一个考虑同步整流管结电容影响的零电压开通条件。进一步利用状态平面建模方法推导了轻载下同步整流管的精确导通时间,提出一种开环同步整流控制策略,有效提高了变换器的轻载效率。最后,研制了一台基于硅器件的1 MHz LLC-DCX变换器样机,实验结果验证了所提设计方法及控制策略的有效性。