基于毫米波雷达的机动目标跟踪算法研究

针对复杂交通环境下高机动目标难度大,易丢失的问题,提出一种适合机动目标的毫米波雷达跟踪流程。首先,提出一种适合毫米波雷达数据的跟踪门——基于规则的自适应跟踪门,能够根据雷达探测范围,目标属性自适应调整跟踪门。然后,根据目标高机动特性,选择匀速模型和匀加速模型为跟踪模型,利用交互式多模型算法跟踪目标。实验结果表明：交互式多模型算法较典型卡尔曼滤波跟踪精度提高18.26%;论文方法跟踪雷达目标准确度提高5.303%,虚警率下降0.813%。     

雷达/红外双模导引头信息融合算法研究

毫米波雷达/红外成像复合制导已成为当前多模复合制导技术的研究热点。从毫米波雷达/红外成像复合导引头系统的特点出发,利用粒子滤波算法替换交互式多模型算法中的次优滤波器,建立了一种基于交互式多模型粒子滤波的集中式雷达/红外双模导引头信息融合算法;该算法将交互式多模型与粒子滤波相结合,有效地解决了系统非线性非高斯条件下的机动目标跟踪问题;仿真结果表明,在系统模型非线性和非高斯的条件下,提出的算法性能要大大优于传统的基于EKF的交互式多模型算法,同时提出算法对目标机动模式的变化很敏感,能够快速响应目标的机动,跟踪精度大大提高。     

基于TsFresh-Stacking的毫米波雷达人体跌倒检测方法

针对雷达频谱图空间信息较少,且通过单一机器学习算法进行毫米波雷达人体跌倒行为识别精度低、稳定性差的问题,使用人体空间雷达点云时序数据,提出了融合TsFresh特征提取和Stacking堆叠集成学习的跌倒识别方法。首先,采用TI-IWR6843毫米波雷达采集人体动作对应的人体运动跟踪时序数据,构建包含不同年龄、身高、体重信息、跌倒方式的数据集。其次,结合TsFresh时序特征提取工具和基于随机森林模型的特征重要性提取人体跌倒关键时序特征。最后,提出了融合随机森林、支持向量机、K-最邻近算法、XGBoost和CatBoost 5种单元机器学习模型的Stacking堆叠式集成学习方法。结果表明,与典型单一机器学习算法相比,Stacking集成学习算法具有明显的性能提升,能够有效提升人体跌倒行为识别准确性和泛化性。     

基于SystemVue汽车雷达系统研究

针对毫米波雷达射频、信号处理以及超分辨测角问题,提出了一种基于SystemVue进行汽车雷达系统设计和信号处理算法设计的方法。首先,利用SystemVue自带的射频库和通用算法库进行雷达系统设计,真实模拟了毫米波射频、天线及目标环境的相互影响;其次,针对快调频的FMCW信号波形,给出了完整的汽车雷达目标距离、速度和角度的信息处理算法流程;最后,针对汽车雷达系统测角精度较低的问题,提出了基于酉变换MUSIC的测角算法,大大降低了汽车雷达超分辨求角的运算量。仿真结果表明,该方法解决了汽车雷达的链路设计、射频指标对雷达信号处理性能影响的评估问题,更真实、更全面地反映了汽车雷达系统的性能,为雷达系统的研究提供了有力依据。     

基于IR/MMW复合导引头信息融合的目标模拟器设计

我们设计了一种旨在评估凝视红外和毫米波雷达信息融合处理器硬件设计方案的正确性及目标跟踪滤波算法的抗干扰性能和对机动目标跟踪的稳定适应性能的目标模拟器;结合红外和雷达探测目标的原理介绍,详细阐述了红外成像和毫米渡雷达前端信号检测获得的目标状态信息的模拟方法及动态攻击仿真软件的结构框架设计和具体编程实现方法;最后通过动态攻击仿真实例和单双模跟踪精度对比,说明了目标模拟器设计的有效性.     

智轨电车多源环境感知系统

智轨电车的多源环境感知系统是车载平台与运行环境的交互纽带,其包括基于激光雷达的障碍物感知子系统、基于毫米波雷达的前侧向障碍物感知子系统以及基于多摄像头的360度环视子系统。基于激光雷达的障碍物感知子系统采用地面分割算法、点云聚类算法和数据关联算法,实现了对运行前方障碍物的检测和跟踪;基于毫米波雷达的前侧向障碍物感知子系统采用目标检测算法和跟踪算法,实现侧向以及前向障碍物探测;基于分布式鱼眼摄像头的360度环视子系统运用图像拼接算法,实现智轨电车周围障碍物感知和预警。实车试验结果表明,该环境感知系统可有效地提高智轨电车的运行安全系数,为车辆智能驾驶提供了全面的环境信息。     

一种基于动态规划的机动目标检测前跟踪方法

针对传统动态规划检测前跟踪算法仅适用于匀速直线运动目标或慢机动目标的局限性,提出了一种将交互式多模型(IMM)滤波与基于动态规划的检测前跟踪算法相结合的机动目标处理算法。该算法应用于近程毫米波雷达探测环境下,根据被测目标的实际运动情况建立了匀加速运动、匀速转弯运动及匀速运动模型,在动态规划算法基础上考虑了多种运动模型以及模型之间的转换和预测,避免了因模型不匹配导致的跟踪效果变差的问题。仿真结果显示,相比于传统动态规划检测算法,该算法能够更加有效地实现对机动目标的检测和跟踪,适于工程应用。     

基于红外相机和毫米波雷达融合的夜间行人检测

为了提升夜间环境行人检测的能力,使用红外相机和毫米波雷达进行信息融合.对两传感器数据进行时间配准并分别进行处理,利用改进YOLO算法处理红外图像得到目标类别特征,处理毫米波雷达数据获得目标的距离和速度特征,再建立空间对准模型对两传感器进行目标匹配,最后利用基于特征的融合算法完成夜间行人多模态信息输出.两传感器检测目标首次匹配之后,可以将类别信息反馈给雷达数据处理单元进行记录,当红外图像检测算法漏检时,利用雷达记录的信息补充输出类别特征.通过实验证明该融合算法提升了单一传感器行人检测成功率,在夜间场景具有良好的应用效果.     

汽车巡航控制用传感器进展

自主智能巡航控制系统利用前视雷达传感器收集前方道路上交通和障碍物的信息。毫米波雷达和激光雷达是常用于汽车自主智能巡航控制的雷达传感器 ,介绍了这两种汽车传感器的工作原理、技术指标和发展趋势     

毫米波雷达点云的高速公路隧道车辆跟踪

针对高速公路隧道车辆跟踪问题,提出一种基于毫米波雷达的低成本解决方案.首先,通过毫米波雷达获取场景目标点云信息,根据每一帧内点云位置、速度以及峰值特点,滤除静态目标与杂波;其次,采用取重心的方法对点云进行匹配,实现感兴趣的车辆目标信息的提取;最后通过相邻帧的时间差预测目标点云下一位置,从而实现不同帧间目标数据匹配跟踪,...     

Vehicle collision risk estimation based on RGB-D camera for urban road

Traffic violation is the main cause of traffic accidents. To reduce the incidence of traffic accidents, the common practice at present is to strength the penalties for traffic violation. However, little attention has been paid to issue warning for dangerous driving behaviors, especially for the case where two vehicles have a good chance of collision. In this paper, a framework for collision risk estimation using RGB-D camera is proposed for vehicles running on the urban road, where the depth information is fused with the video information for accurate calculation of the position and speed of the vehicles, two essential parameters for motion trajectory estimation. Considering that the motion trajectory or its differences can be considered as a steady signal, a method based on autoregressive integrated moving average (ARIMA) models is presented to predict vehicle trajectory. Then, the collision risk is estimated based on the predicted trajectory. The experiments are carried out on the data from the real vehicles. The result shows that the accuracy of position and speed estimation can be guaranteed within urban road and the error of trajectory prediction is very minor which is unlikely to have a significant impact on calculating the probability of collision in most situations, so the proposed framework is effective in collision risk estimation.     

No-beacon collective circular motion of jointly connected multi-agents

In this paper, a decentralized control algorithm is proposed for a group of nonholonomic vehicles to form a class of collective circular motion behavior. Without the guidance of a global beacon, the desired collective behavior occurs provided that the multi-agent system is jointly connected. Moreover, a repulsion mechanism is considered to improve the distribution evenness of the agents’ circular motion phases and hence to avoid collision. The effectiveness of the approach is verified through both theoretical analysis and numerical simulation. Moreover, some interesting variations of the circular motion model are investigated to enrich the collective behaviors.     

A collisions evaluation method in virtual environment for collaborativeassembly

Collision detection is critical for collaborative assembly simulation to assist design processing. However, collisions between polygonal models may not reflect collisions between real objects in reality because of polygonal approximation and designed tolerance. This problem reduces the reliability of simulation in collaborative assembly and sometimes even results in wrong conclusions. To solve the problem, we propose a novel collision evaluation algorithm based on generalized penetration depth, approximation information, and tolerance information. Given two interfered polygonal models, generalized penetration depth is calculated using relative motion information. Then two thresholds, which are based on approximation information and tolerance information, are integrated to evaluate collisions between polygonal models. In order to distinguish the status of collisions for further analysis, the collisions between polygonal models are categorized into three types by evaluation algorithm, namely real collision, potential collision, and fake collision. Computational efficiency and accuracy of the evaluation algorithm are verified in a virtual collaborative assembly environment.     

Vega环境中机动车辆运动仿真的研究和实现

大多数在Vega平台上进行的车辆运动仿真,只是将车体作为一个质点进行处理,在仿真过程中,当车体通过不平坦的路面时,不能随地形起伏改变车体的姿态,仿真的真实感和可靠性很差.通过分析车辆的运动数学模型,建立了三维空间的运动方程组,并结合名为"TRIPDO"相交矢量方法给出了一种通用解决算法和Vega程序实现.结果表明使用了这种解决方法的仿真应用,所仿真的车辆都能够随地形的起伏实时改变姿态,车辆运动仿真的真实感和可靠性显著增强.     

共线三球链问题的碰撞动力学研究

共线三球链的碰撞动力学问题能够展示多刚体系统碰撞问题的困难之一：非唯一解的问题.本文建立了三球链碰撞的Hertz接触模型,研究对其求解的数值算法,并用有限元模型（FEM）对其进行验证,研究表明：同线性模型比较,采用Hertz接触力模拟小球之间的接触力更接近有限元计算结果;在Hertz接触模型基础上,分析碰撞过程中接触力的变化过程;研究刚度比和质量比对于碰撞结束后各个小球运动状态的影响,并研究了两种刚体模型下碰撞次序假设成立的条件.     

基于图像处理的交通事故检测及责任判定

为了在发生轻微交通事故时, 快速使事故车辆驶离现场, 保证道路畅通, 提出了一种车辆碰撞检测及责任判定模型. 首先结合SSD目标检测算法(single shot multibox detector)和MobileNet轻量级深度网络模型, 对其进行改进以获取每一帧视频图像中运动目标的位置和大小信息, 实现对车辆识别与检测. 其次, 利用卡尔曼滤波器对连续图像帧之间的运动目标建立对应匹配关系, 预测目标的运动状态, 对目标的位置及运动趋势做出判断, 实现车辆轨迹跟踪. 随后通过车辆目标检测框的交并比判断是否发生碰撞. 最后针对直行道路中车辆的速度、方向信息结合道路安全条例及机动车事故快速方法对事故车辆进行责任判定. 结果分析表明, 该研究可实现直行道路场景下的追尾及变道引发的车辆碰撞检测及责任判定.     

Driver Intent Prediction and Collision Avoidance With Barrier Functions

For autonomous vehicles and driver assist systems, path planning and collision avoidance algorithms benefit from accurate predictions of future location of other vehicles and intent of their drivers. In the literature, the algorithms that provide driver intent belong to two categories: those that use physics based models with some type of filtering, and machine learning based approaches. In this paper we employ barrier functions (BF) to decide driver intent. BFs are typically used to prove safety by establishing forward invariance of an admissible set. Here, we decide if the “target” vehicle is violating one or more possibly fictitious (i.e., non-physical) barrier constraints determined based on the context provided by the road geometry. The algorithm has a very small computational footprint and better false positive and negative rates than some of the alternatives. The predicted intent is then used by a control barrier function (CBF) based collision avoidance system to prevent unnecessary interventions, for either an autonomous or human-driven vehicle.      

Highly-scalable traffic management of autonomous industrial transportation systems

In this paper, we present a novel method for highly-scalable coordination of free-ranging automated guided vehicles in industrial logistics and manufacturing scenarios. The primary aim of this method is to enhance the current industrial state-of-the-art multi-vehicle transportation systems, which, despite their long presence on the factory floor and significant advances over the last decades, still rely on a centralized controller and predetermined network of paths. In order to eliminate the major drawbacks of such systems, including poor scalability, low flexibility, and the presence of a single point of failure, in the proposed control approach vehicles autonomously execute their assigned pick-up and delivery operations by running a fully decentralized control algorithm. The algorithm integrates path planning and motion coordination capabilities and relies on a two-layer control architecture with topological workspace representation on the top layer and state-lattice representation on the bottom layer. Each vehicle plans its own shortest feasible path toward the assigned goal location and resolves conflict situations with other vehicles as they arise along the way. The motion coordination strategy relies on the private-zone mechanism ensuring reliable collision avoidance, and local negotiations within the limited communication radius ensuring high scalability as the number of vehicles in the fleet increases. We present experimental validation results obtained on a system comprising six Pioneer 3DX robots in four different scenarios and simulation results with up to fifty vehicles. We also analyze the overall quality of the proposed traffic management method and compare its performance to other state-of-the-art multi-vehicle coordination approaches.     

Establishing collision zones for obstacles moving with uncertainty

This paper presents a methodology to include obstacles moving with uncertainty in path planning algorithms. Around each moving obstacle, a collision zone is defined indicating a high collision likelihood space. These zones are treated as stationary obstacles providing the input to a path planning algorithm. Samples of moving obstacles' positions are assumed to be available. Three models of motion for moving obstacles are considered: (1) obstacles moving randomly, (2) obstacles whose motion is structured but consists of random parameters, (3) obstacles whose motion is predictable as a function of time. Simulation examples yielding collision zones are presented.     

Computer-oriented judgement of the collisions of robots in coordinate operation

Based on [1], this paper, using the principles of topology, discusses the collision avoidance problem of moving objects in higher-space and presents the practical algorithm for the solution, in 3D space, to the collision judgement of robots grasping convex polyhedrons with two arms in coordinate operation.This algorithm is well suited for the case in which robots are in complex motion. Furthermore, it becomes possible, by applying this algorithm, to predicate the time at which the collision may happen so that the countermeasure can be made as quickly as possible and the robots can be controlled in real time.This effective algorithm has been developed using the PASCAL language on the Victor9000 microcomputer system.