Real-time validation of vision-based over-height vehicle detection system

Over-height vehicle strikes with low bridges and tunnels are an ongoing problem worldwide. While previous methods have used vision-based systems to address the over-height warning problem, such methods are sensitive to wind. In this paper, we perform a full validation of the system using a constraint-based approach to minimize the number of over-height vehicle misclassifications due to windy conditions. The dataset includes a total of 102 over-height vehicles recorded at frame rates of 25 and 30fps. An analysis is performed of wind and vehicle displacements to track over-height features using optical flow paired with SURF feature detectors. Motion captured within the region of interest was treated as a standard two-class binary linear classification problem with 1 indicating over-height vehicle presence and 0 indicating noise. The algorithm performed with 100% recall, 83.3% precision, false positive rate of 0.2% and warning accuracy of 96.6%.     

Ensemble learning for wind profile prediction with missing values

In this paper, we aim to develop computational intelligence approaches for wind profile prediction. Specifically, we focus on two aspects in this work. First, we investigate the missing value recovery for wind data. Due to the complexity of data collection in such processes, wind data normally include missing values. Therefore, how to effectively recover such missing values for learning and prediction is an important aspect for wind profile prediction. Second, we develop an ensemble learning approach based on multiple neural network models. Our proposed method uses a new strategy based on the temporal information to assign the weights for each model dedicated for wind profile prediction to achieve better prediction performance. Various simulation studies and statistical testing demonstrate the effectiveness of our approach.     

可增量学习的水下航行器噪声源识别中聚类算法研究

水下航行器的噪声源识别具有训练样本有限,存在偶发或突变噪声源等特点。本文针对这些特点,在具有增量学习能力的水下航行器的噪声源识别系统架构下,提出了一种参数自适应可调的基于密度的聚类算法。实验表明,该算法可以有效避免基于密度的聚类算法的参数敏感性对聚类结果的不良影响,在无监督情况下对水下航行器的机械噪声源样本进行有效聚类。通过该聚类算法标注后的样本可直接作为具有增量学习结构的分类器的训练样本,节省了时间和系统开销。     

Spatiotemporal vehicle tracking: the use of unsupervised learning-based segmentation and object tracking

In this paper, a framework for spatiotemporal vehicle tracking using unsupervised learning-based segmentation and object tracking is presented. An adaptive background learning and subtraction method is proposed and applied to two real-traffic video sequences to obtain more accurate spatiotemporal information on the vehicle objects. As demonstrated in the experiments, almost all vehicle objects are successfully identified through this framework.     

风廓线雷达风谱的概率分布研究

研究风廓线雷达风谱的概率分布,对估计噪声水平、评价风谱形成算法的性能、提取风廓线回波的信息等等都有重要的作用和意义.目前,接收机噪声的谱的概率分布得到了较好的研究,而风廓线回波的谱的分布却缺少相应的分析,鉴于此,研究了风谱的概率分布.通过对雷达回波做合理的假设,在分析经典风谱形成算法的基础上,提出雷达噪声谱和风廓线回波的谱分别服从X2,分布和非中心X2分布.利用实际的雷达数据和计算机仿真的方法进行的分布的假设检验,说明该理论模型准确有效.     

Wind Estimation for Accurate Airplane Path Following Applications

This paper explores the flight of small fixed-wing Unmanned Aerial Vehicle (UAV) in a non-steady environment. The vulnerability of light airplanes to wind is analyzed and the effect of such perturbations on airplane performance is incorporated in the equations of motion. A straightforward wind computation approach, which relies on the difference between the predicted motion of the aircraft and the real motion measured by sensors, is presented in order to be used for a path following application. The analysis takes into account the effect of the noise in sensors measurements and in estimates of orientation and airspeed components. One approach to reducing noise in wind estimates is proposed based on on-line adaptation techniques. Parameter estimation with minimum-order design is obtained using tuning functions. Simulations are carried out representing real flight scenarios in which the wind field is not constant and the sensor measurements are imperfect.     

基于深度强化学习的网联车辆队列纵向控制

针对车辆队列中多目标控制优化问题,研究基于强化学习的车辆队列控制方法.控制器输入为队列各车辆状态信息以及车辆间状态误差,输出为基于车辆纵向动力学的期望加速度,实现在V2X通信下的队列单车稳定行驶和队列稳定行驶.根据队列行驶场景以及采用的间距策略、通信拓扑结构等特性,建立队列马尔科夫决策过程(Markov decision process,MDP)模型.同时根据队列多输入-多输出高维样本特性,引入优先经验回放策略,提高算法收敛效率.为贴近实际车辆队列行驶工况,仿真基于PreScan构建多自由度燃油车动力学模型,联合Matlab/ Simulink搭建仿真环境,同时引入噪声对队列控制器中动作网络和评价网络进行训练.仿真结果表明基于强化学习的车辆队列控制燃油消耗更低,且控制器实时性更高,对车辆的控制更为平滑.     

Vision-based approach towards lane line detection and vehicle localization

Localization of the vehicle with respect to road lanes plays a critical role in the advances of making the vehicle fully autonomous. Vision based road lane line detection provides a feasible and low cost solution as the vehicle pose can be derived from the detection. While good progress has been made, the road lane line detection has remained an open one, given challenging road appearances with shadows, varying lighting conditions, worn-out lane lines etc. In this paper, we propose a more robust vision-based approach with respect to these challenges. The approach incorporates four key steps. Lane line pixels are first pooled with a ridge detector. An effective noise filtering mechanism will next remove noise pixels to a large extent. A modified version of sequential RANdom Sample Consensus) is then adopted in a model fitting procedure to ensure each lane line in the image is captured correctly. Finally, if lane lines on both sides of the road exist, a parallelism reinforcement technique is imposed to improve the model accuracy. The results obtained show that the proposed approach is able to detect the lane lines accurately and at a high success rate compared to current approaches. The model derived from the lane line detection is capable of generating precise and consistent vehicle localization information with respect to road lane lines, including road geometry, vehicle position and orientation.     

Functional-type Single-input-rule-modules Connected Neural Fuzzy System for Wind Speed Prediction

Wind is one kind of clean and free renewable energy sources. Wind speed plays a pivotal role in the wind power output. However, due to the random and unstable nature of the wind, accurate prediction of wind speed is a particularly challenging task. This paper presents a novel neural fuzzy method for the hourly wind speed prediction. Firstly, a neural structure is proposed for the functional-type single-input-rule-modules (FSIRMs) connected fuzzy inference system (FIS) to combine the merits of both the FSIRMs connected FIS and the neural network. Then, in order to achieve both the smallest training errors and the smallest parameters, a least square method based parameter learning algorithm is presented for the proposed FSIRMs connected neural fuzzy system (FSIRMNFS). Further, the proposed FSIRMNFS and its parameter learning algorithm are applied to the hourly wind speed prediction. Experiments and comparisons are also made to show the effectiveness and advantages of the proposed approach. Experimental results verified that our study has presented an effective approach for the hourly wind speed prediction. The proposed approach can also be used for the prediction of wind direction, wind power and some other prediction applications in the research field of renewable energy.      

Locally recurrent neural networks for wind speed prediction using spatial correlation

This paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. Owing to the temporal complexity of the problem, we employ local recurrent neural networks with internal dynamics, as advanced forecast models. To improve the prediction performance, the training task is accomplished using on-line learning algorithms based on the recursive prediction error (RPE) approach. A global RPE (GRPE) learning scheme is first developed where all adjustable weights are simultaneously updated. In the following, through weight grouping we devise a simplified method, the decoupled RPE (DRPE), with reduced computational demands. The partial derivatives required by the learning algorithms are derived using the adjoint model approach, adapted to the architecture of the networks being used. The efficiency of the proposed approach is tested on a real-world wind farm problem, where multi-step ahead wind speed estimates from 15 min to 3 h are sought. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that the suggested learning algorithms outperform three gradient descent algorithms, in training of the recurrent forecast models.     

一种基于学习向量量化神经网络的图象分割方法

基于视觉传感器实现道路信息的理解是目前移动机器人自主导航的重要研究方向,其中道路图象的正确分割是提取有效路径信息的关键。该文针对复杂、干扰因素多的室外环境下传统方法难以实现道路图象正确分割的问题,提出了一种基于LV Q神经网络的道路图象分割方法。该方法通过选取道路图象的归一化色彩分量为特征向量,应用基于LV Q学习算法的神经网络分类器进行道路与非道路识别;为解决环境噪声对神经网络输出的影响,本文设计了串行级联式四阶形态滤波器实现对神经网络输出的分割图象的滤波处理。通过对实测图象进行分割处理验证了该方法的有效性和鲁棒性,可用于室外环境下机器人的实时视觉导航控制。     

Modeling and simulation of overtaking behavior involving environment

Overtaking is a complex driving behavior for intelligent vehicles. Current research on modeling overtaking behavior pays little attention on the effect of environment. This paper focuses on the modeling and simulation of the overtaking behavior in virtual reality traffic simulation system involving environment information, such as road geometry and wind. First, an intelligent vehicle model is proposed to better understand environment information and traffic situation. Then, overtaking behavior model is introduced in detail, the lane changing feasibility is analyzed and the fuzzy vehicle controllers considering the road and wind effect are researched. Virtual reality traffic simulation system is designed to realize the simulation of overtaking behavior, with realistic road geometry features. Finally, simulation results show the correctness and the effectiveness of our approach.     

A novel approach of noise statistics estimate using <Emphasis Type="Italic">H</Emphasis><Subscript>∞</Subscript> filter in target tracking

Noise statistics are essential for estimation performance. In practical situations, however, a priori information of noise statistics is often imperfect. Previous work on noise statistics identification in linear systems still requires initial prior knowledge of the noise. A novel approach is presented in this paper to solve this paradox. First, we apply the H_∞ filter to obtain the system state estimates without the common assumptions about the noise in conventional adaptive filters. Then by applying state estimates obtained from the H_∞ filter, better estimates of the noise mean and covariance can be achieved, which can improve the performance of estimation. The proposed approach makes the best use of the system knowledge without a priori information with modest computation cost, which makes it possible to be applied online. Finally, numerical examples are presented to show the efficiency of this approach.     

Error-driven active learning in growing radial basis function networks for early robot learning

In this paper, we describe a new error-driven active learning approach to self-growing radial basis function networks for early robot learning. There are several mappings that need to be set up for an autonomous robot system for sensorimotor coordination and transformation of sensory information from one modality to another, and these mappings are usually highly nonlinear. Traditional passive learning approaches usually cause both large mapping errors and nonuniform mapping error distribution compared to active learning. A hierarchical clustering technique is introduced to group large mapping errors and these error clusters drive the system to actively explore details of these clusters. Higher level local growing radial basis function subnetworks are used to approximate the residual errors from previous mapping levels. Plastic radial basis function networks construct the substrate of the learning system and a simplified node-decoupled extended Kalman filter algorithm is presented to train these radial basis function networks. Experimental results are given to compare the performance among active learning with hierarchical adaptive RBF networks, passive learning with adaptive RBF networks and hierarchical mixtures of experts, as well as their robustness under noise conditions.     

基于FIR神经网络的风电场虚拟风速传感器

风电机组风速传感器易发故障,故障可能导致机组安全风险和发电量损失。针对现行的故障处理方法因与机组控制策略紧密耦合而日益面临挑战,提出了一种基于数据处理的虚拟风速传感器原理与方法：由风电场上风向测量风速计算下风向推算风速,用推算风速取代故障传感器。着重讨论了基于FIR神经网络的推算风速计算方法和计算模型,探讨了系统实现的关键技术。实验证明了虚拟传感器的误差在机组控制系统可接受的程度内。提出的方法独立于机组自身属性,具有普遍适用性,可部署在任意类型的场,在物理传感器故障时向机组提供风速信号,支撑风电机组持续安全运行。     

Wheeled Mobile Robots Control in a Linear Platoon

Future transportation systems will require a number of drastic measures, mostly to lower traffic jams and air pollution in urban areas. Automatically guided vehicles capable of driving in a platoon fashion will represent an important feature of such systems. Platooning of a group of automated wheeled mobile robots relying on relative sensor information only is addressed in this paper. Each vehicle in the platoon must precisely follow the path of the vehicle in front of it and maintain the desired safety distance to that same vehicle. Vehicles have only distance and azimuth information to the preceding vehicle where no inter-vehicle communication is available. Following vehicles determine their reference positions and orientations based on estimated paths of the vehicles in front of them. Vehicles in the platoon are then controlled to follow the estimated trajectories. Then presented platooning control strategies are experimentally validated by experiments on a group of small-sized mobile robots and on a Pioneer 3AT mobile robot. The results and robustness analysis show the proposed platooning approach applicability.     

Experiments in feedback linearized iterative learning‐based path following for center‐articulated industrial vehicles

This paper describes the design, industrial application, and field testing of a technique for autonomous wheeled‐vehicle path following that uses iterative learning control (ILC) in a feedback linearized space. One advantage of this approach is that ILC is used without having to employ approximate linearization at every time step. The main contribution of this paper is the unique field experiments that used two large industrial‐scale center‐articulated underground mining vehicles. The described field work not only tested the underlying technique on commercial vehicles, but also presents a method for parallel speed learning, wherein the speed is adjusted over subsequent learning trials to improve cycle productivity. Finally, presented are field results for an approach to prelearning through simulation before deployment in the field to reduce the initial path‐following errors.     

基于DSP的车型检测器设计及其算法的研究

车型分类是高速公路自动收费和交通流量统计的重要依据,它是智能交通(ITS)的一个重要组成部分。本文针对车型检测器硬件结构和处理算法两方面提出一些具有创新性的设计方案,介绍了由LC振荡电路和TMS320F2812处理芯片构成的车型检测器的硬件结构,为克服LC振荡电路频率不稳定的固有缺陷提出了基频更新算法。并提出了利用一维数学形态滤波方法过滤实际应用中的噪声信号的方法,最后简单介绍了基于粗糙集BP神经网络车型分类算法。     

Physics-informed few-shot learning for wind pressure prediction of low-rise buildings

This research proposes a physics-informed few-shot learning model to predict the wind pressures on full-scale specimens based on scaled wind tunnel experiments. Existing machine learning approaches in the wind engineering domain are incapable of accurately extrapolating the prediction from scaled data to full-scale data. The model presented in this research, on the other hand, is capable of extrapolating prediction from large-scale or small-scale models to full-scale measurements. The proposed ML model combines a few-shot learning model with the existing physical knowledges in the design standards related to the zonal information. This physical information helps in clustering the few-shot learning model and improves prediction performance. Using the proposed techniques, the scaling issue observed in wind tunnel tests can be partially resolved. A low mean-squared error, mean absolute error, and a high coefficient of determination were observed when predicting the mean and standard deviation wind pressure coefficients of the full-scale dataset. In addition, the benefit of incorporating physical knowledge is verified by comparing the results with a baseline few-shot learning model. This method is the first of its type as it is the first time to extrapolate in wind performance prediction by combining prior physical knowledge with a few-shot learning model in the field of wind engineering. With the benefit of the few-shot learning model, only a low-resolution of the measuring tap configuration is required, and the reliance on physical wind tunnel experiments can be reduced. The physics-informed few-shot learning model is an efficient, robust, and accurate alternate solution to predicting wind pressures on full-scale structures based on various modeled scale experiments.     

A potential field approach for reactive navigation of autonomous sailboats

Navigation techniques for autonomous sailboats are faced with two inherent difficulties. The uncontrollable and partially unpredictable nature of thrust forces on one hand and the complex kinematics of sailboats on the other hand. This paper proposes a new reactive navigation approach, based on artificial potential fields, that addresses these two problems simultaneously. Environment and specific sailboat navigation constraints are represented by a local potential built around the vehicle location. Changes of wind direction and detected obstacles affect this periodically updated potential, which guarantees the real-time computation of a feasible heading for the boat. Numerical simulations are presented and validate the proposed algorithm under various wind conditions. Field trials eventually illustrate the efficiency of this navigation technique using a reduced-scale autonomous sailboat prototype.