基于三阶反正切函数模型的平行泊车轨迹规划

现有泊车情况面临两大问题:停车空间小和泊车控制难.针对日益严重的“泊车难”问题,提出一种平行泊车的轨迹规划方法.该方法由带有三阶扰动的反正切式轨迹模型进行路径规划,考虑运动学的约束空间条件,利用遗传算法确定最优轨迹函数参数,最后获得最优泊车轨迹.仿真结果表明车住长与车长比值可达到1.315,多车位与多车型的模型仿真表明该路径规划方法的有效性以及较强的鲁棒性.     

基于伪谱法的自主泊车路径规划方法

目前对泊车方法的相关研究仅适用于平行泊车和垂直泊车中的一种泊车场景。为此,提出通用性的自主泊车路径规划方法。该方法融合车辆运动学约束和路径约束,以泊车时间为性能指标,建立泊车路径规划最优控制问题的数学模型。使用伪谱法求解该最优控制问题,并以细化网格的方式保证所得解符合路径约束,得到无碰撞可行泊车路径。利用该方法可同时求解平行泊车和垂直泊车两种场景的路径规划,仿真实验和实车实验验证了该方法的通用性和可行性。     

基于交互车辆轨迹预测的自动驾驶车辆轨迹规划

针对城市道路等复杂行车场景,提出了一种基于交互车辆轨迹预测的自动驾驶车辆轨迹规划方法,将高维度的轨迹规划解耦为低维度的路径规划和速度规划;首先,采用五次多项式曲线和碰撞剩余时间规划车辆行驶路径;其次,在社会生成对抗网络Social-GAN的基础上结合车辆空间影响和注意力机制对交互车辆进行轨迹预测;然后,结合主车规划路径、交互车辆预测轨迹及碰撞判定模型得到主车S-T图,采用动态规划和数值优化方法求解S-T图,从而得到满足车辆动力学约束的安全、舒适最优速度曲线;最后,搭建PreScan-CarSim-Matlab&Simulink-Python联合仿真模型进行实验验证。仿真结果表明,提出的轨迹规划方法能够在对交互车辆有效避撞的前提下,保证车辆行驶的舒适性和高效性。     

一种自动泊车的仿人智能控制方法

为简化平行泊车,通过总结模拟熟练驾驶员的泊车经验,提出一种自动泊车的仿人智能控制方法。该方法以后轮驱动、前轮转向的四轮汽车为对象,建立车辆运动学模型;通过分析熟练驾驶员泊车流程,将泊车过程分为4个阶段;在相切圆弧加公切线的规划路径上,选取泊车阶段转换时车辆姿态调整的关键点作为跟踪目标;根据泊车过程车辆的位姿信息,提取12种泊车的特征状态,作为描述车辆泊车动态行为的特征模型;根据熟练驾驶员的泊车策略,构建控制模态集。泊车开始后,依据特征模型先验知识和当前车辆位姿与泊车目标的偏差,对当前车辆特征状态进行模式识别,由辨识出的特征状态驱动相应控制模态,控制汽车按规划路径泊车入位。建立了车辆运动学和仿人智能控制器Simulink模型,并进行了仿真实验。仿真结果表明,该方法能有效控制车辆泊入车位。     

基于坐标补偿的自动泊车系统无模型自适应控制

针对自动泊车系统,提出了无模型自适应控制(Model-free adaptive control, MFAC)方案.控制方案的设计仅利用泊车系统的前轮转角输入数据和车身角输出数据,不包含车辆模型信息.因此,针对不同车型的自动泊车系统,该方案均能实现无模型自适应控制.为了改善期望轨迹的坐标跟踪误差,进一步提出基于坐标补偿的无模型自适应控制方案,该方案由控制算法、参数估计算法、参数重置算法和坐标补偿算法构成.针对不同车型不同泊车速度的仿真结果表明,基于坐标补偿的MFAC方案和原型MFAC方案均能较好地完成自动泊车过程,且基于坐标补偿的MFAC方案相比原型MFAC方案和PID控制方案,在轨迹坐标和车身角等方面均具有更小的跟踪误差和更快的响应速度.     

基于无线通信的智能泊车系统设计

自动泊车是车辆辅助驾驶系统中的一项关键技术.当泊车空间较小时,现有的泊车技术无法发挥作用.设计了一种基于无线通信的新型智能泊车方法,引入无线通信协同泊靠的概念,利用通信网络共享资源信息;使用多类型传感器采集车位信息,多MCU共同规划泊车路径,调整已泊靠车辆位置,为需要泊靠的车辆提供足够空间,从而通过多车协同最大化利用泊车空间.通过实验验证,该方法与现有泊车技术相比,在同等条件下,泊车空间利用率提高20％以上.     

无人车辆轨迹规划与跟踪控制的统一建模方法

无人车辆的轨迹规划与跟踪控制是实现自动驾驶的关键.轨迹规划与跟踪控制一般分为两个部分，即先根据车辆周边环境信息以及自车运动状态信息规划出参考轨迹，再依此轨迹来调节车辆纵横向输出以实现跟随控制.本文通过对无人车辆的轨迹规划与跟踪进行统一建模，基于行车环境势场建模与车辆动力学建模，利用模型预测控制中的优化算法来选择人工势场定义下的局部轨迹，生成最优的参考轨迹，并在实现轨迹规划的同时进行跟踪控制.通过CarSim与MATLAB/Simulink的联合仿真实验表明，该方法可在多种场景下实现无人车辆的动态避障.     

基于HMM的车辆行驶状态实时判别方法研究

对交通视频车辆轨迹时序特征下的车辆行驶状态进行研究,提出了一种基于隐马尔科夫模型（Hidden Markov model,HMM）的车辆行驶状态实时判别方法.首先对轨迹序列进行了基于轨迹长度的去不完整轨迹序列、对车辆轨迹点序列的线 性平滑滤波和最小二乘线性拟合的预处理操作,保证了所获得轨迹序列的有效性;其次,提出一种基于车辆运行轨迹点序列方向角的车辆轨迹特征值表示方法和基于方向角区间划分的HMM观察值序列生成方法,该方法以方向角的区间变化来区分不同轨迹模式的特征;最后,采用多观察值序列下的Baum-Welch 算法训练得到相关交通场景轨迹模式类的最优HMM 参数,并通过实时获取车辆行驶轨迹段与相应模型的匹配,实现对车辆行驶状态的实时判别. 仿真实验验证了本文方法的有效性和稳定性.     

基于三次样条插值的自动入库泊车免疫粒子群改进算法

传统自动入库泊车轨迹优化算法不易寻到光滑、精确且优化的泊车轨迹。结合智能自动入库泊车原理,本文提出一种基于三次样条插值的自动入库泊车方法,从而获得理想优化的泊车参考轨迹。为了有效地提升自动入库泊车轨迹寻优算法的性能,以泊车轨迹最短作为优化目标来选定一组合适的泊车位置参考点,在三次样条插值的基础上,又提出一种免疫粒子群改进算法。首先,为提升算法全局搜索性能和收敛速度,引入自适应变异策略;然后,引入免疫机制来有效提升其全局优化能力。测试函数及自动入库泊车实际算例的仿真结果表明,所提出的自动入库泊车免疫粒子群改进算法具有更高的寻优精度和较快的收敛速度。     

五次多项式优化的平行泊车路径规划

针对目前自动泊车路径规划普遍存在的曲率突变问题,提出了一种五次多项式优化的平行泊车路径规划方法。五次多项式曲线由约束条件建立的方程组求解得出,并对路径的曲率突变处进行过渡优化。为简化计算,引入“虚圆半径”的概念,以“虚圆半径”作为最小转弯半径,并按照“圆弧-直线-圆弧”平行泊车路径规划的方法进行求解,由此得出优化的平行泊车路径。仿真结果表明,五次多项式优化的平行泊车路径规划方法能够规划出曲率连续、满足避障约束和车辆运动学约束的优化路径,提高了路径跟踪的效果,保证车辆安全完成泊车。     

Formulation and parameter selection of multi-objective deterministic particle swarm for simulation-based optimization

Global derivative-free deterministic algorithms are particularly suitable for simulation-based optimization, where often the existence of multiple local optima cannot be excluded a priori, the derivatives of the objective functions are not available, and the evaluation of the objectives is computationally expensive, thus a statistical analysis of the optimization outcomes is not practicable. Among these algorithms, particle swarm optimization (PSO) is advantageous for the ease of implementation and the capability of providing good approximate solutions to the optimization problem at a reasonable computational cost. PSO has been introduced for single-objective problems and several extension to multi-objective optimization are available in the literature. The objective of the present work is the systematic assessment and selection of the most promising formulation and setup parameters of multi-objective deterministic particle swarm optimization (MODPSO) for simulation-based problems. A comparative study of six formulations (varying the definition of cognitive and social attractors) and three setting parameters (number of particles, initialization method, and coefficient set) is performed using 66 analytical test problems. The number of objective functions range from two to three and the number of variables from two to eight, as often encountered in simulation-based engineering problems. The desired Pareto fronts are convex, concave, continuous, and discontinuous. A full-factorial combination of formulations and parameters is investigated, leading to more than 60,000 optimization runs, and assessed by three performance metrics. The most promising MODPSO formulation/parameter is identified and applied to the hull-form optimization of a high-speed catamaran in realistic ocean conditions. Its performance is finally compared with four stochastic algorithms, namely three versions of multi-objective PSO and the genetic algorithm NSGA-II.     

Real-time dynamic optimization of batch systems

In this paper a methodology for designing and implementing a real-time optimizing controller for batch processes is proposed. The controller is used to optimize a user-defined cost function subject to a parameterization of the input trajectories, a nominal model of the process and general state and input constraints. An interior point method with penalty function is used to incorporate constraints into a modified cost functional, and a Lyapunov based extremum seeking approach is used to compute the trajectory parameters. The technique is applicable to general nonlinear systems. A precise statement of the numerical implementation of the optimization routine is provided. It is shown how one can take into account the effect of sampling and discretization of the parameter update law in practical situations. A simulation example demonstrates the applicability of the technique.     

Multiobjective optimization of trusses using genetic algorithms

In this paper we propose the use of the genetic algorithm (GA) as a tool to solve multiobjective optimization problems in structures. Using the concept of min–max optimum, a new GA-based multiobjective optimization technique is proposed and two truss design problems are solved using it. The results produced by this new approach are compared to those produced by other mathematical programming techniques and GA-based approaches, proving that this technique generates better trade-offs and that the genetic algorithm can be used as a reliable numerical optimization tool.     

An integrated approach to topology,sizing, and shape optimization

Topology optimization has become very popular in industrial applications, and most FEM codes have implemented certain capabilities of topology optimization. However, most codes do not allow simultaneous treatment of sizing and shape optimization during the topology optimization phase. This poses a limitation on the design space and therefore prevents finding possible better designs since the interaction of sizing and shape variables with topology modification is excluded. In this paper, an integrated approach is developed to provide the user with the freedom of combining sizing, shape, and topology optimization in a single process.     

Effects of dominant wolves in grey wolf optimization algorithm

Bio-inspired computation is one of the emerging soft computing techniques of the past decade. Although they do not guarantee optimality, the underlying reasons that make such algorithms become popular are indeed simplicity in implementation and being open to various improvements. Grey Wolf Optimizer (GWO), which derives inspiration from the hierarchical order and hunting behaviours of grey wolves in nature, is one of the new generation bio-inspired metaheuristics. GWO is first introduced to solve global optimization and mechanical design problems. Next, it has been applied to a variety of problems. As reported in numerous publications, GWO is shown to be a promising algorithm, however, the effects of characteristic mechanisms of GWO on solution quality has not been sufficiently discussed in the related literature. Accordingly, the present study analyses the effects of dominant wolves, which clearly have crucial effects on search capability of GWO and introduces new extensions, which are based on the variations of dominant wolves. In the first extension, three dominant wolves in GWO are evaluated first. Thus, an implicit local search without an additional computational cost is conducted at the beginning of each iteration. Only after repositioning of wolf council of higher-ranks, the rest of the pack is allowed to reposition. Secondarily, dominant wolves are exposed to learning curves so that the hierarchy amongst the leading wolves is established throughout generations. In the final modification, the procedures of the previous extensions are adopted simultaneously. The performances of all developed algorithms are tested on both constrained and unconstrained optimization problems including combinatorial problems such as uncapacitated facility location problem and 0-1 knapsack problem, which have numerous possible real-life applications. The proposed modifications are compared to the standard GWO, some other metaheuristic algorithms taken from the literature and Particle Swarm Optimization, which can be considered as a fundamental algorithm commonly employed in comparative studies. Finally, proposed algorithms are implemented on real-life cases of which the data are taken from the related publications. Statistically verified results point out significant improvements achieved by proposed modifications. In this regard, the results of the present study demonstrate that the dominant wolves have crucial effects on the performance of GWO.     

多元插值全局优化算法及其应用

本文介绍一种多元插值逼近和动态搜索轨迹相结合的全局优化算法.该算法大大减少了目标函数计算次数,寻优收敛速度快,算法稳定,且可获得全局极小,有效地解决了大规模非线性复杂动态系统的参数优化问题.一个具有8个控制参数的电力系统优化控制问题,采用该算法仅访问目标函数78次,便可求得最优控制器参数。     

云搜索优化算法

本文将云的生成、动态运动、降雨和再生成等自然现象与智能优化算法的思想融合,建立了一种新的智能优化算法-云搜索优化算法(CSO)。生成与移动的云可以弥漫于整个搜索空间,这使得新算法具有较强的全局搜索能力;收缩与扩张的云团在形态上会有千奇百态的变化,这使得算法具有较强的局部搜索能力;降雨后产生新的云团可以保持云团的多样性,这也是使搜索避免陷入局优的有效手段。实验表明,基于这三点建立的新算法具有优异的性能,benchmark函数最优值的计算结果以及与已有智能优化算法的比较展现了新算法精确的、稳定的全局求解能力。     

Value Creation in a Network: The Role of Pricing and Revenue Optimization and Enterprise Profit OptimizationTM

The Internet has created a virtual upheaval in the structural features of the supply and demand chains for most businesses. New agents and marketplaces have surfaced. The potential to create value and enhance profitable opportunities has attracted both buyers and sellers to the Internet. Yet, the Internet has proven to be more complex than originally thought. With information comes complexity: the more the information in real time, the greater the difficulty in interpretation and absorption. How can the value-creating potential of the Internet still be realized, its complexity notwithstanding? This paper argues that with the emergence of innovative tools, the expectations of the Internet as a medium for enhanced profit opportunities can still be realized. Creating value on a continuing basis is central to sustaining profitable opportunities. This paper provides an overview of the value creation process in electronic networks, the emergence of the Internet as a viable business communication and collaboration medium, the proclamation by many that the future of the Internet resides in “embedded intelligence”, and the perspectives of pragmatists who point out the other facet of the Internet—its complexity. The paper then reviews some recent new tools that have emerged to address this complexity. In particular, the promise of Pricing and Revenue Optimization (PRO) and Enterprise Profit Optimization^TM (EPO) tools is discussed. The paper suggests that as buyers and sellers adopt EPO, the market will see the emergence of a truly intelligent network—a virtual network—of private and semi-public profitable communities.     

粒子群算法在组合优化问题上的研究与发展

粒子群优化算法是一种新兴的基于群智能搜索的优化技术。该算法简单、易实现、参数少,具有较强的全局优化能力,可有效应用于科学与工程实践中。介绍了算法的基本原理和算法在组合优化上一些改进方法的主要应用形式。最后,对粒子群算法作了一些深入分析并在此基础上对粒子群算法应用于组合优化问题做了一些总结。     

SEO技术研究

为了利用搜索引擎优化SEO（Search Engine Optimization）技术给网站带来高质量的流量并将其转化为商业利益,理解搜索引擎的算法和排名原理十分必要。通过对网站的结构优化、关键词优化、单页优化、防止被搜索引擎惩罚和挽救被惩罚网站等技术的研究,达到提高网站排名,实现网站的价值目的。