Path Planning and Tracking Control for Parking via Soft Actor-Critic Under Non-Ideal Scenarios

Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.

GRU-integrated constrained soft actor-critic learning enabled fully distributed scheduling strategy for residential virtual power plant

In this study,a novel residential virtual power plant(RVPP)scheduling method that leverages a gate recurrent unit(GRU)-integrated deep reinforcement learning(DRL)algorithm is proposed.In the proposed scheme,the GRU-integrated DRL algorithm guides the RVPP to participate effectively in both the day-ahead and real-time markets,lowering the electricity purchase costs and consumption risks for end-users.The Lagrangian relaxation technique is introduced to transform the constrained Markov decision process(CMDP)into an unconstrained optimization problem,which guarantees that the constraints are strictly satisfied without determining the penalty coefficients.Furthermore,to enhance the scalability of the constrained soft actor-critic(CSAC)-based RVPP scheduling approach,a fully distributed scheduling architecture was designed to enable plug-and-play in the residential distributed energy resources(RDER).Case studies performed on the constructed RVPP scenario validated the performance of the proposed methodology in enhancing the responsiveness of the RDER to power tariffs,balancing the supply and demand of the power grid,and ensuring customer comfort.

An Improved Soft Subspace Clustering Algorithm for Brain MR Image Segmentation

In recent years,the soft subspace clustering algorithm has shown good results for high-dimensional data,which can assign different weights to each cluster class and use weights to measure the contribution of each dimension in various features.The enhanced soft subspace clustering algorithm combines interclass separation and intraclass tightness information,which has strong results for image segmentation,but the clustering algorithm is vulnerable to noisy data and dependence on the initialized clustering center.However,the clustering algorithmis susceptible to the influence of noisydata and reliance on initializedclustering centers andfalls into a local optimum;the clustering effect is poor for brain MR images with unclear boundaries and noise effects.To address these problems,a soft subspace clustering algorithm for brain MR images based on genetic algorithm optimization is proposed,which combines the generalized noise technique,relaxes the equational weight constraint in the objective function as the boundary constraint,and uses a genetic algorithm as a method to optimize the initialized clustering center.The genetic algorithm finds the best clustering center and reduces the algorithm’s dependence on the initial clustering center.The experiment verifies the robustness of the algorithm,as well as the noise immunity in various ways and shows good results on the common dataset and the brain MR images provided by the Changshu First People’s Hospital with specific high accuracy for clinical medicine.

Soft Tissue Deformation Model Based on Marquardt Algorithm and Enrichment Function

In order to solve the problem of high computing cost and low simulation accuracy caused by discontinuity of incision in traditional meshless model,this paper proposes a soft tissue deformation model based on the Marquardt algorithm and enrichment function.The model is based on the element-free Galerkin method,in which Kelvin viscoelastic model and adjustment function are integrated.Marquardt algorithm is applied to fit the relation between force and displacement caused by surface deformation,and the enrichment function is applied to deal with the discontinuity in the meshless method.To verify the validity of the model,the Sensable Phantom Omni force tactile interactive device is used to simulate the deformations of stomach and heart.Experimental results show that the proposed model improves the real-time performance and accuracy of soft tissue deformation simulation,which provides a new perspective for the application of the meshless method in virtual surgery.

Soft Electronics for Health Monitoring Assisted by Machine Learning

Due to the development of the novel materials,the past two decades have witnessed the rapid advances of soft electronics.The soft electronics have huge potential in the physical sign monitoring and health care.One of the important advantages of soft electronics is forming good interface with skin,which can increase the user scale and improve the signal quality.Therefore,it is easy to build the specific dataset,which is important to improve the performance of machine learning algorithm.At the same time,with the assistance of machine learning algorithm,the soft electronics have become more and more intelligent to realize real-time analysis and diagnosis.The soft electronics and machining learning algorithms complement each other very well.It is indubitable that the soft electronics will bring us to a healthier and more intelligent world in the near future.Therefore,in this review,we will give a careful introduction about the new soft material,physiological signal detected by soft devices,and the soft devices assisted by machine learning algorithm.Some soft materials will be discussed such as two-dimensional material,carbon nanotube,nanowire,nanomesh,and hydrogel.Then,soft sensors will be discussed according to the physiological signal types(pulse,respiration,human motion,intraocular pressure,phonation,etc.).After that,the soft electronics assisted by various algorithms will be reviewed,including some classical algorithms and powerful neural network algorithms.Especially,the soft device assisted by neural network will be introduced carefully.Finally,the outlook,challenge,and conclusion of soft system powered by machine learning algorithm will be discussed.

Soft measurement model of ring's dimensions for vertical hot ring rolling process using neural networks optimized by genetic algorithm

Vertical hot ring rolling(VHRR) process has the characteristics of nonlinearity,time-variation and being susceptible to disturbance.Furthermore,the ring's growth is quite fast within a short time,and the rolled ring's position is asymmetrical.All of these cause that the ring's dimensions cannot be measured directly.Through analyzing the relationships among the dimensions of ring blanks,the positions of rolls and the ring's inner and outer diameter,the soft measurement model of ring's dimensions is established based on the radial basis function neural network(RBFNN).A mass of data samples are obtained from VHRR finite element(FE) simulations to train and test the soft measurement NN model,and the model's structure parameters are deduced and optimized by genetic algorithm(GA).Finally,the soft measurement system of ring's dimensions is established and validated by the VHRR experiments.The ring's dimensions were measured artificially and calculated by the soft measurement NN model.The results show that the calculation values of GA-RBFNN model are close to the artificial measurement data.In addition,the calculation accuracy of GA-RBFNN model is higher than that of RBFNN model.The research results suggest that the soft measurement NN model has high precision and flexibility.The research can provide practical methods and theoretical guidance for the accurate measurement of VHRR process.

Multi-source coordinated stochastic restoration for SOP in distribution networks with a two-stage algorithm

After suffering from a grid blackout, distributed energy resources(DERs), such as local renewable energy and controllable distributed generators and energy storage can be used to restore loads enhancing the system’s resilience. In this study, a multi-source coordinated load restoration strategy was investigated for a distribution network with soft open points(SOPs). Here, the flexible regulation ability of the SOPs is fully utilized to improve the load restoration level while mitigating voltage deviations. Owing to the uncertainty, a scenario-based stochastic optimization approach was employed,and the load restoration problem was formulated as a mixed-integer nonlinear programming model. A computationally efficient solution algorithm was developed for the model using convex relaxation and linearization methods. The algorithm is organized into a two-stage structure, in which the energy storage system is dispatched in the first stage by solving a relaxed convex problem. In the second stage, an integer programming problem is calculated to acquire the outputs of both SOPs and power resources. A numerical test was conducted on both IEEE 33-bus and IEEE 123-bus systems to validate the effectiveness of the proposed strategy.

Multi-Attribute Group Decision-Making Method under Spherical Fuzzy Bipolar Soft Expert Framework with Its Application

Spherical fuzzy soft expert set(SFSES)theory blends the perks of spherical fuzzy sets and group decision-making into a unified approach.It allows solutions to highly complicated uncertainties and ambiguities under the unbiased supervision and group decision-making of multiple experts.However,SFSES theory has some deficiencies such as the inability to interpret and portray the bipolarity of decision-parameters.This work highlights and overcomes these limitations by introducing the novel spherical fuzzy bipolar soft expert sets(SFBSESs)as a powerful hybridization of spherical fuzzy set theory with bipolar soft expert sets(BSESs).Followed by the development of certain set-theoretic operations and properties of the proposed model,important problems,including the selection of non-powered dam(NPD)sites for hydropower conversion are discussed and solved under the proposed approach.These problems mainly focus on the need for an efficient tool capable of considering the bipolarity of parameters,complicated ambiguities,and multiple opinions.Supporting the new approach by a detailed comparative analysis,it is concluded that the proposed model is more comprehensive and reliable for multi-attribute group decisionmaking(MAGDM)than the previous tools,particularly considering the bipolarity of parameters under SFSES environment.

A New Kind of Generalized Pythagorean Fuzzy Soft Set and Its Application in Decision-Making

The aim of this paper is to introduce the concept of a generalized Pythagorean fuzzy soft set(GPFSS),which is a combination of the generalized fuzzy soft sets and Pythagorean fuzzy sets.Several of important operations of GPFSS including complement,restricted union,and extended intersection are discussed.The basic properties of GPFSS are presented.Further,an algorithm of GPFSSs is given to solve the fuzzy soft decision-making.Finally,a comparative analysis between the GPFSS approach and some existing approaches is provided to show their reliability over them.

Development of mathematically motivated hybrid soft computing models for improved predictions of ultimate bearing capacity of shallow foundations

Ultimate bearing capacity(UBC)is a key subject in geotechnical/foundation engineering as it determines the limit of loads imposed on the foundation.The most reliable means of determining UBC is through experiment,but it is costly and time-consuming which has led to the development of various models based on the simplified assumptions.The outcomes of the models are usually validated with the experimental results,but a large gap usually exists between them.Therefore,a model that can give a close prediction of the experimental results is imperative.This study proposes a grasshopper optimization algorithm(GOA)and salp swarm algorithm(SSA)to optimize artificial neural networks(ANNs)using the existing UBC experimental database.The performances of the proposed models are evaluated using various statistical indices.The obtained results are compared with the existing models.The proposed models outperformed the existing models.The proposed hybrid GOA-ANN and SSA-ANN models are then transformed into mathematical forms that can be incorporated into geotechnical/foundation engineering design codes for accurate UBC measurements.

Soft-output stack algorithm with lattice-reduction for MIMO detection

A computationally efficient soft-output detector with lattice-reduction （LR） for the multiple-input multiple-output （MIMO） systems is proposed. In the proposed scheme, the sorted QR de- composition is applied on the lattice-reduced equivalent channel to obtain the tree structure. With the aid of the boundary control, the stack algorithm searches a small part of the whole search tree to generate a handful of candidate lists in the reduced lattice. The proposed soft-output algorithm achieves near-optimal perfor- mance in a coded MIMO system and the associated computational complexity is substantially lower than that of previously proposed methods.

基于柔性演员-评论家算法的决策规划协同研究

为了解决基于常规深度强化学习(Deep Reinforcement Learning, DRL)的自动驾驶决策存在学习速度慢、安全性及合理性较差的问题,本文提出一种基于柔性演员-评论家(Soft Actor-Critic,SAC)算法的自动驾驶决策规划协同方法,并将SAC算法与基于规则的决策规划方法相结合设计自动驾驶决策规划协同智能体。结合自注意力机制(Self Attention Mechanism, SAM)和门控循环单元(Gate Recurrent Unit, GRU)构建预处理网络;根据规划模块的具体实现方式设计动作空间;运用信息反馈思想设计奖励函数,给智能体添加车辆行驶条件约束,并将轨迹信息传递给决策模块,实现决策规划的信息协同。在CARLA自动驾驶仿真平台中搭建交通场景对智能体进行训练,并在不同场景中将所提出的决策规划协同方法与常规的基于SAC算法的决策规划方法进行比较,结果表明,本文所设计的自动驾驶决策规划协同智能体学习速度提高了25.10%,由其决策结果生成的平均车速更高,车速变化率更小,更接近道路期望车速,路径长度与曲率变化率更小。

基于沙地猫群优化–最小二乘支持向量机的动态NOx排放预测

针对火电机组频繁调峰导致机组燃烧状态不稳,进而导致锅炉出口NOx浓度波动范围大的问题,提出一种基于沙地猫群优化(sand cat sarm optimization,SCSO)的最小二乘支持向量机(leastsquaressupportvectormachine,LSSVM) NOx动态预测模型。首先利用k近邻互信息计算时间延迟的同时筛选辅助变量。然后,基于SCSO算法进行输入变量阶次的选择。使用包含辅助变量时间延迟和阶次的信息作为模型的输入,SCSO算法优化最小二乘支持向量机参数,建立动态NOx排放最小二乘支持向量机预测模型(SCSO-LSSVM动态软测量模型)。最后将模型与未加入迟延的LSSVM模型,加入迟延的LSSVM模型和粒子群优化算法(particle swarm optimization,PSO)优化最小二乘支持向量机参数的动态软测量模型进行对比验证。结果表明,相较于其他模型,该文建立SCSO-LSSVM动态软测量模型均方根误差、平均绝对误差、平均绝对误差最小,预测精度最高,而且在NOx浓度剧烈波动时也能够较好地预测NOx浓度,具有很好的动态特性。

基于路径模仿和SAC强化学习的机械臂路径规划算法

在机械臂路径规划算法的训练过程中,由于动作空间和状态空间巨大导致奖励稀疏,机械臂路径规划训练效率低,面对海量的状态数和动作数较难评估状态价值和动作价值。针对上述问题,提出一种基于SAC(Soft Actor-Critic)强化学习的机械臂路径规划算法。通过将示教路径融入奖励函数使机械臂在强化学习过程中对示教路径进行模仿以提高学习效率,并采用SAC算法使机械臂路径规划算法的训练更快、稳定性更好。基于所提算法和深度确定性策略梯度(DDPG)算法分别规划10条路径,所提算法和DDPG算法规划的路径与参考路径的平均距离分别是0.8 cm和1.9 cm。实验结果表明,路径模仿机制能提高训练效率,所提算法比DDPG算法能更好地探索环境,使得规划路径更加合理。

基于改进Stanley算法的目标假车路径跟踪控制

为了满足智能汽车封闭场地测试的需求,开发了一种智能车场地测试用软目标车,能够有效地提高场地测试的安全性和效率。在封闭场地功能场景的测试中,软目标车应能够按照预设的GPS轨迹高精度行驶。为了提高目标车的路径跟踪精度,设计了基于偏差的比例、积分、微分和Stanley控制算法的横纵向控制器,基于遗传算法得到Stanley控制算法参数的最优知识库,利用模糊控制算法实现Stanley控制算法参数的自适应调节,基于Carsim和Matlab/Simulink联合建立了软目标车仿真模型,最后在封闭场地中进行实车验证。结果表明:提出的控制方法能够满足智能汽车封闭场地测试要求。

基于时间窗的机场地面保障车辆动态调度

机场各类地面资源的优化配置是机场场面运行优化的核心问题,而机场地面保障任务的调度是其中的关键一环。针对机场地面保障车辆的调度问题,考虑航班延误、提前等情况,构建了双阶段机场地面保障车辆调度模型,并设计双阶段启发式算法进行求解;基于中国某大型机场的实际运行数据,以清水车和食品车调度为例分别进行仿真实验。结果表明:对比先到先服务策略,清水车行驶总距离减少55.31%,食品车行驶总距离减少47.38%;对比传统遗传算法,清水车行驶总距离减少19.31%,食品车行驶总距离减少22.93%;动态调整后,清水车新增总行驶距离1.2%,食品车总行驶距离新增3.2%,均在可接受范围之内。可见,双阶段机场地面保障车辆调度模型能提高大型机场场面运行效率,为机场航班实际地面保障任务调度提供理论依据和决策支持。

高质量加工五次多项式速度规划算法研究

通过分析直线、指数、S曲线以及正弦函数几种常用的加减速算法,针对传统的速度规划算法存在的加工曲线不连续以及加工过程出现振荡、加工精度低等问题,提出适用于高质量加工的五次多项式速度规划算法,将整个加工过程分段,细化每一段的方程,并介绍对于待定的NURBS曲线使用五次多项式速度规划算法进行插补的过程,针对快速插补和实时插补两个阶段进行优化。结尾根据仿真加工实验图像得出结论,该算法实现了加工过程中运动曲线的连续变化、柔性变化。并将加工精度控制在理想范围之内,适应于高质量的加工。

基于最大熵深度强化学习的双足机器人步态控制方法

针对双足机器人连续直线行走的步态稳定控制问题,提出一种基于最大熵深度强化学习(DRL)的柔性演员-评论家(SAC)步态控制方法。首先,该方法无需事先建立准确的机器人动力学模型,所有参数均来自关节角而无需额外的传感器;其次,采用余弦相似度方法对经验样本分类,优化经验回放机制;最后,根据知识和经验设计奖励函数,使双足机器人在直线行走训练过程中不断进行姿态调整,确保直线行走的鲁棒性。在Roboschool仿真环境中与其他先进深度强化学习算法,如近端策略优化(PPO)方法和信赖域策略优化(TRPO)方法的实验对比结果表明,所提方法不仅实现了双足机器人快速稳定的直线行走,而且鲁棒性更好。

面向幼儿园的接送人管理与场景监控系统

针对幼儿园冒领、错接、拐骗和绑架幼儿等一系列安全事故,本文设计了一种面向幼儿园的接送人管理与场景监控系统。该系统基于虹软ArcFace算法的离线人脸识别技术开发,获取接送人员的人脸特征值与事先注册录入人脸库中的家长或亲友的人脸特征值进行比对,若匹配成功,则将接送场景照片和视频上传至系统的接送记录中,家长可以通过手机微信小程序查看接送记录。该系统提高了幼儿接送过程的安全性,降低幼儿被接错等安全风险,也为家长提供了查看接送记录、场景照片和视频的平台。

多中心半开放式同时送取货的车辆路径问题研究

研究了带软时间窗约束的多配送中心半开放式同时送取货的车辆路径问题,所有客户点均存在送取两种需求,并采用同一辆车同时提供送取服务.车辆服务完路线上所有客户点后,不一定返回起始配送中心,可就近返回任意配送中心.在此条件下,构建了以车辆运输成本、车辆租赁成本、时间窗惩罚成本等总和最小为目标的优化模型.根据问题特征,设计了自适应精英遗传算法对该问题进行求解,引入自适应机制,根据个体的适应度动态地调节交叉和变异概率,采用精英保留策略将优秀个体进行遗传保留,不仅增强了算法的全局优化能力,还均衡了算法的局部搜索能力.通过案例仿真,验证了模型和算法的可行性和有效性.研究成果丰富了车辆路径问题的相关研究,为物流企业提供了一种决策参考.