基于ROS构建无人驾驶车辆环境感知系统

无人驾驶系统由环境感知等多个组件构成,一般基于各类分布式程序框架来实现.基于ROS系统这类消息传递通信的分布式多进程框架来构建环境感知系统,是一种可行的参考.本文讨论了无人驾驶系统环境感知信息融合中的ROS机制和组成,基于ROS系统下的目标检测与跟踪等环境感知具体实践,讨论了无人驾驶车辆中ROS性能分析及其改进等内容,可以作为相关技术实现的有益参考.     

基于可编程移动软设备的主动网络执行环境

执行环境是主动网络中各种应用、移动代码的编制、管理和运行的基础,提出了一种基于可编程移动软设备的主动网络执行环境,该执行环境中的可编程单元称为可移动软设备,在功能上按协议子树划分,通过执行环境中的多路分解器,网络中的主动包和被动包都能找到相应的处理代码,在执行环境里,主动节点的功能易于扩充,大量的API方便用户编程,协议或应用的调试和部署简单.     

基于情绪感知的机器人辅助主动康复训练任务控制方法

在现有机器人辅助康复训练过程中,患者与康复机器人之间的交互控制主要以感知患者主动"运动"参与为主,未能考虑患者"心理"层次的主动参与,具有一定的局限.针对此问题,以康复训练过程中患者挫败、兴奋及厌烦为目标情绪状态,提出一种基于情绪感知的机器人辅助主动康复任务控制方法.该方法首先提取机器人辅助主动康复过程中患者目标情绪生理响应及性能数据特征;其次,基于径向基核的支持向量机设计目标情绪分类器,并研究与患者目标情绪变化相一致的机器人辅助康复任务自适应控制方法;最后,运用Barrett公司4自由度WAM^{m TM}康复机器人构建试验系统平台,选取12例临床脑卒中患者,对方法有效性进行试验验证.     

Development of A Behavior‐Based Cooperative Search Strategy for Distributed Autonomous Mobile Robots Using Zigbee Wireless Sensor Network

To achieve efficient and objective search tasks in an unknown environment, a cooperative search strategy for distributed autonomous mobile robots is developed using a behavior‐based control framework with individual and group behaviors. The sensing information of each mobile robot activates the individual behaviors to facilitate autonomous search tasks to avoid obstacles. An 802.15.4 ZigBee wireless sensor network then activates the group behaviors that enable cooperative search among the mobile robots. An unknown environment is dynamically divided into several sub‐areas according to the locations and sensing data of the autonomous mobile robots. The group behaviors then enable the distributed autonomous mobile robots to scatter and move in the search environment. The developed cooperative search strategy successfully reduces the search time within the test environments by 22.67% (simulation results) and 31.15% (experimental results).     

MSDL-IEW:面向文本分类的密集度感知主动学习算法

为了解决文本分类任务中未标注数据无法即时标注及成本过高的问题,提出一种面向文本分类的不确定性主动学习方法.提出MSDL(Measure sample density by LDA)算法对未标注样本密集度进行计算,引入新的度量样本聚集情况的密集度计算方式,在密集度高的样本区域选取初始训练集样本,从而使初始训练集更具代表性...     

A Novel Boundary Control Solution for Unstable Heat Conduction Systems Based on Active Disturbance Rejection Control

In this study, a new boundary control scheme is proposed for a class of unstable heat conduction systems based on active disturbance rejection control and frequency domain analysis methods. The unstable heat conduction systems studied here corresponds to a thin rod with surface heat loss and internal heat generation. An active disturbance rejection boundary controller is designed to stabilize the unstable heat conduction systems. Using the frequency domain analysis method, the Nyquist stability criterion for distributed parameter systems, the relative stability indices (gain margin, phase margin, and exponential stability speed) can be obtained for performance evaluation, and a constructive parameter‐tuning method for controller is proposed. Finally, it is proved that an active disturbance rejection boundary controller can stabilize the unstable heat conduction systems with one unstable pole, and the simulation results demonstrate that the temperature profile of the whole rod has good convergence properties under both Dirichlet and Neumann boundary control.     

心脏序列图像运动估计新方法:基于广义模糊梯度矢量流场的形变曲线运动估计与跟踪

应用动态轮廓线模型(ACM)解决心脏运动估计问题是该领域的主要研究方法之一．采用经典外力和传统ACM模型对感兴趣边缘进行搜索及跟踪时，普遍存在模型的局部适应性程度不高的缺陷．为解决这一挑战性难题，该文提出了广义模糊梯度矢量流(GFGVF)的概念，并构造出一组新的Snake平衡方程，该方程可对心脏内部边缘逐帧进行鲁棒跟踪．为进一步跟踪每一特征点的运动，该文将前一步的轮廓跟踪结果作为似然条件，结合一致性和连续性先验条件，通过最大后验概率(MAP)的方法对整个过程进行了优化计算．通过对MR及CT两类心脏序列图像进行运动跟踪实验并对计算结果进行多种比较，此方法显示了较好的鲁棒性．