基于信息增益一致性的多机器人地图融合算法

针对多机器人协同SLAM(同步定位与地图构建)的地图融合中,由于通信距离受限或网络拓扑变化造成信息缺失、从而影响全局地图构建的问题,提出一种基于信息增益一致性原理的动态地图融合算法.该算法是完全分布式的,且不依赖于任何特殊的机器人通信网络结构.该算法利用机器人所测局部地图的历史数据和当前数据之间的新增信息,使每个机器人都能同步地获取一致的、最新的全局地图.在有限的网络连接条件下,所提出的地图融合算法能够通过渐近收敛的方式获得准确的全局地图.在每一次迭代中,每个机器人得到的全局地图都是无偏的.在实验中通过实际环境的RGB-D(彩色-深度)数据验证了算法的有效性.     

一种桌面机器人及其自主地图绘制算法

利用嵌入式技术设计了一种桌面机器人系统,机器人体积不到200 cm3,系统利用全局摄像机采集图像,通过无线通信组件对机器人定位导航,从而进行面向地图绘制的智能行为研究;从桌面机器人系统采集到地图信息,并生成神经网络训练样本,利用可增长自组织特征映射图GSOM(Growing Self-organizing Map)的地图绘制算法,通过不断增加新的神经元实现网络规模的增长,从而生成以少数SOM图神经元分布描述环境特征信息的拓扑地图;在机器人系统上进行了基于GSOM模型的自主地图的绘制实验,并利用所得拓扑地图进行了准确的机器人导航实验.实验结果表明基于GSOM的自主地图绘制方法可行,机器人系统表现出类似生物的自主智能行为.该方法可以应用于大环境下机器人的自主地图测绘与导航.     

基于免疫自适应遗传算法的机器人栅格地图融合

融合各机器人独自创建的环境地图,实现信息共享,是提高分布式多移动机器人系统环境探索效率的关键.研究了在没有公共参考坐标系及机器人相对位置信息未知情况下的栅格地图融合问题,提出了一种基十免疫自适应遗传算法的栅格地图融合方法,该算法把反映两个栅格地图重叠区域相异程度的优化函数作为抗原,每个可能的平移、旋转平面转换对应一个抗体.仿真结果表明了该算法可以较快的收敛速度和较强的全局搜索能力,搜索到两个栅格地图的最佳重叠区域,实现地图融合.     

多机器人地图融合方法研究

多机器人建图是实现机器人自主导航,完成复杂智能任务的关键.其中如何将不同机器人采集的数据融合到全局地图中,成了多机器人建图中的一个核心问题.文中采用独立探索、集中建图的探索策略,提出一种基于改进差异进化算法的多机器人概率栅格地图的融合.该算法在地图相似度的概念基础上,建立相异度函数,利用改进的进化算法搜索策略快速地搜索各局部地图之间的最大重叠部分,实现了多机器人系统栅格地图的融合,有效的解决了相对位置未知情况下的地图创建问题.通过实验验证了该方法正确、可行.     

一种基于离散时间一致性理论的多机器人分布式巡逻算法

在多机器人巡逻任务中,由于通信距离的限制,单个机器人很难获得全局信息。然而,现有的大多数多机器人分布式巡逻算法都要求每个机器人获得其巡逻区域的全局信息进行决策。因此,考虑到通信半径约束和局部信息约束,为了通过相邻机器人之间的交互完成巡逻任务,基于离散时间一致性理论提出了两种巡逻算法。算法1使用全局信息进行决策,算法2基于离散时间一致性理论实现局部信息对全局信息的预测进行决策。通过模拟器Stage对所提算法与对比算法在不同机器人数量、通信半径、地图环境下进行了对比。实验验证了所提出的基于局部信息的分布式多机器人巡逻算法具有与原算法类似的特性和性能,能够使机器人在没有全局信息的情况下判断全局状态,并基于邻居之间的协商完成巡逻任务。     

全自主机器人足球系统的全局地图构建研究

研究和讨论了如何通过多机器人的协作,实现全局地图的构建．在单个机器人通过自身携带的多传感器进行局部地图构建的基础上,研究了前向单目视觉传感器的建模方法,在此观测模型的基础上,用极大似然融合算法对球的位置信息进行融合,而对于多机器人返回的对方机器人位置信息,使用基于密度的空间聚类算法（DBSCAN）进行信息融合,从而实现全局地图构建．实验结果表明,通过多机器人的协作,可以准确地构建出全局地图,弥补了单个机器人自身传感器的有限感知范围,本文研究的方法完全满足全自主机器人足球比赛中动态环境地图构建的需要．     

多机器人同步定位与地图构建的地图融合算法的改进

本文主要研究了多机器人同步定位与地图构建(SLAM)的地图实时融合问题.在本文中提出一种混合的SLAM算法(HybridSLAM)算法,可以同时观测和更新多个路标,并根据FastSLAM2.0思想利用选取的最准确的路标观测值来修正机器人位姿.然后,在改进HybridSLAM算法基础上,进一步提出一种改进的多机器人HybridSLAM算法(MR–IHybridSLAM).每个机器人在不同初始位置运行IHybridSLAM算法构建子地图,并将子地图信息实时发送到同一工作站中.根据卡尔曼滤波(KF)原理将每个机器人构建的子地图融合成全局地图.最后,通过仿真实验构建多机器人融合的特征地图并与单一机器人快速的SLAM算法(FastSLAM)和HybridSLAM算法构建的地图进行误差对比,进一步来验证该算法的准确性、快速性和可行性.     

低带宽条件下机器人探索地图的传输方法

为了满足用户在无线低带宽条件下高效构建移动机器人探索地图的需求,设计并实现了一种机器人探索地图远程传输系统。该系统通过基于占据栅格的机器人同时定位与地图创建算法(Fast-SLAM)进行探索地图的构建;针对无线低带宽环境下地图高效传输问题,对地图数据进行压缩并设计了地图交互协议,采用C/S模式实现地图准确、高效的无线传输。实验结果表明,该系统解决了无线低带宽条件下大面积地图高效传输问题,满足用户方便、高效、准确地构建探索地图的要求。     

多机器人协同的SLAM算法研究

针对传统的室内多机器人SLAM算法存在探索任务分配灵活低,重叠度高,导致地图融合和建图精度不高的问题。设计一个基于PSO算法的多机器人协同建图与路径规划系统。首先,采用SLAM系统中的Gmapping算法作为基础算法,加入PSO算法将地图融合问题转化为最优求解问题,即找到两个地图重叠度最高的转换矩阵,实现地图融合和多机器人协同建图。结果表明,相同室内环境下,单机器人的平均探索时间为216 s,探索覆盖率为73..38%;而双机器人的平均探索时间仅为47 s,比单机器人的探索时间低了169 s;且双机器人的探索覆盖率为99.69%,比单机器人高出了26.31%。由此说明,双机器人的探索效率和探索覆盖率更高。对比于现有的EKF-CSLAM算法和基于因子图地图融合算法,本算法的建图精度高达99.75%。地图融合和建图精度明显更佳,进一步说明提出的融合算法可提升多机器人室内环境协同建图的效率和鲁棒性。     

多机器人协同SLAM技术研究进展

由于单机器人同步定位与建图（SLAM）技术在实际应用中的局限性,多机器人协同SLAM技术以较强的灵活性和鲁棒性受到研究人员的广泛关注,并且在农业生产、环境监测、海上搜救等领域具有巨大应用前景。多机器人协同SLAM是多机器人协同工作的核心及大范围复杂环境内及时获得场景感知信息的关键,能使多个机器人在协同工作时共同定位并构建任务空间地图,主要基于单机器人SLAM算法、多机器人系统架构、地图融合等技术实现。结合多机器人协同SLAM的发展历程,对比分析当前主流的多机器人协同SLAM算法。从传感器的角度,将多机器人协同SLAM分为激光协同SLAM、视觉协同SLAM以及激光视觉融合协同SLAM三类,并对多机器人协同SLAM的架构选择、多机通信、相对位姿、地图融合和后端优化问题进行讨论,同时指出异构机器人协同、基于深度学习的语义SLAM是多机器人协同SLAM的未来发展趋势。     

Distributed multi-robot coordination in area exploration

This paper proposes a reliable and efficient multi-robot coordination algorithm to accomplish an area exploration task given that the communication range of each robot is limited. This algorithm is based on a distributed bidding model to coordinate the movement of multiple robots. Two measures are developed to accommodate the limited-range communications. First, the distances between robots are considered in the bidding algorithm so that the robots tend to stay close to each other. Second, a map synchronization mechanism, based on a novel sequence number-based map representation and an effective robot map update tracking, is proposed to reduce the exchanged data volume when robot subnetworks merge. Simulation results show the effectiveness of the use of nearness measure, as well as the map synchronization mechanism. By handling the limited communication range we can make the coordination algorithms more realistic in multi-robot applications.     

基于卡诺图的三变量可逆逻辑综合算法

提出了一种基于卡诺图的可逆逻辑综合算法,该算法可以快速地求解带垃圾位的可逆逻辑综合问题。大量特定的可逆逻辑门都不可避免地带有一定的垃圾位, 如果使用真值表、置换群等经典可逆逻辑综合算法求解这些带垃圾位的可逆逻辑门,则因无法获得全局状态而很难得到结果。根据卡诺图的特点,将可逆逻辑问题分解为多个变量分别求解,无需关心全局状态。提出的卡诺图可逆逻辑综合算法 根据在卡诺图上的邻接性将3变量可逆逻辑问题划分为5个等价类;对每个等价类分别进行计算,在常数时间内解决了带垃圾位的可逆逻辑综合问题。     

Efficient Boustrophedon Multi-Robot Coverage: an algorithmic approach

This paper presents algorithmic solutions for the complete coverage path planning problem using a team of mobile robots. Multiple robots decrease the time to complete the coverage, but maximal efficiency is only achieved if the number of regions covered multiple times is minimized. A set of multi-robot coverage algorithms is presented that minimize repeat coverage. The algorithms use the same planar cell-based decomposition as the Boustrophedon single robot coverage algorithm, but provide extensions to handle how robots cover a single cell, and how robots are allocated among cells. Specifically, for the coverage task our choice of multi-robot policy strongly depends on the type of communication that exists between the robots. When the robots operate under the line-of-sight communication restriction, keeping them as a team helps to minimize repeat coverage. When communication between the robots is available without any restrictions, the robots are initially distributed through space, and each one is allocated a virtually-bounded area to cover. A greedy auction mechanism is used for task/cell allocation among the robots. Experimental results from different simulated and real environments that illustrate our approach for different communication conditions are presented.     

基于双混沌系统的数字混沌加密算法

由于混沌信号的隐蔽性、不可预测性、高度复杂性和易于实现等特性,基于混沌系统的加密算法也得到了广泛的研究.提出了一种基于Cat 映射和改进的Logistic 映射双混沌系统的数字混沌加密算法,并对算法的安全性和加密性能进行了分析.结果表明:算法具有较高的强度和较快的加密速度,可以应用于实时性较高的场合.     

Robot Formations Using a Single Camera and Entropy-based Segmentation

This work presents a new problem along with our new algorithm for a multi-robot formation with minimally controlled conditions. For multi-robot cooperation, there have traditionally been prevailing assumptions in order to collect the necessary information. These assumptions include the existence of communication systems among the robots or the use of specialized sensors such as laser scanners or omnidirectional cameras. However, they are not always valid, especially in emergency situations or with miniature robots. We, therefore, need to deal with the conditions that have received less attention in research regarding a multi-robot formation. There are several challenges: (1) less information is available than the well-known formation algorithms assume, (2) following strategies for deformable shapes in a formation with only local information available are needed, and (3) target segmentation without any markers is required. This work presents a formation algorithm based on a visual tracking algorithm, including how to process the image measurements provided by a single monocular camera. Through several experiments with real robots (developed at the University of Minnesota), we show that the proposed algorithms work well with minimal sensing information.     

A learning particle swarm optimization algorithm for odor source localization

This paper is concerned with the problem of odor source localization using multi-robot system. A learning particle swarm optimization algorithm, which can coordinate a multi-robot system to locate the odor source, is proposed. First, in order to develop the proposed algorithm, a source probability map for a robot is built and updated by using concentration magnitude information, wind information, and swarm information. Based on the source probability map, the new position of the robot can be generated. Second, a distributed coordination architecture, by which the proposed algorithm can run on the multi-robot system, is designed. Specifically, the proposed algorithm is used on the group level to generate a new position for the robot. A consensus algorithm is then adopted on the robot level in order to control the robot to move from the current position to the new position. Finally, the effectiveness of the proposed algorithm is illustrated for the odor source localization problem.     

Multi-robot coalition formation

As the community strives towards autonomous multi-robot systems, there is a need for these systems to autonomously form coalitions to complete assigned missions. Numerous coalition formation algorithms have been proposed in the software agent literature. Algorithms exist that form agent coalitions in both super additive and non-super additive environments. The algorithmic techniques vary from negotiation-based protocols in multi-agent system (MAS) environments to those based on computation in distributed problem solving (DPS) environments. Coalition formation behaviors have also been discussed in relation to game theory. Despite the plethora of MAS coalition formation literature, to the best of our knowledge none of the proposed algorithms have been demonstrated with an actual multi-robot system. There exists a discrepancy between the multi-agent algorithms and their applicability to the multi-robot domain. This paper aims to bridge that discrepancy by unearthing the issues that arise while attempting to tailor these algorithms to the multi-robot domain. A well-known multi-agent coalition formation algorithm has been studied in order to identify the necessary modifications to facilitate its application to the multi-robot domain. This paper reports multi-robot coalition formation results based upon simulation and actual robot experiments. A multi-agent coalition formation algorithm has been demonstrated on an actual robot system.