湍流烟羽环境下多机器人主动嗅觉实现方法研究

给出了一种用于实现主动嗅觉(也称气味/气体源定位或化学烟羽跟踪)的多机器人协同搜索策略. 将蚁群算法与逆风搜索相结合用于协调多机器人的运动方向. 蚁群算法可有效调动机器人朝信息素高的区域运动且保证机器人之间的距离不会过大; 逆风搜索可降低算法过早地陷入局部最优的概率. 为正确判断转移方向, 蚁群算法中还增加了对历史信息的考虑. 在源头确认方面, 本文提出了气味/气体浓度持久性判断结合机器人旋转计算流体质量通量散度的方法. 仿真表明, 本文的主动嗅觉搜索策略可适用于湍流烟羽环境, 且可有效地逃脱浓度局部最优和风场的漩涡, 另外可最终确认源头位置.     

自主移动机器人路径规划与避障策略

文章提出一种基于深度确定策略梯度（Deep Deterministic Policy Gradient,DDPG）算法和激光雷达数据的路径规划与导航方法，通过在机器人操作系统（Robot Operating System,ROS）系统中搭建仿真实验环境，验证了该方法的有效性。实验结果表明，该方法在仿真实验中成功实现了机器人的路径规划与导航，具有较好的导航性能。     

未知环境下多机器人搜捕策略研究

针对在未知环境下多机器人围捕入侵者所存在的问题,提出了基于occupancy grid方法构造并合成环境地图指导单个机器人以分散搜索、抛物线模型预测并追踪入侵者、以及多机器人基于leader的可重构队形结构进行围捕的策略,使未知环境的地图构造和对入侵者追踪搜索过程得以同步完成,降低了机器人团队对环境的依赖,对未知环境具有较高的适应能力.最后通过仿真实验验证了该策略的正确性、有效性和鲁棒性.     

基于四叉树环境模型的轮式移动机器人平滑路径生成方法

生成平滑的路径是轮式动移机器人路径规划的要求．基于四叉树环境模型,本文提出 了生成平滑路径的算法．首先简单介绍了基于位置码的四叉树环境模型,然后详细分析了在 该环境模型下路径搜索结果的组成特点,并提出了相应的平滑路径生成策略．最后给出了路 径生成的算法,并通过仿真实验验证了算法的正确性．     

危险气体泄漏源搜寻多机器人系统的设计与实现

危险气体泄漏源搜寻是仿生嗅觉技术的重要应用领域之一.为了提高气体泄露源定位的效率和准确性,设计并实现了一种基于无线传感器网络的气源目标搜寻多机器人系统.该系统由多个嗅觉机器人组成,每个机器人作为无线传感器网络节点实现信息交换,协同工作,实现危险气体泄漏源的定位.嗅觉机器人以DSP处理器(TMS320F28335)为控制核心,对MOS气体传感器和风速传感器的输出信号进行融合,设计了浓度梯度与风速信息相结合的单一气体泄漏源搜寻算法.当嗅觉机器人完成气源定位时将发出警报,其他机器人利用装配的麦克风阵列和声源定位算法实现对泄漏源的间接定位.最后,为了说明所设计的多机器人系统对气体泄露源定位的有效性和准确性,本文设计了针对单一泄露源的气源搜寻实验进行验证.     

基于简化虚拟受力模型的群机器人多目标搜索协调控制

针对未知凸和非凸障碍物以及动态障碍物环境下群机器人多目标搜索问题,提出了一种基于简化虚拟受力分析模型的循障和避碰方法(SRSMT-SVF).对复杂环境下群机器人多目标搜索行为进行了分解并抽象出简化虚拟受力分析模型.基于此受力模型,设计了个体机器人协同搜索和漫游状态下的运动控制策略,使得机器人在搜索目标的同时能够实时避碰.通过对不同群体规模系统的仿真实验表明,本文控制方法能够使个体机器人在整个搜索过程中保持良好的避碰性能,有效地减少系统与环境之间和系统内部个体之间的碰撞冲突.相比于扩展粒子群算法(EPSO),本文方法使得搜索耗时和系统能耗至少减少了13.78%、11.96%,数值仿真结果验证了本文方法的有效性.     

基于无线传感器网络的气体泄漏源定位机器人设计

如何确定有害气体泄漏源的位置是机器人主动嗅觉要解决的关键问题。围绕移动机器人气体泄漏源定位问题,将Z字形算法和浓度梯度法相结合用于机器人气味源搜索运动控制,使其快速找到气味源。同时,在传统的移动嗅觉机器人上增加了无线传感器定位模块,使操作人员在远离泄漏源的电脑上即可获得气味源的坐标信息。实验证明：机器人可以找到泄漏源,并确定气味源位置,搜索效率比单独使用浓度梯度法高。     

RAOS:3维机器人主动嗅觉仿真平台

为便于开展气味源定位或烟羽建图等研究,设计了3维机器人主动嗅觉仿真平台RAOS(robot active olfaction simulator).RAOS围绕旋翼无人机主动嗅觉研究进行设计,同时支持地面移动机器人仿真,主要包括3维场景、机器人、风场、气味扩散及传感器仿真5部分.通过CAD(computer aided design)软件生成3维场景并导入仿真平台;采用CFD(computational fluid dynamics)软件仿真环境自由风场;基于旋翼无人机气动嗅觉效应模型仿真尾流诱导风场,并利用全连接网络近似计算诱导风场以提高计算实时性;结合CFD环境风场和烟丝扩散模型对气味扩散过程进行仿真;同时提出了简化的TDLAS(tunable diode laser absorption spectroscopy)传感器仿真模型.为验证仿真环境与真实环境中气味扩散过程的一致性,提出利用弗雷歇距离和推土机距离2个指标分别定量地描述气味扩散轮廓和气味浓度分布的相似性,结合KS(Kolmogorov-Smirnov)检验进行一致性判定.通过与实物实验及风洞数据对比,验证了RAOS平台仿真烟羽与真实环境烟羽扩散分布的一致性,可为3维环境主动嗅觉研究提供一致、可重复的仿真环境.     

基于虚拟子目标的移动机器人主动寻径导航

纯粹的反应式导航算法有时会出现“没有远见现象”,为此设计了一种基于行为和虚拟路径子目标的 移动机器人主动寻径导航策略．该策略首先在机器人的局部探测域内运用改进的可视点寻径法寻找最优虚拟子目 标,接着使用行为决策树实现快速的行为决策．机器人将如人类寻路一样,主动地灵巧绕过障碍物,基于圆弧轨迹 的运动方式使之能以平滑的路径到达目标．仿真结果验证了本策略的可行性和有效性．     

一种并行免疫进化策略算法研究

基于克隆选择原理，提出一种自适应并行免疫进化策略．在算法中根据抗体抗原亲和度将初始抗体种群分为两个子群，相应地提出了精英克隆算子和超变异算子．通过精英克隆算子提高算法局部搜索能力，同时利用超变异算子维持种群多样性，通过这两个功能互补算子的并行操作实现种群进化．仿真表明，自适应并行免疫进化策略搜索效率高，能有效抑制早熟收敛现象，可用于解决复杂机器学习问题．     

基于移动机器人的主动嗅觉技术研究

使用移动机器人来定位气味源已经成为一个研究热点,机器人主动嗅觉是指使用机器人自主发现并跟踪烟羽,最终确定气味源所在位置的技术。本文对当前主动嗅觉技术进行概述,并根据生物嗅觉行为介绍一种气味源定位算法,这种算法不依赖某一点气味浓度值,仅依靠气味浓度变化率就可找到气味源。并在高斯模型下对烟羽分布模型进行仿真。     

主动嗅觉研究现状

对主动嗅觉（或称移动机器人气味/气体定位）问题的研究现状进行了较为详细的介绍．分析了当前此研究所使用的具有代表性的气味/气体和风向传感器原理．总结了主动嗅觉所包含的三个步骤,即气味/气体烟羽的发现、跟踪和气味/气体源确认,及每一步所采取的主要策略．最后,指出了当前主动嗅觉研究的主要难点．     

基于认知差异的多机器人协同信息趋向烟羽源搜索方法

多机器人协同稀疏烟羽源搜索研究中,追求群体信息一致而忽视个体独立搜索能力的发挥,导致群体无法有效适应复杂搜索状况.为此,提出一种基于认知差异的协同信息趋向源搜索方法.首先,利用相对熵度量群内个体对源位置估计的认知差异;然后,据此赋予不同个体烟羽采样以相应权重,在贝叶斯推理过程自适应权衡自身线索与群体线索;最后,采用分布式信息熵决策实施协同信息趋向搜索.多种场景下的仿真结果验证了所提出算法的优越性.     

基于微粒群优化的有限通信多机器人气味寻源

考虑机器人间的通信受限约束,将机器人抽象为微粒,提出基于微粒群优化的多机器人气味寻源方法.首先,采用结合斥力函数的策略,引导机器人快速搜索烟羽;然后,基于无线信号对数距离损耗模型,估计机器人间的通讯范围,据此形成微粒群的动态拓扑结构,并确定微粒的全局极值;最后,将传感器的采样/恢复时间融入微粒更新公式,以跟踪烟羽.将所提出方法应用于3个不同场景的气味寻源,实验结果验证了该方法的有效性.     

A biomimetic robot for tracking specific odors in turbulent plumes

Two basic tasks must be performed by an olfactory robot tracking a specific odor source: navigate in a turbulent odor plume and recognize an odor regardless of its concentration. For these two tasks, we propose simple biologically inspired strategies, well suited for building dedicated circuits and for on-board implementation on real robots. The odor recognition system is based on a spiking neural network using a synchronization coding scheme. The robot navigation system is based on the use of bilateral comparison between two spatially separated gas sensors arrays at either side of the robot. We propose binary or analog navigation laws depending on the nature of the available sensory information extracted from the plume structure (isolated odor patches or smoother concentration field). Dominique Martinez received his PhD degree in electrical and electronic engineering from the University Paul Sabatier in Toulouse, France, in 1992. He was a post-doctoral fellow at MIT, Dept. Brain and Cog. Sciences, and Harvard, VLSI group, in Cambridge, MA, USA, in 1992 and 1994, respectively. From 1993 to 1999 he worked at LAAS-CNRS in Toulouse where his research interests were concerned with machine learning (artificial neural networks, support vector machines). In 2000 he joined LORIA in Nancy and his research interests currently focus on biologically-plausible spiking neural networks for sensory processing, with particular application to artificial olfaction (neuromorphic electronic noses). Olivier Rochel obtained his PhD from the LORIA/Université H. Poincaré, in Nancy, France, where he was working on modelling large and complex networks of biological neurons, and bio-inspired robotics. Now working in the Biosystems Group at the university of Leeds, his research interests lie in multi-disciplinary studies in computational neuroscience, modelling and simulation techniques in general, and biological data analysis. Etienne Hugues has received his Ph.D. in theoretical physics from Paris XI University (Orsay). He has been a postdoctoral researcher at INRIA where he worked on olfactory perception in animals and robots. He is now a postdoctoral researcher in the Physics Department of SUNY at Buffalo. His main research interest is in computational neuroscience.     

基于场景图谱的室内移动机器人目标搜索

在移动机器人执行日常家庭任务时,首先需要其能够在环境中避开障碍物,自主地寻找到房间中的物体。针对移动机器人如何有效在室内环境下对目标物体进行搜索的问题,提出了一种基于场景图谱的室内移动机器人目标搜索,其框架结合了导航地图、语义地图和语义关系图谱。在导航地图的基础上建立了包含地标物体位置信息的语义地图,机器人可以轻松对地标物体进行寻找。对于动态的物体,机器人根据语义关系图中物体之间的并发关系,优先到关系强度比较高的地标物体旁寻找。通过物理实验展示了机器人在语义地图和语义关系图的帮助下可以实现在室内环境下有效地寻找到目标,并显著地减少了搜索的路径长度,证明了该方法的有效性。     

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).     

Path planning strategy for autonomous mobile robot navigation using Petri-GA optimisation

In this paper, a novel knowledge based genetic algorithm (GA) for path planning of multiple robots for multiple targets seeking behaviour in presence of obstacles is proposed. GA technique has been incorporated in Petri-Net model to make an integrated navigational controller. The proposed algorithm is based upon an iterative non-linear search, which utilises matches between observed geometry of the environment and a priori map of position locations, to estimate a suitable heading angle, there by correcting the position and orientation of the robots to find targets. This knowledge based GA is capable of finding an optimal or near optimal robot path in complex environments. The Petri-GA model can handle inter robot collision avoidance more effectively than the stand alone GA. The resulting navigation algorithm has been implemented on real mobile robots and tested in various environments to validate the developed control scheme.     

Exploration strategies based on multi-criteria decision making for searching environments in rescue operations

Some applications require autonomous robots to search an initially unknown environment for static targets, without any a priori information about environment structure and target locations. Targets can be human victims in search and rescue or materials in foraging. In these scenarios, the environment is incrementally discovered by the robots exploiting exploration strategies to move around in an autonomous and effective way. Most of the strategies proposed in literature are based on the idea of evaluating a number of candidate locations on the frontier between the known and the unknown portions of the environment according to ad hoc utility functions that combine different criteria. In this paper, we show some of the advantages of using a more theoretically-grounded approach, based on Multi-Criteria Decision Making (MCDM), to define exploration strategies for robots employed in search and rescue applications. We implemented some MCDM-based exploration strategies within an existing robot controller and we evaluated their performance in a simulated environment.