Concurrent Map Building and Behavior Learning for Navigation in Unknown Environments

In this paper, we report a robust and low-cost navigation algorithm for an unknown environment based on integration of a grid-based map building algorithm with behavior learning. The study focuses on mobile robots that utilize ultrasonic sensors as their prime interface with the outside world. The proposed algorithm takes into account environmental information to augment the readings from the low angular accuracy sonar measurements for behavior learning. The environmental information is obtained by an online grid-based map learning design that is concurrently operating with the behavior learning algorithm. The proposed algorithm is implemented and tested on an in-house-built mobile robot, and its performance is verified through online navigation in an indoor environment.     

Prune-Able Fuzzy ART Neural Architecture for Robot Map Learning and Navigation in Dynamic Environments

Mobile robots must be able to build their own maps to navigate in unknown worlds. Expanding a previously proposed method based on the fuzzy ART neural architecture (FARTNA), this paper introduces a new online method for learning maps of unknown dynamic worlds. For this purpose the new Prune-able fuzzy adaptive resonance theory neural architecture (PAFARTNA) is introduced. It extends the FARTNA self-organizing neural network with novel mechanisms that provide important dynamic adaptation capabilities. Relevant PAFARTNA properties are formulated and demonstrated. A method is proposed for the perception of object removals, and then integrated with PAFARTNA. The proposed methods are integrated into a navigation architecture. With the new navigation architecture the mobile robot is able to navigate in changing worlds, and a degree of optimality is maintained, associated to a shortest path planning approach implemented in real-time over the underlying global world model. Experimental results obtained with a Nomad 200 robot are presented demonstrating the feasibility and effectiveness of the proposed methods.     

未知环境中移动机器人实时导航与避障的分层模糊控制

为了解决单模糊控制器的“规则库爆炸”问题,设计了一种分层的模糊控制器,用于指导移动机器人通过未知环境到达指定的目标点．控制器根据8个超声传感器的信息和目标相对于机器人的方位确定机器人的运动．首先,每个超声传感器的信息被输入到危险度模糊控制器（DFC）中,产生关于周围环境中障碍物危险度的模糊向量．这些模糊向量经过融合与归一化处理后分别输入到上层的速度模糊控制器（VFC）和角速度模糊控制器（RFC）的推理机中．VFC根据目标的距离和障碍物的危险度控制机器人的前进速度．RFC根据目标的方向和障碍物的危险度控制机器人的转向,并采用最大隶属度法的反模糊化策略解决“对称不确定”问题．仿真与实验结果证明了所设计的模糊控制器简单而有效．     

基于模糊控制器的未知环境下移动机器人导航

研究机器人导航控制优化难题时,为实现未知环境中移动机器人自主导航并解决反应式导航策略中存在的局部陷阱问题,提出一种局部路径规划与目标切换相结合的导航方法.首先分析了移动机器人动力学模型,应用模糊推理构建反应式模糊控制器实现局部路径规划,并提出一种改进的目标切换方式,以机器人与目标相对方向的变化作为陷阱区域判断条件,当检测到陷阱情况时,引入合理的虚拟子目标,面向运动,直到脱离陷阱状态并恢复实际目标.方法可有效驱动机器人在复杂未知环境下以合理的路径脱离陷阱区域到达目标.仿真结果验证了方法的可行性和有效性,为应用于实际系统提供了可靠依据.     

大规模环境下拓扑地图在线创建与导航.doc

本文提出了一种新型的拓扑地图，该地图用激光的扇区特征和视觉的比例不变特征（SIFT）来联合表示节点。与传统地图相比，该地图在创建过程中不依赖任何人工路标和机器人的全局定位。机器人通过综合考虑单个节点的相似度和不同节点间的空间关系，利用隐马尔可夫模型来提高节点识别的准确率。实验表明，本文的拓扑地图不仅易于创建和维护，而且适用于机器人在大规模室内环境下的自主导航。     

一种基于声纳信息的移动机器人实时导航方法

提出了一种基于声纳信息的移动机器人实时导航方法。首先建立声纳感知数据向地图映射的概率模型,将声纳感知到的环境信息以基于栅格的概率值进行表示,并利用D-S证据理论对其进行数据融合,得到机器人的局部环境。在此基础上,采用基于滚动窗口的方法进行移动机器人路径规划,最终实现实时导航。试验结果表明该方法是可行和有效的。     

室内未知环境下移动机器人特征地图创建研究

介绍了在室内未知环境下移动机器人利用激光雷达、电子罗盘和里程计等传感器信息创建特征地图的方法;从激光雷达数据中提取直线特征作为地图的主要环境描述特征,采用构建直线模板的方法对雷达数据进行分簇,通过最小二乘法拟合出相应的直线并对冗余地图线段进行合并,从而得到较精确的特征地图;实验表明该机器人建立的环境特征地图是精确有效的,且与栅格地图相比数据量小,可进一步用于机器人的避障、路径规划等复杂任务.     

一种用于导航的2.5维地图的构建

为了使仿人机器人能够在真实世界中自由行走,包括上下楼梯、跨过障碍物,本文提出了一种构建机器人环境的2.5维网格地图的方法。首先利用传感器数据建立并更新一个3D占有率网格和一个平地网格,3D占有率网格为最终的地图提供概率支持,以保证环境模型对传感器噪声的鲁棒性,平地网格用来存储平面高度值。然后结合两个网格建立导航地图,该地图上每一个单元格被标记为平地或障碍物类型以及它的高度值,平地的高度信息是精确的而障碍物的高度信息是粗略的。最后在仿真平台上验证了所提出的方法,仿真结果证实此方法能够有效地产生用于机器人避障和路径规划的地图。     

移动机器人在未知狭窄环境中的路径规划

在障碍物体积比较庞大,自由空间相对狭窄的未知环境中,人工势场法很容易产生反复、徘徊等现象．本文结合几何信息和参考方向来纠正人工势场法这些缺陷,实现在这类环境中的有目的的平滑的路径规划．并且提出一种能够适应复杂环境的避障策略．仿真结果证明了上述方法的有效性．     

基于神经网络的信息收集机器人导航界面

采用任务分派型策略远程导航一个坦克型救援机器人，为某化工厂在灾难发生时收集危险信息。远程人员用鼠标点击目标图像给出导航任务。系统自动计算目标方位，并规划路径，发出底层命令，将机器人移动到目标位置。系统采用BP神经网络技术，从被点击的目标图像在窗口中的位置求解目标的世界坐标。实验结果表明，基于神经网络的导航界面能够很好地实现远程人员分派的导航任务。     

Novel Autonomous Navigation Algorithms in Dynamic and Unknown Environments

Because the range of mobile robot sensors is limited and navigation maps are not always accurate, autonomous navigation in dynamic and unknown environments is a big challenge. In this article, we propose two novel autonomous navigation algorithms, which are based on the analysis of three conditions for unobserved and uncertain environments during navigation.

The algorithm for a dynamic environment uses the “known space” and “free space” conditions. It corrects false obstacles in the map when the conventional path is stuck. The navigation algorithm for unknown environments uses the “unknown space” and “free space” conditions. We use the Monte Carlo method to evaluate the performance of our algorithms and the other methods. Experimental results show that our autonomous navigation algorithms are better than the others.     

移动机器人全覆盖路径规划优化方法

从全局优化的角度出发,提出一种基于子区域分割的环境建模方法,将各个子区域缩成节点、子区域重心间距离缩成节点间连线,建立起含障区域的全连通图——广义距离矩阵模型,对Hopfield神经网络求解旅行商问题的动态规划方法进行改进后,将其用于求该模型的最优有向连通图。机器人沿最短路径完成覆盖,就是按最优顺序走过连通图中所有节点并依次覆盖各节点所代表的子区域,从而完成移动机器人在含障区域内的全覆盖路径规划问题的优化解决方案。     

未知环境中地图创建的一种改进算法

基于栅格的地图创建是概率模型:工作环境被划分成栅格,每一个栅格赋一个值,标志栅格中有障碍物的概率。在研究中发现它存在一些问题,如把移动缓慢的物体作为路标。为了解决这些问题,通过引入临时局部栅格法(TLOG),给出了改进算法。     

一种动态未知环境中自主机器人的导航方法

提出一种动态未知环境中机器人自主导航方法,利用少量的人类辅助避免了繁琐的地图描述．该方法分两个阶段：用户引导阶段和自主导航阶段．在用户引导阶段,利用多种传感器信息融合生成局部环境的粗略的极坐标地图,利用它可以得到全局地图,还给出了消除传感器数据误差的方法;在自主导航阶段,利用引导阶段得到的地图在动态环境中进行运动,并给出了运动控制的约束条件以及动态避障的方法．机器人利用该方法可以处理突发的障碍物,还能对路径进行优化,实验结果证明了其有效性．     

A Vision and GPS-Based Real-Time Trajectory Planning for a MAV in Unknown and Low-Sunlight Environments

In this paper we address the problem of real-time optimal trajectory generation of a micro Air Vehicle (MAV) in unknown and low-sunlight environments. The MAV is required to navigate from an initial and outdoor position to a final position inside of a building. In order to achieve this goal, the MAV must estimate a window of the building. For this purpose, we develop a safe path planning method using the information provided by the GPS and a consumer depth camera. With the aim of developing a safe path planning with obstacle avoidance capabilities, a model predictive control approach is developed, which uses the environment information acquired by the navigation system. The results are tested on simulations and some preliminary experimental results are given. Our system’s ability to identify and estimate a window model and the relative position w.r.t. the window is demonstrated through video sequences collected from the experimental platform.     

基于神经网络的未知环境路径规划算法研究

文章提出了一种新的神经网络算法——“距离定位法”来实现机器人在未知环境情况下的路径规划。地图采用神经元阵列表示,机器人通过自带传感器收集周围局部环境信息以及与目标点的距离信息,经过对局部神经网络的实时训练,可以快速地产生一条光滑无碰撞且简捷有效的运动轨迹。算法在静态和动态环境下均能有高效率的路径搜索表现。模拟仿真结果也证明了算法的有效性。     

未知环境中一种基于激光雷达的全局位姿估计算法

1.引言 在许多应用中,移动机器人都必须知道它自身的位置[1],以及如何在不断跟踪自身的全局位姿的同时有效地到达环境中的另一个位置.因此近年来机器人的自定位获得了研究人员的广泛关注.由于激光雷达具有精度高的特点,已成为多数移动机器人配备的传感器之一,研究人员也提出了许多基于激光雷达的定位方法[2].这些方法主要分为两大类:把距离数据与全局地图进行匹配的方法和匹配一对距离数据帧的方法.在未知环境中,由于不具备先验地图,机器人只能使用两帧距离数据帧匹配的方法来跟踪位姿,并逐渐地建立起全局地图.     

不确定动态环境下移动机器人的完全遍历路径规划

基于生物激励神经网络、滚动窗口和启发式搜索,提出了一种新的完全遍历路径规划方法．该方法用Grossberg的生物神经网络实现移动机器人的局部环境建模,将滚动窗口的概念引入到局部路径规划,由启发式算法决定滚动窗口内的局域路径规划目标．该方法能在不确定动态环境中有效地实现机器人自主避障的完全遍历路径规划．仿真研究证明了该方法的可用性和有效性．     

A New Navigation Function Based Decentralized Control of Multi-Vehicle Systems in Unknown Environments

This paper deals with navigation for a group of vehicles while avoiding collisions and ensuring global network connectivity in unknown environments using a new decentralized navigation function. It is pointed out that the traditional navigation function is not effective in the situation where vehicles work in a large environment. It is shown that in this situation velocity of the vehicle would be extremely small, which is not realistic in practical applications. This paper proposes a new decentralized navigation function with a novel goal function based on which a decentralized control law that is along the negative gradient of the decentralized navigation function is derived. Finally the proposed decentralized control law is applied in a multi-vehicle navigation scenario. Based on the properties of the proposed navigation function and dual Lyapunov theorem, a sufficient condition is derived for vehicles to converge to regions surrounding their corresponding goal positions in a collision-free and connectivity-keeping manner. Simulation results demonstrate the efficacy of the proposed method.     

Neural Network Controller against Environment: A Coevolutive approach to Generalize Robot Navigation Behavior

In this paper, a new coevolutive method, called Uniform Coevolution, is introduced to learn weights of a neural network controller in autonomous robots. An evolutionary strategy is used to learn high-performance reactive behavior for navigation and collisions avoidance. The introduction of coevolutive over evolutionary strategies allows evolving the environment, to learn a general behavior able to solve the problem in different environments. Using a traditional evolutionary strategy method, without coevolution, the learning process obtains a specialized behavior. All the behaviors obtained, with/without coevolution have been tested in a set of environments and the capability of generalization is shown for each learned behavior. A simulator based on a mini-robot Khepera has been used to learn each behavior. The results show that Uniform Coevolution obtains better generalized solutions to examples-based problems.