Autonomous robot navigation in outdoor cluttered pedestrian walkways

This paper describes an implementation of a mobile robot system for autonomous navigation in outdoor concurred walkways. The task was to navigate through nonmodified pedestrian paths with people and bicycles passing by. The robot has multiple redundant sensors, which include wheel encoders, an inertial measurement unit, a differential global positioning system, and four laser scanner sensors. All the computation was done on a single laptop computer. A previously constructed map containing waypoints and landmarks for position correction is given to the robot. The robot system's perception, road extraction, and motion planning are detailed. The system was used and tested in a 1‐km autonomous robot navigation challenge held in the City of Tsukuba, Japan, named “Tsukuba Challenge 2007.” The proposed approach proved to be robust for outdoor navigation in cluttered and crowded walkways, first on campus paths and then running the challenge course multiple times between trials and the challenge final. The paper reports experimental results and overall performance of the system. Finally the lessons learned are discussed. The main contribution of this work is the report of a system integration approach for autonomous outdoor navigation and its evaluation. © 2009 Wiley Periodicals, Inc.     

基于多传感器的可变形机器人自主控制方法研究

将GPS、电子罗盘、倾角仪、码盘传感器应用到可变形机器人自主运动控制中。针对可变形机器人自身结构特点，提出了一种基于多传感器信息融合的可变形机器人在野外环境中自主控制的方法。该方法主要实现了在非结构环境中机器人的自主变形、自主避障和自主导航定位的功能。实验验证了该方法的有效性。     

Sensor Integration for Satellite-Based Vehicular Navigation Using Neural Networks

Land vehicles rely mainly on global positioning system (GPS) to provide their position with consistent accuracy. However, GPS receivers may encounter frequent GPS outages within urban areas where satellite signals are blocked. In order to overcome this problem, GPS is usually combined with inertial sensors mounted inside the vehicle to obtain a reliable navigation solution, especially during GPS outages. This letter proposes a data fusion technique based on radial basis function neural network (RBFNN) that integrates GPS with inertial sensors in real time. A field test data was used to examine the performance of the proposed data fusion module and the results discuss the merits and the limitations of the proposed technique     

Visual navigation and obstacle avoidance using a steering potential function

Humans have a remarkable ability to navigate using only vision, but mobile robots have not been nearly as successful. We propose a new approach to vision-guided local navigation, based upon a model of human navigation. Our approach uses the relative headings to the goal and to obstacles, the distance to the goal, and the angular width of obstacles, to compute a potential field over the robot heading. This potential field controls the angular acceleration of the robot, steering it towards the goal and away from obstacles. Because the steering is controlled directly, this approach is well suited to local navigation for nonholonomic robots. The resulting paths are smooth and have continuous curvature. This approach is designed to be used with single-camera vision without depth information but can also be used with other kinds of sensors. We have implemented and tested our method on a differential-drive robot and present our experimental results.     

A Highly-Maneuverable Demining Autonomous Robot: an Over-Actuated Design

Based on the well-known advantages of using an over-actuated mechanism for robots, this research proposes a holonomic highly-maneuverable autonomous robot design for demining service applications. The proposed approach provides an interesting compromise between the design requirements of the demining robot applications and the over-actuated autonomous robots. The robot body is mainly divided into two parts: the first part provides the robot with its required locomotion and it consists of a driving/steering subsystem with four driving wheels (4WD), four steering mechanisms (4SW), and a passive suspension subsystem. The second part is a manipulator with three degrees of freedom that is designed based on two parallelogram mechanisms. The proposed design insures many advantages over existing designs, including stability, maneuverability, autonomous navigation, and simplicity of the control effort constraints. The robot model and its corresponding stability analysis were conducted and simulated in order to evaluate the motion of the robot over different environments rough terrains and slanted surfaces. Moreover, a prototype of the proposed robot was developed and built and different types of sensors were used in order to help it take precise actuation decisions for navigation and control. The prototype was experimentally tested for different scenarios and environments in order to validate the proposed design. The testing results demonstrated decent performance of the robot in autonomous navigation and in localizing the detected objects.     

行人导航系统中航迹推算参数估计方法的研究

将GPS/DR组合导航技术应用到行人导航系统中。利用加速度计对行人步态进行判别,将神经网络用于行人步幅信息的标定。同时利用电子罗盘实现方位角的测量,并结合加速度计信息进行倾斜角度的误差补偿。现场测试结果表明,本文提出的DR参数估计方法不但提高参数估计的精度,而且能够满足行人导航定位的要求。     

基于模糊神经网络的六足机器人自主导航闭环控制系统设计

针对未知环境中六足机器人的自主导航问题,设计了一种基于模糊神经网络的自主导航闭环控制算法,并依据该算法设计了六足机器人的导航控制系统．算法融合了模糊控制的逻辑推理能力与神经网络的学习训练能力,并引入闭环控制方法对算法进行优化．所设计的控制系统由信息输入、模糊神经网络、指令执行以及信息反馈4个模块组成．环境及位置信息的感知由GPS（全球定位系统）传感器、电子罗盘传感器和超声波传感器共同完成．采用C语言重建模糊神经网络控制算法,并应用于该系统．通过仿真实验,从理论上论证了基于模糊神经网络的闭环控制算法性能优于开环控制算法,闭环控制算法能够减小六足机器人在遇到障碍物时所绕行的距离,行进速度提高了6.14%,行进时间缩短了8.74%．在此基础上,开展了实物试验．试验结果表明,该控制系统能够实现六足机器人自主导航避障控制功能,相对于开环控制系统,能有效地缩短行进路径,行进速度提高了5.66%,行进时间缩短了7.25%,验证了闭环控制系统的可行性和实用性．     

TCM3电子罗盘的特性与应用

电子罗盘正广泛应用于各类导航定位系统中。介绍了TCM3电子罗盘的特性,详细说明了TCM3的控制编程和航向、俯仰、横滚等参数的读取,利用TCM3和GPS组合实现在农业机器人控制平台上的导航应用。经试验测试,TCM3在农业机器人导航平台上航向精度为±1℃,能够满足大部分精准农业应用的需要。     

Learning locomotion reflexes: A self-supervised neural system for a mobile robot

This article is concerned with an artificial neural system for a mobile robot reactive navigation in an unknown, cluttered environment. Reactive navigation is a process of immediately choosing locomotion actions in response to measured spatial situations, while no planning occurs. A task of a presented system is to provide a steering angle signal letting a robot reach a goal while avoiding collisions with obstacles. Basic reactive navigation methods are briefly characterized, special attention is paid to a neural approach to the considered problem. The authors describe the system's architecture and important details of the algorithm. The main parts of the system are: the Fuzzy ART neural self-organizing classifier, performing a perceptual space partitioning, and a neural associative memory, memorizing the system's experience and superposing influences of different behaviors. Tests show that the learning process, starting from zero, is efficient, despite some initial fluctuations of its effectiveness.     

The visual homing problem: An example of robotics/biology cross fertilization

In this paper, we describe how a mobile robot under simple visual control can retrieve a particular goal location in an open environment. Our model neither needs a precise map nor to learn all the possible positions in the environment. The system is a neural architecture inspired by neurobiological analysis of how visual patterns named landmarks are recognized. The robot merges these visual informations and their azimuth to build a plastic representation of its location. This representation is used to learn the best movement to reach the goal. A simple and fast on-line learning of a few places located near the goal allows this goal to be reached from anywhere in its neighborhood. The system uses only a very rough representation of the robot environment and presents very high generalization capabilities. We describe an efficient implementation of autonomous and motivated navigation tested on our robot in real indoor environments. We show the limitations of the model and its possible extensions.     

湖水环境下自主监测船的GPS导航设计

建立导航系统所需的全局静坐标系、局部静坐标系、船体动坐标系和自主船运动学模型。模拟人的驾驶技术,建立巡航和定区域节能2种导航模式,设计推理规则。分析实测的电子罗盘和GPS数据误差原因。为提高定位精度,设计海明窗FIR数字滤波器以及巡航面积计算方法。基于VC++开发导航软件,在自主研发的监测船上开展实验。结果表明,FIR对电子罗盘信号的滤波效果优于GPS信号,巡航模式可实现大范围监测,定区域模式对重点区域进行监测时能耗较低。     

Real-time map building and navigation for autonomous robots inunknown environments

An algorithmic solution method is presented for the problem of autonomous robot motion in completely unknown environments. Our approach is based on the alternate execution of two fundamental processes: map building and navigation. In the former, range measures are collected through the robot exteroceptive sensors and processed in order to build a local representation of the surrounding area. This representation is then integrated in the global map so far reconstructed by filtering out insufficient or conflicting information. In the navigation phase, an A*-based planner generates a local path from the current robot position to the goal. Such a path is safe inside the explored area and provides a direction for further exploration. The robot follows the path up to the boundary of the explored area, terminating its motion if unexpected obstacles are encountered. The most peculiar aspects of our method are the use of fuzzy logic for the efficient building and modification of the environment map, and the iterative application of A*, a complete planning algorithm which takes full advantage of local information. Experimental results for a NOMAD 200 mobile robot show the real-time performance of the proposed method, both in static and moderately dynamic environments.     

助行机器人导航与远程监护系统的设计与实现

针对助行机器人在室外未知环境中的导航需求,分析了不同导航方式的优缺点,设计并实现基于全球定位系统(GPS)的机器人定位导航系统.详细地描述了室外环境地图的创建过程和地图精度的控制.为了提高定位的精度,利用地图匹配修正GPS定位误差,同时融合机器人实时速度数据,得到最终的机器人位置.在机器人定位的基础上,实现助行机器人的...     

Localization along routes,based upon iconic and Global Positioning System information in large-scale outdoor environments

This paper proposes a method of robot navigation in outdoor environments based upon panoramic view and Global Positioning System (GPS) information. Our system is equipped with a GPS navigator and a camera. The route scene can be described by three-dimensional objects extracted as landmarks from panoramic representations. For an environment having limited routes, a two-dimensional map can be made based upon routes scenes, assuming that the topological relation of routes at intersections is known. By using GPS information, the global position of a mobile robot can be known, and a coarse-to-fine method is used to generate an outdoor environment map and locate a mobile robot. First, a robot finds its approximate position based on the GPS information. Then, it identifies its location from the image information. Experimental results in outdoor environments are given.     

Smartphone-based pedestrian tracking in indoor corridor environments

As the use of smartphones spreads rapidly, user localization becomes an important issue for providing diverse location-based services (LBS). While tracking users in outdoor environments is easily done with GPS, the solution for indoor tracking is not trivial. One common technique for indoor user tracking is to employ inertial sensors, but such a system needs to be capable of handling noisy sensors that would normally lead to cumulative locating errors. To reduce such error, additional infrastructure has often been deployed to adjust for these cumulative location errors. As well, previous work has used highly accurate sensors or sensors that are strapped to the body. This paper presents a stand-alone pedestrian tracking system, using only a magnetometer and an accelerometer in a smartphone in indoor corridor environments that are normally laid out in a perpendicular design. Our system provides reasonably accurate pedestrian locations without additional infrastructure or sensors. The experiment results show that the location error is less than approximately 7 m, which is considered adequate for indoor LBS applications.     

Visual servoing control of autonomous robot calibration and navigation

This article addresses the problem of how to visually control a mobile robot in a navigation process. The algorithms proposed may be used either for external calibration to locate the robot accurately in a structured environment, or in visual servoing as feedback to the controller which is maintaining the robot on a navigation course. Herein, we examine the problem in a special case, where the ground plane is assumed to be horizontal and there are two locally parallel sidelines available. This assumption holds in many indoor environments, such as hallways, where the system's success has been demonstrated. The algorithms use geometric features such as vanishing points and line orientations. Both theoretical analysis and experimental results show that the algorithms work robustly and accurately. ©1999 John Wiley & Sons, Inc.     

Multi-sensor fusion methodology for enhanced land vehicle positioning

It is a main challenge for land vehicles to achieve reliable and low-cost navigation solution in various situations, especially when Global Positioning System (GPS) is not available. To address this challenge, we propose an enhanced multi-sensor fusion methodology to fuse the information from low-cost GPS, MEMS Inertial Measurement Unit (IMU), and digital compass in this paper. First, a key data preprocessing algorithm based on Empirical Mode Decomposition (EMD) interval threshold filter is developed to remove the noises in inertial sensors so as to offer more accurate information for subsequent modeling. Then, a Least-Squares Support Vector Machine (LSSVM)-based nonlinear autoregressive with exogenous input (NARX) model (LSSVM-NARX) is designed and augmented with Kalman filter (KF) to construct a novel LSSVM-NARX/KF hybrid strategy. In case of GPS outages, the recently updated LSSVM-NARX is adopted to predict and compensate for the INS position errors. Finally, the performance of proposed methodology was evaluated with real-world data collected in urban settings including typical driving maneuvers. The results indicate that the proposed methodology can achieve remarkable enhancement in positioning accuracy in GPS-denied environments.