Autonomous Mobile Robot System Research Articles

Emotion Behavior Learning System for Autonomous Mobile Robot Based on Target Selection-Type Q-Learning

Emotion Behavior Learning System for Autonomous Mobile Robot Based on Target Selection-Type Q-Learning

On-line modeling for real-time 3D target tracking

Model-based object tracking can provide autonomous mobile robotic systems with real-time 6-dof pose information, for example, enabling them to rendezvous with targets from a particular desired direction. Most existing model-based trackers, however, require the geometric model of the target to be known a priori, which may pose a practical problem in real-world environments. This paper presents a novel 3D modeler capable of building an approximate model of a target object on-line. The proposed technique rapidly constructs a 3D tessellated enveloping mesh and uses projective texture mapping to further model the target object’s surface features. Separation of the target object from background clutter is achieved via customizable interest filters. The resulting real-time object-tracking system was tested extensively via simulations and experiments.

Development of an Autonomous Mobile Robot with Several Sensors using Neuro‐Fuzzy Control Based on Server/Client Model

AbstractThe purpose of this paper is to detail the development of an autonomous mobile robot and a control support system. The robot has five infrared sensors and three ultrasonic sensors to enable it to follow a ‘ guide person’ with an infrared ray transmitter. The robot will follow the infrared rays emitted by a transmitter with the guide person, and move to the destination. The control system has been developed by the network technology based on server/client model. The advanced control strategy for the autonomous mobile robot is carried out with a high‐speed host server computer connected through the TCP/IP network. Therefore, it is enough for the CPU of the robot to be of low speed. In this paper, the autonomous mobile robot system and the control system using the server/client model are described. Copyright © 2008 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Real-time building of a thinning-based topological map

An accurate and compact map is essential to an autonomous mobile robot system. A topological map, one of the most popular map types, can be used to represent the environment in terms of discrete nodes with edges connecting them. It is usually constructed by Voronoi-like graphs, but in this paper the topological map is incrementally built based on the local grid map by using a thinning algorithm. This algorithm, when combined with the application of the C-obstacle, can easily extract only the meaningful topological information in real-time and is robust to environment change, because this map is extracted from a local grid map generated based on the Bayesian update formula. In this paper, position probability is defined to evaluate the quantitative reliability of the end node extracted by the thinning process. Since the thinning process builds only local topological maps, a global topological map should be constructed by merging local topological maps according to nodes with high position probability. For real and complex environments, experiments showed that the proposed map building method based on the thinning process can accurately build a local topological map in real-time, with which an accurate global topological map can be incrementally constructed.

Convergence of Autonomous Mobile Robots with Inaccurate Sensors and Movements

A number of recent studies concern algorithms for distributed control and coordination in systems of autonomous mobile robots. The common theoretical model adopted in these studies assumes that the positional input of the robots is obtained by perfectly accurate visual sensors, that robot movements are accurate, and that internal calculations performed by the robots on (real) coordinates are perfectly accurate as well. The current paper concentrates on the effect of weakening this rather strong set of assumptions and replacing it with the more realistic assumption that the robot sensors, movement, and internal calculations may have slight inaccuracies. Specifically, the paper concentrates on the ability of robot systems with inaccurate sensors, movements, and calculations to carry out the task of convergence. The paper presents several impossibility theorems, limiting the inaccuracy levels that still allow convergence, and prohibiting a general algorithm for gathering, namely, meeting at a point, in a finite number of steps. The main positive result is an algorithm for convergence under bounded measurement, movement, and calculation errors.

A Component-Oriented Programming for Embedded Mobile Robot Software

Applying software reuse to many Embedded Real-Time (ERT) systems poses significant challenges to industrial software processes due to the resource-constrained and real-time requirements of the systems. Autonomous Mobile Robot (AMR) system is a class of ERT systems, hence, inherits the challenge of applying software reuse in general ERT systems. Furthermore, software reuse in AMR systems is challenged by the diversities in terms of robot physical size and shape, environmental interaction and implementation platform. Thus, it is envisioned that component-based software engineering will be the suitable way to promote software reuse in AMR systems with consideration to general requirements to be self-contained, platform-independent and real-time predictable. A framework for component-oriented programming for AMR software development using PECOS component model is proposed in this paper. The main features of this framework are: (1) use graphical representation for components definition and composition; (2) target C language for optimal code generation with resource-constrained micro-controller; and (3) minimal requirement for run-time support. Real-time implementation indicates that, the PECOS component model together with the proposed framework is suitable for resource constrained embedded AMR systems software development.

전자 나침반과 초음파 센서를 이용한 이동 로봇의 Simultaneous Localization and Mapping

전자나침반(DMC)은 실내의 전자기적 요소나 강한 자성체 건물구조에서는 쉽게 방해를 받던 나침반보다 실내에서 간섭에 강한 특징을 가지고 있다. 그리고 초음파 센서는 물체와의 거리를 계산해 줄뿐만 아니라 값싼 센서로서 경제적인 이점을 가지고 있어 Simultaneous Localization and Mapping(SLAM)에서 많이 사용하고 있다. 본 논문에서는 자율 이동 로봇의 구동에서 전자나침반과 초음파 센서를 이용한 SLAM의 구현에 대해 연구하였다. 로봇의 특성상 한정된 센싱 데이터만으로 방향과 위치를 파악하고 그 데이터 값으로 가능한 빠르게 위치 측정을 하여야 한다. 그러므로 자율 이동 로봇에서의 SLAM 적용함으로 위치측정의 구현과 지도 작성을 수행한다. 그리고 SLAM 구현상의 주된 연구 중의 하나인 Kid Napping 문제에 중점을 두고 연구한다. 특히, 위치 측정의 구현을 수행하기 위한 데이터의 센싱 방법으로 초음파 센서를 사용하였고 비슷한 위치의 데이터 값이 주어지거나 사전 정보 없는 상태에서는 로봇의 상태를 파악하기 위해서 전자 나침반을 사용하였다. 그래서 자율 이동 로봇의 위치를 정확하게 측정하기 위해서 활용하였다. Digital Magnetic Compass(DMC) has a robust feature against interference in the indoor environment better than compass which is easily disturbed by electromagnetic sources or large ferromagnetic structures. Ultrasonic Sensors are cheap and can give relatively accurate range readings. So they ate used in Simultaneous Localization and Mapping(SLAM). In this paper, we study the Simultaneous Localization and Mapping(SLAM) of mobile robot in the indoor environment with Digital Magnetic Compass and Ultrasonic Sensors. Autonomous mobile robot is aware of robot's moving direction and position by the restricted data. Also robot must localize as quickly as possible. And in the moving of the mobile robot, the mobile robot must acquire a map of its environment. As application for the Simultaneous Localization and Mapping(SLAM) on the autonomous mobile robot system, robot can find the localization and the mapping and can solve the Kid Napping situation for itself. Especially, in the Kid Napping situation, autonomous mobile robot use Ultrasonic sensors and Digital Magnetic Compass(DMC)'s data for moving. The robot is aware of accurate location By using Digital Magnetic Compass(DMC).

자율이동로봇의 목표물 추적을 위한 시각구동장치의 설계 및 제어

자율이동로봇에 관한 연구, 개발이 활성화되고 있다. 본 논문에서는 목표물 추적 및 목표물 명중을 위해 사격을 할 수 있는 자율이동로봇의 설계 및 제작에 관하여 기술한다. 여기서는 목표물의 이동을 추적할 수 있도록 팬-틸트(pan-tilt)를 제어한다. USB 웹캠(web cam) 영상에서 대상체의 특정을 추출하고, 추출한 특징으로부터 시각구동장치의 이동 위치 및 방향을 결정하기 위한 퍼지논리시스템을 설계한다. 시뮬레이션을 통해 제안한 방법의 유용성을 검증하고, 이를 실제 자율이동로봇의 시각구동장치에 적용하여 타당성을 입증한다. The research and development for autonomous mobile robots has widely been reported. This paper describes a fuzzy logic based visual servoing system for an autonomous mobile robot. An existing system always needs to keep a moving object in overall image. This makes difficult to move the autonomous mobile robot spontaneously. In this paper we first explain an autonomous mobile robot and fuzzy logic system. And then we design a fuzzy logic based visual servoing system. We extract some features of the object from an overall image and then design a fuzzy logic system for controlling the visual servoing system to an exact position. We here introduce a shooting robot that can track an object and hit it. We show that the proposed system presents a desirable performance by a computer simulation and some experiments.

지역 및 전역 환경에 대한 세선화 기반 위상지도의 작성

An accurate and compact map is essential to an autonomous mobile robot system. For navigation, it is efficient to use an occupancy grid map because the environment is represented by probability distribution. But it is difficult to apply it to the large environment since it needs a large amount of memory proportional to the environment size. As an alternative, a topological map can be used to represent it in terms of the discrete nodes with edges connecting them. It is usually constructed by the Voronoi-like graphs, but in this paper the topological map is incrementally built based on the local grid map using the thinning algorithm. This algorithm can extract only meaningful topological information by using the C-obstacle concept in real-time and is robust to the environment change, because its underlying local grid map is constructed based on the Bayesian update formula. In this paper, the position probability is defined to evaluate the quantitative reliability of the end nodes of this thinning-based topological map (TTM). The global TTM can be constructed by merging each local TTM by matching the reliable end nodes determined by the position probability. It is shown that the proposed TTM can represent the environment accurately in real-time and it is readily extended to the global TTM.

2P1-E06 環境地図をRFIDから取得して自律走行するロボットシステム

2P1-E06 環境地図をRFIDから取得して自律走行するロボットシステム

A Real-Time Image Recognition System for Tiny Autonomous Mobile Robots

Intelligent sensors for mobile robots play an important role in many technical applications. In this paper a real-time image recognition system for a tiny autonomous mobile robot is presented, capa...

Convergence Properties of the Gravitational Algorithm in Asynchronous Robot Systems

This paper considers the convergence problem in autonomous mobile robot systems. A natural algorithm for the problem requires the robots to move towards their center of gravity. This paper proves the correctness of the gravitational algorithm in the fully asynchronous model. It also analyzes its convergence rate and establishes its convergence in the presence of crash faults.

Learning of Emergent Behaviors in Collective Virtual Robots using ANN and Genetic Algorithm

In distributed autonomous mobile robot system, each robot (predator or prey) must behave by itself according to its states and environments, and if necessary, must cooperate with other robots in order to carry out a given task. Therefore it is essential that each robot have both learning and evolution ability to adapt to dynamic environment. This paper proposes a pursuing system utilizing the artificial life concept where virtual robots emulate social behaviors of animals and insects and realize their group behaviors. Each robot contains sensors to perceive other robots in several directions and decides its behavior based on the information obtained by the sensors. In this paper, a neural network is used for behavior decision controller. The input of the neural network is decided by the existence of other robots and the distance to the other robots. The output determines the directions in which the robot moves. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. Here, the fitness values imply how much group behaviors fit adequately to the goal and can express group behaviors. The validity of the system is verified through simulation. Besides, in this paper, we could have observed the robots’ emergent behaviors during simulation.

A global path planning Java-based system for autonomous mobile robots

We present an autonomous robot motion planning system developed in Java. This interactive system enables users to set up the working environment by creating obstacles and a robot of different shapes, specifying starting and goal positions and setting other path or environment parameters from a user-friendly interface. A collision-free path is computed upon specifying the goal point. The path planning system involves several phases: collision detection, obstacle avoidance, free-path generation and then selecting the shortest one. Each of these modules is complex and therefore we provide the possibility of visualizing graphically the output of each phase. It has been shown that this system can be an effective computer-aided learning (CAL) tool in classroom teaching and/or motivating junior researchers in this field of research to further implement practical complex systems.

Development of a master–slave robot system for farm operations

The primary objective of this study was to develop a control system for autonomous mobile robots used in farm operations. To accomplish this objective, it was necessary to develop mobile robots having minimal centralized control. This paper focuses on the development of two basic motion control algorithms, namely a GOTO algorithm and a FOLLOW algorithm, for use in a master–slave multi-robot system. These two robot motion control algorithms would have wide applicability in farm operations. The GOTO algorithm can be applied when the master wants the slave to go to a specific place, a certain distance from the current operational position. Safety is one important issue in controlling the master–slave system because the master and the slave move independently. In this GOTO algorithm, the slave was set to slow-down to allow the master pass the slave safely in case there was a potential collision due to path overlap in the field. The slave was also able to change its path to avoid a crash based on the collaborative GOTO algorithm. The FOLLOW algorithm allows for a more cooperative way to guide the slave to follow the master at a predetermined relative distance and angle, regardless of the traveling speed and direction. This FOLLOW algorithm incorporated a nonlinear sliding mode controller to provide a robust control for the slave. The validation tests indicated that the sliding mode controller could provide a better performance in terms of both lateral offset and spacing controls compared than using a conventional PD controller.

523 自律移動型溶接ロボットによる自動溶接線追従および溶接制御

An autonomous mobile welding robot system with arc sensor and vision sensor was developed. Especially, control system of automatic seam-tracking, welding current and arc length in real time were constructed. For the seam-tracking system, Hough transform was applied to detect welding line. And welding speed on straight line was changed. So this system can not only detect welding line stably, but also speed up welding process. Neural network for penetration control was constructed. Input parameters including geometric parameters of molten pool were detected from image acquired by vision sensor. In order to keep constant arc length, arc length control system using Fuzzy reasoning was constructed. This autonomous mobile welding robot system was applied to the butt-welding of 1.6mm SPCC mild steel plates.

Autonomous Mobile Robot System for Monitoring and Control of Penetration during Fixed Pipes Welding

In order to obtain sound welded joints in the welding of horizontal fixed pipes, it is important to control the back bead width in the first pass. However, it is difficult to obtain optimum back bead width, because the proper welding conditions change with welding position. In this paper, in order to fully automatize the welding of fixed pipes, a new method is developed to control the back bead width with monitoring the shape and dimensions of the molten pool from the reverse side by autonomous mobile robot system. This robot has spherical shape so as to move in a complex route including curved pipe, elbow joint and so on. It has also a camera to observe inner surface of pipe and recognize a route in which the robot moves. The robot moves to welding point in the pipe, and monitors the reverse side shape of molten pool during welding. The host computer processes the images of molten pool acquired by the robot vision system, and calculates the optimum welding conditions to realize adaptive control of welding. As a result of the welding control experiments, the effectiveness of this system for the penetration control of fixed pipes is demonstrated.

FRAMEWORK FOR DEVELOPING REAL-TIME MOBILE ROBOTIC APPLICATIONS BASED ON BEHAVIOURAL MODELS

In complex real-time control systems such as autonomous mobile robotic systems, the use of development tools for the design, analysis and validation of robotic applications is highly desirable, specially to improve the robot performances and to avoid early software and hardware design faults. This paper presents a framework for developing real-time mobile robotic applications. The main feature of the environment is that it permits the integrated analysis and validation of the functional behaviour of the robot (i.e. robot carrying out its plans) and the guarantee of the temporal constraints of the system processes (i.e. reactive and deliberative process execution). The verification of the correctness of the functional requirements is supported by means of a robot simulation tool that reflects the progress of the system at the application level. Likewise, a temporal analysis tool, based on scheduling analytical techniques, guarantees the schedulability of the system load at the execution level. The usefulness of the development tool is shown through design examples applied to mobile robotic applications.

419 Autonomous Mobile Robot System for Monitoring and Control of Penetration during Fixed Pipes Welding

419 Autonomous Mobile Robot System for Monitoring and Control of Penetration during Fixed Pipes Welding

A Space-Division Optical Wireless Communication System for Fully Distributed Multiple Autonomous Mobile Robots

This paper describes the realization of a space-division optical communication system specifically designed to perform local inter-robot communication in fully distributed multiple autonomous mobile robot systems. Requirements for autonomy and robustness of communication functions among moving robots are discussed. The communication system uses a set of modules, or transceivers, which is arranged in the circumference of the robot body. Each module comprises an IR detector/receiver and an IR transmitter. Each IR module detects the angle of incidence of infrared rays. Space-division communication networks can be created, because a robot can commumcate with more than one robot through different modules at the same time. Hardware realization and performance measurements are illustrated to reveal the effectiveness of the developed system.