A novel ball handling mechanism for the RoboCup middle size league

This paper presents the hardware design and control design of a novel ball handling mechanism in the RoboCup Middle Size League used by team Tech United Eindhoven. The ball handling mechanism consist of two levers with two actively driven wheels attached to it, to exert forces on the ball in order to control its position relative to the robot. The proposed design is fully compliant to the rules and regulations imposed by the RoboCup Middle Size League community. The control design consists of a cascaded velocity and position feedback loop in combination with a feedforward controller which compensates for the robots ego motion. The proposed design is validated on a robot used by the Tech United Eindhoven team.     

关于足球机器人系统工作模式及RoboCup仿真比赛机制的研究

机器人足球比赛是一个有趣且复杂的新兴人工智能研究领域,他融合了实时视觉系统、机器人控制、无线通讯、多机器人控制等多个领域的技术,为人工智能和智能控制的理论学习与研究及多种技术的集成应用提供了相当好的实验平台。对足球机器人系统的2种主要工作模式进行了比较和分析,并讨论了RoboCup仿真比赛的机制,对于分布式人工智能理论的研究具有重要意义。     

A robust omnidirectional vision sensor for soccer robots

How to make robot vision work robustly under varying lighting conditions and without the constraint of the current color-coded environment are two of the most challenging issues in the RoboCup community. In this paper, we present a robust omnidirectional vision sensor to deal with these issues for the RoboCup Middle Size League soccer robots, in which two novel algorithms are applied. The first one is a camera parameters auto-adjusting algorithm based on image entropy. The relationship between image entropy and camera parameters is verified by experiments, and camera parameters are optimized by maximizing image entropy to adapt the output of the omnidirectional vision to the varying illumination. The second one is a ball recognition method based on the omnidirectional vision without color classification. The conclusion is derived that the ball on the field can be imaged to be an ellipse approximately in our omnidirectional vision, and the arbitrary FIFA ball can be recognized by detecting the ellipse imaged by the ball. The experimental results show that a robust omnidirectional vision sensor can be realized by using the two algorithms mentioned above.     

受限视觉下RoboCup3D中机器人的定位

针对RoboCup3D中机器人视觉模型的重大改变,即由原来的完美视觉模型变为受限视觉模型,在综合完美视觉下机器人的定位方法,即陀螺仪定位、1个标志杆定位,3个标志杆定位,提出一种受限视觉下机器人自身定位策略,并应用卡尔曼滤波器来提高定位的精度,在Rcssserver3D仿真环境中进行了定位数据的采样和对比,实验表明此定位方法具有很好的竞赛适应性与健壮性。     

An efficient omnidirectional vision system for soccer robots: From calibration to object detection

Robotic soccer is nowadays a popular research domain in the area of multi-robot systems. In the context of RoboCup, the Middle Size League is one of the most challenging. This paper presents an efficient omnidirectional vision system for real-time object detection, developed for the robotic soccer team of the University of Aveiro, CAMBADA. The vision system is used to find the ball and white lines, which are used for self-localization, as well as to find the presence of obstacles. Algorithms for detecting these objects and also for calibrating most of the parameters of the vision system are presented in this paper. We also propose an efficient approach for detecting arbitrary FIFA balls, which is an important topic of research in the Middle Size League. The experimental results that we present show the effectiveness of our algorithms, both in terms of accuracy and processing time, as well as the results that the team has been achieving: 1st place in RoboCup 2008, 3rd place in 2009 and 1st place in the mandatory technical challenge in RoboCup 2009, where the robots have to play with an arbitrary standard FIFA ball.     

基于计算机视觉原理的自主足球机器人位置规划

在计算机视觉原理的基础上，本文提出了一种求取从视平面坐标到实际坐标转换矩阵的算法。根据机器人及足球在视平面上的坐标，即可计算出其实际坐标。运用于自主足球机器人比赛中，可获取本方、对方及足球的位置和角度，为制定比赛策略提供重要的数据。     

融合多传感信息的仿人机器人姿态解算

在RoboCup Soccer仿人机器人比赛中,机体姿态实时解算是仿人机器人运动控制系统的核心技术之一。文中分析了MEMS加速度计、磁强计和陀螺仪性能,以自主姿态测量为前提,融合惯性测量单元中多传感信息,提出了一种基于四元数的姿态解算算法。针对仿人机器人步行姿态控制中传感器数据存在的噪声干扰和测量误差,设计卡尔曼滤波器实现了对数据漂移的有效补偿,从而提高了全姿态检测的测量精度。试验结果验证了该算法对仿人机器人运动控制系统机体姿态实时解算的有效性。     

Cooperation Issues and Distributed Sensing for Multirobot Systems

This paper considers the properties a multirobot system should exhibit to perform an assigned task cooperatively. Our experiments regard specifically the domain of RoboCup middle-size league (MSL) competitions. But the illustrated techniques can be usefully applied also to other service robotics fields like, for example, videosurveillance. Two issues are addressed in the paper. The former refers to the problem of dynamic role assignment in a team of robots. The latter concerns the problem of sharing the sensory information to cooperatively track moving objects. Both these problems have been extensively investigated over the past years by the MSL robot teams. In our paper, each individual robot has been designed to become reactively aware of the environment configuration. In addition, a dynamic role assignment policy among teammates is activated, based on the knowledge about the best behavior that the team is able to acquire through the shared sensorial information. We present the successful performance of the Artisti Veneti robot team at the MSL Challenge competitions of RoboCup-2003 to show the effectiveness of our proposed hybrid architecture, as well as some tests run in laboratory to validate the omnidirectional distributed vision system which allows us to share the information gathered by the omnidirectional cameras of our robots.     

Robot team coordination using dynamic role and positioning assignment and role based setplays

The coordination methodologies of CAMBADA, a robotic soccer team designed to participate in the RoboCup Middle-Size League (MSL), are presented in this paper. The approach, which relies on information sharing and integration within the team, is based on formations, flexible positionings and dynamic role and positioning assignment. Role assignment is carried out locally on each robot to increase its reactivity. Positioning assignment is carried out at a lower frequency by a coach agent following a new priority-based algorithm that maintains a competitive formation, covering the most important positionings when malfunctions lead to a reduction of the team size. Coordinated procedures for passing and setplays have also been implemented. With this design, CAMBADA reached the 1st place in RoboCup’2008 and the 3rd place in RoboCup’2009. Competition results and performance measures computed from logs and videos of real competition games are presented and discussed.     

基于CMAC的Q算法在机器人足球中的应用

RoboCup是全球影响力最大的机器人足球比赛，是机器人学和人工智能及其应用的标准研究问题之一。仿真组在RoboCup中是重要的一部分。由于仿真组的比赛环境非常复杂，采用手工编码实现的Agent的高层决策无法考虑到比赛的所有情况，缺乏灵活性，并且需要花大量的时间对手工编码中的参数进行调整，结果也不是很理想。所以本文采用机器学习来实现Agent的决策。本文运用了一种基于CMAC的Q学习方法，把该方法应用在禁区内进行2VSl进攻的策略学习训练实例中，实验结果表明了本方法的可行性和有效性。     

Multi-robot coordination using Setplays in the middle-size and simulation leagues

Strategic planning and multi-agent coordination are major research topics in the domain of RoboCup. Innovations in these areas are, however, often developed and applied to only a single RoboCup league and/or one domain, without proper generalization. Moreover, the more technical leagues, like middle-size and humanoid, tend to focus development on low-level skills, that often suffice to gain a competitive edge over other teams. In these leagues, the development of high-level cooperation is secondary.Although the importance of the concept of Setplay, to structure a robotic soccer team behaviour, has been acknowledged by many researchers, no general framework for the development and execution of generic Setplays has been introduced in the context of RoboCup. This paper presents such a framework for high-level Setplay definition and execution, applicable to any RoboCup cooperative league and similar domains. The framework is based on a flexible, standard and league-independent language, which defines Setplays that are interpreted and executed at run-time, using inter-robot communication.An initial major step in the development of the Setplay framework was its usage and testing in the scope of the FCPortugal team, which participates in the RoboCup 2D-simulation and 3D-simulation leagues, where it won several titles both in the 2D and 3D leagues. This framework was also recently implemented in the middle-size team CAMBADA. This team has, in the recent past and with previous versions of the control software, ranked first and third in RoboCup’s 2008 and 2009 editions. The implementation is described with concrete examples of Setplay definition and execution, which shows the usefulness of this approach and motivate its use as a major coordination tool for teams participating in the simulation, small-size, middle-size, standard platform and humanoid leagues of RoboCup.     

RoboCup中整体与局部混合防御模型的研究

在RoboCup仿真比赛中,防守是一支球队的一个重要战术。基于强化学习原理提出了整体与局部混合防御模型,通过智能体之间的角色转换提高防守能力,与传统相比更有优势。     

Node localization using mobile robots in delay-tolerant sensor networks

We present a novel scheme for node localization in a delay-tolerant sensor network (DTN). In a DTN, sensor devices are often organized in network clusters that may be mutually disconnected. Some mobile robots may be used to collect data from the network clusters. The key idea in our scheme is to use this robot to perform location estimation for the sensor nodes it passes based on the signal strength of the radio messages received from them. Thus, we eliminate the processing constraints of static sensor nodes and the need for static reference beacons. Our mathematical contribution is the use of a robust extended Kalman filter (REKF)-based state estimator to solve the localization. Compared to the standard extended Kalman filter, REKF is computationally efficient and also more robust. Finally, we have implemented our localization scheme on a hybrid sensor network test bed and show that it can achieve node localization accuracy within 1 m in a large indoor setting.     

A networking framework for teleoperation in safety, security, and rescue robotics - [wireless communications in networked robotics]

Safety, security, and rescue robotics is an important application field that can be viewed as a prototypical example of a domain where networked mobile robots are used for the exploration of unstructured environments that are inaccessible to or dangerous for humans. Teleoperation, based on wireless networks, is much more complex than what one might expect at first glance because it goes well beyond mere mappings of low-level user inputs ? like joystick commands ? to motor activations on a robot. Teleoperation for SSRR must move up to the behavior and mission levels where a single operator triggers short-time, autonomous behaviors, respectively, and supervises a whole team of autonomously operating robots. Consequently, a significant amount of heterogeneous data ? video, maps, goal points, victim data, and so on ? must be transmitted between robots and mission control. In this article, a networking framework for teleoperation in SSRR is presented. It was evaluated in a series of field tests and competitions, including the European Land Robot Trials and RoboCup events.     

Visual servoing for constrained planar robots subject to complex friction

The theoretical framework and the experimental validation of a new image-based position-force control for planar robots are presented in this paper. This scheme produces simultaneous convergence of the constrained visual position and the contact force between the end effector and the constraint surface. Camera, robot, and the visual jacobian parameters are considered unknown. This approach is based on a new formulation of the orthogonalization principle used in the robot force control, termed the visual orthogonalization principle. This allows, under the framework of passivity, to yield a synergetic closed-loop system that fuses accordingly camera, encoder, and the force sensor signals. Furthermore, due to the technological limitations, it can be noticed that the visual servoing contact tasks are characterized by slow motion, typically with frequent velocity reversals along the constraint surface, thus, important friction problems arise at the joints and the contact points. Therefore, visual compensation of the complex dynamic joint friction and the viscous contact friction are also studied. A Linux real-time operating-system-based experimental system is implemented to visually drive a constrained direct-drive planar robot manipulator, equipped with six-axes JR3 force sensor and a digital fixed camera, thus proving the effectiveness of the proposed scheme.     

Machine Learning With AIBO Robots in the Four-Legged League of RoboCup

Robot learning is a growing area of research at the intersection of robotics and machine learning. The main contributions of this paper include a review of how machine learning has been used on Sony AIBO robots and at RoboCup, with a focus on the four-legged league during the years 1998-2004. The review shows that the application-oriented use of machine learning in the four-legged league was still conservative and restricted to a few well-known and easy-to-use methods such as standard decision trees, evolutionary hill climbing, and support vector machines. Method-oriented spin-off studies emerged more frequently and increasingly addressed new and advanced machine learning techniques. Further, the paper presents some details about the growing impact of machine learning in the software system developed by the authors' robot soccer team-the NUbots     

Nonlinear coordination control for a group of mobile robots using a virtual structure

This paper considers the problem of creating a coordination algorithm for a team of mobile robots. The goal for coordinating a group of mobile robots is to create an efficient architecture and control algorithm that enables them to work both individually and in meaningful robot formations. This is achieved by employing coordination and trajectory following techniques, and the knowledge derived by the localization of the robots from their environments.The model use a combination of the Lyapunov technique and graph theory embedded in the virtual structure. In this way, the knowledge derived by the localization of the robots in the group allows for efficient coordination and trajectory following, which can then create useful robot formations.The results obtained from experiments, using three mobile robots in differing formations, show the performance of the controller and the coordination algorithm. They also demonstrate the ability of the algorithm to recover from position sensor measurement errors and temporary delays or failures in the communication, which may cause the robots to momentarily abandon their place in the group formation.     

基于高维状态空间的移动机器人定位

位置跟踪是移动机器人自主导航中的一个主要任务.扩展的卡尔曼滤波定位方法是一个常用的位置跟踪方法,但是在对非线性系统方程进行线性化近似过程中引入了线性化误差.文中给出了一个基于线性系统模型的位置估计方法.用一个高维的状态向量表示机器人的位置空间,并选用环境路标的全局信息作为观测向量,此时系统动态模型和系统观测模型都是线性的,从而直接运用最优的线性卡尔曼滤波技术进行移动机器人位置估计.这种方法免除了非线性方程的线性近似过程,避免了线性化误差.实验表明,位置估计过程是收敛的、一致的.     

Robotic system for underwater inspection of bridge piers

The research objective is to develop an automated robotic system that will enable safe and cost-effective underwater inspection of bridge substructures. The system concept being developed is a semiautonomous robotic system that can carry a sensor platform underwater to detect scour, deterioration, or damage to support columns. It provides positional data and sensor information (video images) to the system operator; these can be verbally annotated while being recorded. The operator initiates basic commands and transmits them to the underwater apparatus. On-board microprocessor-based controllers automatically accomplish the detailed control. The primary underwater apparatus has a team of two identical mobile robots designed to travel along opposite surfaces of the pier while connected to each another by a cable and winch system. Each robot has rubber tracks or wheels with cleats and is driven by internal motors. Tensioning the cables that connect the two robots provides traction. The robots can move both vertically and horizontally. While each robot operates its own drive motors and cable winches, coordination of movement and cable tensioning occurs automatically through feedback between the robots and the control console. Multiple robots, evenly spaced around a support column, may inspect larger structures