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.     

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.     

World modeling on an MSL robotic soccer team

When a team of robots is built with the objective of playing soccer, the coordination and control algorithms must reason, decide and actuate based on the current conditions of the robot and its surroundings. This is where sensor and information fusion techniques appear, providing the means to build an accurate model of the world around the robot, based on its own limited sensor information and the also limited information obtained through communication with the team mates. One of the most important elements of the world model is the robot self-localization, as to be able to decide what to do in an effective way, it must know its position in the field of play. In this paper, the team localization algorithm is presented focusing on the integration of visual and compass information. An important element in a soccer game, perhaps the most important, is the ball. To improve the estimations of the ball position and velocity, two different techniques have been developed. A study of the visual sensor noise is presented and, according to this analysis, the resulting noise variation is used to define the parameters of a Kalman filter for ball position estimation. Moreover, linear regression is used for velocity estimation purposes, both for the ball and the robot. This implementation of linear regression has an adaptive buffer size so that, on hard deviations from the path (detected using the Kalman filter), the regression converges faster. A team cooperation method based on sharing the ball position is presented. Other important data during the soccer game is obstacle data. This is an important challenge for cooperation purposes, allowing the improvement of team strategy with ball covering, dribble corridor estimation, pass lines, among other strategic possibilities. Thus, detecting the obstacles is ceasing to be enough and identifying which obstacles are team mates and opponents is becoming a need. An approach for this identification is presented, considering the visual information, the known characteristics of the team robots and shared localization among team members. The described work was implemented on the CAMBADA team and allowed it to achieve particularly good performances in the last two years, with a 1st and a 3rd place in the world championship RoboCup 2008 and RoboCup 2009 editions, respectively, as well as distinctively achieve 1st place in 2008 and 2009 editions of the Portuguese Robotics Open.     

A modelling language for cooperative plans in highly dynamic domains

Cooperative behaviour is one of the challenges most pronounced in the RoboCup Middle Size League. Especially the dynamic nature of the domain, which calls for swift adaptation by each robot and the team as a whole, is a distinctive property of the league. The ability to establish highly responsive teamwork while facing unreliable communication and sensory noise is a key to successful soccer teams. Moreover, modelling such responsive, cooperative behaviour is difficult. In this work, we specify a novel model for cooperative behaviour geared towards highly dynamic domains, focussing on the language syntax and semantics. In our approach, agents estimate each other’s decision and correct these estimations once they receive contradictory information. We provide a comprehensive approach for agent teamwork featuring intuitive modelling capabilities for multi-agent activities, abstractions over activities and agents, and a clear operational semantics. Moreover, we briefly present a graphical modeling tool for cooperative strategies, which is based directly on the theory laid out, together with a practical framework for executing said strategies. We show experimentally the responsiveness and coherence of the resulting team play.     

Dynamic control of steerable wheeled mobile platforms applied to an eight-wheeled RoboCup Middle Size League soccer robot

In the RoboCup Middle Size League two teams of mobile robots play soccer against each other. During the game, agility, i.e. the ability to quickly change the direction of platform movements, is important to react or anticipate fast on the intention of opponents to efficiently perform maneuvers like ball shielding and interception. Therefore, high accelerations are desired which ideally would ask all wheels to contribute to traction in the target direction. However none of the current omnidirectional wheel-based robots in the league offers such a feature. Each pair of wheels can rotate independently about its suspension axis . The new configuration brings new challenges in control: the platform becomes kinematically nonholonomic due to the kinematic constraints around the pivot axes, but it is shown that in the context of the driving task the controller can keep the wheel configurations such that they can generate a force and torque in the directions needed by the task. Hereby, the restriction to minimize the position-error in its three degrees of freedom with respect to a predefined trajectory is relaxed by taking only the degrees of freedom relevant for the task into consideration. A cascaded control strategy is proposed that combines kinematic and dynamic control and also addresses the control-allocation problem. Compared to a full kinematic approach as typically applied on steerable wheeled systems, 2.3 times higher translational and 1.8 times higher angular velocity are demonstrated. For the translational acceleration and angular acceleration, improvement factors of 2.7 and 3.2 are achieved, respectively. The platform made a successful debut during the RoboCup Portuguese Open 2019, showing the robustness of the proposed approach.     

Self-localisation of indoor mobile robots using multi-hypotheses and a matching algorithm

This paper proposes a new, fast and computationally light weight methodology to pinpoint a robot in a structured scenario.The localisation algorithm performs a tracking routine to pinpoint the robot’s pose as it moves in a known map, without the need for preparing the environment, with artificial landmarks or beacons. To perform such tracking routine, it is necessary to know the initial position of the vehicle. This paper describes the tracking routine and presents a solution to pinpoint that initial position in an autonomous way, using a multi-hypotheses strategy.This paper presents experimental results on the performance of the proposed method applied in two different scenarios: (1) in the Middle Size Soccer Robotic League (MSL), using artificial vision data from an omnidirectional robot and (2) in indoor environments using 3D data from a tilting Laser Range Finder of a differential drive robot (called RobVigil).This paper presents results comparing the proposed methodology and an Industrial Positioning System (the Sick NAV350), commonly used to locate Autonomous Guided Vehicles (AGVs) with a high degree of accuracy in industrial environments.     

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.     

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。     

基于RoboCup3D仿真平台的双足机器人大脚球进攻策略设计

RoboCup3D仿真系统融合了人工智能、传感器、通信、智能控制等多门学科的相关技术.针对RoboCup3D仿真中双足机器人的踢球动作设计问题(如:踢球力度弱、摔倒等)提出了一种基于大脚球的进攻策略.采用大脚球的进攻策略可以有效的促使足球快速的踢进对方半场后方,在仿真比赛中极具攻击性.仿真结果验证了它的有效性和实用性.     

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。     

中型组机器人运动控制系统的FPGA设计

以RoboCup中型组足球机器人为实验平台,提出一种基于FPGA的全方位移动足球机器人运动控制系统的实现方法。首先分析和研究三轮全方位移动机器人的运动学特性,建立其运动控制模型,然后以FPGA为主要处理器,设计了PID速度闭环控制算法,实现了对机器人的精确控制。实验发现,该设计方法具有很好的实时性,能够对全方位移动机器人进行快速、准确的控制。     

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.     

Control design of a novel compliant actuator for rehabilitation robots

Rehabilitation robots have direct physical interaction with human body. Ideally, actuators for rehabilitation robots should be compliant, force controllable, and back drivable due to safety and control considerations. Series Elastic Actuators (SEA) offers many advantages for these applications and various designs have been developed. However, current SEA designs face a common performance limitation due to the compromise on the spring stiffness selection. This paper presents a novel compact compliant force control actuator design for portable rehabilitation robots to overcome the performance limitations of current SEAs. Our design consists of a servomotor, a ball screw, a torsional spring between the motor and the ball screw, and a set of translational springs between the ball screw nut and the external load. The soft translational springs are used to handle the low force operation, while the torsional spring with high effective stiffness is used to deal with the large force operation. It is a challenging task to design the controller for such a novel design as the control system needs to handle both the force ranges. In this paper, we develop the force control strategy for this actuator. First, two dynamical models of the actuator are established based on different force ranges. Second, we propose an optimal control with friction compensation and disturbance rejection which is enhanced by a feedforward control for the low force range. The proposed optimal control with feedforward term is also extended to the high force range. Third, a switching control strategy is proposed to handle a transition between low force and high force control. The mathematical proof is given to ensure the stability of the closed-loop system under the proposed switching control. Finally, the proposed method is validated with experimental results on a prototype of the actuator system and is also verified with an ankle robot in walking experiments.     

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。     

Position Synchronization Control Algorithm of Legged Robot Based on DSP Centralized Control

When the traditional RRT algorithm is used to control the position of the legged robot synchronously, its adaptability is poor and it is easy to be disturbed by the surrounding environment, which leads to the low stability of the robot when avoiding obstacles. The position synchronization control algorithm of the legged robot based on DSP centralized control is proposed. The parameter on-line fuzzy self-tuning PID algorithm is used in the position loop of the control system of the robot car controller to improve the adaptive ability of the robot. The inverse Fourier transform of cross power spectrum is used to determine the position and orientation angle of the robot, and the displacement theorem of the robot is used to control the position of the robot synchronously. The experimental results show that the proposed algorithm can effectively synchronize and control the robot running safely and accurately in obstacle-free environment. The average time is 18 s, the maximum robustness is 0.45, and the maximum control error rate is 0.25. It has the advantages of high control efficiency, high robustness and small error, which ensures the stable operation of the robot.

     

Position control of hybrid pneumatic–electric actuators using discrete-valued model-predictive control

The design, modeling and position control of a novel hybrid pneumatic–electric actuator for applications in robotics and automation is presented. The design incorporates a pneumatic cylinder and DC motor connected in parallel. By avoiding the need for a high ratio transmission, the design greatly reduces the mechanical impedance that can make collisions with conventionally actuated robot arms dangerous. A novel discrete-valued model-predictive control (DVMPC) algorithm is proposed for controlling the position of the pneumatic cylinder with inexpensive on/off solenoid valves. A variant of inverse dynamics control is proposed for the DC motor. A prototype was built for validating the actuator design and control algorithms. It is used to rotate a single-link robot arm. The actuator inertia and static friction torque values for the prototype were only 0.6% and 4%, respectively, of the values found for a comparable actuator from an industrial robot. Simulation results for position control of pneumatic actuators with different valve speeds and friction coefficients show that the DVMPC algorithm outperforms a sliding mode control algorithm in terms of position error and expected valve life. Experimental results are presented for vertical rotary cycloidal trajectories. Even with the poor quantization caused by the on/off valves, the pneumatic cylinder controlled by the proposed DVMPC algorithm achieved a 0.7% root mean square error (RMSE) and a 0.25% steady-state error (SSE). With the addition of the DC motor to form the hybrid actuator, the RMSE and SSE were reduced to 0.12% and 0.04%, respectively. By incorporating a novel estimation algorithm, the system was made robust to an unknown payload.     

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.     

Arbitrarily colored ball detection using the structure tensor technique

In this paper we present a new technique for ball detection in the RoboCup environment. The proposed method is an advanced version of the Hough transform and its main detection feature is local rotational invariance. This feature is utilized by means of the structure tensor technique, which optimizes linear parameters in partial differential equations within a local neighborhood. For our application we use the vanishing angular derivative describing the rotational invariance of the ball. Since no color information is used, the method can be used for the detection of any arbitrarily colored ball using a vision system. Compared to the standard version of the Hough transform for circle detection our version is a lot more robust, because the structure tensor technique directly provides the circles’ center coordinates as well as the radii and the accumulator space is only used to improve accuracy.     

基于ANSYS的供球机构摆动轴静动态特性分析

供球机构摆动轴的静动态特性对稳定供球、提高供球成功率和提高植球良率有着重要意义。因此,有必要对摆动轴静动态特性进行仿真分析。通过建立简化的摆动轴力学模型,并应用有限元分析软件ANSYS对摆动轴摆动角0°中间位置和±45° QUOTE 极限位置进行了静态分析,得到了摆动轴在这些位置的应力、变形云图。对摆动轴进行模态分析,得到了摆动轴前6阶固有频率以及振形。分析结果表明,摆动轴的初步设计符合设计要求,同时判断出摆动角±45° QUOTE 位置是摆动轴危险位置,为植球机供球机构的下一步设计与优化提供了参考。     

线激光器的手眼标定方法

为解决线激光器与多轴式机器人组成测量系统时,激光器与机器人位置关系不确定的问题,提出一种适用于线激光器的手眼标定方法,以空间定点在基坐标系下的坐标不变为基础,通过多姿态测量固定点,求解出手眼标定矩阵。同时设计了以标准球为靶标,以标准球球心为定点的寻点方案,提高了测量精度与可靠性。