Fig 3 - uploaded by António J. R. Neves
Content may be subject to copyright.
Captures of an image acquired by the robot camera and processed by the vision algorithms. Left a) : the image acquired by the camera; Right b) : the same image after processing with magenta dots over the detected field lines.
Source publication
This paper is focused on the sensor and information fusion techniques used by a robotic soccer team. Due to the fact that
the sensor information is affected by noise, and taking into account the multi-agent environment, these techniques can significantly
improve the accuracy of the robot world model. One of the most important elements of the world...
Context in source publication
Context 1
... a list of positions relative to the robot where the scanlines intercept the field line markings [5]. The idea is to analyse the detected line points, estimating a position, and through an error function describe the fitness of the estimate. This is done by reducing the error of the matching between the detected lines and the known field lines (Fig. 3). The error function must be defined considering the substantial amount of noise that affect the detected line points which would distort the representation estimate ...
Similar publications
Characterisation of an information fusion system (IFS) is a very difficult challenge. There are many levels of information fusion and there are many decision fusion models. One can argue that each problem is very specific and thus developing a generalized framework is utopia. This paper presents a simplified, and sometimes naïve representation of I...
Hypertension is one of the major causes of heart cerebrovascular diseases. With a good accumulation of hypertension clinical data on hand, research on hypertension's ZHENG differentiation is an important and attractive topic, as Traditional Chinese Medicine (TCM) lies primarily in "treatment based on ZHENG differentiation." From the view of data mi...
This paper discusses the properties of Bayesian networks (BNs) in the context of accurate state estimation. We focus on a relevant class of problems where state estimation can be viewed as a classification of possible states based on the fusion of heterogeneous and noisy information. We introduce the inference meta model (IMM), a coarse runtime per...
We propose an adaptive tracking system for assisted living that integrates user information about emergency events. Information fusion between user data and visual data is performed in order to estimate and assess the situation at hand. The system is able to dynamically switch between different segmentation and tracking algorithms improving its per...
A significant challenge in the distribution of goods is assessing the potential threat that an individual shipping container poses. Due to the high volume of shipped goods, a primary concern is balancing accuracy and container scan time. The application of information fusion to the problem enables automated threat determination and the presentation...
Citations
... Unfortunately, our linear program is not Totally Unimodular [38] due to the constraints in Eqs. (2)(3)(4), and hence, we have to explicitly enforce integrality. Consequently, solving the ILP is in general NP-Hard, but we have found that due to our temporal abstraction, using a branch and cut approach efficiently finds the optimal solution on the size of our data. ...
... As for the constraints of our original formulation, Eqs. (2)(3)(4), these are all summations over the assignment matrix (now represented by x) and the coefficients d f e ∈ {0, 1}, encoding over which entries (in x) we perform summation (e.g. the set of visible tracklets active at time t). These are clearly nonnegative as required in the covering problem formulation. ...
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse’s location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the object identification problem as an assignment problem (solved using Integer Linear Programming), (b) a novel probabilistic model of the affinity between tracklets and RFID data, and (c) a curated dataset with per-frame BB and regularly spaced ground-truth annotations for evaluating the models. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden.
... This setting is not unique to animal tracking. Similar situations arise e.g., when identifying specific team-mates in robotic soccer [1] (where the identification is provided by the weak self-localisation of each robot), or identifying vehicles observed by traffic cameras at a busy junction (as required for example for law-enforcement), making use of a weak location signal provided by cell-phone data. ...
Our objective is to track and identify mice in a cluttered home-cage environment, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse's location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the identification problem as an assignment problem (solved using Integer Linear Programming), and (b) a novel probabilistic model of the affinity between tracklets and RFID data. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this identification problem, and is able to reject spurious detections when the animals are hidden.
... 1,2 In order to improve the abilities of multirobot systems, information fusion is a necessary task to suppress the noise in a multiagent environment. 3 Finding a way to most effectively utilize the information captured from these multiple sensors, possibly of different modalities, is of considerable interest. Image fusion provides one versatile solution, where multiple aligned images acquired by different sensors are merged into a composite image. ...
In order to assess the performance of multisensor image registration algorithms that are used in the multirobot information fusion, we propose a model based on structural similarity whose name is vision registration assessment model. First of all, this article introduces a new image concept named superimposed image for testing subjective and objective assessment methods. Therefore, we assess the superimposed image but not the registered image, which is different from previous image registration assessment methods that usually use reference and sensed images. Then, we calculate eight assessment indicators from different aspects for superimposed images. After that, vision registration assessment model fuses the eight indicators using canonical correlation analysis, which is used for evaluating the quality of an image registration results in different aspects. Finally, three kinds of images which include optical images, infrared images, and SAR images are used to test vision registration assessment model. After evaluating three state-of-the-art image registration methods, experiments indict that the proposed structural similarity-motivated model achieved almost same evaluation results with that of the human object with the consistency rate of 98.3%, which shows that vision registration assessment model is efficient and robust for evaluating multisensor image registration algorithms. Moreover, vision registration assessment model is independent of the emotional factors and outside environment, which is different from the human.
... In this method, the uncertainty of the robot self-localization was taken into consideration, which was propagated to the uncertainty of the observation of the ball. The CAMBADA team described their work on the information fusion for multi-robot system in [56,62]. A real-time database [63] was used to realize information sharing between the robots. ...
Visual perception is the most important method for providing information about the competition environment for RoboCup Middle Size League (MSL) soccer robots. The paper reviews the advancement of visual perception in RoboCup MSL soccer robots from several points of view including the design and calibration of the vision system, the visual object recognition, the estimation of the object's motion, robot visual self-localization and multi-robot cooperative sensing. The research progress we have achieved is also introduced in this review. The developing trends and the future research focuses on this problem are also discussed.
... Therefore, the ball velocity estimation could be modelled as a standard linear regression problem, which could be solved by ridge regressiona least squares mathcing method (LSM). In [3], Kalman Filter was employed for ball position estimation; based on the estimated positions, an algorithm similar as that in [2] was utilized to evaluate the ball velocity, resulting improved ball velocity estimation accuracy. ...
... To further improve the robustness and accuracy, we also use Kalman filter to optimize the ball positions before estimating the ball velocity similar as that in [3]. As the ball velocity is assumed to be constant between cycles in a short time, we use the prediction model as follows: ...
Effective object motion estimation is significant to improve the performance of soccer robots in RoboCup Middle Size League. In this paper, a hybrid vision system is constructed by combining omnidirectional vision and stereo vision for ball recognition and motion estimation in three-dimensional (3D) space. When the ball is located on the ground field, a novel algorithm based on RANSAC and Kalman filter is proposed to estimate the ball velocity using the omnidirectional vision. When the ball is kicked up into the air, an iterative and coarse-to-fine method is proposed to fit the moving trace of the ball with paraboic curve and predict the touchdown-point in 3D space using the stereo vision. Experimental results show that the robot can effectively estimate ball motion in 3D space using the hybrid vision system and the proposed algorithms, furthermore, the advantages of the 360∘ field of view of the omnidirectional vision and the high object localization accuracy of the stereo vision in 3D space can be combined.
... The communication regarding the robots' positions increases certainty and reduces imprecision about the robots' own poses [4]. Kalman filter was applied to improve the ball position estimation for a robotic soccer team [76] and its extensions were explored for cooperative behavior of mobile robots [68]. It is also applied for robot localization, we will detail this in the next section. ...
This chapter is devoted to illustrate and characterize the relationship between Swarm Intelligence and cooperation among robots. Individuals with very limited computational capabilities are able to carry out very complex tasks when they can work together. From a methodological point of view, Swarm Intelligence is a set of heuristic solutions inspired by animal swarm behaviors and capable to offer empirical solutions to many computationally hard problems pertaining to several disciplines. In this chapter, we will try to outline the main research directions in Swarm Intelligence implementation within a robot network through the cooperation among the robots. The latter topic will be presented along with its advantages, issues and challenges. The convergence of robot cooperation and Swarm Intelligence is leading towards a new discipline, called Swarm Robotics. In this chapter, we will introduce this new field of study, its most relevant works and its main research directions. © 2014 by World Scientific Publishing Co. Pte. Ltd. All rights reserved.
... More details regarding the detection and identification of obstacles can be found in [22]. Fig. 16 presents an example of an acquired image, the corresponding segmented image and the detected color blobs. ...
... The position of the white lines, the position of the ball and the information about the obstacles are then sent to the Real-time Database [1,23] and used, afterward, by the high level process responsible for the behaviors of the robots [24,25,22,26]. ...
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.
... However, many teams are working on approaches using shape and gray level edges [19, 20] since the color coding of objects like the ball will disappear during the next years. The information extracted from the images is used in sensor fusion and tracking approaches to obtain a consistent geometric model of the environment [21, 22]. The robots are able to determine their own pose on the field [23, 24, 25] and estimate the ball movement [26, 27, 28]. ...
Computational concepts of cognition, their implementation in complex autonomous systems, and their empirical evaluation are key techniques to understand and validate concepts of cognition and intelligence. In this paper we want to describe computational concepts of cognition that were successfully implemented in the domain of soccer playing robots and show the interactions between cognitive concepts, software engineering and real-time application development. Beside a description of the general concepts we will focus on aspects of perception, behavior architecture, and reinforcement learning.
... A large body of robotics research in several areas related to the Robocup middle size league competition has been published during the past decade. These research areas include real-time motion planning [3], data fusion [4], robot platform design [5], communications among robots [6], and multiagent control structure [7]. Among these areas, the platform design is where a new robot team would start. ...
RoboCup is an international research and education initiative, which aims to foster artificial intelligence and robotics research by using competitive soccer as a standard problem. This paper presents a detailed engineering design process and the outcome for an omni-directional mobile robot platform for the Robocup Middle Size League competition. A prototype that can move omnidirectionally with kicking capability was designed, built, and tested by a group of senior students. The design included a mechanical base, pneumatic kicking mechanism, a DSP microcontroller-based control system, various sensor interfacing units, and the analysis of omnidirectional motions. The testing results showed that the system was able to move omnidirectionally with a speed of ∼2 m/s and able to kick a size 5 FIFA soccer ball for a distance of at least 5 meters.
... The self-localization task lends itself well to the implementation with a Monte Carlo Localization [8] approach using a particle filter due to its ability to represent ambiguous, multimodal state estimates as well as nonlinear motion and observation models. Ball Modeling on the other hand is often performed using a Kalman Filter or Multihypothesis Kalman Filter, as tracking of a single unambiguous object can be done well using these parametric filters [9], [10]. ...
In recent years, humanoid robot soccer robots have shown increasingly robust and fast locomotion, making percep-tion, world modeling and behavior control important. In this paper, we present the world modeling approach of the Darmstadt Dribblers humanoid robot team, which won the competitions in the RoboCup Humanoid KidSize League in 2009 and 2010. The paper focuses on modeling observation uncertainties originating from different contributing factors centrally in one module. This allows different state estimators to use this data in a consistent way, independently of the specific state estimation approach used.
