Active markers for outdoor and indoor robot localization

Modelling, Identification and Control / 801: Advances in Computer Science, 2013

This paper presents a multi-camera system for mobile robot localization in indoor environment. The system consists of wall-mounted cameras with LED illuminator and a processing unit. The processing unit is a PC-cluster developed in-house. It consists of a two-computer system connected by PCI-to-PCI interface board with fiber-optic cable. The camera system provides robot pose information, position and orientation, in real-time with respect to the global reference frame. Three artificial landmarks, which are spherical reflective markers, are mounted on the robot to reduce complexity in localization and tracking. The Kalman filter tracking algorithm is applied to estimate markers position. With this estimation, the system bandwidth and robustness are improved. The robot is controlled by sending command via wireless Ethernet connection. By using measurements from the camera system, experiments on robot motion control with specified trajectories show the effectiveness of our developed system. In the near future, the system can use information from robot's onboard sensors such as laser range finder and sonar for development of obstacle detection and autonomous navigation.

1998

Active cameras provide a mobile robot with the capability to fixate and track features over a wide field of view. However, their use emphasises serial attention focussing on a succession of scene features, raising the question of how this should be best achieved to provide localisation information. This paper describes a fully automatic system, able to detect, store and track suitable landmark features during goal-directed navigation.

2019

2013

Tactical mobility systems have gained focus and interest in several areas including: homeland security, battlefield intelligence, space missions, surveillance systems, etc. Tactical systems work in a very sophisticated environment, and usually they need accuracy and consistency to achieve robust situational awareness. One important aspect of situation awareness is reliable localization of object of interest. This paper describes the design and implementation of an indoor mobile robot localization system using Machine Vision methods, namely, Vision-Based Indoor Positioning System (VIPS). This approach relies on color detection to identify the robot in the environment using a ceiling-mounted camera. Camera calibration model is developed to dynamically estimate the robot position in real time. The camera calibration model is based on environment grid modeling and Euclidian interpolation method to enhance the estimated gross position. Finally, Gaussian zero-phase filter is exploited to ...

IEEE Transactions on Robotics, 2004

This paper addresses the problems of building a functional mobile robot for urban site navigation and modeling with focus on keeping track of the robot location. We have developed a localization system that employs two methods. The first method uses odometry, a compass and tilt sensor, and a global positioning sensor. An extended Kalman filter integrates the sensor data and keeps track of the uncertainty associated with it. The second method is based on camera pose estimation. It is used when the uncertainty from the first method becomes very large. The pose estimation is done by matching linear features in the image with a simple and compact environmental model. We have demonstrated the functionality of the robot and the localization methods with real-world experiments.

2017

During the last years, the market of embedded vision-based systems has been growing at an accelerated rate. Virtual and augmented reality has the potential to become one of the most innovative technologies for the next decade. One of the most important aspects of these technologies is related to the spatial location of objects or people in defined environments, for which there are several techniques. One of the most widely used is based on visual marker recognition. The main problems of these approaches are related to the accuracy, the changing environments, the processing time, the operating range/distance and the price. The popularization of these technologies produces a pull effect toward the companies developing the best technology at the lowest price. This paper proposes a marker design and an algorithm to detect the markers under different ambient conditions, with a long range to be executed on embedded systems with low computational requirements. The proposed method reduces the existing problems in the state-of-the-art related to the use of different environments and conditions such as different distances or different illumination. Moreover, the requisites of the method are minimal to reduce the cost of deployment.

2013 16th International Conference on Advanced Robotics (ICAR), 2013

We present a fast and precise vision-based software intended for multiple robot localization. The core component of the proposed localization system is an efficient method for black and white circular pattern detection. The method is robust to variable lighting conditions, achieves sub-pixel precision, and its computational complexity is independent of the processed image size. With off-the-shelf computational equipment and low-cost camera, its core algorithm is able to process hundreds of images per second while tracking hundreds of objects with millimeter precision. We propose a mathematical model of the method that allows to calculate its precision, area of coverage, and processing speed from the camera's intrinsic parameters and hardware's processing capacity. The correctness of the presented model and performance of the algorithm in real-world conditions are verified in several experiments. Apart from the method description, we also publish its source code; so, it can be used as an enabling technology for various mobile robotics problems.

2000

A visual system provides many advantages against other types of sensors, observing and measuring of the process from a safe distance for example, but on the other hand new objectives and problems must be solved, e.g. significant data transfer, camera vibration elimination, speed of data processing and many others. Visual systems can be applied to perform dimensions verification, quality testing of surface attributes, object identification, mobile robot localization, etc. This paper’s content is aimed at the use of visual systems for navigation and localization of mobile robot with help of circular marks placed in unknown environment. The mark recognition consists of combination of several image processing algorithms. The results have showed stability, satisfactory dynamics and program effectivity. Optimization of control parameters was done by genetic algorithms.

IEEE Pervasive Computing, 2000

S m a r t e r P h o n e S G PS-based navigation systems have become very popular, mainly because they let people rapidly explore unknown areas. However, GPS works only outdoors, because the required satellite links are blocked or unreliable inside buildings. For indoor location sensing, many types of sensors exist, including ultrasonic, infrared, magnetic, and radio sensors. But they all require a permanent electronic infrastructure to facilitate measurements, and localizable objects relying on this infrastructure need special sensors or actuators. Practical problems such as power consumption, wiring, and overall infrastructure cost have inhibited such technology's deployment in entire buildings. In previous work, 1 we demonstrated how to detect and decode square fiduciary markers in real time using off-the-shelf camera phones. Such markers contain a 2D barcode that provides a unique ID from the camera image, which the camera phone can use to estimate in real time its position and orientation relative to the marker. The indoor navigation system we describe in this article takes advantage of associating locations with markers to provide an inexpensive, building-wide orientation guide that relies solely on camera phones. Whereas previous work on barcodebased location tracking, such as QR Codes (www.qrcode.com), relies on non-real-time "snapshot" processing, our approach allows for continuously scanning an environment in real time (15 Hz or more) in search of navigation hints. Thus, navigation scales from sparse, strategically placed fiduciary markers to continuous navigation in 3D.