Conference Paper

Point pattern matching based visual global localization using ceiling lights

Robot. Program, Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejeon, South Korea
Conference: Control Conference (ASCC), 2011 8th Asian
Source: IEEE Xplore

ABSTRACT This paper proposes a new system for point pattern matching based visual global localization using spot lightings in ceiling. The proposed algorithm is suitable for system that demands high localization accuracy and fast update rate such as a service guide robot in the exhibition or fair. A single camera looking upward direction is mounted on the head of the mobile robot, and spot lighting positions are detected by thresholding and identification process. For detecting more spot lightings, we choose wide FOV lens, and inevitably there is serious image distortion. But by applying correction calculation only for the positions of spot lightings not whole image pixels, we can decrease the processing time. And then using point pattern matching and least square estimation, finally we can get the precise position and orientation of the mobile robot. Experimental results demonstrate the accuracy and update rate of the proposed algorithm in real environments.

0 Followers
 · 
124 Views
 · 
4 Downloads
  • Source
    • "But this approach is sensitive to illumination change. A point pattern matching using ceiling lights in indoor environment has been described in [8]. They have used a single camera on the head of mobile robot facing in upward direction. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we discussed about a new mobile robot navigation technique, which will be used for home security. The objective is to perform indoor navigation efficiently and at the same time make the cost of the device as low as possible so as to make it commercializable. Here, we proposed an approach based on recognition of two infrared generated ceiling spots, which remains invisible to human eyes but easily captured by infrared camera. Then we use this image to locate the position of a robot and finally control the robot to the destination in the room, for example to its charging station. Experimental results show that the proposed approach is effective in real environment and opens new doors for future research.
    IEEE International Conference on Information Science and Technology, Shenzhen; 04/2014
  • Source
    • "But this approach is sensitive to illumination change. A point pattern matching using ceiling lights in indoor environment has been described in [6]. They have used a single camera on the head of mobile robot facing in upward direction. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we will discuss about the navigation of a mobile robot, which will be used for home security. The objective is to perform indoor navigation efficiently and at the same time make the cost of the device as low as possible so as to make it commercializable. Here, we propose an approach based on recognizing two spots generated by laser pointers on the ceiling, which are invisible to human eyes but easily captured by infrared camera. Then we use this image to locate the position of a robot and finally employ a path planning algorithm to navigate the robot to any location in the room; for example to its charging station. Experimental results show that the proposed approach is effective in real environment and opens new doors for future research.
    International Conference on Intelligent Robots and Systems; 11/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Efficient localization is a highly desirable property for an autonomous navigation system. Weightless neural networks offer a real-time approach to robotics applications by reducing hardware and software requirements for pattern recognition techniques. Such networks offer the potential for objects, structures, routes and locations can to be easily identified and maps constructed from fused limited sensor data as information becomes available. We show that in the absence of concise and complex information, localisation can be obtained using simple algorithms from data with inherent uncertainties using a combination of Genetic Algorithm techniques applied to a Weightless Neural Architecture.
    ESANN 2012: European Symposium on Artificial Neural Networks, Computational Intelligence, Bruges, Belgium; 04/2012
Show more

Preview

Download
4 Downloads
Available from