Loading...

Indoor Office Environment Mapping Using a Mobile Robot with Kinect Sensor

Sartipi, Kourosh | 2013

587 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 44838 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Jamzad, Mansour
  7. Abstract:
  8. In recent years with advancement of Robotics, the applications of wide scale use of robots in our homes is not as far-fetched as it was before. One of the important problems for an indoor robot is moving inside a new and unknown environment. To achieve this, the robot should, with the help of its sensors, not only calculate its location; but should also build a map of the environment for later use. Additionally, the robot must be able to explore this unknown environment. The most important drawbacks of the classical solutions to these problems are long computation times, heavy memory usage and absence of precision. In recent years, large amount of research effort has put on solving these problems and we will review the most important contributions to the relative fields in this thesis. In this thesis, three methods have been proposed to improve current state of the art algorithms. The first algorithm proposes a new method to calculate robot motion using Kinect sensor’s RGB and depth images. To achieve this, the algorithm tries to minimize the error of depth and image transformation, computing the most probable motion in the process. This algorithm does not use image features and does not need extra steps to compute these features. The algorithm is also reasonably fast and robust for real-time execution. The second method merges SLAM and Octomap mapping algorithm. After SLAM loop-closure causes a significant update; the current mapping algorithm cannot update itself and has to be built from scratch. As this is a time consuming operation, the method proposes a way to update only the parts of the map that have changed, and not the whole map. The third method improves feature matching performance for the features of two images. The current algorithm does not use the available constraints to their full extent and this method tries to achieve this goal by defining new constrains on error thresholds
  9. Keywords:
  10. Mobile Robot ; Simultaneous Localization and Mapping (SLAM) ; Motion Planning ; Exploration ; Kinect Sensor ; Path Planning ; Indoor Environment

 Digital Object List

 Bookmark

No TOC