Dissertation > Excellent graduate degree dissertation topics show

The SLAM Research of Indoor Robot Based on Laser Range Finders

Author: PengZuoYuan
Tutor: WuHuaiYu
School: Wuhan University of Science and Technology
Course: Control Theory and Control Engineering
Keywords: Mobile Robot Simultaneous Localization and Mapping (SLAM) Particle Filter Scan Matching
CLC: TP242
Type: Master's thesis
Year: 2012
Downloads: 249
Quote: 0
Read: Download Dissertation

Abstract


These years the SLAM problem has been a hot issue in research on intelligent robot. It isa basic and important function to use the information captured from sensors to locate the robotreliably. It is also a challenging topic of much concern in the research of robot. SimultaneousLocalization and Mapping (SLAM) is an essential capability for mobile robots to move inunknown environments. The two key questions of navigation are building map in real time andobtaining robot’s pose precisely.Firstly this paper introduces the two key techniques of SLAM, one of which isrepresentative expression means of environmental map, and another is typical localizationmethods of mobile robots. To avoid the inborn problem of the odometry whose angle error willaccumulate ceaselessly with time growing, a mixed localization approach which fuses theodometry and laser information is developed. An agglomerative hierarchical clusteringalgorithm is used to extract line features whose parameters are extracted from range scans,while using least squares algorithm to fit straight lines. ICP is used to match the consecutivescan data to correct the angle error of the odometry.In addition, to reduce the complexity of data association and enhance the real-timeperformance of the algorithm, an improved the re-sampling part of Rao-BlackwellizedFastSLAM algorithm is put forward using Bayesian gird map and partial filter. We called itRPF, regular particle filter. It approximately could restore the discrete posterior probabilitydensity into a series of distribution, so RPF could avoid the problem of lacking variety.Simulation results demonstrate that the estimate errors of the pose and the landmarkscalculated by RPF are far less than EKF-based and normal particle filter approaches under thesame noise condition.Finally, many experiments are performed based on mobile robot MT-R with proposedSLAM method. The experimental results demonstrate that the proposed method cansuccessfully create a consistent map while locate itself using the map.

Related Dissertations

  1. Research on Cooperative Orbit Determination in Satellite Network Based on Multi-Agent System Theory,V474
  2. The Maneuvering Target Tracking Research Based on VRPF,TN957.52
  3. The Research of 3D Human Motion Capture Based on Reference Points,TP391.41
  4. Research on the Theory of Visual Object Tracking Based on Particle Filter for Autonomous Robot,TP242
  5. Space Infrared Target Simulation and Application of Target Trace,TP391.41
  6. A Navigation and Control System of Mobile Robot Designed for Path Following,TP242
  7. The Research and Realization of Audio-Video Capture and Transmission about Mine Search and Rescue Robot,TP274.2
  8. Detection and Tracking of Moving Object in Complex Background,TP391.41
  9. Design and Research on Intelligent Control Virtual Machine Based on μC/OS-II,TP242
  10. Moving Target Tracking Method Research in Video Sequences,TP391.41
  11. Research on the Problem of Path Planning for Mobile Robot Based on Improved Ant Colony Algorithms,TP242
  12. Mobile Robot Navigation Control Based on the Weights of Multi-sensor Information,TP242
  13. Moving Objects Detection and Tracking Using Fisheye Camera,TP391.41
  14. Research on Target Tracking in Wireless Sensor Network,TN929.5
  15. The Research on the Target Localization and Tracking Based on WSN,TN929.5
  16. Research on Mobile Robot Path Planning and Simulation Realization,TP242
  17. The Study of Moving Object Detection and Tracking Algorithm Based on Image Information,TP391.41
  18. Research on Vision-Based Traffic Vehicle Detection and Tracking,TP391.41
  19. Research on Target Tracking Algorithms Based on Particle Filter Method,TP391.41
  20. Research of Parallel Particle Filter Tracking Algorithm on CUDA Platform,TP391.41
  21. Modular Design and Implement of a Small Mobile Robot System Platform,TP242

CLC: > Industrial Technology > Automation technology,computer technology > Automation technology and equipment > Robotics > Robot
© 2012 www.DissertationTopic.Net  Mobile