A Novel Method for Perception and Map Construction of Environment Information Based on Laser Range Finder

2013 ◽  
Vol 347-350 ◽  
pp. 307-311
Author(s):  
Wen Jie Zhu ◽  
Guang Long Wang ◽  
Feng Qi Gao ◽  
Zhong Tao Qiao ◽  
Ji Chen Li

A method for perception and map construction of the unknown environmental information is described in this paper by analyzing and processing the data measured by laser range finder (LRF). The structure of the laser range finder, the structure of its returned measurement data, its working principle, and communication protocol are presented. The physical meaning of the data are studied and illustrated as well as its representation methods. The corresponding algorithm routine and the GUI interface program are introduced. Experiments are conducted to verify the range finding accuracy of the sensor and the data visualization method is also introduced. Results indicate that the proposed method is sufficiently valid and can satisfy the desired requirements.

2013 ◽  
Vol 25 (1) ◽  
pp. 25-37 ◽  
Author(s):  
Hung-Hsiu Yu ◽  
◽  
Hsiang-Wen Hsieh ◽  
Yu-Kuen Tasi ◽  
Zhi-Hung Ou ◽  
...  

In this paper, we propose a novel mobile robot visual localization method consisting of two processing stages: map construction and visual localization. In the map construction stage, both laser range finder and camera are used to construct a composite map. Depth data are collected from laser range finder while distinct features of salient feature points are gathered from camera provided images. In the visual localization stage, only camera is used and the robot system detects feature points from camera provided images, computes features of the detected feature points, matches them with the features recorded in previously constructed composite map, and decides location of the robot. Using this method, a robot can locate its own position effectively without expensive laser range finder so that greater acceptance can be expected due to affordability. With the proposedmethod, several experiments have been performed. The matching accuracy of proposed feature extraction achieves 97.79%, compared with 92.96% of SURF. Experiment results show that our method not only reduces hardware cost of robot localization, but also offers high accuracy.


Sign in / Sign up

Export Citation Format

Share Document