A New 3D Map Reconstruction Based Mobile Robot Navigation

In order to build a precise 3D map of outdoor environment, a novel map reconstruction algorithm is proposed based on a mobile robot. The robot used a four-layer laser radar (LD_ML) to obtain space information and used a DGPS/INS (difference GPS/inertial navigation system) position system to obtain itself pose and position information. With the aim of building a complete 3D grid map, the range data of environment need be changed into a world coordinate system with the simultaneous position data of the robot. Since the outdoor environment is always complicated, the 3D grid map is built by updating z-coordinate value using obstacle detection results. And the obstacle detection is achieved by LD_ML according to the gradient and height information of detection regions. The results of 3D grip map reconstruction testified the 3D map reconstruction algorithm was reliable and stable

[1]  Oliver Grau,et al.  A scene analysis system for the generation of 3-D models , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[2]  Richard Szeliski,et al.  3-D Scene Data Recovery Using Omnidirectional Multibaseline Stereo , 2004, International Journal of Computer Vision.

[3]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Richard Szeliski,et al.  3-D Scene Data Recovery Using Omnidirectional Multibaseline Stereo , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Takeo Kanade,et al.  Virtualized Reality: Constructing Virtual Worlds from Real Scenes , 1997, IEEE Multim..