E ective Perception Capability for a Planetary Exploration Rover via Stereo Vision and Data Fusion

Current space mission plans foresee a strong robotic presence, with the purpose to rely on automatic systems for all tasks resulting di cult or dangerous to man. In the present paper, a project for the development of a robotic platform, to demonstrate robotic autonomy, is generally described. It is based on a flexible and modular software architecture in which each functional module implements a key functionality of the GNC (Guidance Navigation and Control). Details about the stereo vision algorithm for the three-dimensional world point reconstruction are provided, together with hints about a possible fusion with data from a laser scanner. Finally, some preliminary experimental results are shown.

[1]  Steven Mills,et al.  Stereo Reconstruction for Visual Navigation , 2008 .

[2]  Giuseppe Casalino,et al.  A new software architecture for developing and testing algorithms for space exploration missions , 2011, Intell. Serv. Robotics.

[3]  Francis Schmitt,et al.  Multi-stereo 3D object reconstruction , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.

[4]  Ho Gi Jung,et al.  Stereo Vision Based Localization of Free Parking Site , 2005, CAIP.

[5]  Nour-Eddin El Faouzi,et al.  Sensor and Data Fusion , 2012, Handbook of Soft Computing for Video Surveillance.

[6]  Devendra P. Garg,et al.  Multi-Sensor Data Fusion in Presence of Uncertainty and Inconsistency in Data , 2009 .

[7]  Stefano Soatto,et al.  Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance , 2005, International Journal of Computer Vision.

[8]  Takeo Kanade,et al.  High-Resolution Terrain Map from Multiple Sensor Data , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Yuri Vershinin,et al.  A data fusion algorithm for multisensor systems , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).