Gaussian Markov Random Fields for Fusion in Information Form

Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:
Conference Proceeding
Citation:
Proceedings - IEEE International Conference on Robotics and Automation, 2016, pp. 1840 - 1845
Issue Date:
2016-05-16
Full metadata record
Files in This Item:
Filename Description Size
F6AA7196-DB47-4A07-9AB9-E086B01E3549 am.pdfAccepted Manuscript version629.01 kB
Adobe PDF
2.5D maps are preferable for representing the environment owing to compactness. When noisy observations from diverse sensors at different resolutions are available, the problem of 2.5D mapping turns to how to compound the information in an effective and efficient manner. This paper proposes a generic probabilistic framework for fusing efficiently multiple sources of sensor data to generate amendable, high-resolution 2.5D maps. The key idea is to exploit the sparsity of the information matrix. Gaussian Markov Random Fields are employed to learn a prior map, using the conditional independence property between location to obtain a representation of the state. This prior map encoded in information form can then be updated with other sources of data in constant time. Later, mean state vector and variances can be efficiently recovered using numerical methods. The proposed approach allows accurate estimation of 2.5D maps at arbitrary resolution, while incorporating sensor noise and spatial dependency in a statistically reasonable way. We apply the proposed framework to pipe wall thickness mapping and fuse data from two diverse sensors that have different resolutions. Experimental results are compared with three other approaches, showing that, while greatly reducing computation time, the proposed framework is able to capture in large extend the spatial correlation to generate equivalent results to the expensive optimal fusion method in covariance form with a Gaussian Process prior.
Please use this identifier to cite or link to this item: