MRF‐based terrain map inference using variational feature projection. Issue 9 (1st May 2018)

• Record Type: Journal Article
• Authors: Yu, H.W.; Lee, B.H.
• Is Part Of: Electronics letters. Volume 54:Issue 9(2018)
• Page Start: 595
• Page End: 597
• Publication Date: 2018-05-01
• Subjects: Markov processes -- mobile robots -- Gaussian processes -- Bayes methods -- maximum likelihood estimation -- path planning -- terrain mapping; variational feature projection -- unobserved field -- navigation paths -- vibrations -- vehicle–terrain interactions -- adjacent terrain grids -- robot paths -- Markov random field -- MRF -- approximate the complex likelihood -- vibration features -- tractable distribution -- variational auto‐encoder -- intractable features -- approximated likelihood -- neural network classifier -- numerical maximum a posterior inference -- inferred terrain maps -- feature likelihood -- terrain map inference; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2017.3622
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : A method to infer the terrain of unobserved fields as well as navigation paths using vibrations from vehicle–terrain interactions is presented. The relationships between adjacent terrain grids and robot paths are modelled by Markov random field (MRF) for inferring the classes of unobserved field. In order to approximate the complex likelihood of vibration features as a tractable distribution, a variational auto‐encoder is adopted. By projecting intractable features to the latent space, an approximated likelihood that gives similar performance to a neural network classifier is obtained. Then the numerical maximum a posterior inference for MRF is obtained. The result of inferred terrain maps are compared with that from the feature likelihood as a Gaussian‐mixture model.