Publications:Comparison of Machine Learning Approaches for Soil Embedding Detection of Planetary Exploration Rovers

From ISLAB/CAISR
Revision as of 22:42, 30 September 2016 by Slawek (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Do not edit this section

Keep all hand-made modifications below

Title Comparison of Machine Learning Approaches for Soil Embedding Detection of Planetary Exploration Rovers
Author Ramon Gonzalez and Stefan Byttner and Karl Iagnemma
Year 2016
PublicationType Conference Paper
Journal
HostPublication Proceedings of the 8th ISTVS Americas Conference, Detroit, September 12-14, 2016.
Conference International Conference of the ISTVS (International Society for Terrain-Vehicle Systems), Detroit, Michigan, USA, 12-14 September, 2016
DOI
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:971911
Abstract This paper analyzes the advantages and limitations of known machine learning approaches to cope with the problem of incipient rover embedding detection based on propioceptive signals. In particular, two supervised learning approaches (Support Vector Machines and Feed-forward Neural Networks) are compared to two unsupervised learning approaches (K-means and Self-Organizing Maps) in order to identify various degrees of slip (e.g. low slip, moderate slip, high slip). A real dataset collected by a single-wheel testbed available at MIT has been used to validate each strategy. The SVM algorithm achieves the best performance (accuracy >95 %). However, the SOM algorithm represents a better solution in terms of accuracy and the need of hand-labeled data for training the classifier (accuracy >84 %).