2015 IEEE International Conference on Advanced Intelligent Mechatronics (AIM) 2015
DOI: 10.1109/aim.2015.7222667
|View full text |Cite
|
Sign up to set email alerts
|

Appearance-based localization using Group LASSO regression with an indoor experiment

Abstract: This paper proposes appearance-based localization using online vision images collected from an omnidirectional camera attached on a mobile robot or a vehicle. Our approach builds on a combination of the group Least Absolute Shrinkage and Selection Operator (LASSO) and the extended Kalman filter (EKF). Fast Fourier transform (FFT) and Histogram are extracted from omni-directional images, the features of which are selected via the group LASSO regression. The EKF takes the output of the group LASSO regression bas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2017
2017
2018
2018

Publication Types

Select...
1
1
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 17 publications
0
4
0
Order By: Relevance
“…Although the GSE-based functions V GSE (w) (23) and Φ GSE (θ) (24) accurately approximate the sought-for functions ψ(w) and Φ(θ), respectively, they cannot be considered as the solution to the Robot Localization problem because the mappings g GSE,u (y) and g GSE,v (y) (17), (18) depend on the argument…”
Section: A Splitting Of An Arbitrary Vectormentioning
confidence: 99%
See 2 more Smart Citations
“…Although the GSE-based functions V GSE (w) (23) and Φ GSE (θ) (24) accurately approximate the sought-for functions ψ(w) and Φ(θ), respectively, they cannot be considered as the solution to the Robot Localization problem because the mappings g GSE,u (y) and g GSE,v (y) (17), (18) depend on the argument…”
Section: A Splitting Of An Arbitrary Vectormentioning
confidence: 99%
“…Various types of regression between images or their low-dimensional features and robot coordinates are constructed including Gaussian process regression, random forest, etc. [15], [16], [17], [18], [19], [20], [21], [22]. This paper proposes new geometrically motivated machine learning approach to the appearance-based robot localization problem by combining a few advanced techniques.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Preliminary results for indoor and outdoor experiments were reported in Refs. [27] and [28], respectively.…”
Section: Introductionmentioning
confidence: 99%