A Direct Localization Method Using only the Bearings Extracted from Two Panoramic Views Along a Linear Trajectory

Huang, Haochu; Maire, Frédéric; Keeratipranon, Narongdech

doi:10.1007/3-540-29344-2_30

Search citation statements

Order By: Relevance

Paper Sections

Select...

Vision Based Navigation1

Training a Som Using Estimated Robot Positions1

Citation Types

Supporting

Mentioning

Contrasting

Publication Types

Select...

Book1

Article1

Relationship

Self Cite2

Independent0

Authors

Journals

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If a robot can move straight, the estimation of a landmark range from a monocular vision will be the same as the estimation in a stereo vision. Such approach was first proposed by Huang et al (2005a). In this paper, a localization method with two observed bearings along a linear trajectory was presented.…”

Section: Vision Based Navigationmentioning

confidence: 99%

Bearing-only Simultaneous Localization and Mapping for Vision-Based Mobile Robots

Huang¹,

Maire²,

Keeratipranon³

2007

Vision Systems: Applications

Self Cite

View full text Add to dashboard Cite

Section: Vision Based Navigationmentioning

confidence: 99%

Bearing-only Simultaneous Localization and Mapping for Vision-Based Mobile Robots

Huang¹,

Maire²,

Keeratipranon³

2007

Vision Systems: Applications

Self Cite

View full text Add to dashboard Cite

“…29 The method estimates landmark positions by computing the intersections of the vision cones rooted at the two observation points in the robot-centered frame. After an appropriate change of basis, the positions of the robot are expressed in the landmark-centered frame.…”

Section: Training a Som Using Estimated Robot Positionsmentioning

confidence: 99%

Manifold Learning for Robot Navigation

Keeratipranon

Maire

Huang

2006

Int. J. Neur. Syst.

Self Cite

View full text Add to dashboard Cite

In this paper we introduce methods to build a SOM that can be used as an isometric map for mobile robots. That is, given a dataset of sensor readings collected at points uniformly distributed with respect to the ground, we wish to build a SOM whose neurons (prototype vectors in sensor space) correspond to points uniformly distributed on the ground. Manifold learning techniques have already been used for dimensionality reduction of sensor space in navigation systems. Our focus is on the isometric property of the SOM. For reliable path-planning and information sharing between several robots, it is desirable that the robots build an internal representation of the sensor manifold, a map, that is isometric with the environment. We show experimentally that standard Non-Linear Dimensionality Reduction (NLDR) algorithms do not provide isometric maps for range data and bearing data. However, the auxiliary low dimensional manifolds created can be used to improve the distribution of the neurons of a SOM (that is, make the neurons more evenly distributed with respect to the ground). We also describe a method to create an isometric map from a sensor readings collected along a polygonal line random walk.

show abstract

A Direct Localization Method Using only the Bearings Extracted from Two Panoramic Views Along a Linear Trajectory

Cited by 2 publications

References 6 publications

Bearing-only Simultaneous Localization and Mapping for Vision-Based Mobile Robots

Bearing-only Simultaneous Localization and Mapping for Vision-Based Mobile Robots

Manifold Learning for Robot Navigation

Contact Info

Product

Resources

About