Abstract:
This paper deals with automatically learning the spatial distribution of a set of measurements: images, in the examples presented here. The solution to this problem can be viewed as an instance of robot mapping although it can also be used in other contexts. We examine the problem of organizing an ensemble of images of an environment in terms of the positions from which the images were obtained, and where only limited prior odometric information is available. Our approach employs a feature-based method derived from a probabilistic robot localization framework. Initially, a set of visual landmarks are selected from the images and correspondences are found across the ensemble. The images are then localized by first assembling the small subset of images for which odometric confidence is high, and sequentially inserting the remaining images, localizing each against the previous estimates, and taking advantage of any priors that are available. We present experimental results validating the approach, and demonstrating metrically and topologically accurate results over two large image ensembles, even given only four initial ground truth poses. Finally, we discuss the results, their relationship to the autonomous exploration of an unknown environment, and their utility for robot localization and navigation. 1
Citations
|
2252
|
Self-Organizing Maps
– Kohonen
- 1995
|
|
1055
|
Self-organization and associative memory
– Kohonen
- 1984
|
|
362
|
A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations
– Kuipers, Byun
- 1991
|
|
351
|
A probabilistic approach to concurrent mapping and localization for mobile robots
– Thrun, Fox, et al.
- 1998
|
|
198
|
Learning metric-topological maps for indoor mobile robot navigation
– Thrun
- 1998
|
|
192
|
Mobile Robot Localization by Tracking Geometric Beacons
– Leonard, Durrant-Whyte
- 1991
|
|
130
|
Topological simultaneous localization and mapping (slam): Toward exact localization without explicit localization
– Choset, Nagatani
- 2001
|
|
119
|
Learning topological maps with weak local odometric information
– Shatkay, Kaelbling
- 1997
|
|
115
|
A computationally efficient method for large-scale concurrent mapping and localization
– Leonard, Feder
- 1999
|
|
111
|
Simultaneous Map Building and Localization for an Autonomous Mobile Robot
– Leonard, Durrant-Whyte
- 1991
|
|
72
|
Mobile robot exploration and map-building with continuous localization
– Yamauchi, Schultz, et al.
- 1998
|
|
55
|
Bootstrap learning for place recognition
– Kuipers, Beeson
- 2002
|
|
40
|
A qualitative approach to robot exploration and map-learning
– Kuipers, Byun
- 1987
|
|
32
|
3D simultaneous localisation and map-building using active vision for a robot moving on undulating terrain
– Davison, Kita
- 2001
|
|
30
|
Theoretical problems for the realization of distributed robotic systems
– Beni, Wang
- 1991
|
|
21
|
Self-organization mechanisms in ant societies (II): Learning in foraging and division of labor
– Deneubourg, Goss, et al.
- 1987
|
|
21
|
Competitive robot mapping with homogeneous markers
– Deng, Mirzaian
- 1996
|
|
17
|
Shape representation and recognition from curvature
– Dudek, Tsotsos
- 1991
|
|
14
|
Learning Generative Models of Scene Features
– Sim, Dudek
- 2001
|
|
11
|
On the representation and estimation of spatial undertainty
– Smith, Cheeseman
- 1986
|
|
8
|
Sensory-based robot navigation using selforganizing networks and q-learning
– Gross, Stephan, et al.
- 1996
|
|
5
|
Evangelos Milios. Collaborative exploration for the construction of visual maps
– Rekleitis, Sim, et al.
- 2001
|
|
3
|
Takio Kurita. Self-organization of place cells and reward-based navigation for a mobile robot
– Takahashi, Tanaka, et al.
- 2001
|
|
2
|
The organization of organization
– Selfridge
- 1962
|
