2012
DOI: 10.15676/ijeei.2012.4.1.2
|View full text |Cite
|
Sign up to set email alerts
|

GPGPU computation in mobile robot applications

Abstract: The paper concerns the results related with GPGPU computing applied for mobile robotics applications. The scalable implementation of the point to point and point to plane 3D data registration methods with an improvement based on regular grid decomposition is shown. 3D data is delivered by mobile robot equipped with 3D laser measurement system for INDOOR environments. Presented empirical analysis of the implementation shows the On-Line computation capability using modern graphic processor unit NVIDIA GF 580. In… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2014
2014
2020
2020

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 22 publications
0
3
0
Order By: Relevance
“…The ICP algorithm implemented in the SLAM procedure defined for the APR mobile robots use the point to plane strategy. In general, it is well known that point to plane is a noticeably slower metric than point to point due to its complexity [ 31 ]. However, in an indoor scenario, point to plane provides better results when merging scanned point clouds that are mostly composed of straight lines (such as the large walls that conform the explored area) because it tries to align the current point cloud with the nearest planes of the 2D map rather than trying to reduce the distance between the point clouds to zero like the point to point.…”
Section: Methodsmentioning
confidence: 99%
“…The ICP algorithm implemented in the SLAM procedure defined for the APR mobile robots use the point to plane strategy. In general, it is well known that point to plane is a noticeably slower metric than point to point due to its complexity [ 31 ]. However, in an indoor scenario, point to plane provides better results when merging scanned point clouds that are mostly composed of straight lines (such as the large walls that conform the explored area) because it tries to align the current point cloud with the nearest planes of the 2D map rather than trying to reduce the distance between the point clouds to zero like the point to point.…”
Section: Methodsmentioning
confidence: 99%
“…However, most existing parallel implementations of SVD are specialized for large matrices [29]. For SVD of a large number of small matrices, Bedkowski et al introduced an algorithm for three-dimensional reconstruction using mobile robots [30]. In the present work, the algorithm introduced by Bedkowski et al is modified.…”
Section: Additional Filementioning
confidence: 99%
“…e) f) g) h) Fig. 3: Operational field trials for requirements validation: a, e): Ground robots navigating indoor and outdoor on rough terrain [16]; b, f): Aerial platforms searching for human victims and doing site surveys; c, g): Maritime platforms testing deployment of rescue capsules for rescuing victims in water [13]; d): Communication tools trials [17] and h) 3D reconstruction of the environment [18]…”
Section: Operational Validation Of the User Requirements And Conclusionmentioning
confidence: 99%