2007
DOI: 10.1007/978-3-540-74024-7_29
|View full text |Cite
|
Sign up to set email alerts
|

A Novel Approach to Efficient Monte-Carlo Localization in RoboCup

Abstract: Recently, efficient self-localization methods have been developed, among which probabilistic Monte-Carlo localization (MCL) is one of the most popular. However, standard MCL algorithms need at least 100 samples to compute an acceptable position estimation. This paper presents a novel approach to MCL that uses an adaptive number of samples that drops down to a single sample if the pose estimation is sufficiently accurate. Experiments show that the method remains in this efficient single sample tracking mode for… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
12
0

Year Published

2007
2007
2013
2013

Publication Types

Select...
3
2
1

Relationship

3
3

Authors

Journals

citations
Cited by 8 publications
(12 citation statements)
references
References 9 publications
0
12
0
Order By: Relevance
“…Second, the extraction of the green and the white color class is robust enough to cope with a sudden change in illumination as shown in section II-A. This enables the robust self-localization [5] to keep track of the correct pose of the robot until the other color classes are adapted.…”
Section: The Automatic Color Training Algorithmmentioning
confidence: 99%
See 1 more Smart Citation
“…Second, the extraction of the green and the white color class is robust enough to cope with a sudden change in illumination as shown in section II-A. This enables the robust self-localization [5] to keep track of the correct pose of the robot until the other color classes are adapted.…”
Section: The Automatic Color Training Algorithmmentioning
confidence: 99%
“…By incorporating the pose of the robot computed by our self-localization algorithm ( [5]) this algorithm is able to constantly re-train the mapping according to the changing lighting conditions. By keeping the amount of training per cycle as low as possible, the algorithm can be processed 50 times a second on our RoboCup MSL robots.…”
Section: Introductionmentioning
confidence: 99%
“…One of the most used algorithms for self-localization is Monte Carlo [8] [1] [5]. Since Monte Carlo is very used, some improvements on it had been proposed [3] [7]. However, rather than proposing a new localization algorithm, this paper proposes a new way of sorting out one step of the localization task, namely the orientation.…”
Section: Introductionmentioning
confidence: 99%
“…A common method to determine the number of particles is KLD-sampling [12]. Heinemann et al project the current sensor data onto the map, based on the position estimate [13]. They choose the number of particles based on the distance between the map data and the projected sensor data.…”
Section: Introductionmentioning
confidence: 99%