2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2016
DOI: 10.1109/iros.2016.7759665
|View full text |Cite
|
Sign up to set email alerts
|

Towards effective localization in dynamic environments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
23
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 34 publications
(23 citation statements)
references
References 10 publications
0
23
0
Order By: Relevance
“…Dynamic obstacles may produce distance measurements that are shorter than expected. Those relative short measurements can be filtered through the distance filter [35]. To effectively integrated distance filter with BnB-AMCL, unscented transformation is adopted to improve the original distance filter, which leads to UDF.…”
Section: B Udfmentioning
confidence: 99%
“…Dynamic obstacles may produce distance measurements that are shorter than expected. Those relative short measurements can be filtered through the distance filter [35]. To effectively integrated distance filter with BnB-AMCL, unscented transformation is adopted to improve the original distance filter, which leads to UDF.…”
Section: B Udfmentioning
confidence: 99%
“…The number of nonempty state spaces is small; k is small, and the upper bound N top of the number of particles decrease. In this way, the number of particles is effectively dynamically adjusted [16]. The total number of particles is reduced which results in better computational efficiency.…”
Section: Monte Carlo Localization Algorithmmentioning
confidence: 99%
“…It is important to take note that on every turn in estimating the probability of the next pose estimation in Bayes' theorem, previous measurements and control inputs need to be taken into consideration. As we can see in (1), z 0:k sensor measurements and u 0:k input controls were taken from time 0 all the way to time k. This is from the concept of online SLAM that takes estimation measurements in an incremental fashion because it can reduce the computation complexities as the map gets bigger which directly can increase the number of variables [8]. This approach is the total opposite of full SLAM that takes not only the whole sensor measurements and input controls, but as well as the whole vehicle pose estimations, x 0:k in its estimation [9][24].…”
Section: Fig 1: Example Lidar Sensor Measurementsmentioning
confidence: 99%