2011 IEEE International Conference on Robotics and Automation 2011
DOI: 10.1109/icra.2011.5979742
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Abstract-The probabilistic belief networks that result from standard feature-based simultaneous localization and map building cannot be directly used to plan trajectories. The reason is that they produce a sparse graph of landmark estimates and their probabilistic relations, which is of little value to find collision free paths for navigation. In contrast, we argue in this paper that Pose SLAM graphs can be directly used as belief roadmaps. We present a method that devises optimal navigation strategies by sear… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2013
2013
2019
2019

Publication Types

Select...
4
3
2

Relationship

1
8

Authors

Journals

citations
Cited by 34 publications
(6 citation statements)
references
References 20 publications
(18 reference statements)
0
6
0
Order By: Relevance
“…On real datasets where loop-closing constraints are sparse, our method is able to perform at full precision with a considerable recall, resulting in a smaller absolute trajectory error. The aim of SLAM is not just to build a nice looking map but to use it further to carry out higher-level tasks such as planning (Carrillo et al, 2012) and navigation (Valencia et al, 2011). In that regard, loop closing links provide traversability information.…”
Section: Discussionmentioning
confidence: 99%
“…On real datasets where loop-closing constraints are sparse, our method is able to perform at full precision with a considerable recall, resulting in a smaller absolute trajectory error. The aim of SLAM is not just to build a nice looking map but to use it further to carry out higher-level tasks such as planning (Carrillo et al, 2012) and navigation (Valencia et al, 2011). In that regard, loop closing links provide traversability information.…”
Section: Discussionmentioning
confidence: 99%
“…However, occupancy maps are normally thresholded and used in the aforementioned ternary form [14]. Uncertainty is then accounted for in different ways, e.g., through planning in a belief state over obstacle positions to minimize path uncertainty [15] or by inflating or deflating obstacles depending on collision probability [16].…”
Section: Related Work a Uncertainty In Robotic Mobilitymentioning
confidence: 99%
“…The lane detection problem stated in this paper can be formulated as a graph searching problem, which is degraded as SPP. As a general problem, the SPP has been applied in many fields, including path planning [28], computer vision [29], and network flow [30]. By constructing a graph from raw data, problems can be solved efficiently by applying a general shortest path searching algorithm, such as A* search [31], the Dijkstra's algorithm [32], the Floyd-Warshal algorithm [33] or the ant colony optimization algorithm [34].…”
Section: B Visual Recognition Based On Shortest Path Problemmentioning
confidence: 99%