2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020
DOI: 10.1109/iros45743.2020.9341781
|View full text |Cite
|
Sign up to set email alerts
|

Informative Path Planning for Gas Distribution Mapping in Cluttered Environments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
14
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 17 publications
(14 citation statements)
references
References 17 publications
0
14
0
Order By: Relevance
“…GDM is a task of creating a map of the distribution of an airborne chemical over an area of interest through gathering spatially distributed chemical measurements. The mobile robot can only sample so many points within an acceptable time frame, and so the sparse measurements along with fluctuations in chemical concentration make this a difficult task (Rhodes et al, 2020). In comparison to chemical localization algorithms which attempt to navigate to the chemical source location, GDM algorithms often require the robot to follow a predetermined trajectory whilst periodically gathering concentration measurements.…”
Section: Gas Distribution Mapping (Gdm) With Mobile Robotsmentioning
confidence: 99%
“…GDM is a task of creating a map of the distribution of an airborne chemical over an area of interest through gathering spatially distributed chemical measurements. The mobile robot can only sample so many points within an acceptable time frame, and so the sparse measurements along with fluctuations in chemical concentration make this a difficult task (Rhodes et al, 2020). In comparison to chemical localization algorithms which attempt to navigate to the chemical source location, GDM algorithms often require the robot to follow a predetermined trajectory whilst periodically gathering concentration measurements.…”
Section: Gas Distribution Mapping (Gdm) With Mobile Robotsmentioning
confidence: 99%
“…Note that the framework proposed in this paper can use both model types (e.g. (Rhodes et al, 2020)), therefore leaving flexibility in the system. However, a parametric model is used in this work, not only due to its computational efficiency and wide spread adoption in the literature, but also because one of the motivations of this work is to show that such simple ATD models are adequate to inform robotic source localisation in urban environments, given features can be accommodated in the path planning algorithm.…”
Section: Estimationmentioning
confidence: 99%
“…While the above path-planning approaches suggest mapping policies for estimating gas distribution in obstacle-free environments, there is a need for path planning in cluttered areas—in which the risk for humans is greater. Attempting to overcome this problem, the Gaussian Markov Random Field approach maps the task zone as a factor graph, connecting the safe path edges to produce a path that is free from obstacles [ 23 ].…”
Section: Related Workmentioning
confidence: 99%