Header

UZH-Logo

Maintenance Infos

Exploiting photometric information for planning under uncertainty


Costante, Gabriele; Delmerico, Jeffrey; Werlberger, Manuel; Valigi, Paolo; Scaramuzza, Davide (2017). Exploiting photometric information for planning under uncertainty. In: Bicchi, Antonio; Burgard, Wolfram. Robotics Research. Cham: Springer, 107-124.

Abstract

Vision-based localization systems rely on highly-textured areas for achieving an accurate pose estimation. However, most previous path planning strategies propose to select trajectories with minimum pose uncertainty by leveraging only the geometric structure of the scene, neglecting the photometric information (i.e, texture). Our planner exploits the scene’s visual appearance (i.e, the photometric information) in combination with its 3D geometry. Furthermore, we assume that we have no prior knowledge about the environment given, meaning that there is no pre-computed map or 3D geometry available. We introduce a novel approach to update the optimal plan on-the-fly, as new visual information is gathered. We demonstrate our approach with real and simulated Micro Aerial Vehicles (MAVs) that perform perception-aware path planning in real-time during exploration. We show significantly reduced pose uncertainty over trajectories planned without considering the perception of the robot.

Abstract

Vision-based localization systems rely on highly-textured areas for achieving an accurate pose estimation. However, most previous path planning strategies propose to select trajectories with minimum pose uncertainty by leveraging only the geometric structure of the scene, neglecting the photometric information (i.e, texture). Our planner exploits the scene’s visual appearance (i.e, the photometric information) in combination with its 3D geometry. Furthermore, we assume that we have no prior knowledge about the environment given, meaning that there is no pre-computed map or 3D geometry available. We introduce a novel approach to update the optimal plan on-the-fly, as new visual information is gathered. We demonstrate our approach with real and simulated Micro Aerial Vehicles (MAVs) that perform perception-aware path planning in real-time during exploration. We show significantly reduced pose uncertainty over trajectories planned without considering the perception of the robot.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

14 downloads since deposited on 22 Aug 2017
14 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Date:July 2017
Deposited On:22 Aug 2017 14:37
Last Modified:19 Feb 2018 08:28
Publisher:Springer
Series Name:Springer Proceedings in Advanced Robotics
Number:1
ISBN:978-3-319-51531-1
OA Status:Green
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1007/978-3-319-51532-8_7
Official URL:http://rpg.ifi.uzh.ch/docs/Springer17_Costante.pdf
Other Identification Number:merlin-id:15106

Download

Download PDF  'Exploiting photometric information for planning under uncertainty'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 5MB
View at publisher
Get full-text in a library