• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Visually Adaptive Geometric Navigation.
Shravan Ravi, Gary Wang, Shreyas Satewar, Xuesu
Xiao, Garrett Warnell, Joydeep
Biswas, and Peter Stone.
In IEEE International Symposium on Safety,Security,and
Rescue Robotics, November 2023.
While classical autonomous navigation systemscan move robots from one point toanother in a collision-free manner due to geometric modeling, recent approachestovisual navigation allow robots to consider semantic information.However,most visual navigation systems do not explicitly reasonabout geometry, whichmay potentially lead to collisions. Thispaper presents Visually AdaptiveGeometric Navigation (VAGN),which marries the two schools of navigationapproaches toproduce a navigation system that is able to adapt to thevisualappearance of the environment while maintaining collision-freebehavior.Employing a classical geometric navigation system toaddress geometric safetyand efficiency, VAGN consults visualperception to dynamically adjust theclassical planner’s hyper-parameters (e.g., maximum speed, inflation radius) toenablenavigational behaviors not possible with purely geometricreasoning. VAGNis implemented on two different physicalground robots with different actionspaces, navigation systems,and parameter sets. VAGN demonstrates superiornavigationperformance in both a test course with rich semantic andgeometricfeatures and a real-world deployment compared toother navigation baselines
@InProceedings{shravan_ravi_SSRR2023,
author = {Shravan Ravi and Gary Wang and Shreyas Satewar and Xuesu Xiao and Garrett Warnell and Joydeep Biswas and Peter Stone},
title = {Visually Adaptive Geometric Navigation},
booktitle = {IEEE International Symposium on Safety,Security,and Rescue Robotics},
year = {2023},
month = {November},
location = {Fukushima, Futaba District, Naraha, Yamadaoka},
abstract = {
While classical autonomous navigation systems
can move robots from one point to
another in a collision-
free manner due to geometric modeling, recent approaches
to
visual navigation allow robots to consider semantic information.
However,
most visual navigation systems do not explicitly reason
about geometry, which
may potentially lead to collisions. This
paper presents Visually Adaptive
Geometric Navigation (VAGN),
which marries the two schools of navigation
approaches to
produce a navigation system that is able to adapt to the
visual
appearance of the environment while maintaining collision-free
behavior.
Employing a classical geometric navigation system to
address geometric safety
and efficiency, VAGN consults visual
perception to dynamically adjust the
classical planner’s hyper-
parameters (e.g., maximum speed, inflation radius) to
enable
navigational behaviors not possible with purely geometric
reasoning. VAGN
is implemented on two different physical
ground robots with different action
spaces, navigation systems,
and parameter sets. VAGN demonstrates superior
navigation
performance in both a test course with rich semantic and
geometric
features and a real-world deployment compared to
other navigation baselines
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Sun Nov 24, 2024 20:24:57