arXiv Analytics

Sign in

arXiv:2006.16235 [cs.RO]AbstractReferencesReviewsResources

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Travis Manderson, Juan Camilo Gamboa Higuera, Stefan Wapnick, Jean-Fran├žois Tremblay, Florian Shkurti, David Meger, Gregory Dudek

Published 2020-06-29Version 1

We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided by a user without any prior map, all while avoiding obstacles and choosing paths that cover user-informed regions of interest. Our approach is based on recent advances in conditional imitation learning. General-purpose, safe and informative actions are demonstrated by a human expert. The learned policy is subsequently extended to be goal-conditioned by training with hindsight relabelling, guided by the robot's relative localization system, which requires no additional manual annotation. We deployed our method on an underwater vehicle in the open ocean to collect scientifically relevant data of coral reefs, which allowed our robot to operate safely and autonomously, even at very close proximity to the coral. Our field deployments have demonstrated over a kilometer of autonomous visual navigation, where the robot reaches on the order of 40 waypoints, while collecting scientifically relevant data. This is done while travelling within 0.5 m altitude from sensitive corals and exhibiting significant learned agility to overcome turbulent ocean conditions and to actively avoid collisions.

Comments: RSS 2020. Video and project details can be found at
Categories: cs.RO
Related articles: Most relevant | Search more
arXiv:1507.01932 [cs.RO] (Published 2015-07-07)
Demonstration of an Aerial and Submersible Vehicle Capable of Flight and Underwater Navigation with Seamless Air-Water Transition
arXiv:1701.00860 [cs.RO] (Published 2017-01-03)
Design, Control and Visual Navigation of the DelftaCopter
arXiv:1906.07207 [cs.RO] (Published 2019-06-17)
Visual Navigation by Generating Next Expected Observations