Korea Advanced Institute of Science and Technology (KAIST)
Nominated as an outstanding navigation paper finalist at ICRA22.
(As finalists, only 39 papers were selected out of a total of 1,498 published papers.)
Video:
Abstract:
This paper considers the problem of prolonged
occlusions on navigation sensors due to dust, smudges, soils,
etc. Such uncontrollable occlusions often cause lower visibility
as well as higher uncertainty that require considerably sophisticated
behavior. To secure visibility (i.e., confidence about the
world), we propose a confidence-based navigation method that
encourages the robot to explore the uncertain region around
the robot maximizing its local confidence. To effectively extract
features from the variable size of sensor occlusions, we adopt a
point-cloud based representation network. Our method returns
a resilient navigation policy via deep reinforcement learning,
autonomously avoiding collisions under sensor occlusions while
reaching a goal. We evaluate our method in simulated and
real-world environments with either static or dynamic obstacles
under various sensor-occlusion scenarios. The experimental
result shows that our method outperforms baseline methods
under the highly occurring sensor occlusion, and achieves
maximum 90% and 80% success rates in the tested static and
dynamic environments, respectively.
@inproceedings{ryu2022confidence,
title={Confidence-Based Robot Navigation Under Sensor Occlusion with Deep Reinforcement Learning},
author={Ryu, Hyeongyeol and Yoon, Minsung and Park, Daehyung and Yoon, Sung-Eui},
booktitle={2022 International Conference on Robotics and Automation (ICRA)},
pages={8231--8237},
year={2022},
organization={IEEE}
}