IEEE International Conference on Robotics and Automation (ICRA) 2022

Confidence-Based Robot Navigation Under Sensor Occlusion with Deep Reinforcement Learning

Confidence-Based Robot Navigation Under Sensor Occlusion with Deep Reinforcement Learning

by Hyeongyeol Ryu, Minsung Yoon, Daehyung Park, and Sung-Eui Yoon

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.

Contents:

Paper: paper.pdf
Slide: slide.pptx
Poster: poster.pptx
Source code: code.zip

Bibtex:

	@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}
	}
	

Media:

- Published as a research highlight on the website of the Department of Computer Science at KAIST (Link).
- Presented at KROC 2023 Flagship Conference / Journal Session. (slide.pptx)