Incremental Map Modeling for Lightweight SLAM via Deep Reinforcement Learning

Chien Heng Yu, Ching Chun Huang

研究成果: Conference contribution同行評審

摘要

Simultaneous localization and mapping (SLAM) technology which builds a map in a pose graph has high accuracy but low memory utilization and limitations in handling full memory. This paper proposes a keyframe decision-making method based on the visual SLAM framework and deep reinforcement learning. The keyframe selection instruction is given to the mapper, and the map size is controlled to achieve map modeling. Furthermore, the map increment obtained by 3D reconstruction can obtain the intersection relationship between keyframes. We use a self-defining reward function to create the network learning policy to maximize map coverage and minimize memory usage. Experiments demonstrate that our method can perform accurate map modeling without affecting the quality of the mapping, thus reducing memory requirements.

原文English
主出版物標題2023 IEEE International Conference on Consumer Electronics, ICCE 2023
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665491303
DOIs
出版狀態Published - 2023
事件2023 IEEE International Conference on Consumer Electronics, ICCE 2023 - Las Vegas, United States
持續時間: 6 1月 20238 1月 2023

出版系列

名字Digest of Technical Papers - IEEE International Conference on Consumer Electronics
2023-January
ISSN(列印)0747-668X

Conference

Conference2023 IEEE International Conference on Consumer Electronics, ICCE 2023
國家/地區United States
城市Las Vegas
期間6/01/238/01/23

指紋

深入研究「Incremental Map Modeling for Lightweight SLAM via Deep Reinforcement Learning」主題。共同形成了獨特的指紋。

引用此