Multi-Sensor Fusion Simultaneous Localization Mapping Based on Deep Reinforcement Learning and Multi-Model Adaptive Estimation
學年 112
學期 1
出版（發表）日期 2023-12-21
作品名稱 Multi-Sensor Fusion Simultaneous Localization Mapping Based on Deep Reinforcement Learning and Multi-Model Adaptive Estimation
作品名稱（其他語言）
著者 Ching-Chang Wong, Hsuan-Ming Feng, Kun-Lung Kuo
單位
出版者
著錄名稱、卷期、頁數 Sensors 24(1), 48
摘要 In this study, we designed a multi-sensor fusion technique based on deep reinforcement learning (DRL) mechanisms and multi-model adaptive estimation (MMAE) for simultaneous localization and mapping (SLAM). The LiDAR-based point-to-line iterative closest point (PLICP) and RGB-D camera-based ORBSLAM2 methods were utilized to estimate the localization of mobile robots. The residual value anomaly detection was combined with the Proximal Policy Optimization (PPO)-based DRL model to accomplish the optimal adjustment of weights among different localization algorithms. Two kinds of indoor simulation environments were established by using the Gazebo simulator to validate the multi-model adaptive estimation localization performance, which is used in this paper. The experimental results of the proposed method in this study confirmed that it can effectively fuse the localization information from multiple sensors and enable mobile robots to obtain higher localization accuracy than the traditional PLICP and ORBSLAM2. It was also found that the proposed method increases the localization stability of mobile robots in complex environments.
關鍵字 simultaneous localization and mapping (SLAM); deep reinforcement learning (DRL); multi-model adaptive estimation (MMAE); sensor fusion
語言 en
ISSN 1424-8220
期刊性質 國外
收錄於 SCI
產學合作
通訊作者
審稿制度 否
國別 CHE
公開徵稿
出版型式 ,電子版
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/125591 )

SDGS 優質教育,產業創新與基礎設施