Abstract:
The indirect visual simultaneous localization and mapping (VSLAM) is widely used in robot localization and navigation, thanks to its potential to achieve high localizatio...Show MoreMetadata
Abstract:
The indirect visual simultaneous localization and mapping (VSLAM) is widely used in robot localization and navigation, thanks to its potential to achieve high localization accuracy with the local feature observations. However, the existing local features are subject to drift and mismatches under various visual conditions, which causes a degrading in localization accuracy and tracking loss. This article proposes a quantized self-supervised local feature for the indirect VSLAM to handle the environmental interference in robot localization tasks. A joint feature detection and description network is built in a lightweight manner to extract local features in real time. The network is iteratively trained by a self-supervised learning strategy, and the extracted local features are quantized by an orthogonal transformation for efficiency. We utilize frame-wise matching in Hamming space and bundle adjustment to establish a parallel indirect VSLAM. The proposed VSLAM demonstrates outstanding localization accuracy and tracking stability in the evaluation on multiple datasets and robustness in real-world experiments with the Realsense D435 RGB-D sensor. The efficiency experiment on Jetson TX2 indicates that the quantized self-supervised local feature is suitable for feature-based tasks on edge computing platforms.
Published in: IEEE/ASME Transactions on Mechatronics ( Volume: 27, Issue: 3, June 2022)
Funding Agency:
Department of Automation, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Shenghao Li received the B.S. degree in mechanical design manufacture and automation and the M.S. degree in mechanical engineering from the East China University of Science and Technology, Shanghai, China, in 2017 and 2020, respectively. He is working toward the Ph.D. degree in control science and engineering from with the Shanghai Jiao Tong University, Shanghai, China.
His research interests include local feature learning...Show More
Shenghao Li received the B.S. degree in mechanical design manufacture and automation and the M.S. degree in mechanical engineering from the East China University of Science and Technology, Shanghai, China, in 2017 and 2020, respectively. He is working toward the Ph.D. degree in control science and engineering from with the Shanghai Jiao Tong University, Shanghai, China.
His research interests include local feature learning...View more
School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China
Shuang Liu received the Ph.D. degree in instrument science and technology jointly from the Joint Research Center, City University of Hong Kong, Hong Kong, and the University of Science and Technology of China, Suzhou, China, in 2010.
Since 2014, he has been an Associate Professor with the School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China. His research interests inc...Show More
Shuang Liu received the Ph.D. degree in instrument science and technology jointly from the Joint Research Center, City University of Hong Kong, Hong Kong, and the University of Science and Technology of China, Suzhou, China, in 2010.
Since 2014, he has been an Associate Professor with the School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China. His research interests inc...View more
Department of Automation, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Qunfei Zhao received the B.S.E.E. degree from Xi’an Jiao Tong University, Xi’an, China, in 1982, and the Sc.D. degree in system science from the Tokyo Institute of Technology, Tokyo, Japan, in 1988.
He is currently a Professor with the School of Electronic Information and Electric Engineering, Shanghai Jiao Tong University, Shanghai, China. His research interests include robotics, machine vision, and optimal control of com...Show More
Qunfei Zhao received the B.S.E.E. degree from Xi’an Jiao Tong University, Xi’an, China, in 1982, and the Sc.D. degree in system science from the Tokyo Institute of Technology, Tokyo, Japan, in 1988.
He is currently a Professor with the School of Electronic Information and Electric Engineering, Shanghai Jiao Tong University, Shanghai, China. His research interests include robotics, machine vision, and optimal control of com...View more
School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China
Qiaoyang Xia received the M.S. degree in mechanical engineering from the Mechanical Engineering Department, East China University of Science and Technology, Shanghai, China, in 2021.
His research interests include robotics localization, trajectory planning, and multirobot systems.
Qiaoyang Xia received the M.S. degree in mechanical engineering from the Mechanical Engineering Department, East China University of Science and Technology, Shanghai, China, in 2021.
His research interests include robotics localization, trajectory planning, and multirobot systems.View more
Contents Department of Automation, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Shenghao Li received the B.S. degree in mechanical design manufacture and automation and the M.S. degree in mechanical engineering from the East China University of Science and Technology, Shanghai, China, in 2017 and 2020, respectively. He is working toward the Ph.D. degree in control science and engineering from with the Shanghai Jiao Tong University, Shanghai, China.
His research interests include local feature learning, visual-inertial slam, and mobile robots.
Shenghao Li received the B.S. degree in mechanical design manufacture and automation and the M.S. degree in mechanical engineering from the East China University of Science and Technology, Shanghai, China, in 2017 and 2020, respectively. He is working toward the Ph.D. degree in control science and engineering from with the Shanghai Jiao Tong University, Shanghai, China.
His research interests include local feature learning, visual-inertial slam, and mobile robots.View more
School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China
Shuang Liu received the Ph.D. degree in instrument science and technology jointly from the Joint Research Center, City University of Hong Kong, Hong Kong, and the University of Science and Technology of China, Suzhou, China, in 2010.
Since 2014, he has been an Associate Professor with the School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China. His research interests include mobile robots, multi-robot systems, and motion planning.
Shuang Liu received the Ph.D. degree in instrument science and technology jointly from the Joint Research Center, City University of Hong Kong, Hong Kong, and the University of Science and Technology of China, Suzhou, China, in 2010.
Since 2014, he has been an Associate Professor with the School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China. His research interests include mobile robots, multi-robot systems, and motion planning.View more
Department of Automation, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Qunfei Zhao received the B.S.E.E. degree from Xi’an Jiao Tong University, Xi’an, China, in 1982, and the Sc.D. degree in system science from the Tokyo Institute of Technology, Tokyo, Japan, in 1988.
He is currently a Professor with the School of Electronic Information and Electric Engineering, Shanghai Jiao Tong University, Shanghai, China. His research interests include robotics, machine vision, and optimal control of complex mechatronic systems.
Qunfei Zhao received the B.S.E.E. degree from Xi’an Jiao Tong University, Xi’an, China, in 1982, and the Sc.D. degree in system science from the Tokyo Institute of Technology, Tokyo, Japan, in 1988.
He is currently a Professor with the School of Electronic Information and Electric Engineering, Shanghai Jiao Tong University, Shanghai, China. His research interests include robotics, machine vision, and optimal control of complex mechatronic systems.View more
School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, China
Qiaoyang Xia received the M.S. degree in mechanical engineering from the Mechanical Engineering Department, East China University of Science and Technology, Shanghai, China, in 2021.
His research interests include robotics localization, trajectory planning, and multirobot systems.
Qiaoyang Xia received the M.S. degree in mechanical engineering from the Mechanical Engineering Department, East China University of Science and Technology, Shanghai, China, in 2021.
His research interests include robotics localization, trajectory planning, and multirobot systems.View more
