This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
An Object-Centric Hierarchical Pose Estimation Method Using Semantic High-Definition Maps for General Autonomous Driving
by
Jeong-Won Pyo
Jeong-Won Pyo
Jeong-Won Pyo received his B.S. degree from the Department of Mechatronics Engineering, Korea South [...]
Jeong-Won Pyo received his B.S. degree from the Department of Mechatronics Engineering, Korea Polytechnic University, Siheung, South Korea, in 2014. He received a Ph.D. degree from the School of Electrical and Electronics Engineering at SungKyunKwan University, Suwon, South Korea, in 2024. From March 2014 to August 2019, he was a researcher at the robot group at the Korea Institute of Industrial Technology (KITECH), South Korea. From October 2019 to February 2024, he was a chief researcher at the Creative Algorithms and Sensor Evolution Laboratory (CASELAB), Suwon, South Korea. His research interests include autonomous driving, artificial intelligence, and image processing.
*
,
Jun-Hyeon Choi
Jun-Hyeon Choi
Jun-Hyun Choi received his B.S. degree from the School of Electronic Engineering at Dong-A in 2021. [...]
Jun-Hyun Choi received his B.S. degree from the School of Electronic Engineering at Dong-A University in 2021. He has been with the School of Electrical and Electronics Engineering at Sunkyunkwan University, Suwon, Korea, where he is currently a Ph.D. student. His primary research interests are cognitive vision and SLAM for mobile robots.
and
Tae-Yong Kuc
Tae-Yong Kuc
Tae-Yong Kuc received a B.S. degree in control and instrumentation engineering from Seoul National a [...]
Tae-Yong Kuc received a B.S. degree in control and instrumentation engineering from Seoul National University, South Korea, in 1988, and M.S. and Ph.D. degrees from the Pohang University of Science and Technology, South Korea, in 1990 and 1993, respectively. From April to August 1993, he was the chief research engineer at the Precision Machinery Institute of Samsung Aerospace Company. From September 1993 to February 1995, he was a senior lecturer at the Department of Electrical Engineering at Mokpo National University, South Korea. Since March 1995, he has been with the School of Electrical and Electronics Engineering, Sungkyunkwan University, Suwon, South Korea, where he is currently a professor. His research interests include intelligent robotics, adaptive and learning control, and visual sensor processing for computer-aided control systems.
Department of Electrical and Computer Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
*
Author to whom correspondence should be addressed.
Sensors 2024, 24(16), 5191; https://doi.org/10.3390/s24165191 (registering DOI)
Submission received: 3 July 2024
/
Revised: 7 August 2024
/
Accepted: 8 August 2024
/
Published: 11 August 2024
Abstract
To achieve Level 4 and above autonomous driving, a robust and stable autonomous driving system is essential to adapt to various environmental changes. This paper aims to perform vehicle pose estimation, a crucial element in forming autonomous driving systems, more universally and robustly. The prevalent method for vehicle pose estimation in autonomous driving systems relies on Real-Time Kinematic (RTK) sensor data, ensuring accurate location acquisition. However, due to the characteristics of RTK sensors, precise positioning is challenging or impossible in indoor spaces or areas with signal interference, leading to inaccurate pose estimation and hindering autonomous driving in such scenarios. This paper proposes a method to overcome these challenges by leveraging objects registered in a high-precision map. The proposed approach involves creating a semantic high-definition (HD) map with added objects, forming object-centric features, recognizing locations using these features, and accurately estimating the vehicle’s pose from the recognized location. This proposed method enhances the precision of vehicle pose estimation in environments where acquiring RTK sensor data is challenging, enabling more robust and stable autonomous driving. The paper demonstrates the proposed method’s effectiveness through simulation and real-world experiments, showcasing its capability for more precise pose estimation.
Share and Cite
MDPI and ACS Style
Pyo, J.-W.; Choi, J.-H.; Kuc, T.-Y.
An Object-Centric Hierarchical Pose Estimation Method Using Semantic High-Definition Maps for General Autonomous Driving. Sensors 2024, 24, 5191.
https://doi.org/10.3390/s24165191
AMA Style
Pyo J-W, Choi J-H, Kuc T-Y.
An Object-Centric Hierarchical Pose Estimation Method Using Semantic High-Definition Maps for General Autonomous Driving. Sensors. 2024; 24(16):5191.
https://doi.org/10.3390/s24165191
Chicago/Turabian Style
Pyo, Jeong-Won, Jun-Hyeon Choi, and Tae-Yong Kuc.
2024. "An Object-Centric Hierarchical Pose Estimation Method Using Semantic High-Definition Maps for General Autonomous Driving" Sensors 24, no. 16: 5191.
https://doi.org/10.3390/s24165191
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.