Abstract
Autonomous parking in an indoor parking lot without human intervention is one of the most demanded and challenging tasks of autonomous driving systems. The key to this task is precise real-time indoor localization. However, state-of-the-art low-level visual feature-based simultaneous localization and mapping systems (VSLAM) suffer in monotonous or texture-less scenes and under poor illumination or dynamic conditions. Additionally, low-level feature-based mapping results are hard for human beings to use directly. In this paper, we propose a semantic landmark-based robust VSLAM for real-time localization of autonomous vehicles in indoor parking lots. The parking slots are extracted as meaningful landmarks and enriched with confidence levels. We then propose a robust optimization framework to solve the aliasing problem of semantic landmarks by dynamically eliminating suboptimal constraints in the pose graph and correcting erroneous parking slots associations. As a result, a semantic map of the parking lot, which can be used by both autonomous driving systems and human beings, is established automatically and robustly. We evaluated the real-time localization performance using multiple autonomous vehicles, and an repeatability of 0.3 m track tracing was achieved at a 10 kph of autonomous driving.
Highlights
Autonomous driving has seen considerable progress in recent years
We present a robust visual feature-based simultaneous localization and mapping systems (VSLAM) system based on the recognition of high-level landmarks for parking, i.e., parking slots
We design and implement a low-cost and robust visual-based simultaneous localization and mapping (SLAM) system using a typical visual landmark of parking slots with aid from a limited number of visual fiducial tags, which is immune to monotonous texture, varying illumination and dynamic conditions; We propose a robust SLAM back-end approach to associate parking slots considering the confidence level of the landmarks; We analyse the effectiveness and arrangement strategy of visual fiducial tags in a typical indoor parking lot
Summary
Autonomous driving has seen considerable progress in recent years. Researchers have made breakthroughs in several challenging fields, including obstacle detection, real-time motion planning and high-precision localization (many based on differential global navigation satellite system (GNSS)). Deep learning-based methods have shown their capability for accurate and robust detection of such meaningful objects [12] Inspired by these methods, we present a robust VSLAM system based on the recognition of high-level landmarks for parking, i.e., parking slots. To support localization in slot-lack area such as passways, we introduce visual fiducial tags detected from the front view camera for improving the overall accuracy and robustness. Their numbers and configurations are further analyzed.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
