A Visual SLAM Based-Method for Vehicle Localization Automotive Research and Testing Center

Format:

Book

Conference/Event

Author/Creator:

Xu, Zhiyuan, author.

Contributor:

Lin, Nong-Hong

Conference Name:

WCX SAE World Congress Experience (2024-04-16 : Detroit, Michigan, United States)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2024

Summary:

One of the main challenges of autonomous driving is to integrate different modules, such as perception, planning, control, and communication, that work together to enable the vehicle to drive safely and efficiently. A key module of autonomous driving is the vehicle localization system, which estimates the vehicle's position in the environment, and provides guidance for the optimal route. The vehicle localization system is essential for ensuring the safety of autonomous driving. This paper proposes a vehicle localization method based on visual simultaneous localization and mapping (SLAM) using a monocular camera. The method captures images of the environment with a monocular camera and extracts ORB (Oriented FAST and rotated BRIEF) features from them. It then tracks the features across the images and constructs a sparse map of the scene. The map is used to estimate the vehicle's pose, which is the position and orientation of the vehicle, in local coordinates. The pose is then rescaled and converted to geographic coordinates. The method is tested and evaluated on outdoor datasets. The average localization error is less than 0.5 meter. The method is suitable for low-cost applications

Notes:

Vendor supplied data

Publisher Number:

2024-01-2845

Access Restriction:

Restricted for use by site license