AV-SLAM: Autonomous vehicle SLAM with gravity direction initialization
Paper in proceeding, 2020

Simultaneous localization and mapping (SLAM) algorithms aimed for autonomous vehicles (AVs) are required to utilize sensor redundancies specific to AVs and enable accurate, fast and repeatable estimations of pose and path trajectories. In this work, we present a combination of three SLAM algorithms that utilize a different subset of available sensors such as inertial measurement unit (IMU), a gray-scale mono-camera, and a Lidar. Also, we propose a novel acceleration-based gravity direction initialization (AGI) method for the visual-inertial SLAM algorithm. We analyze the SLAM algorithms and initialization methods for pose estimation accuracy, speed of convergence and repeatability on the KITTI odometry sequences. The proposed VI-SLAM with AGI method achieves relative pose errors less than 2%, convergence in half a minute or less and convergence time variability less than 3s, which makes it preferable for AVs.


Kaan Yilmaz

Student at Chalmers

Baris Suslu

Student at Chalmers

Sohini Roychowdhury

Volvo Cars

L. Srikar Muppirisetty


Proceedings - International Conference on Pattern Recognition

10514651 (ISSN)

8093-8100 9412466

25th International Conference on Pattern Recognition, ICPR 2020
Virtual (Milano), Italy,

Subject Categories


Control Engineering

Computer Vision and Robotics (Autonomous Systems)



More information

Latest update