Self-driving vehicles' localization approaches are based either on pre-mapped features collected from the environment or on GPS information. While the former depends on remapping the environment constantly with fine precision, the latter requires GPS signal availability and strength at most of the time. On the other hand, computer vision, allied to machine learning, became a valuable resource in the detection of objects on images. These objects can be used as global landmarks that can be useful for autonomous vehicles' localization. In a highway, for instance, signs provide meaningful information for humans that could be potentially useful for localizing a self-driving vehicle as well. Therefore, in this paper, we propose a method based on the Kalman filter that uses odometry and road signs information for localizing the vehicle. We simulated the experiments using Gazebo and performed the Kalman filter prediction using inertial odometry. Comparison was performed between: (i) uncorrected estimation; (ii) corrected estimation using only the velocity provided by simulated speedometer readings ; (iii) corrected estimation using only signs' information; and (iv) corrected estimation using both speedometer readings and signs' information. The results yielded by the experiments show that, in an 8 kilometers non-linear track, the filter is able to perform localization with error in position as low as 100 meters at high prediction frequency (100 Hertz). Furthermore, the code developed in this project is available online.
Localization Correction Using Road Signs
2019-10-01
354168 byte
Conference paper
Electronic Resource
English