Research on Safety-certifible Navigation Algorithms for Robotics

Dr. Jiachen Zhang, Zhengxi, Dr. Li-ta Hsu, Dr. Wen, W..

Abstract

The visual/LiDAR SLAM methods are challenged in complex urban scenarios. In this project, we aim to study the mechanism of the impacts cuased by the dynamic scenarios on the visual/LiDAR SLAM methods. We try to answer the quesitons of how the dynamic objects affect the state estimation of visual/LiDAR SLAM methods and how to improve.

Recent News

• The manuscript entitled “Safety-quantifiable Line Feature-based Monocular Visual Localization with 3D Prior Map” is submitted to the IEEE Transactions on Intelligent Transportation Systems. The video about this paper is avaiable by Youtube and Bilibili. The preprint verison can be found by Link.