Outdoor autonomous navigation using monocular vision

TLDR

The paper presents a complete system for outdoor robot navigation. The system uses monocular vision, recording a video during a human‑guided learning phase to build a 3D map of the trajectory and environment. After computing the map, the robot can autonomously follow the same trajectory, and experiments with an urban electric vehicle confirm the approach against ground truth.

Abstract

In this paper, a complete system for outdoor robot navigation is presented. It uses only monocular vision. The robot is first guided on a path by a human. During this learning step, the robot records a video sequence. From this sequence, a three dimensional map of the trajectory and the environment is built. When this map has been computed, the robot is able to follow the same trajectory by itself. Experimental results carried out with an urban electric vehicle are shown and compared to the ground truth.