A Region-Based Approach to Monocular Mapless Navigation Using Deep Learning Techniques

In recent years, there have been significant advances in navigation methods for autonomous robotic systems, giving rise to a diverse range of navigation techniques. These techniques include GPS-based, SLAM-based, and monocular depth-based navigation. However, each of these approaches has its limitations. Typically, these techniques rely on either external sensors and positioning systems or require the creation of a local map prior to initiating navigation. This paper introduces a new approach for autonomous navigation of ground robots: mapless navigation using a pre-trained monocular depth network. This technique offers an efficient and cost-effective way of navigating without the need for a pre-existing map of the environment. To evaluate and compare the performance of our method, we conducted experiments using two different depth estimation models tested within the Gazebo simulation environment.