Monocular Based Navigation System for Autonomous Ground Robots Using Multiple Deep Learning Models

Abstract

In recent years, the development of ground robots with human-like perception capabilities has led to the use of multiple sensors, including cameras, lidars, and radars, along with deep learning techniques for detecting and recognizing objects and estimating distances. This paper proposes a computer vision-based navigation system that integrates object detection, segmentation, and monocular depth estimation using deep neural networks to identify predefined target objects and navigate towards them with a single monocular camera as a sensor. Our experiments include different sensitivity analyses to evaluate the impact of monocular cues on distance estimation. We show that this system can provide a ground robot with the perception capabilities needed for autonomous navigation in unknown indoor environments without the need for prior mapping or external positioning systems. This technique provides an efficient and cost-effective means of navigation, overcoming the limitations of other navigation techniques such as GPS-based and SLAM-based navigation. Graphical Abstract

Outdoor Tests of Autonomous Navigation System Based on Two Different Reference Points of PurePursuit Algorithm for 10-ton Articulated Vehicle

“…In area of autonomous navigation, several methods are being explored based on use of one or multiple sensors such as GPS, cameras, lidar, radar and other dead reckoning methods [1] depending on applications. One recent research has utilized deep neural networks for vison-based navigation in unknown indoor environments [2]. Another studied energy efficient motion planning of forklifts transportation utilizing Deep neural networks (DNNs) [3].…”