Off-Road Detection Analysis for Autonomous Ground Vehicles: A Review

Abstract

When it comes to some essential abilities of autonomous ground vehicles (AGV), detection is one of them. In order to safely navigate through any known or unknown environment, AGV must be able to detect important elements on the path. Detection is applicable both on-road and off-road, but they are much different in each environment. The key elements of any environment that AGV must identify are the drivable pathway and whether there are any obstacles around it. Many works have been published focusing on different detection components in various ways. In this paper, a survey of the most recent advancements in AGV detection methods that are intended specifically for the off-road environment has been presented. For this, we divided the literature into three major groups: drivable ground and positive and negative obstacles. Each detection portion has been further divided into multiple categories based on the technology used, for example, single sensor-based, multiple sensor-based, and how the data has been analyzed. Furthermore, it has added critical findings in detection technology, challenges associated with detection and off-road environment, and possible future directions. Authors believe this work will help the reader in finding literature who are doing similar works.

Development and Experimental Validation of Control Algorithm for Person-Following Autonomous Robots

“…For security reasons, mainly if they work in congested environments with human operators in the workplace, autonomous vehicles must be able to detect any objects on the path and avoid collisions. This is an issue address for other types of ground vehicles, as shown in the review by Islam et al, 2022. In this case, the paper focuses on ground vehicle detection methods for the offroad environment [12]. Closer to our approach, the paper by Pires et al (2022) develops an autonomous navigation system for an AGV in order to detect and avoid obstacles based on the processing of data acquired with a frontal depth camera mounted on the vehicle [13].…”

Reinforcement and Curriculum Learning for Off-Road Navigation of an UGV with a 3D LiDAR

“…Off-road navigation of Unmanned Ground Vehicles (UGVs) is a challenging task that requires the ability to avoid obstacles below and above the surface level, including overhangs [ 1 ]. This can be accomplished with classical approaches, such as potential fields [ 2 ], or with modern machine learning (ML) [ 3 ].…”

An enhanced YOLOv5 model for fish species recognition from underwater environments

“…In computer vision, deep learning has been widely used to solve a variety of issues, including detection, localization, estimation, and classification. [10][11][12][13] Several machine learning (ML) and deep learning algorithms have been developed to categorize fish species. For instance, Jager et al 14 employed AlexNet architecture for feature extraction and multiclass SVM for classification, whereas hierarchical features and support vector machine (SVM) are used for fish classification.…”