A Review on Autonomous Driving Systems

Yaakub, Salma; Alsibai, Mohammed Hayyan · 2018 · Crossref

DOI: 10.15282/ijets.v5i1.2800

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This review paper addresses the technological components and applications of autonomous driving systems, motivated by the need to reduce traffic crashes, improve mobility, and enhance traffic efficiency. The authors highlight that human error causes approximately 93% of vehicle crashes in the USA, resulting in significant loss of life and economic waste. The study aims to evaluate existing autonomous technologies within the context of Industry 4.0 and specifically identify the most suitable systems for converting manual wheelchairs into smart electric wheelchairs. The paper categorizes autonomous vehicles into aerial, ground, and underwater types, noting that they rely on four integrated subsystems: position identifying and navigation, surrounding environment situation analysis, motion planning, and trajectory control. The authors review various technologies used in these subsystems. For navigation, they discuss Global Positioning System (GPS), Vehicle-to-Vehicle (V2V) communication, and Dedicated Short-Range Communications (DSRC). For environmental analysis, the review covers sensors such as video cameras, radar, ultrasonic sensors, Laser Rangefinders (LRF), and Light Detection and Ranging (LiDAR), often combined with Simultaneous Localization and Mapping (SLAM) techniques. Motion planning algorithms, including driving corridors and Voronoi Diagrams, are examined for path generation, while trajectory control methods involve mixed-integer linear programming to manage speed and direction. The findings summarize significant applications across different domains. Aerial vehicles, such as Unmanned Aerial Vehicles (UAVs), are used for search and rescue and surveillance, utilizing GPS and LiDAR. Underwater vehicles employ sonar and cameras for scientific data collection. Ground vehicles, including military mine-sweeping robots and commercial self-driving cars like Google’s Lexus RX 450h, utilize complex sensor arrays and artificial intelligence for navigation and collision avoidance. The paper also details specific autonomous wheelchair systems, such as the Bremen Autonomous Wheelchair, which uses ultrasonic sensors for obstacle avoidance, and systems employing Microsoft Kinect for 3D depth imaging. The significance of the study lies in its recommendation for a specific autonomous wheelchair design. The authors conclude that a combination of Microsoft Kinect and GPS modules is the most suitable approach for their project, suggesting the use of the RANSAC algorithm to process Kinect data and combining GPS with tachometers and gyroscopes for accurate positioning. They also note limitations of current autonomous systems, including high costs, sensor failures in adverse weather, and the lack of human empathy or adaptability. Future work is identified as focusing on safety testing, particularly regarding tipping risks and the implementation of auto-braking systems and center of gravity evaluations to ensure stability.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• driverless ads