DESIGN AND CONSTRUCTION OF AUTONOMOUS DELIVERY ROBOT
Abstract
ABSTRACT
Autonomous Delivery Robots (ADRs) are increasingly being adopted in logistics to improve the efficiency of last-mile delivery, particularly within structured environments such as campuses, hospitals, estates, and military zones. However, challenges persist in achieving reliable autonomous navigation, terrain adaptability, and real-time package handling in semi-structured environments. This project presents the design and implementation of a Level 4 ADR built on a six-wheeled differential drive platform with a rocker-bogie suspension system to enhance mobility across uneven surfaces. The system uses LiDAR, ultrasonic sensors, and depth cameras for environment perception, controlled by an NVIDIA Jetson Nano running ROS2. Navigation and localization are achieved through SLAM and LoRa-based GPS correction, while obstacle avoidance and path planning are handled via AI-enhanced algorithms. A mobile and web application interface connects to a cloud server for remote tracking and secure delivery operations. The results show the robot's ability to navigate autonomously, recognize obstacles, and move items reliably across a variety of terrain. The developed ADR contributes to sustainable delivery by reducing emissions and supports contactless logistics operations through full system autonomy.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.