A Real-Time App-Controlled Robotic Navigation System With Gated Recurrent Unit (GRU)-Based User Destination Prediction

Read full text Summarise with VIRAT
Authors: Heonjong Yoo, Wan‐Young Chung
Cited by: 0
References: 22

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Autonomous navigation in structured environments, such as solar power panels, plays a vital role in improving operational efficiency and reducing human dependency. This study focuses on the trajectory tracking and control of a 4-wheel mobile platform (Ranger Mini V2) for autonomous navigation between designated solar panels areas. The brief report contributes to the control of the mobile platform 4 on the solar panel location based on the determination of the app. The state flow method facilitates the 4 wheel mobile platform to recognize its current location information and heading angle meanwhile the platform is moving at the solar panel location. The trajectory tracking method is an important technique that facilitates the driving performance of a 4 mini wheel ranger without human intervention. Ubuntu ROS and the ROS trajectory tracking program laptop are connected through robot operating system network. Firstly, the previous line following method is incorporated into the switch block in ROS trajectory tracking program to divide various line generation to the solar 1, 2, 3 panels. Additionally, the Gated recurrent unit(GRU) and app determine the destination number, then send the number to ROS trajectory tracking program during experimentation. The gain parameter in the block is automatically changed to the destination number during experimentation. This setup enables automatic gain adjustment based on AI predictions and user input from the app. Lastly, the experiment is carried out through the ranger mini version 2 mobile platform on the place.

Fields of Study & Subjects

Control and Dynamics of Mobile Robots Robotics and Automated Systems Reinforcement Learning in Robotics

Publication details

Journal / source
IEEE Access
Volume
14
Pages
53292–53307
Publication date
1 January 2026
Language
EN