Steering Control of Ackermann Architecture Weed Managing Mobile Robot

Abstract

A robot designed to identify and remove weeds from crops is known as a weed control robot. Weeds compete with primary crops for moisture, hinder their growth, and may harm both human and animal health, leading to reduced crop yields. Traditionally, herbicides and other chemicals have been used to eliminate weeds, but these methods can damage crops and pollute the environment. In this work, we propose a new semantic weed detection method based on the PC/BC-DIM network, which demonstrates superior performance and classification accuracy compared to existing approaches. We developed an autonomous weed control robot incorporating Ackermann Architecture and a delta robot. The delta robot is equipped with a camera at its base to detect weeds in real-time. First, the robot captures images using the camera, and through image processing techniques, it differentiates weeds from crops. Detected weeds are then eliminated using an electrical discharge method, where electrodes attached to the robot’s end effector burn the targeted weeds. Additionally, we developed a path-planning and obstacle-avoidance system to help the mobile robot navigate the field. This system uses stereo vision to capture stereo images of the environment and calculate their disparity. By extracting depth information, the robot can detect obstacles, avoid them, and follow the shortest path using the A* algorithm. The results from this work are simulation-based, demonstrating effective weed detection in field images and efficient robot navigation using stereo images. The system achieved an overall accuracy of 81.25%. Although the system performs moderately well, the relatively high False Positive Rate and Root Mean Square (RMS) Error indicate the need for further improvements to reduce errors and false positives. Future work will focus on enhancing weed removal and implementing the simulated results on hardware.

Authors and Affiliations

Faryal Naeem Mehmood, Syeda Ambreen Zahra, Syed Muhammad Wasif, Zubair Mehmood, Muhammad Jehanzeb Irshad, Nazam Siddique

Keywords

Related Articles

Enhanced Skin Cancer Classification with MobileNetV3 and Morphological Preprocessing: A Deep Learning-Based Extension

Skin cancer detection continues to pose challenges due to the visual similarity between the types of lesions and the limitations of traditional diagnostic methods. This study presents an extended and...

Effects of Exogenous Calcium and Magnesium on Physio-Hormonal Attributes of Trigonella Foenum-Graecum L:Under Polyethylene Glycol (PEG) Induce Drought Stress

Drought stress is one of the abiotic stresses that adversely affect the plant growth parameters and physio-hormonal attributes. In the current work, we study the adverse effects of induced PEG drought stress in Trigone...

A Robotic Simulation forAerialMonitoringand Disease Detection of Gladiolus Field

Agriculture is an essential sector that is witnessing the integration of advanced technologies to improve productivity and efficiency. Aerial crop monitoring using drones has surfaced as a pivotal technology for precis...

Gender-Based Analysis of Employee Attrition Prediction Using Machine Learning

Employee turnover is a significant problem in organizations because it comes with productivity and cost implications. This paper focuses on predicting employee turnover using machine learning techniques that incorporat...

An Enhanced Novel Iot-Based Car Accident Detection and AlertSystem

The excessive use of vehicles for our day-to-day tasks in this revolutionized era has become a necessity, making our lives convenient and technology-dependent. This rise in the use of vehicles has led to a greater numb...

Download PDF file
  • EP ID EP764472
  • DOI -
  • Views 23
  • Downloads 0

How To Cite

Faryal Naeem Mehmood, Syeda Ambreen Zahra, Syed Muhammad Wasif, Zubair Mehmood, Muhammad Jehanzeb Irshad, Nazam Siddique (2025). Steering Control of Ackermann Architecture Weed Managing Mobile Robot. International Journal of Innovations in Science and Technology, 7(5), -. https://europub.co.uk/articles/-A-764472