DESIGN AND DEVELOPMENT OF SMART WEEDING ROBOT USING MACHINE LEARNING

Agriculture is the backbone of our economy, In Pakistan 62% population lives rural areas, where they are mainly dependent on agriculture sector. One of the major problem in the agriculture is control of weed among the planted yield crop. At present these weed are removed manually, which is time cons

Project Title

DESIGN AND DEVELOPMENT OF SMART WEEDING ROBOT USING MACHINE LEARNING

Project Area of Specialization

Mechatronics Engineering

Project Summary

Agriculture is the backbone of our economy, In Pakistan 62% population lives rural areas, where they are mainly dependent on agriculture sector. One of the major problem in the agriculture is control of weed among the planted yield crop. At present these weed are removed manually, which is time consuming and, it also effects the human health that cause in back pain due to continuous bending. In conventional weed control system, herbicide is sprayed all over the field. This technique is not sufficient because along with weeds it will result in loss of yield crop too and lot of herbicide waste which is very costly. To overcome these issues As technology is growing day by day in every field , several innovative technology companies are developing weed-killing robots that selectively poison weeds microbursts of herbicides. In this project ,we resolve this issue by design and development of smart weeding robot using machine learning. The robot works without being controlled by human operator. Reliance on solar power makes the robot completely autonomous in terms of energy.

Project Objectives

• To develop weed detection system to identify weeds using machine learning.
• To develop navigation system using GPS.
• To establish onboard plucking system for weed removal.
• To develop graphical user interface for monitoring.

Project Implementation Method

The firsts step is image acquisition which is accomplished by the Raspberry-Pi Camera. The camera is mounted facing downwards on an extended arm from the chassis of the robot. Image acquisition is done in the presence of natural light. The next step is the processing of the captured image. The image is subjected to morphological modifications like thresholding, erosion and dilation to detect the presence of the plants in the region of interest, if present determining whether it is weed or the yield crop. The final step is directed to removal of weed in the region of interest.

Benefits of the Project

The Smart weed removal robot is introduced and implemented which is aimed to increase the yield crop product and to reduce the human efforts. 100% Autonomous Solar traction without recharging. Can Work 12 hours a day without a human operator. A human can not work for 12 hours a day, this robot would be helpful to the farmers in weed control with high accuracy without damaging the yield crops. High precision, no crops affected no loss of yield. Reduce your costs and your environmental impact. Easy to control and easy to maintain.

Technical Details of Final Deliverable

This project is comprises of both hardware and software integrated system. In hardware parts it contains four wheels which are running on servo motors. Photovoltaic panels are used for power With camera mounted on its top to capture image that gives to the image acquisition system, its direction is controlled by GPS and sensors. A  robotic arm is constructed to remove detected weeds. In software we are using “python” to run algorithm code that will provide information to the robot whether  it is weed or planted crop. The end delivery will be closed loop hardware and software integrated system working together in real-time.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Agriculture

Other Industries

Core Technology

Robotics

Other Technologies

Sustainable Development Goals

No Poverty, Zero Hunger, Good Health and Well-Being for People, Gender Equality

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com