auto roboculture
Published © MIT

Nindamani the Weed Removal Robot

Nindamani, the AI based mechanically weed removal robot, which autonomously detects and segment the weeds from crop using AI.

IntermediateFull instructions providedOver 4 days5,479

Things used in this project

Hardware components

NVIDIA Jetson Nano Developer Kit
NVIDIA Jetson Nano Developer Kit
×1
Stepper motors
×3
Stepper driver
×3
Servo motor
×1
Arduino Mega 2560 & Genuino Mega 2560
Arduino Mega 2560 & Genuino Mega 2560
×1
Power supply
×1
Camera Module V2
Raspberry Pi Camera Module V2
×1

Software apps and online services

Robot Operating System
ROS Robot Operating System
TensorFlow
TensorFlow

Hand tools and fabrication machines

3D Printer (generic)
3D Printer (generic)
CNC machine

Story

Read more

Custom parts and enclosures

Delta Arm

3D software file, use this to 3d print Delta arm parts

Code

Github

In this following repository, you will find instructions for software installation, control mechanism and how to run Nindamani robot.

Github

Installing Arduino IDE on Jetson nano. This is a reference link from Jetson hacks.

Github

Control Arduino Mega from Linux command line interface without use of Arduino-IDE GUI. And integrate it with python script.

Github

Control stepper motors with Jetson Nano with help of Arduino Mega stepper library. Delta arm uses stepper motor.

Github

Train multiple objects with different categories on your custom dataset using Mask-RCNN and predict test dataset. Here, We have used it for weed vs crop detection.

Github

Delta robot (parallel arm) working in simulation Gazebo software. Same Delta kinematics library used in hardware pick and place application.

Credits

auto roboculture

auto roboculture

1 project • 4 followers
Building Agricultural Robot Prototypes, Since Jan,2019. Working with AI and Robotics in agri tech field

Comments