HarvestHero - Autonomous Agriculture Bot

While fertilizers increase crop yields, excessive application can result in pollution and soil degradation. Our project is a prototype for an autonomous precision fertilizing vehicle.

Comment

What it does

Using the OpenCV computer vision library and live input from a raspberry pi camera feed, our bot detects areas of a field in need of fertilizing. The bot stops on these areas, represented by the color blue, then moves on. Thus, the bot will not fertilize any areas other than what’s necessary.

How we built it

  • Vehicle Chassis
    • 2 Rubber wheels
    • 2 Speed encoders
    • Swivel wheel and connectors
    • Acrylic frame
    • 3D Printed battery frame
  • Raspberry Pi
    • Raspberry Pi 4 Model B 4GB RAM
    • 64 GB Micro SDXC Card
    • Ethernet Cable
    • USB-C to Ethernet Adapter
  • Power
    • 10,000mAh Rechargeable Battery
    • USB-C to USB-C: for powering Raspberry Pi / recharing battery
    • USB-A to Micro USB: for powering Raspberry Pi HAT / motors
  • Electronics
    • Printed Circuit Board
    • 2 Button Switches - to be read by Raspberry Pi
    • Slide Switch - to control motor power circuit
    • 2 LEDs
    • H-Bridge
    • Camera
    • 2 Ultrasonic Distance Sensors
    • 2 Electric Motors

Challenges we ran into

  • Managed to short-circuit our sensor with only 5 volts
  • Configuring our new functions with the “brain”

Accomplishments that we're proud of/What we learned

  • OpenCV computer vision library
  • Live input from a raspberry pi camera feed

What's next for HarvestHero

  • Add live video feed
  • Detect various shades of green or soil conditions
  • More sensitive object detection

Built With

Share this project:

Updates