Minecraft Auto Fisher Bot 🎣

An over-engineered bot using computer vision and deep learning for automatic fishing in Minecraft

Minecraft Steve has now retired from an adventurous lifestyle and now enjoys fishing on peaceful river banks and coasts!

How does the bot work?

  1. Capture screenshot and then crop it to the region of interest
  2. Pass the cropped screenshot to a Convolutional Neural Network to obtain a prediction
  3. Use the prediction and a timing constraint to determine when to reel
  4. If it is time to reel, reel in the find, throw the bait and repeat
Left: Bobber floating | Right: Bobber sunk

Why use a Convolutional Neural Network (CNN)?

The Minecraft Auto Fisher bot uses a CNN to obtain the sense of vision required to determine if the bobber is floating or underwater. Since we use a CNN, the bot will work effectively in different lighting conditions in the game and will also work even if aquatic life (Both flora and fauna) tries to get in the way. Furthermore, the bot will also work in both warm and cold oceans in the game as well as when it rains.

Evaluation

  • The catch rate depends on multiple factors but the bot has an overall catch rate of 97%
  • The gains will mostly include fish but there is a possibility to get any item that can be obtained by fishing if the bot is run long enough
Gains from three 15 minute auto-fishing runs

Feel free to access the source code for the bot using the link below:

https://github.com/InputBlackBoxOutput/Minecraft-Auto-Fisher-Bot

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store