bones-ai / rust-drive-ai Goto Github PK

View Code? Open in Web Editor NEW

106.0 3.0 16.0 911 KB

Self driving car AI in road fighter world

Home Page: https://youtu.be/H7RWcNgE-6s

License: MIT License

Rust 99.96% RenderScript 0.04%

ai bevy retro roadfigther rust self-driving-car neural-network

rust-drive-ai's Introduction

AI learns to drive

AI learns to drive in a road-fighter inspired environment

The cars are controlled using a neural network, and are trained using a genetic algorithm.

Built with Rust and Bevy game engine

Demo

Here's the entire timelapse of the AI learning to drive

Devlog

Here's a devlog of how this was built

Usage

Clone the repo

git clone [email protected]:bones-ai/rust-drive-ai.git
cd rust-drive-ai

Run the simulation
```
cargo run --release
```

Configurations

The project config file is located at src/configs.rs

Forks

Here's a list of of forks that extend this project, let me know if you have an interesting fork to add:

https://gitlab.com/ThibaultLemaire/rust-drive-ai

Assets

rust-drive-ai's People

Contributors

Stargazers

Watchers

Forkers

sangelxyz cartridge-gg duckyblender cryptomaestro2888 maraist boyquotes po1206 minchang-kim

rust-drive-ai's Issues

License / Contributions ?

Hey!! What a fun little simulation, I love it!

This has made me want to get back to small neural net sims like this one.

I'd like to use and/or contribute to your code, can I? :)

Also if you need help choosing a license, I'm not an expert but I know a thing or two :)

crashes on initialization

on M1 silicon MacBook, app crashes after after running

Finished `release` profile [optimized] target(s) in 0.14s
     Running `target/release/steering`
2024-07-26T14:00:02.857264Z  INFO bevy_render::renderer: AdapterInfo { name: "Apple M1 Pro", vendor: 0, device: 0, device_type: IntegratedGpu, driver: "", driver_info: "", backend: Metal }
2024-07-26T14:00:02.971056Z  INFO bevy_prototype_debug_lines: Loaded 2d debug lines plugin.
2024-07-26T14:00:02.981619Z  INFO bevy_winit::system: Creating new window "Bevy App" (0v0)
2024-07-26 17:00:03.112 steering[78715:8272772] CAMetalLayer ignoring invalid setDrawableSize width=4294967295.000000 height=4294967295.000000
2024-07-26T14:00:03.113864Z ERROR wgpu::backend::direct: Handling wgpu errors as fatal by default
thread 'Compute Task Pool (0)' panicked at /Users/blackbird/.cargo/registry/src/index.crates.io-6f17d22bba15001f/wgpu-0.15.1/src/backend/direct.rs:3024:5:
wgpu error: Validation Error

Caused by:
    In Device::create_texture
      note: label = `main_texture_a`
    Dimension X value 4294967295 exceeds the limit of 16384


note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
thread 'Compute Task Pool (1)' panicked at /Users/blackbird/.cargo/registry/src/index.crates.io-6f17d22bba15001f/bevy_ecs-0.10.1/src/schedule/executor/multi_threaded.rs:194:60:
A system has panicked so the executor cannot continue.: RecvError
thread '<unnamed>' panicked at /Users/blackbird/.cargo/registry/src/index.crates.io-6f17d22bba15001f/bevy_tasks-0.10.1/src/task_pool.rs:376:49:
called `Option::unwrap()` on a `None` value
thread 'main' panicked at /Users/blackbird/.cargo/registry/src/index.crates.io-6f17d22bba15001f/bevy_render-0.10.1/src/pipelined_rendering.rs:136:45:
called `Result::unwrap()` on an `Err` value: RecvError
thread 'main' panicked at /Users/blackbird/.cargo/registry/src/index.crates.io-6f17d22bba15001f/bevy_tasks-0.10.1/src/task_pool.rs:376:49:
called `Option::unwrap()` on a `None` value

/tmp/rust-drive-ai main* ❯                                             17:00:03

I came across your work a few weeks ago and was interested in the possibility in using dojo to implement provable model inference. The gist of it is Dojo is a provable game engine inspired by Rust. It is written in Cairo which means that we can generate a mathematical proof of computation using a zkSTARK. It creates an interesting dynamic where a player can train a neural network to drive the car, then run inference using the Dojo implementation, and a submit a proof of their score, without having to expose the model weights. It's mostly an experiment with this new affordance. Essentially, with provable computation it is no longer necessary to verify a clients computation using a trusted centralized server, which enables interesting new architectures and also fully private information.

I wanted to share here incase you found it interesting. Happy to share more if so!

Thanks for the original implementation!

bones-ai / rust-drive-ai Goto Github PK

rust-drive-ai's Introduction

AI learns to drive

Demo

Devlog

Usage

Configurations

Forks

Assets

rust-drive-ai's People

Contributors

Stargazers

Watchers

Forkers

rust-drive-ai's Issues

License / Contributions ?

crashes on initialization

Verifiable simulation fork

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent