JZ76/Training-Overtaking-Algorithm

This repository has code of how to train a RNN that can perform overtaking in F1TENTH simulator as well as a dataset I have created

35
/ 100
Emerging

This project helps roboticists and autonomous driving researchers develop F1TENTH race car algorithms. It provides code and pre-recorded datasets to train a machine learning model that enables a simulated race car to overtake an opponent. You input simulated sensor data (LiDAR scans) and car state, and the model outputs desired speed and steering angles for the car to execute an overtaking maneuver.

No commits in the last 6 months.

Use this if you are working with F1TENTH simulators and want to implement or study machine learning-based overtaking strategies.

Not ideal if you intend to directly apply this to a real-world F1TENTH car without extensive adaptation, data collection, and model retraining.

autonomous-racing robotics-simulation machine-learning-for-vehicles f1tenth imitation-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

13

Forks

3

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JZ76/Training-Overtaking-Algorithm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.