Rishikesh-Jadhav/Adaptive-Neural-Network-Based-Control-of-Autonomous-car-in-AirSim

This repository highlights the integration of neural network-based control with PID and MPC approaches in the AirSim simulator to enhance steering inputs for autonomous vehicles. Employing imitation learning and a hybrid neural network architecture, the project aims to create a robust and unbiased model for improved autonomous vehicle control.

13
/ 100
Experimental

This project helps automotive engineers and researchers enhance the steering control of autonomous vehicles in simulated environments. By taking sensor data like camera images, speed, and steering angles from a simulator, it produces improved, more stable steering inputs for the autonomous car. This is ideal for those working on advanced driver-assistance systems (ADAS) or autonomous vehicle development.

No commits in the last 6 months.

Use this if you need to create more robust and unbiased steering control models for autonomous vehicles by learning from existing PID or MPC controllers rather than human driving data.

Not ideal if you are looking for a solution to directly deploy in real-world autonomous vehicles without extensive adaptation, or if your primary focus is on human-like driving imitation.

autonomous-driving vehicle-control ADAS-development robotics-simulation imitation-learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

Last pushed

Jan 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Rishikesh-Jadhav/Adaptive-Neural-Network-Based-Control-of-Autonomous-car-in-AirSim"

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