gustavomoers/CollisionAvoidance-Carla-DRL-MPC

A hybrid collision avoidance system combining Deep Reinforcement Learning with Model Predictive Control, designed for autonomous vehicles in CARLA to navigate scenarios with stationary obstacles.

32
/ 100
Emerging

This project helps autonomous vehicle engineers develop and test advanced collision avoidance systems. It takes information about a car's position, speed, and surrounding stationary obstacles within the CARLA simulator. It then outputs a safe driving path and controls for the vehicle to avoid collisions, demonstrating how a car can navigate around parked vehicles.

No commits in the last 6 months.

Use this if you are an autonomous vehicle engineer working on developing or evaluating collision avoidance strategies for self-driving cars, especially in simulation environments like CARLA.

Not ideal if you are looking for a system to manage dynamic obstacles or complex urban traffic scenarios, as this is designed for stationary obstacle avoidance.

autonomous-vehicles collision-avoidance driver-assistance-systems vehicle-simulation path-planning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

58

Forks

4

Language

Python

License

MIT

Last pushed

May 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gustavomoers/CollisionAvoidance-Carla-DRL-MPC"

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