mozturan/AutonomousDrive2D-DRL
Autonomous Driving W/ Deep Reinforcement Learning in Lane Keeping - DDQN and SAC with kinematics/birdview-images
This project offers a comparative analysis of different reinforcement learning algorithms (SAC and DDQN with PER) for autonomous lane-keeping. It takes simulated vehicle data, specifically kinematics or bird's-eye view images, and outputs optimized driving policies for steering and throttle. Autonomous vehicle researchers and engineers working on control systems would use this to evaluate algorithm performance.
No commits in the last 6 months.
Use this if you are a researcher or engineer exploring deep reinforcement learning algorithms for autonomous lane-keeping in simulated environments.
Not ideal if you are looking for a ready-to-deploy autonomous driving solution or a project focused on raw sensor data processing.
Stars
13
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mozturan/AutonomousDrive2D-DRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI...
lgsvl/simulator
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
microsoft/AirSim-NeurIPS2019-Drone-Racing
Drone Racing @ NeurIPS 2019, built on Microsoft AirSim
DeepTecher/AutonomousVehiclePaper
无人驾驶相关论文速递
learn-to-race/l2r
Open-source reinforcement learning environment for autonomous racing — featured as a conference...