modanesh/LEADER
Author implementation of the LEADER algorithm: integrating learning and planning to have safer agents
This project helps researchers and developers working on autonomous driving to train and test intelligent agents in highly realistic urban simulations. It takes real-world map data and traffic scenarios as input, and outputs trained models that enable autonomous vehicles to make safer decisions when planning under uncertain conditions, like varied human driving behaviors. Its primary users are robotics researchers and engineers focused on self-driving car development.
No commits in the last 6 months.
Use this if you are a researcher or engineer developing autonomous driving algorithms and need a high-fidelity simulator to test how agents perform in complex, unregulated, and densely-crowded urban environments with diverse human driving behaviors.
Not ideal if you are looking for an out-of-the-box self-driving car solution for deployment, as this is a research implementation for training and testing agent planning.
Stars
27
Forks
—
Language
C++
License
—
Category
Last pushed
Oct 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/modanesh/LEADER"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ArztSamuel/Applying_EANNs
A 2D Unity simulation in which cars learn to navigate themselves through different courses. The...
idreesshaikh/Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning
Deep Reinforcement Learning (PPO) in Autonomous Driving (Carla) [from scratch]
kevinhughes27/TensorKart
self-driving MarioKart with TensorFlow
lexfridman/deeptraffic
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
KimangKhenng/Traffic-SImulation-and-Visualization
Traffic Intersection Simulation Using C++ and Qt