behavioral-cloning

Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"

Third Project of the Udacity Self-Driving Car Nanodegree Program

Jax (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

Be Driven 🚘

A collection of all projects pertaining to different layers in the SDC software stack

Elastic Boundary Projection for 3D Medical Image Segmentation - CVPR 2019

Implementation of Generatve Adversarial Imitation Learning (GAIL) for classic environments from OpenAI Gym.

Implementation of the paper "End to End Learning for Self-Driving Cars"

Udacity Self Driving Car ND projects - including lane detection, Traffic sign classifier, behaviour cloning

Computer Vision and Machine Learning related projects of Udacity's Self-driving Car Nanodegree Program

ROS2 End-to-End Lane Following Model with SVL Simulator

Deep Learning based pipeline for alignment of a robot with stairs

Autonomous driving simulation in the Unity engine.

Deep learning to train an autonomous vehicle to mimic human driving

end to end learning for self-driving

Behavioral Cloning Project for Self-Driving Car Nano Degree Term 1. The project includes designing a neural network and then training the car on the road in unity simulator. The CNN learns and clones the driving behavior.

End-to-end Self-driving Car (Behavioral Cloning)

Solving Haxball (www.haxball.com) using Imitation Learning methods.

Reinforcement Learning + Imitation Learning based approach to AI Driving Olympics

Behavioural cloning experiments with video games

Library for controlling and capturing images from video games

Simulating a Self-Driving Car with basics of Deep Learning and Computer Vision

Path planning policy learned by behavior cloning, from RRT to neural network

Projects for the UDACITY Self-Driving Car Nanodegree

Deep Learning to Clone Driving Behavior

End to End Steering Angle Prediction for Self-Driving Cars

donkeycar fork for LitterBug

Reinforcement Learning -- Imitation Learning, Behavior Cloning, DAgger (Data Aggregation)

behavior cloning from observation

In this project, I used a deep neural network (built with Keras) to clone car driving behavior. The dataset used to train the network is generated from Udacity's Self-Driving Car Simulator, and it consists of images taken from three different camera angles (Center - Left - Right), in addition to the steering angle, throttle, brake, and speed during each frame. The network is based on NVIDIA's paper End to End Learning for Self-Driving Cars, which has been proven to work in this problem domain.