Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture

10/11/2021
by   Chinmay Vilas Samak, et al.
0

In this work, we present a rigorous end-to-end control strategy for autonomous vehicles aimed at minimizing lap times in a time attack racing event. We also introduce AutoRACE Simulator developed as a part of this research project, which was employed to simulate accurate vehicular and environmental dynamics along with realistic audio-visual effects. We adopted a hybrid imitation-reinforcement learning architecture and crafted a novel reward function to train a deep neural network policy to drive (using imitation learning) and race (using reinforcement learning) a car autonomously in less than 20 hours. Deployment results were reported as a direct comparison of 10 autonomous laps against 100 manual laps by 10 different human players. The autonomous agent not only exhibited superior performance by gaining 0.96 seconds over the best manual lap, but it also dominated the human players by 1.46 seconds with regard to the mean lap time. This dominance could be justified in terms of better trajectory optimization and lower reaction time of the autonomous agent.

READ FULL TEXT

page 1

page 3

page 4

page 7

research
09/29/2022

A Benchmark Comparison of Imitation Learning-based Control Policies for Autonomous Racing

Autonomous racing with scaled race cars has gained increasing attention ...
research
10/16/2021

Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments

Autonomous driving is a complex task, which has been tackled since the f...
research
01/18/2022

Ray Based Distributed Autonomous Vehicle Research Platform

My project tackles the question of whether Ray can be used to quickly tr...
research
02/26/2018

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

We propose a model-free deep reinforcement learning method that leverage...
research
07/16/2019

Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving

We present a training pipeline for the autonomous driving task given the...
research
12/04/2016

Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision

We propose a scheme for training a computerized agent to perform complex...
research
05/23/2023

iCOIL: Scenario Aware Autonomous Parking Via Integrated Constrained Optimization and Imitation Learning

Autonomous parking (AP) is an emering technique to navigate an intellige...

Please sign up or login with your details

Forgot password? Click here to reset