Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning

Autonomous car racing is a challenging task in the robotic control area. Traditional modular methods require accurate mapping, localization and planning, which makes them computationally inefficient and sensitive to environmental changes. Recently, deep-learning-based end-to-end systems have shown p...

Full description

Saved in:
Bibliographic Details
Published inIEEE robotics and automation letters Vol. 6; no. 4; pp. 7262 - 7269
Main Authors Cai, Peide, Wang, Hengli, Huang, Huaiyang, Liu, Yuxuan, Liu, Ming
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.10.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Algorithms
Automobiles
Autonomous cars
autonomous racing
Computational modeling
Deep learning
imitation learning
Knowledge acquisition
Machine learning
model learning for control
Racing
Reinforcement learning
Robot control
Robots
Sensors
Task analysis
Training
uncertainty awareness
Online AccessGet full text

Cover

More Information
Summary:Autonomous car racing is a challenging task in the robotic control area. Traditional modular methods require accurate mapping, localization and planning, which makes them computationally inefficient and sensitive to environmental changes. Recently, deep-learning-based end-to-end systems have shown promising results for autonomous driving/racing. However, they are commonly implemented by supervised imitation learning (IL), which suffers from the distribution mismatch problem, or by reinforcement learning (RL), which requires a huge amount of risky interaction data. In this work, we present a general deep imitative reinforcement learning approach (DIRL), which successfully achieves agile autonomous racing using visual inputs. The driving knowledge is acquired from both IL and model-based RL, where the agent can learn from human teachers as well as perform self-improvement by safely interacting with an offline world model. We validate our algorithm both in a high-fidelity driving simulation and on a real-world 1/20-scale RC-car with limited onboard computation. The evaluation results demonstrate that our method outperforms previous IL and RL methods in terms of sample efficiency and task performance. Demonstration videos are available at https://caipeide.github.io/autorace-dirl/ .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2021.3097345