Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
- 16 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 7262-7269
Abstract
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/.Keywords
All Related Versions
Funding Information
- Zhongshan Municipal Science and Technology Bureau Fund (ZSST21EG06)
- Collaborative Research Fund by Research Grants Council Hong Kong (C4063-18G)
- Department of Science and Technology of Guangdong Province Fund (GDST20EG54)
This publication has 15 references indexed in Scilit:
- Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor FusionIEEE Robotics and Automation Letters, 2020
- A Survey of Autonomous Driving: Common Practices and Emerging TechnologiesIEEE Access, 2020
- High-Speed Autonomous Drifting With Deep Reinforcement LearningIEEE Robotics and Automation Letters, 2020
- Imitation learning for agile autonomous drivingThe International Journal of Robotics Research, 2019
- Vision-based control in the open racing car simulator with deep and reinforcement learningJournal of Ambient Intelligence and Humanized Computing, 2019
- Learning to Drive in a Day2019
- CIRL: Controllable Imitative Reinforcement Learning for Vision-Based Self-driving2018
- End-to-End Driving Via Conditional Imitation Learning2018
- Repetitive learning model predictive control: An autonomous racing example2017
- Optimization‐based autonomous racing of 1:43 scale RC carsOptimal Control Applications and Methods, 2014