Deep Reinforcement Learning for Autonomous Driving

By Sen Wang, Daoyuan Jia, Xinshuo Weng. 2018

184 citations recorded by the source corpus.

Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. However, these success is not easy to be copied to autonomous driving because the state spaces in real world are extreme complex and action spaces are continuous and fine control is required. Moreover, the autonomous driving vehicles must also keep functional safety under the complex environments. To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action spaces in continuous domain. We then choose The Open Racing Car Simulator (TORCS) as our environment to avoid physical damage. Meanwhile, we select a set of appropriate sensor information from TORCS and design our own rewarder. In order to fit DDPG algorithm to TORCS, we design our network architecture for both actor and critic inside DDPG paradigm. To demonstrate the effectiveness of our model, We evaluate on different modes in TORCS and show both quantitative and qualitative results.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Reinforcement Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey I. Nikolenko
2. Ibrahim Sobh
3. B. R. Kiran
4. Patrick Pérez
5. David Held
6. Senthil Kumar Yogamani
7. Jianren Wang
8. Ahmad A. Al Sallab

In Computational Theory and Mathematics

1. Patrick Pérez
2. David Held
3. Sergey I. Nikolenko
4. Senthil Kumar Yogamani
5. Kris M. Kitani
6. Patrick Mannion
7. Xinshuo Weng

In Reinforcement Learning

1. Ibrahim Sobh
2. B. R. Kiran
3. Patrick Pérez
4. David Held
5. Sergey I. Nikolenko
6. Senthil Kumar Yogamani
7. Jianren Wang
8. Ahmad A. Al Sallab

In Robotics & Control

1. Sergey I. Nikolenko
2. Ibrahim Sobh
3. Patrick Pérez
4. David Held
5. Senthil Kumar Yogamani
6. Kris M. Kitani
7. Patrick Mannion
8. Victor Talpaert

Citations in the corpus

• Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, background): “…vehicle at a standstill [82], collisions with other road users or scene objects [79], [80], [82], infractions on sidewalks [79], keeping in lane [79], [81]–[83], maintaining comfort and stability (avoiding extreme acceleration, braking or steering) [80], [82], [83], and following traffic rules [80].”
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics (2019, background): “ywords: 3D multi-object tracking, real-time, evaluation metrics 1 Introduction Multi-object tracking (MOT) is an essential component technology for many vision applications such as autonomous driving [1,2,3], robot collision prediction [4,5] and video face alignment [6, 7,8]. Due to the significant a”
• Synthetic Data for Deep Learning (2019, background): “[626] train a deep RL agent for autonomous driving in TORCS, Barati et al.”
• Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction (2019, unknown): “In this paper, we focus on solving continual reinforcement learning problems in the field of continuous control, a task widely occurred in physical control [28] and autonomous driving [30].”