Modified DDPG car-following model with a real-world human driving experience with CARLA simulator
On the map: End-to-end autonomous driving → Reinforcement learning for driving
Abstract (arXiv)
In the autonomous driving field, fusion of human knowledge into Deep Reinforcement Learning (DRL) is often based on the human demonstration recorded in a simulated environment. This limits the generalization and the feasibility of application in real-world traffic. We propose a two-stage DRL method to train a car-following agent, that modifies the policy by leveraging the real-world human driving experience and achieves performance superior to the pure DRL agent. Training a DRL agent is done within CARLA framework with Robot Operating System (ROS). For evaluation, we designed different driving scenarios to compare the proposed two-stage DRL car-following agent with other agents. After extracting the "good" behavior from the human driver, the agent becomes more efficient and reasonable, which makes this autonomous agent more suitable for Human-Robot Interaction (HRI) traffic.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 20 of its 60 references that are in the map. First posted on arXiv 29 Dec 2021.
Builds on
20 of 60 references.
Closest ancestors · 2
Same direction, newest first
- 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving19 Mar
- 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving18 Feb
Other references · 18
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
- 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
- 2016End to End Learning for Self-Driving Carscited by 1,000
- 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
- 2017End-to-end Driving via Conditional Imitation Learningcited by 479
- 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
- 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
- 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302
- 2019Causal Confusion in Imitation Learningcited by 286
6 more
- 2018How to Start Training: The Effect of Initialization and Architecturecited by 109
- 2018A Reinforcement Learning Based Approach for Automated Lane Change Maneuverscited by 44
- 2021Offline Reinforcement Learning with Pseudometric Learningcited by 28
- 2016End-to-End Deep Reinforcement Learning for Lane Keeping Assistcited by 27
- 2018Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Mapscited by 17
- 2021Formulation and validation of a car-following model based on deep reinforcement learningcited by 4
Built on by
Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 3; 2026: 1.
9 papers.
- 2023FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modelingcited by 21
- 2023A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Drivingcited by 7
- 2024Autonomous Driving Small-Scale Cars: A Survey of Recent Developmentcited by 6
- 2022Vessel-following model for inland waterways based on deep reinforcement learningcited by 2
- 2023Vision-based DRL Autonomous Driving Agent with Sim2Real Transfercited by 2
- 2025Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersectionscited by 1
- 2025Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Drivingcited by 1
- 2025Knowledge-data fusion dominated vehicle platoon dynamics modeling and analysis: A physics-encoded deep learning approachcited by 0
- 2026A Computationally Efficient Learning of Artificial Intelligence System Reliability Considering Error Propagationcited by 0
- 2026A Computationally Efficient Learning of Artificial Intelligence System Reliability Considering Error Propagation18 Mar 2026
- 2025Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving19 Aug 2025
- 2025Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersections13 May 2025
- 2025Knowledge-data fusion dominated vehicle platoon dynamics modeling and analysis: A physics-encoded deep learning approach9 Feb 2025
- 2024Autonomous Driving Small-Scale Cars: A Survey of Recent Development9 Apr 2024
- 2023FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling25 May 2023
- 2023Vision-based DRL Autonomous Driving Agent with Sim2Real Transfer19 May 2023
- 2023A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Driving14 Apr 2023
- 2022Vessel-following model for inland waterways based on deep reinforcement learning7 Jul 2022
Similar, not cited
Close in wording, no citation either way
- 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learning
- 2022Bilateral Deep Reinforcement Learning Approach for Better-than-human Car Following Model
- 2020Deep Reinforcement Learning for Autonomous Driving: A Survey
- 2023Review of Deep Reinforcement Learning for Autonomous Driving
- 2021Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving
- 2024HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving
- 2025A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator
- 2022Incorporating Voice Instructions in Model-Based Reinforcement Learning for Self-Driving Cars