Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification
Not on the map. Why?
Abstract (arXiv)
Self-evolution is indispensable to realize full autonomous driving. This paper presents a self-evolving decision-making system based on the Integrated Decision and Control (IDC), an advanced framework built on reinforcement learning (RL). First, an RL algorithm called constrained mixed policy gradient (CMPG) is proposed to consistently upgrade the driving policy of the IDC. It adapts the MPG under the penalty method so that it can solve constrained optimization problems using both the data and model. Second, an attention-based encoding (ABE) method is designed to tackle the state representation issue. It introduces an embedding network for feature extraction and a weighting network for feature fusion, fulfilling order-insensitive encoding and importance distinguishing of road users. Finally, by fusing CMPG and ABE, we develop the first data-driven decision and control system under the IDC architecture, and deploy the system on a fully-functional self-driving vehicle running in daily operation. Experiment results show that boosting by data, the system can achieve better driving ability over model-based methods. It also demonstrates safe, efficient and smart driving behavior in various complex scenes at a signalized intersection with real mixed traffic flow.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 19 Oct 2022.
Builds on
20 of 34 references.
References · 20
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
- 2016End to End Learning for Self-Driving Carscited by 1,000
- 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
- 2018Learning to Drive in a Daycited by 266
- 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
- 2018Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansioncited by 167
- 2015Learning Continuous Control Policies by Stochastic Value Gradientscited by 156
- 2018Model-Based Value Estimation for Efficient Model-Free Reinforcement Learningcited by 152
- 2018Baidu Apollo EM Motion Plannercited by 99
- 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 96
- 2017Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Carcited by 65
8 more
- 2019PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaoscited by 56
- 2018A Reinforcement Learning Based Approach for Automated Lane Change Maneuverscited by 44
- 2018End-to-End Race Driving with Deep Reinforcement Learningcited by 38
- 2021Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligencecited by 25
- 2020Numerically Stable Dynamic Bicycle Model for Discrete-time Controlcited by 15
- 2021Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and modelcited by 8
- 2020Hierarchical Reinforcement Learning for Self-Driving Decision-Making without Reliance on Labeled Driving Datacited by 7
- 2021Fixed-Dimensional and Permutation Invariant State Representation of Autonomous Drivingcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024A Safe and Efficient Self-evolving Algorithm for Decision-making and Control of Autonomous Driving Systems
- 2024A Safety-Oriented Self-Learning Algorithm for Autonomous Driving: Evolution Starting from a Basic Model
- 2021A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
- 2024Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making
- 2025Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving
- 2021A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles
- 2024Automated Driving with Evolution Capability: A Reinforcement Learning Method with Monotonic Performance Enhancement
- 2022Tackling Real-World Autonomous Driving using Deep Reinforcement Learning