DeepAI AI Chat
Log In Sign Up

Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification

by   Yang Guan, et al.

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.


page 1

page 2

page 6

page 7

page 9


Encoding Integrated Decision and Control for Autonomous Driving with Mixed Traffic Flow

Reinforcement learning (RL) has been widely adopted to make intelligent ...

Encoding Distributional Soft Actor-Critic for Autonomous Driving in Multi-lane Scenarios

In this paper, we propose a new reinforcement learning (RL) algorithm, c...

Fixed-Dimensional and Permutation Invariant State Representation of Autonomous Driving

In this paper, we propose a new state representation method, called enco...

Integrated Decision and Control at Multi-Lane Intersections with Mixed Traffic Flow

Autonomous driving at intersections is one of the most complicated and a...

Integrated Decision and Control: Towards Interpretable and Efficient Driving Intelligence

Decision and control are two of the core functionalities of high-level a...

Learning Scalable Policies over Graphs for Multi-Robot Task Allocation using Capsule Attention Networks

This paper presents a novel graph reinforcement learning (RL) architectu...

Mixed Policy Gradient

Reinforcement learning (RL) has great potential in sequential decision-m...