Autonomous Overtaking for Intelligent Vehicles Considering Social Preference Based on Hierarchical Reinforcement Learning

Abstract

As intelligent vehicles usually have complex overtaking process, a safe and efficient automated overtaking system (AOS) is vital to avoid accidents caused by wrong operation of drivers. Existing AOSs rarely consider longitudinal reactions of the overtaken vehicle (OV) during overtaking. This paper proposed a novel AOS based on hierarchical reinforcement learning, where the longitudinal reaction is given by a data-driven social preference estimation. This AOS incorporates two modules that can function in different overtaking phases. The first module based on semi-Markov decision process and motion primitives is built for motion planning and control. The second module based on Markov decision process is designed to enable vehicles to make proper decisions according to the social preference of OV. Based on realistic overtaking data, the proposed AOS and its modules are verified experimentally. The results of the tests show that the proposed AOS can realize safe and effective overtaking in scenes built by realistic data, and has the ability to flexibly adjust lateral driving behavior and lane changing position when the OVs have different social preferences.

[Retracted] Motion Control System of IoT Intelligent Robot Based on Improved ResNet Model

“…With the development of intelligent manufacturing and industrialization, the demand for automatic control and intelligent control systems in every field is also increasing, and industrial intelligent robots are no exception, with the continuous expansion of application fields, it puts forward strict requirements on the performance and functions of industrial robots, at the same time, it also promotes the rapid development of motion simulation, intelligent control, and other fields [5]. When the intelligent robot is in motion, it can adjust and control its posture by controlling each joint, so as to realize the function of the end operation of the robot [6]. This control method is quite different from single-step control, but it also has certain connections.…”

Towards Safe Autonomous Driving: Decision Making with Observation-Robust Reinforcement Learning

“…In many studies, the RL has been applied to generate lane change behaviors during autonomous driving [12,13]. One popular approach is developed based on the deep Q-network (DQN).…”