Vehicle control method based on reinforcement learning control strategy in hybrid fleet

A control strategy, a technology of vehicle control, applied in vehicle position/route/height control, non-electric variable control, control/regulation system, etc., which can solve the problems of easy deviation of results and strong dependence on human factors.

Active Publication Date: 2021-01-01
YANSHAN UNIV
View PDF10 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The system includes a state monitoring module, a simulated driving module, an analysis module, a comparison module, etc. By analyzing the driving op

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle control method based on reinforcement learning control strategy in hybrid fleet
  • Vehicle control method based on reinforcement learning control strategy in hybrid fleet
  • Vehicle control method based on reinforcement learning control strategy in hybrid fleet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] like figure 1 As shown, in general, the problem of knowing the state transition probability is called "model-based" problem, and the problem of not knowing is called "model-free" problem. The Markov decision process in the prior art is a modeling method proposed for the "no model" problem. The reinforcement learning algorithm of mixed traffic that the present invention proposes is a kind of model-free free control strategy, and this method forms a database with the driving data of vehicles in the mixed fleet, such as speed, acceleration, and driving distance, and combines this database with the traffic on the road. The situation is used as the environment, and each vehicle in the formation is regarded as an agent, and the environment can realize the feedback status and rewards to the agent. The input is the defined environment state, vehicle state, and optimal control action, and the output is the reward value caused by the action in this state. It can be applied to m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a vehicle control method based on a reinforcement learning control strategy in a hybrid fleet, and the method comprises the steps: initializing a hybrid fleet, and building a fixed reference system and an inertial reference system; establishing a model of a mixed vehicle longitudinal queue in the inertial reference system; constructing a Lagrange quadratic queue car-following cost function, and obtaining an expression of a Q value function; training information obtained by the influence of surrounding vehicles on own vehicles by using a deep Q learning network; trainingparameters by using a DDPG algorithm, and if the Q value function process and the control input process realize convergence at the same time, completing the solution of the current optimal control strategy; inputting the optimal control strategy into the model of the longitudinal queue of the hybrid vehicle, and updating the state of the hybrid vehicle by the hybrid vehicle queue; and repeating the steps to finally complete the control task of the vehicles in the hybrid fleet. With the system, the problem of hybrid motorcade autonomous training is solved.

Description

technical field [0001] The invention belongs to the technical field of intelligent traffic control, and in particular relates to a vehicle control method based on a reinforcement learning control strategy in a mixed fleet. Background technique [0002] With the rapid development of artificial intelligence technology, unmanned driving technology has become more mature, and the mixed longitudinal car-following queue composed of manned and unmanned vehicles has become a hot research direction in the field of intelligent transportation. Among them, the longitudinal platoon car-following problem combines traditional dynamics and kinematics methods to study the influence of the driving state of the vehicle in front of the platoon on the car-following vehicle. However, due to the randomness of the positions of manned and unmanned vehicles in practical mixed longitudinal platoons, and the need for drivers' behavior to be identified in advance as part of the platooning system, there ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G05D1/02
CPCG05D1/0221G05D1/0223G05D1/0253G05D1/0276G05D1/0295G05D2201/0212
Inventor 罗小元刘劭玲李孟杰郑心泉刘乐
Owner YANSHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap