State prediction and estimation method for unmanned vehicle

A technology for unmanned vehicles and vehicle states, which is applied in the field of state estimation of unmanned vehicles and can solve problems such as control effect lag

Active Publication Date: 2021-05-07
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The control of traditional manned vehicles is generally based on the judgment of vehicle stability to determine whether to apply control commands, which has a certain lag in the control effect

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
  • State prediction and estimation method for unmanned vehicle
  • State prediction and estimation method for unmanned vehicle
  • State prediction and estimation method for unmanned vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0136] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0137] The invention proposes a state estimation method for distributed driving unmanned vehicles. Such as figure 1 As shown, first, a new velocity prediction method suitable for unmanned vehicles is proposed. For the known 20 working conditions, 400 working condition blocks with different lengths of time are randomly selected, and 10 features corresponding to each working condition block are extracted from them, and the proposed speed prediction formula with vehicle torque correction is used, and the acceleration and acceleration derivative The optimal parameters of the speed prediction formula are determined by such characteristics, and the genetic algorithm neural network is used for training, and the historical data of the vehicle's current driving conditions are introduced to update and optimize parameters such as acceleration and acceleration deriva...

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 discloses a state prediction and estimation method for an unmanned vehicle, and the method comprises the steps: employing a provided vehicle torque correction speed prediction formula, determining the optimal parameters of the speed prediction formula through the characteristics of acceleration, acceleration derivative and the like, and carrying out the training through a genetic algorithm neural network, introducing historical data of a current driving condition of a vehicle to update and optimize acceleration and an acceleration derivative in time, fusing a kinematics method and a dynamics method to estimate a road slope angle, using a least square method to estimate vehicle mass, and improving estimation precision of the vehicle mass and sprung mass. Estimating the vertical force of the wheels by using an information fusion method, introducing a road adhesion coefficient, and performing joint estimation on the lateral force and the state of the vehicle by using a nonlinear estimation method; finally, a vehicle state rolling estimation method in which vehicle variable parameters and variable working conditions are introduced is provided, and the precision of vehicle speed prediction under the conditions of vehicle variable parameters and variable working conditions is improved.

Description

technical field [0001] The invention belongs to the technical field of state estimation of unmanned vehicles, and in particular relates to a state prediction and estimation method for unmanned vehicles. Background technique [0002] Real-time estimation of vehicle state is the basis of vehicle dynamics control. From the perspective of physical model, it is generally divided into dynamic method and kinematic method. The kinematics method is generally based on the kinematics method and uses sensors to observe the quantity to be estimated, and the dynamics method uses the limited sensor configuration to realize the vehicle state estimation observation based on the dynamics method. From the classification of estimation algorithm, it can be divided into Kalman filter algorithm, Lomberg algorithm, robust algorithm, sliding mode algorithm and nonlinear observation algorithm. The Kalman filter algorithm is currently the most commonly used method for vehicle state estimation. [0...

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
Patent Type & Authority Applications(China)
IPC IPC(8): B60W40/00B60W40/10B60W50/00
CPCB60W40/00B60W40/10B60W50/00B60W2050/0043Y02T90/00
Inventor 陈勇任宏斌陈思忠高泽鹏赵玉壮齐志权李长隆
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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