Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A vehicle control method, model training method and device

A vehicle and model fitting technology, applied in neural learning methods, biological neural network models, etc., can solve a large number of parameter adjustment processes, difficult to obtain vehicle power configuration parameters, difficult vehicle speed conditions, etc., to achieve strong robustness, Avoid manual calibration, strong adaptability effect

Active Publication Date: 2021-05-04
MOMENTA SUZHOU TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The model-free control method has strong versatility, but often requires a large number of parameter tuning processes, and it is difficult to adapt well to all vehicle speed conditions
The method based on the vehicle dynamics model can basically cover all working conditions, the premise is that an accurate model of the vehicle needs to be established, and it is often very difficult to obtain the power configuration parameters of the vehicle due to technical factors

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
  • A vehicle control method, model training method and device
  • A vehicle control method, model training method and device
  • A vehicle control method, model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] see figure 1 , figure 1 It is a schematic flowchart of a training method for a dynamic fitting model provided by an embodiment of the present invention. This method is applied in automatic driving and can be executed by a training device for dynamic fitting model, which can be realized by software and / or hardware, and can generally be integrated in a vehicle-mounted computer or a vehicle-mounted industrial personal computer (IPC). and other vehicle-mounted terminals, the embodiments of the present invention are not limited. Such as figure 1 As shown, the training method of the dynamic fitting model provided in this embodiment specifically includes:

[0086] 110. Obtain historical dynamic data corresponding to different historical opening degrees of the actuator of the vehicle.

[0087] Wherein, the actuator of the vehicle includes the accelerator pedal and the brake pedal of the vehicle, and the opening degree of the actuator represents the percentage of the depth o...

Embodiment 2

[0102] see figure 2 , figure 2 It is a schematic flowchart of a vehicle control method provided by an embodiment of the present invention. The method is applied in automatic driving and can be executed by the control device of the vehicle. The device can be realized by means of software and / or hardware, and generally can be integrated in a vehicle-mounted terminal such as a vehicle-mounted computer or a vehicle-mounted industrial control computer. Embodiments of the present invention do not Do limited. Such as figure 2 As shown, the vehicle control method provided in this embodiment specifically includes:

[0103] 210. Acquire dynamic data of the vehicle. Among them, the dynamic data includes the current initial velocity and the expected acceleration.

[0104] Wherein, the current initial velocity refers to the actual velocity of the vehicle at any moment, which can be used as the initial velocity of the vehicle at that moment. The expected acceleration is obtained ac...

Embodiment 3

[0110] see image 3 , image 3 It is a structural schematic diagram of a training device for a dynamic fitting model provided by an embodiment of the present invention. Such as image 3 As shown, the device includes: a historical dynamic data acquisition module 310 , a characteristic data determination module 320 , a training sample set generation module 330 and a model training module 340 . in,

[0111] The historical dynamic data acquisition module 310 is configured to acquire the historical dynamic data corresponding to the actuators of the vehicle at different historical openings, wherein the historical dynamic data includes historical initial speed and corresponding historical expected acceleration;

[0112] The characteristic data determination module 320 is configured to perform feature extraction on the historical dynamic data to obtain a feature sequence;

[0113] The training sample set generating module 330 is configured to generate a training sample set based o...

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 embodiment of the invention discloses a vehicle control method, a model training method and a device. Wherein, the control method of the vehicle includes: acquiring the dynamic data of the vehicle, the dynamic data including the current initial velocity and the expected acceleration, and the expected acceleration is obtained according to the expected velocity and the current initial velocity through the preset proportional-integral PI control algorithm ; According to the dynamic data and the preset dynamic fitting model, determine the opening degree of the actuator of the vehicle to control the longitudinal movement of the vehicle; wherein, the preset dynamic fitting model makes the dynamic data of the vehicle and The opening degrees of actuators of the vehicle, including an accelerator pedal and a brake pedal, are correlated. By adopting the above technical solution, the longitudinal motion of the vehicle can be accurately controlled without the need for vehicle power components and characteristic parameter adjustment of traditional system components.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a vehicle control method, a model training method and a device. Background technique [0002] In the field of autonomous driving, the driving force and braking force of the vehicle are crucial to the control of the vehicle's longitudinal motion. Among them, the driving force of the vehicle is output from the power components of the vehicle and then transmitted to the wheels through various components of the transmission system, and the braking force of the vehicle is delivered to the wheels from the braking system. [0003] At present, the longitudinal speed controller of the vehicle has a model-free control method based on PID (proportional, integral, differential), etc. and a control method based on a vehicle dynamics model. The model-free control method has strong versatility, but often requires a large number of parameter tuning processes, and it is difficult to ad...

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 Patents(China)
IPC IPC(8): B60W50/00G06N3/08
Inventor 刘召栋万登科潘金文牛晨骁
Owner MOMENTA SUZHOU TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products