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

Vehicle path transformation model training method, path transformation method and device

A technology for transforming models and vehicle paths, applied in the field of vehicle path transformation model training, which can solve problems such as high computational complexity, inapplicability to real-time application process, and inability to enumerate trajectories, so as to improve accuracy, fast and smooth path Effects that transform, improve accuracy and speed

Active Publication Date: 2022-05-13
MOMENTA SUZHOU TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above method has a large computational complexity in the implementation process, and cannot list all feasible trajectories, and is not suitable for real-time application process

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 path transformation model training method, path transformation method and device
  • Vehicle path transformation model training method, path transformation method and device
  • Vehicle path transformation model training method, path transformation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] see figure 1 , figure 1 It is a schematic flowchart of a training method for a vehicle path transformation 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 a vehicle path transformation model. This device can be realized by means of software and / or hardware, and generally can be integrated in a vehicle-mounted computer, a vehicle-mounted industrial personal computer (IPC), etc. In the vehicle-mounted terminal, the embodiments of the present invention are not limited. Such as figure 1 As shown, the method provided in this embodiment specifically includes:

[0092]110. Acquire the historical motion information of the own vehicle when the current vehicle receives the path change instruction, and the historical motion information of other vehicles other than the current vehicle in the corresponding historical environmental perception information.

[0093] Wherein, the path...

Embodiment 2

[0113] see image 3 , image 3 It is a schematic flowchart of a vehicle path changing method provided by an embodiment of the present invention. In this embodiment, on the basis of the path transformation model constructed in the above-mentioned embodiments, the path transformation model is applied to the actual driving process of the vehicle. It can be implemented in a manner, and generally can be integrated in a vehicle-mounted terminal such as a vehicle-mounted computer, a vehicle-mounted industrial personal computer (IPC), etc., which is not limited in the embodiment of the present invention. Such as image 3 As shown, the method includes:

[0114] 210. Acquire environment perception information and path transformation instructions.

[0115] Wherein, the environmental perception information includes current motion information of other vehicles other than the current vehicle, and the current motion information includes: speed, position and acceleration. The path change...

Embodiment 3

[0123] see Figure 4 , Figure 4 It is a schematic structural diagram of a training device for a vehicle path transformation model provided by an embodiment of the present invention. Such as Figure 4 As shown, the device includes: historical motion information acquisition module 310, planning path generation module 320, training sample set generation module 330 and path transformation model establishment module 340; wherein,

[0124] The historical movement information acquisition module 310 is configured to acquire the historical movement information of the own vehicle when the current vehicle receives the path change instruction, and the historical movement information of other vehicles other than the current vehicle in the corresponding historical environment perception information, the history Motion information including velocity, position and acceleration;

[0125] The planned route generation module 320 is configured to generate a planned route that satisfies the ve...

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 present invention discloses a training method, a path transformation method and a device for a vehicle path transformation model. The method includes: acquiring the historical motion information of the vehicle when the current vehicle receives a path transformation instruction, and the corresponding historical environment perception information. The historical motion information of other vehicles; according to the historical motion information of the own vehicle and other vehicles, generate a planned path that satisfies the vehicle position constraints and makes the preset objective function reach the preset convergence condition; The target driving path and the corresponding historical motion information that meet the preset path transformation requirements in the detection results are used as the training sample set; the initial neural network model is trained by using the training sample set, and the path transformation model of the vehicle is obtained. The path transformation model makes the current vehicle and the The motion information of other vehicles is associated with the target travel path of the current vehicle when the path is changed. By adopting the above technical solution, the accuracy and efficiency of path planning are improved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a training method for a vehicle path transformation model, a path transformation method and a device. Background technique [0002] Motion planning is to find a constraint-compliant path for an unmanned vehicle between a given location A and location B. This constraint can be no collision, shortest path, minimum mechanical work, etc. It is an important research field of robotics. [0003] For safe and efficient unmanned vehicle planning, the planning method based on optimization solution can provide an optimal strategy for unmanned vehicles. Most of the existing path planning algorithms are based on search to generate a series of feasible trajectories satisfying the dynamics, and then filter out more suitable motion paths through collision detection and fusion of some artificial trajectory features. [0004] The above method has a large computational complexity in th...

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): G08G1/01G08G1/16
CPCG08G1/0129G08G1/166G08G1/167
Inventor 时天宇席晨阳陈杰
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com