An automatic driving model training method and device
A technology of automatic driving and training methods, applied in character and pattern recognition, registration/indication of vehicle operation, instruments, etc., can solve problems such as low safety and lack of deviation correction ability
Active Publication Date: 2019-05-03
APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
View PDF3 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Embodiments of the present invention provide a training method and device for an automatic driving model. The current end-to-end automatic driving model lacks the ability to correct deviations, which leads to the problem of low safety when the vehicle is driving automatically.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0024] see figure 1 , figure 1 It is a flowchart of a training method for an automatic driving model provided by an embodiment of the present invention, such as figure 1 shown, including the following steps:
[0025] Step 101, obtaining first training data and second training data;
[0026] Step 102, using the first training data and the second training data to train the end-to-end model to obtain an automatic driving model;
[0027] Wherein, the f...
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
Login to View More Abstract
The invention provides a training method and device for an automatic driving model. The method comprises the steps that first training data and second training data are acquired; using the first training data and the second training data to train the end-to-end model to obtain an automatic driving model; wherein the first training data comprises data collected by the vehicle in the driving processof a preset route; wherein the second training data comprises data collected by the vehicle in a deviation rectifying path driving process deviating from the path, the deviation rectifying path is different from a preset path, and the deviation rectifying path is a path for driving the vehicle after deviation rectifying in the deviation rectifying path. According to the training method of the automatic driving model provided by the embodiment of the invention, the first training data and the second training data are used as training samples of the end-to-end model, so that the automatic driving model obtained through training has a deviation rectifying capability, and the safety of a vehicle during automatic driving is improved.
Description
technical field [0001] The invention relates to the technical field of automobiles, in particular to a training method and device for an automatic driving model. Background technique [0002] Self-driving cars use ECU (Electronic Control Unit, electronic control unit) and other vehicle-mounted terminal equipment to carry out precise control and calculation and analysis of various parts of the vehicle, so as to realize the fully automatic operation of the vehicle and achieve the purpose of unmanned driving. With the rapid development of deep learning and in-depth research on artificial intelligence, automatic driving through end-to-end deep learning is a major research direction in the field of automatic driving. [0003] In the existing end-to-end autonomous driving model training, the training data provided for the training model is usually that the vehicle travels according to a predetermined route. However, during the automatic driving process, the vehicle may deviate fr...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G07C5/08
Inventor 闫泳杉
Owner APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD