AU2020104282A4 - Intelligent Training Aiding Method And System For Instructional Cars - Google Patents
Intelligent Training Aiding Method And System For Instructional Cars Download PDFInfo
- Publication number
- AU2020104282A4 AU2020104282A4 AU2020104282A AU2020104282A AU2020104282A4 AU 2020104282 A4 AU2020104282 A4 AU 2020104282A4 AU 2020104282 A AU2020104282 A AU 2020104282A AU 2020104282 A AU2020104282 A AU 2020104282A AU 2020104282 A4 AU2020104282 A4 AU 2020104282A4
- Authority
- AU
- Australia
- Prior art keywords
- instructional
- training
- instructional car
- path
- driving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
- G09B9/02—Simulators for teaching or training purposes for teaching control of vehicles or other craft
- G09B9/04—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles
- G09B9/042—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles providing simulation in a real vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/16—Control of vehicles or other craft
- G09B19/167—Control of land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to an intelligent training aiding method and system for
instructional cars. The method comprises: acquiring image information of a training
field in real time through a camera, and uploading the image information into a
machine learning model; detecting an image of the training field by a model to
determine the type of the training field and determine whether or not there is an
instructional car in the image of the training field; if there is an instructional car in the
image of the training field, generating a driving path by calculation and analysis of the
model; calculating and analyzing the driving path by the model to determine whether
or not the driving path deviates from a preset path; if so, generating correction
information by the model and sending the information to the instructional car; and
displaying and broadcasting the correction information in the car, so that a learner in
the car can adjust personal driving actions according to the correction information to
make the driving path close to the preset path. The method can replace instructors to
some extent to intelligently aid the learner in driving training and can improve the
training level of the learner to a certain extent.
Description
Technical Field
[0001] The embodiments of the invention relates to the technical field of
intelligent teaching aiding techniques for driving schools, in particular to an
intelligent training aiding method and system for instructional cars.
Background
[0002] With the development of the society and the gradual improvement of
people's living standard, more and more families possess cars, and more and more
people start to learn driving. Due to the fact that the number of driving instructors in
driving schools is relatively smaller while the number of driving learners is great, the
workload of the driving instructors is large, and the same learning instructor has to
repeat the same technical action over and over in one day and may finally get
impatient, thus leading to contradictions between the learners and the instructors. In
addition, due to the great number of driving learners and the limitations of traditional
face-to-face teaching methods in learning time and frequency, the learners cannot
flexibly select the instructors, so the improvement of the driving skills of the learners
is limited to some extent.
[0003] Most existing intelligent products used by driving schools, such as
driving training simulators, are virtual products. Because of the drastic difference
between the driving training simulators and the cars in operating followability and the
poor practicability of necessary teaching materials, the training effect is unsatisfactory;
and driving teachings in different regions are different, but such products cannot make
changes to adapt to different driving schools, so the training simulators in the driving
schools perform practically no function.
[0004] In the drive learning process, it generally takes a lot of time of the
learners to carry out training for the second subject, especially for reverse parking in the second subject. Due to the complicated driving actions of reverse parking, the learners have to put more effort into training to improve their proficiency; moreover, during reverse parking, the learners need to slightly adjust the direction of cars to reversely park the cars in parking spaces, but it is difficult for the beginners to master the adjustment direction and angle, and it is also impossible for the instructors to prompt the learners in real time; if the instructors is in a bad mood, the learners will feel more strained, which is not beneficial to the improvement of the driving skills of the learners. In view of this, it is necessary to solve one or more problems of the related art.
[0005] It should be noted that this section aims to introduce the background
or context of the implementation of the invention stated in the claims, but the
description in this section does not necessarily belong to the prior part.
Summary
[0006] The objective of the embodiments of the invention is to provide an
intelligent training aiding method and system for instructional cars to, at least to some
extent, solve one or more problems caused by the limitations and drawbacks of the
related art.
[0007] In a first aspect, the embodiments of the invention provide an
intelligent training aiding method for instructional cars, comprising:
[0008] Acquiring image information of a training field in real time through
a camera disposed above the training field, and uploading the image information of
the training field into a machine learning model;
[0009] Detecting an image of the training field by a target detection model
pre-established in the machine learning model to determine the type of the training
field and determine whether or not there is an instructional car in the image of the
training field;
[0010] Wherein, the machine learning model detects the image of the training field by means of a pre-established instructional car target detection model based on deep learning;
[0011] If there is an instructional car in the image of the training field, calculating and analyzing multiple movement positions of the instructional car by the machine learning model to generate a driving path based on the multiple movement positions;
[0012] Calculating and analyzing the driving path by the machine learning model to determine whether or not the driving path deviates from a preset path;
[0013] Wherein, the machine learning model is used after parameters are cured therein by learning and training multiple driving paths of the instructional car;
[0014] If the driving path deviates from the preset path, generating correction information according to the degree of deviation of the driving path and sending the correction information to a receiving module on the instructional car, by the machine learning model;
[0015] Sending the correction information to a control module in the instructional car by the receiving module, and controlling the correction information to be displayed and broadcast in the instructional car by the control module, so that a learner can adjust personal driving actions according to the correction information to make the driving path close to the preset path;
[0016] Wherein, the correction information includes voice prompt information and video demonstration information, and the video demonstration information is demonstrative animation information about a pre-turning direction and angle of a steering wheel in the instructional car;
[0017] Every time the instructional car completes a training subject, storing an actual driving path of the instructional car in the machine learning model;
[0018] Comparing the actual driving path stored in the machine learning
model with the preset path to generate path comparison information, and sending the
path comparison information to a terminal for timely correction of the learner.
[0019] In one embodiment, the method further comprises:
[0020] In the process of completing the training subject by the instructional
car, monitoring the driving speed of the instructional car in real time and determining
whether or not the driving speed is within a preset range; and
[0021] If the driving speed exceeds the preset range, generating a prompt
message, and sending the prompt message to the instructional car.
[0022] In one embodiment, the method further comprises:
[0023] When the driving path of the instructional car deviates from the
preset path beyond a preset deviation and the machine learning model recognizes that
the instructional car is under a dangerous condition, sending a brake signal to the
instructional car to control the instructional car to stop in time.
[0024] In one embodiment of the invention, the path comparison
information is video comparison information of an actual driving video of the
instructional car and a preset virtual driving video of the instructional car.
[0025] In one embodiment of the invention, the type of the training field
includes: a reverse parking training subject, a parallel parking training subject, a
zigzag driving training subject and a left or right turning training subject.
[0026] In a second aspect, the embodiments of the invention provide an
intelligent training aiding system for instructional cars, comprising:
[0027] A camera module disposed above a training field and used for acquiring image information of the training field in real time and uploading the image information of the training field into a machine learning model;
[0028] The machine learning model used for detecting an image of the training field through a target detection model pre-established in the machine learning model to determine the type of the training field and determine whether or not there is an instructional car in the image of the training field, wherein the machine learning model detects the image of the training field by means of a pre-established instructional car target detection model based on deep learning; if there is an instructional car in the image of the training field, the machine learning model calculates and analyzes multiple movement positions of the instructional car to generate a driving path based on the multiple movement positions;
[0029] The machine learning model is used for calculating and analyzing the driving path to determine whether or not the driving path deviates from a preset path, wherein the machine learning model is used after parameters are cured therein by learning and training multiple driving paths of the instructional car; if the driving path deviates from the preset path, the machine learning model generates correction information according to the degree of deviation of the driving path and sends the correction information to a receiving module on the instructional car; every time the instructional car completes a training subject, an actual driving path of the instructional car is stored in the machine learning model;
[0030] An instructional car module comprising a receiving module and a control module, wherein the receiving module is used for sending the received correction information to the control module in the instructional car, and the control module is used controlling the correction information to be displayed and broadcast in the instructional car, so that a learner in the instructional car can adjust personal driving actions according to the correction information to make the driving path close to the preset path;
[0031] The correction information includes voice prompt information and video demonstration information, and the video demonstration information is demonstrative animation information about a pre-turning direction and angle of a steering wheel in the instructional car;
[0032] A comparison module used for comparing the actual driving path stored in the machine learning model with the preset path to generate path comparison information and sending the path comparison information to a terminal for timely correction of the learner.
[0033] In one embodiment of the invention, the machine learning module is used for monitoring the driving speed of the instructional car in real time in the process of completing the training subject by the instructional car, determining whether or not the driving speed is within a preset range, generating a prompt message if the driving speed exceeds the preset range, and sending the prompt message to the instructional car.
[0034] In one embodiment of the invention, the machine learning model is also used for sending a brake signal to the instructional car to control the instructional car to stop in time when the driving path of the instructional car deviates from the preset path beyond a preset deviation and the machine learning model recognizes that the instructional car is under a dangerous condition.
J [0035] In one embodiment of the invention, the path comparison information is video comparison information of an actual driving video of the instructional car and a preset virtual driving video of the instructional car.
[0036] In one embodiment of the invention, the type of the training field includes: a reverse parking training subject, a parallel parking training subject, a zigzag driving training subject and a left or right turning training subject.
[0037] The technical solution provided by the embodiments of the invention may have the following beneficial effects:
[0038] According to the intelligent training aiding method and system for
instructional cars provided by the embodiments of the invention, image information is
captured in real time through a camera disposed above a training field and is uploaded
to a machine learning model, then an actual driving path of an instructional car is
calculated and analyzed through the machine learning model to obtain a deviation of
the actual driving path from a preset path, and correction information is generated
according to the deviation and can be displayed and broadcast in the instructional car
in real time, so that a learner can visually adjust the turning direction and angle of the
steering wheel according to video demonstrations in the correction information; a
voice prompt is broadcast in the instructional car at the same time, so that the learner
can correct personal driving actions under the combined action of the video
demonstrations and the voice prompt. The intelligent training aiding method can
replace instructors to some extent to intelligently aid the learner in driving training
and can improve the training level of the learner to a certain extent.
Brief Description of the Drawings
[0039] The drawings, incorporated into the specification and constituting
one part of the specification, illustrate feasible embodiments of the disclosure and are
used to explain the principle of the disclosure together with the specification.
Obviously, the drawings in the following description merely illustrate some
embodiments of the disclosure, and those ordinarily skilled in the art can obtain other
drawings according to the following ones without creative labor.
[0040] FIG. 1 illustrates a flow diagram of an intelligent training aiding
method for instructional cars in an illustrative embodiment of the invention;
[0041] FIG. 2 illustrates a schematic diagram of the modules of an
intelligent training aiding system for instructional cars in the illustrative embodiment
of the invention;
[0042] FIG. 3 is a schematic diagram of the turning direction and angle of a steering wheel displayed on a display screen of an instructional car in the illustrative embodiment of the invention;
[0043] FIG. 4 is a schematic diagram of a preset driving path of the
instructional car in a training field in the illustrative embodiment of the invention;
[0044] FIG. 5 is a schematic diagram of an actual driving path of the
instructional car in the training field in the illustrative embodiment of the invention;
[0045] FIG. 6 is a comparison diagram of the actual driving path and the
preset path of the instructional car in the training field in the illustrative embodiment
of the invention.
Detailed Description of Embodiments
[0046] Illustrative embodiments will be more comprehensively described
below with reference to the accompanying drawings. Clearly, the illustrative
embodiments may be implemented in different forms, and should not be limited to the
forms expounded herein. These illustrative embodiments are provided to make the
invention more comprehensive and completed and to comprehensively convey the
conception of the illustrative embodiments to those skilled in the art. The features,
structures or properties described below can be combined in one or more
embodiments in any suitable manners.
[0047] In addition, the accompanying drawings are merely illustrative
drawings of the embodiments of the invention, and are not necessarily drawn to scale.
Identical reference signs in the drawings represent identical or similar parts, so
repeated descriptions of these identical reference signs are omitted. Some block
diagrams in the accompanying drawings illustrate functional entities and do not
necessarily correspond to physically or logically independent entities.
[0048] This illustrative embodiment provides an intelligent training aiding
method for instructional cars. Referring to FIG. 1, the method may comprise:
[0049] S101: image information of a training field is acquired in real time through a camera disposed above the training field, and the image information of the training field is uploaded into a machine learning model.
[0050] S102: an image of the training field is detected by a target detection model pre-established in the machine learning model to determine the type of the training field and to determine whether or not there is an instructional car in the image of the training field, wherein the machine learning model detects the image of the training field by means of a pre-established instructional car target detection model based on deep learning.
[0051] S103: if there is an instructional car in the image of the training field, multiple movement positions of the instructional car are calculated and analyzed by the machine learning model to generate a driving path based on the multiple movement positions.
[0052] S104: the machine learning model calculates and analyzes the driving path to determine whether or not the driving path deviates from a preset path, wherein the machine learning model is used after parameters are cured therein by learning and training multiple driving paths of the instructional car.
[0053] S105: if the driving path deviates from the preset path, the machine learning model generates correction information according to the degree of deviation of the driving path and sends the correction information to a receiving module on the instructional car.
[0054] S106: the receiving module sends the received correction information to a control module in the instructional car, and the control module controls the correction information to be displayed and broadcast in the instructional car, so that a learner can adjust personal driving actions according to the correction information to make the driving path close to the preset path, wherein the correction information includes voice prompt information and video demonstration information, and the video demonstration information is demonstrative animation information about a pre-turning direction and angle of a steering wheel in the instructional car.
[0055] S107: every time the instructional car completes one training subject, an actual driving path of the instructional car is stored in the machine learning model.
[0056] S108: the actual driving path stored in the machine learning model is compared with the preset path to generate path comparison information, and the path comparison information is sent to a terminal for timely correction of the learner.
[0057] According to the intelligent training aiding method for instructional cars, image information is captured in real time through a camera disposed above a training field and is uploaded to a machine learning model, then an actual driving path of the instructional car is calculated and analyzed through the machine learning model to obtain a deviation of the actual driving path from a preset path, and correction information is generated according to the deviation and can be displayed and broadcast in the instructional car in real time, so that a learner can visually adjust the turning direction and angle of the steering wheel according to video demonstrations in the correction information; a voice prompt is broadcast in the instructional car at the same time, so that the learner can correct personal driving actions under the combined action of the video demonstrations and voice prompt. The intelligent training aiding method can replace instructors to some extent to intelligently aid the learner in driving training and can improve the training level of the learner to a certain extent.
[0058] Below, the steps of the intelligent training aiding method for instructional cars in this illustrative embodiment will be described in further detail with reference to FIG. 1 to FIG. 6.
[0059] S101: image information of a training field is acquired in real time through a camera disposed above the training field, and the image information of the training field is uploaded into a machine learning model.
[0060] Illustratively, the camera is fixedly disposed above the training field; when a learner carries out training for the second subject of the driver test, the camera above the training field will be started to acquire image information of the training field in real time and upload the acquired image information of the training field to the machine learning model, wherein the image information may be, but is not limited to, image frame data. The machine learning model reads the data, namely collects the data, and then processes and corrects the data in advance such as through feature extraction, feature dimension reduction, feature null-value processing, feature transformation, feature normalization, target null-value processing and target value transformation; in the model test stage, the data can be classified in advance through a cross validation method; after the data is processed, a training model is established by means of the processed data, and the model can be evaluated by different parameters such as score, precision rate and recall ratio. Specific details can be understood with reference to the prior art and will not be detailed anymore here.
[0061] S102: an image of the training field is detected by a target detection model pre-established in the machine learning model to determine the type of the training field and to determine whether or not there is an instructional car in the image of the training field, wherein the machine learning model detects the image of the training field by means of a pre-established instructional car target detection model based on deep learning.
[0062] Illustratively, the instructional car target detection model based on deep learning can be established through the following steps: an instructional car target detection deep-learning network is established, wherein the instructional car target detection deep-learning network comprises an instructional car feature extractor formed by eight convolutional layers, eight ReLU activation layers and three pooling layers, and a first convolutional layer and a second convolutional layer connected to the instructional car feature extractor; image samples of the training field under different angles, illuminations and image qualities are obtained; an area where the instructional car starts training is marked out in each image sample of the training field through a rectangular box, and coordinate information of the rectangular frame is recorded; an instructional car target detection training dataset is generated with each image sample of the training field and the coordinate information of the rectangular box in the image sample of the training field as a set of training data; the instructional car target detection deep-learning network is trained by means of the generated instructional car target detection training datasets, and the instructional car target detection model based on deep learning is obtained after parameter updating. Specific details can be understood with reference to the prior art. After an image of the training field is detected by the target detection model, the type of the training field will be obtained. In one example, the type of the training field includes: a reverse parking training subject, a parallel parking training subject, a zigzag driving training subject and a left or right turning training subject. The intelligent training aiding method provided by this embodiment can be used for training of each of these subjects.
[0063] S103: if there is an instructional car in the image of the training field, multiple movement positions of the instructional car are calculated and analyzed by the machine learning model to generate a driving path based on the multiple movement positions.
[0064] Illustratively, the machine learning model can receive image information of the training field acquired by the camera in real time. In the case where there is an instructional car in the training field, parameters can be cured in the machine learning model for use by means of a large number of positive and negative samples of the instructional car, wherein the positive samples are samples corresponding to a category to be correctly sorted out, and in this embodiment, the positive samples are the instructional car in the image information, the negative samples are other objects, except the instructional car, in the training field such as cement grounds, grass lawns and yellow lines; the machine learning model calculates and analyzes multiple received movement positions of the instructional car to generate a driving path based on the multiple movement positions. For example, when the learner carries out training in the field for reverse parking, the camera uploads acquired image frames to the machine learning model, and the machine learning model calculates and processes each image frame to form a driving path together with the previous image frame and previous images. In this way, the driving path is generated at the moment the learner backs up the instructional car, and changes along with the movement of the instructional car.
[0065] S104: the machine learning model calculates and analyzes the
driving path to determine whether or not the driving path deviates from a preset path,
wherein the machine learning model is used after parameters are cured therein by
learning and training multiple driving paths of the instructional car.
[0066] Illustratively, the machine learning model is used after parameters
are cured therein by learning and training multiple driving paths of the instructional
car, that is to say, after being trained by a large number of samples, the machine
learning model can figure out how the instructional car should be driven to be
reversely parked successfully or how to adjust the turning direction and angle of the
steering wheel to reversely park the instructional car under the condition where the
instructional car deviates from an original path, and this adjustment is converted into
speeches to aiding the learner in training. As shown in FIG. 4, when the learner drives
the instructional car for reverse-parking training, the machine learning model will
calculate and analyze the driving path of the instructional car according to captured
image information and will determine whether or not the driving path deviates from a
preset path, at this moment, the machine learning model will supervise the learner like
an instructor; when the driving path is different from a common path, the instructor
will timely remind the learner to adjust the direction to keep the instructional car close
to the common path.
[0067] S105: if the driving path deviates from the preset path, the machine learning model generates correction information according to the degree of deviation of the driving path and sends the correction information to a receiving module on the instructional car.
[0068] Illustratively, if the machine learning model finds by calculation that the driving path of the instructional car deviates from the preset path or the learner will fail in the training subject along the current driving path, the machine learning model will generate correction information according to the degree of deviation of the driving path from the preset path and send the correction information to the instructional car. For example, when carrying out training for reverse parking, if the learner turns the steering wheel too early, the instructional car will inevitably roll on lines of a target parking space along the current path; at this moment, the machine learning model will generate correction information by calculation and analysis and send the correction information to the receiving module on the instructional car to prompt the learner to adjust the direction.
[0069] S106: the receiving module sends the received correction information to a control module in the instructional car, and the control module controls the correction information to be displayed and broadcast in the instructional car, so that a learner can adjust personal driving actions according to the correction information to make the driving path close to the preset path, wherein the correction information includes voice prompt information and video demonstration information, and the video demonstration information is demonstrative animation information about a pre-turning direction and angle of the steering wheel in the instructional car.
[0070] Illustratively, the control module is disposed in the instructional car and is used for controlling a display screen in the instructional car to display the correction information and controlling a speaker in the car to broadcast the voice prompt. For example, when carrying out training for reverse parking, if the learner turns the steering wheel too early, the instructional car will inevitably roll on lines of a target parking space along the current path, and the learner will fail in this training subject; at this moment, the machine learning model will generate correction information by calculation and analysis and send the correction information to the receiving module on the instructional car, the receiving module sends the correction information to the control module in the car, and the control module controls the display screen to display the correction information. As shown in FIG. 3, contents displayed on the display screen includes video demonstration information in the correction information, the video demonstration information is specifically about a pre-turning direction and angle of the steering wheel in the instructional car, and the turning direction of the steering wheel is marked out by an arrow. By displaying a video on the display screen, the leaner can be instructed how to operate the steering wheel more visually, and the training efficiency of the learner is improved; moreover, the instructional car will give a voice prompt according to the voice prompt information in the correction information, such as "turn the steering wheel back by half a circle". After the instructional car travels along this path by a certain distance, the machine learning model will generate another correction information by calculation and analysis and sends the correction information to the instructional car, at this moment, a video animation about a different turning angle and direction of the steering wheel will be displayed on the display screen, a voice prompt such as "turn the steering wheel rightward to the end", and under the combined action of the video prompt displayed on the display screen and the voice prompt, the learner can correctly park the instructional car in the parking space. It should be noted that the voice prompt information in the correction information can be selected and set according to the actual condition and is not limited to those mentioned in this embodiment.
[0071] S107: every time the instructional car completes one training subject, an actual driving path of the instructional car is stored in the machine learning model; S108: the actual driving path stored in the machine learning model is compared with the preset path to generate path comparison information, and the path comparison information is sent to a terminal for timely correction of the learner.
[0072] Illustratively, as shown in FIG. 5 and FIG. 6, every time the learner
completes a training subject, an actual driving path of the training car will be stored in
a storage module in the machine learning model and will be compared with the preset
path to generate path comparison information. In one example, the path comparison
information is video comparison information of an actual driving video of the
instructional car and a preset virtual driving video of the instructional car. Specifically,
the camera disposed above the training field can acquire the actual path of the
instructional car in a training subject to obtain a video, namely the actual driving
video of the instructional car, and the video is stored and is compared with the preset
virtual driving video of the instructional car by a comparison module to generate a
comparison video which is sent to a terminal such as a mobile phone of the learner, so
that the learner can more visually realize his/her own driving problems during training
by watching the path comparison video.
[0073] After S103, the training aiding method further comprises:
[0074] S1031: in the process of completing the training subject by the
instructional car, the driving speed of the instructional car is monitored in real time,
and whether or not the driving speed is within a preset range is determined;.
[0075] S1032: if the driving speed exceeds the preset range, a prompt
message is generated and is sent to the instructional car.
[0076] Illustratively, during a test of the second subject, particularly during
reverse parking and parallel parking, the learner can adjust the state of the car more
easily by decreasing the speed of the car, so in the process of completing this training
subject, the driving speed of the instructional car can be monitored in real time, and
whether or not the driving speed is within a preset range is determined. For example,
the instructional car will give a voice prompt to remind the learner to slow down when
the driving speed of the instructional car is over 5km/h. The preset range can be set
according to the actual condition, and the invention has no limitation in this aspect.
[0077] After S104, the training aiding method further comprises:
[0078] S1041: when the driving path of the instructional car deviates from
the preset path beyond a preset deviation and the machine learning model recognizes
that the instructional car is under a dangerous condition, a brake signal is sent to the
instructional car to control the instructional car to stop in time.
[0079] Illustratively, in the driving training process of the learner, to
prevent an accident such as the situation where the instructional car is out of control
due to mistaken slam on the brake, the machine learning model will determine that the
instructional car is under a dangerous condition when the instructional car deviates
from the preset path excessively or abnormally, and send a brake signal to the
receiving module in the instructional car, and a brake module in the instructional car
will receive the brake signal sent from the receiving module to control the
instructional car to stop, so that the safety of the learner in the driving training process
is guaranteed.
[0080] This illustrative embodiment further provides an intelligent training
aiding system for instructional cars. Referring to FIG. 2, the system may comprise a
camera module, a machine learning model, an instructional car module and a
comparison module.
[0081] The camera module is disposed above a training field and used for
acquiring image information of the training field in real time and uploading the image
information of the training field into a machine learning model;
[0082] The machine learning model is used for detecting an image of the
training field through a target detection model pre-established in the machine learning
model to determine the type of the training field and determine whether or not there is
an instructional car in the image of the training field, wherein the machine learning
model detects the image of the training field by means of a pre-established instructional car target detection model based on deep learning; if there is an instructional car in the image of the training field, the machine learning model calculates and analyzes multiple movement positions of the instructional car to generate a driving path based on the multiple movement positions;
[0083] The machine learning model is used for calculating and analyzing
the driving path to determine whether or not the driving path deviates from a preset
path, wherein the machine learning model is used after parameters are cured therein
by learning and training multiple driving paths of the instructional car; if the driving
path deviates from the preset path, the machine learning model generates correction
information according to the degree of deviation of the driving path and sends the
correction information to a receiving module on the instructional car; every time the
instructional car completes one training subject, an actual driving path of the
instructional car is stored in the machine learning model.
[0084] The instructional car module is used for sending the received
correction information to the control module in the instructional car, and the control
module is used controlling the correction information to be displayed and broadcast in
the instructional car, so that a learner in the instructional car can adjust personal
driving actions according to the correction information to make the driving path close
to the preset path; the correction information includes voice prompt information and
video demonstration information, and the video demonstration information is
demonstrative animation information about a pre-turning direction and angle of a
steering wheel of the instructional car.
[0085] The comparison module is used for comparing the actual driving
path stored in the machine learning model with the preset path to generate path
comparison information and sending the path comparison information to a terminal
for timely correction of the learner.
[0086] The specific implementation of the system can be understood with reference to the above embodiment and will not be detailed anymore here.
[0087] In one example, the machine learning module is used for monitoring the driving speed of the instructional car in real time in the process of completing the training subject by the instructional car, determining whether or not the driving speed is within a preset range, generating a prompt message when the driving speed exceeds the preset range, and sending the prompt message to the instructional car.
[0088] In one example, the machine learning model is also used for sending a brake signal to the instructional car to control the instructional car to stop in time when the driving path of the instructional car deviates from the preset path beyond a preset deviation and the machine learning model recognizes that the instructional car is under a dangerous condition.
[0089] In one example, the path comparison information is video comparison information of an actual driving video of the instructional car and a preset virtual driving video of the instructional car.
[0090] In one example, the type of the training field includes: a reverse parking training subject, a parallel parking training subject, a zigzag driving training subject and a left or right turning training subject.
[0091] According to the intelligent training aiding method and system for instructional cars, image information is captured in real time through a camera disposed above a training field and is uploaded to a machine learning model, then an actual driving path of the instructional car is calculated and analyzed through the machine learning model to obtain a deviation of the actual driving path from a preset path, and correction information is generated according to the deviation and can be displayed and broadcast in the instructional car in real time, so that a learner can visually adjust the turning direction and angle of the steering wheel according to video demonstrations in the correction information; a voice prompt is broadcast in the instructional car at the same time, so that the learner can correct personal driving actions under the combined action of the video demonstrations and voice prompt. The intelligent training aiding method can replace instructors to some extent to intelligently aid the learner in driving training and can improve the training level of the learner to a certain extent.
[0092] It should be noted that the terms such as "central", "lengthwise", "crosswise", "length", "width", "thickness", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise" and "anticlockwise" in the above description are used to indicate directional or positional
relations on the basis of the drawings merely for the purpose of facilitating and simplifying the description of the embodiments of the invention, do not indicate or imply that devices or elements referred to must be in a specific direction or must be configured or operated in a specific direction, and thus should not be construed as limitations of the embodiments of the invention.
[0093] In addition, the terms "first" and "second" are merely for the purpose of description, should not be construed as indications or implications of relative importance or implicit indications of the number of technical features referred to. Thus, in case where a feature defined by "first" or "second", it may explicitly or implicitly indicate that one or more said features are included. In the description of the embodiments of the invention, "multiple" refers to two or more, unless otherwise specifically defined.
[0094] In the embodiments of the invention, unless otherwise expressly stated or defined, the terms such as "install", "link", "connect" and "fix" should be broadly understood. For example, "connect" may refer to fixed connection, detachable connection or integral connection, or mechanical connection or electrical connection, or direct connection or indirect connection via an intermediate, or internal communication of two elements or interaction of two elements. Those ordinarily skilled in the art can appreciate the specific meaning of these terms in the invention as the case may be.
[0095] In the embodiments of the invention, unless otherwise expressly
stated or defined, the expression that a first feature is located "above" or "below" a
second feature may include the case where the first feature directly makes contact
with the second feature and the case where the first feature makes contact with the
second feature through another feature rather than directly making contact with the
second feature. In addition, the expression that a first feature is located "over" or
"above" a second feature or located on an "upper side" of the second feature means
that the first feature is located over or above the second feature or means that the first
feature is horizontally higher than the second feature. The expression that a first
feature is located "under" or "below" a second feature or located on a "lower side" of
a second feature means that the first feature is located under or below the second
feature or means that the first feature is horizontally lower than the second feature.
[0096] In the specification, the description of the reference term "one
embodiment", "some embodiments", "example", "specific example" or "some
examples" is intended to point out that the specific features, structures, materials of
characteristics incorporated in said embodiment or example are included in at least
one embodiment or example of the invention. In this specification, the illustrative
description of this term does not necessarily refer to one embodiment or example. In
addition, the specific features, structures, materials or characteristics referred to may
be incorporated in one or more embodiments or examples in any suitable manners.
Moreover, those skilled in the art can integrate and combine different embodiments or
examples described in this specification.
[0097] By reading the specification and implementing the invention, those
skilled in the art can easily come up with other embodiments of the invention. The
application is intended to include any transformations, usage, or adaptive variations of
the invention, which follow the basic principle of the invention and include common
knowledge or technical means, not disclosed by the invention, of the prior art. The specification and embodiments are merely for an illustrative purpose, and the essential scope and spirit of the invention should be defined by the appended claims.
Claims (12)
1. An intelligent training aiding method for instructional cars, comprising:
acquiring image information of a training field in real time through a camera
disposed above the training field, and uploading the image information of the training
field into a machine learning model;
detecting an image of the training field by a target detection model
pre-established in the machine learning model to determine the type of the training
field and determine whether or not there is an instructional car in the image of the
training field;
wherein, the machine learning model detects the image of the training field
by means of a pre-established instructional car target detection model based on deep
learning;
if there is an instructional car in the image of the training field, calculating
and analyzing multiple movement positions of the instructional car by the machine
learning model to generate a driving path based on the multiple movement positions;
calculating and analyzing the driving path by the machine learning model to
determine whether or not the driving path deviates from a preset path;
wherein, the machine learning model is used after parameters are cured
therein by learning and training multiple driving paths of the instructional car;
if the driving path deviates from the preset path, generating correction
information according to the degree of deviation of the driving path, and sending the
correction information to a receiving module on the instructional car, by the machine
learning model;
sending the correction information to a control module in the instructional car
by the receiving module, and controlling the correction information to be displayed
and broadcast in the instructional car by the control module, so that a learner can
adjust personal driving actions according to the correction information to make the
driving path close to the preset path;
wherein, the correction information includes voice prompt information and video demonstration information, and the video demonstration information is demonstrative animation information about a pre-turning direction and angle of a steering wheel in the instructional car;
2. The intelligent training aiding method for instructional cars according to Claim 1, further comprising: in the process of completing a training subject by the instructional car, monitoring a driving speed of the instructional car in real time and determining whether or not the driving speed is within a preset range; and if the driving speed exceeds the preset range, generating a prompt message, and sending the prompt message to the instructional car.
3. The intelligent training aiding method for instructional cars according to Claim 2, further comprising: when the driving path of the instructional car deviates from the preset path beyond a preset deviation and the machine learning model recognizes that the instructional car is under a dangerous condition, sending a brake signal to the instructional car to control the instructional car to stop in time.
4. The intelligent training aiding method for instructional cars according to Claim 1, further comprising: every time the instructional car completes one training subject, storing an actual driving path of the instructional car in the machine learning model; comparing the actual driving path stored in the machine learning model with the preset path to generate path comparison information, and sending the path comparison information to a terminal for timely correction of the learner.
5. The intelligent training aiding method for instructional cars according to Claim 4, wherein the path comparison information is video comparison information of an actual driving video of the instructional car and a preset virtual driving video of the instructional car.
6. The intelligent training aiding method for instructional cars according to
Claim 1, wherein the type of the training field includes: a reverse parking training
subject, a parallel parking training subject, a zigzag driving training subject and a left
or right turning training subject.
7. An intelligent training aiding system for instructional cars, comprising:
a camera module disposed above a training field and used for acquiring
image information of the training field in real time and uploading the image
information of the training field into a machine learning model;
the machine learning model used for detecting an image of the training field
by a target detection model pre-established in the machine learning model to
determine the type of the training field and determine whether or not there is an
instructional car in the image of the training field, wherein the machine learning
model detects the image of the training field by means of a pre-established
instructional car target detection model based on deep learning; if there is an
instructional car in the image of the training field, the machine learning model
calculates and analyzes multiple movement positions of the instructional car to
generate a driving path based on the multiple movement positions;
the machine learning model is used for calculating and analyzing the driving
path to determine whether or not the driving path deviates from a preset path, wherein
the machine learning model is used after parameters are cured therein by learning and
training multiple driving paths of the instructional car; if the driving path deviates
from the preset path, the machine learning model generates correction information
according to the degree of deviation of the driving path and sends the correction
information to a receiving module on the instructional car; every time the instructional
car completes one training subject, an actual driving path of the instructional car is
stored in the machine learning model;
J an instructional car module comprising a receiving module and a control module, wherein the receiving module is used for sending the received correction information to the control module in the instructional car, and the control module is used controlling the correction information to be displayed and broadcast in the instructional car, so that a learner in the instructional car can adjust personal driving actions according to the correction information to make the driving path close to the preset path; the correction information includes voice prompt information and video demonstration information, and the video demonstration information is demonstrative animation information about a pre-turning direction and angle of a steering wheel in the instructional car.
8. The intelligent training aiding system for instructional cars according to Claim 7, wherein the machine learning module is used for monitoring a driving speed of the instructional car in real time in the process of completing the training subject by the instructional car, determining whether or not the driving speed is within a preset range, generating a prompt message when the driving speed exceeds the preset range, and sending the prompt message to the instructional car.
9. The intelligent training aiding system for instructional cars according to Claim 8, wherein the machine learning model is also used for sending a brake signal to the instructional car to control the instructional car to stop in time when the driving path of the instructional car deviates from the preset path beyond a preset deviation and the machine learning model recognizes that the instructional car is under a dangerous condition.
10. The intelligent training aiding system for instructional cars according to Claim 7, further comprising: a comparison module used for comparing the actual driving path stored in the machine learning model with the preset path to generate path comparison information and sending the path comparison information to a terminal for timely correction of the learner.
11. The intelligent training aiding system for instructional cars according to
Claim 10, wherein the path comparison information is video comparison information
of an actual driving video of the instructional car and a preset virtual driving video of
the instructional car.
12. The intelligent training aiding system for instructional cars according to
Claim 7, wherein the type of the training field includes: a reverse parking training
subject, a parallel parking training subject, a zigzag driving training subject and a left
or right turning training subject.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010696315.X | 2020-07-20 | ||
| CN202010696315.XA CN111667742A (en) | 2020-07-20 | 2020-07-20 | Intelligent auxiliary training method and system for learner-driven vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2020104282A4 true AU2020104282A4 (en) | 2021-04-15 |
Family
ID=72392693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2020104282A Active AU2020104282A4 (en) | 2020-07-20 | 2020-12-23 | Intelligent Training Aiding Method And System For Instructional Cars |
Country Status (5)
| Country | Link |
|---|---|
| CN (1) | CN111667742A (en) |
| AU (1) | AU2020104282A4 (en) |
| SE (1) | SE2051569A1 (en) |
| WO (1) | WO2022016583A1 (en) |
| ZA (1) | ZA202007882B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114399932A (en) * | 2021-12-28 | 2022-04-26 | 南京财经大学 | Talent training simulation training system based on intelligent learning |
| CN116645848A (en) * | 2023-04-17 | 2023-08-25 | 武汉未来幻影科技有限公司 | Vehicle operation control method and related equipment |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112201113A (en) * | 2020-10-21 | 2021-01-08 | 广东星唯信息技术有限公司 | Method for monitoring backing and warehousing of learner-driven vehicle by RTK mapping technology |
| CN114822169B (en) * | 2022-05-06 | 2023-06-09 | 辽宁科技大学 | Auxiliary driving exercise method and device for learner-driven vehicle |
| US11643108B1 (en) * | 2022-06-23 | 2023-05-09 | Motional Ad Llc | Generating corrected future maneuver parameters in a planner |
| CN115578914B (en) * | 2022-11-23 | 2023-03-14 | 湖南视觉伟业智能科技有限公司 | Training system and method for backing in place during driving training |
| CN116729422B (en) * | 2023-06-07 | 2024-03-08 | 广州市德赛西威智慧交通技术有限公司 | Deviation correction method for vehicle track, vehicle driving assistance method and device |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8930227B2 (en) * | 2012-03-06 | 2015-01-06 | State Farm Mutual Automobile Insurance Company | Online system for training novice drivers and rating insurance products |
| CN105590449B (en) * | 2015-12-29 | 2017-12-12 | 南京邮电大学 | A kind of learner-driven vehicle traveling monitoring system and monitoring method |
| CN208376741U (en) * | 2017-03-24 | 2019-01-15 | 多伦科技股份有限公司 | A kind of intelligent robot coach DAS (Driver Assistant System) |
| CN108109481A (en) * | 2017-12-21 | 2018-06-01 | 云南冲浪科技有限公司 | A kind of vehicle driver training intelligent coach system |
| CN108389477A (en) * | 2018-03-05 | 2018-08-10 | 广州星唯信息科技有限公司 | A kind of correction guidance method for driving training field training |
| CN108806371B (en) * | 2018-08-31 | 2020-06-26 | 成都的卢青创网络科技有限公司 | Intelligent judgment method and system based on driving test subject training |
| CN109272821A (en) * | 2018-10-22 | 2019-01-25 | 广州星唯信息科技有限公司 | A kind of place driving evaluation method based on high-precision vision positioning |
| CN110599853B (en) * | 2019-08-05 | 2022-07-05 | 深圳华桥智能设备科技有限公司 | Intelligent teaching system and method for driving school |
| CN111047948B (en) * | 2019-11-27 | 2022-06-10 | 康忠文 | Auxiliary method and system for learning to train |
-
2020
- 2020-07-20 CN CN202010696315.XA patent/CN111667742A/en active Pending
- 2020-07-28 SE SE2051569A patent/SE2051569A1/en not_active Application Discontinuation
- 2020-07-28 WO PCT/CN2020/105268 patent/WO2022016583A1/en active Application Filing
- 2020-12-17 ZA ZA2020/07882A patent/ZA202007882B/en unknown
- 2020-12-23 AU AU2020104282A patent/AU2020104282A4/en active Active
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114399932A (en) * | 2021-12-28 | 2022-04-26 | 南京财经大学 | Talent training simulation training system based on intelligent learning |
| CN116645848A (en) * | 2023-04-17 | 2023-08-25 | 武汉未来幻影科技有限公司 | Vehicle operation control method and related equipment |
| CN116645848B (en) * | 2023-04-17 | 2024-06-11 | 武汉未来幻影科技有限公司 | Vehicle operation control method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| ZA202007882B (en) | 2021-09-29 |
| WO2022016583A1 (en) | 2022-01-27 |
| CN111667742A (en) | 2020-09-15 |
| SE2051569A1 (en) | 2022-01-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020104282A4 (en) | Intelligent Training Aiding Method And System For Instructional Cars | |
| CN106710360B (en) | Intelligent driving training system and method based on enhancing virtual reality human-computer interaction | |
| CN107895244A (en) | Classroom teaching quality assessment method | |
| CN106228293A (en) | teaching evaluation method and system | |
| CN108806371B (en) | Intelligent judgment method and system based on driving test subject training | |
| CN107067879A (en) | A kind of intelligent Piano Teaching system | |
| CN113723250B (en) | Intelligent analysis method and system for assisting teacher in retrospective growth in class | |
| CN113139885A (en) | Teaching management system and management method thereof | |
| CN108182649A (en) | For the intelligent robot of Teaching Quality Assessment | |
| CN109830132A (en) | A kind of foreign language language teaching system and teaching application method | |
| CN110827856A (en) | Evaluation method for teaching | |
| CN111796676A (en) | AI (Artificial intelligence) interactive auxiliary learning system and learning method | |
| CN114422820A (en) | Education interactive live broadcast system and live broadcast method | |
| CN110930781B (en) | Recording and broadcasting system | |
| CN111402671A (en) | Driving school driving language audio and video teaching method and device | |
| CN111522877B (en) | Online synchronous processing system for education courses | |
| CN118260480A (en) | Teaching course recommendation method | |
| CN114821016A (en) | Unmanned automatic intelligent body measurement equipment and intelligent body measurement method thereof | |
| CN112801526B (en) | Driving training cheating supervision system and method based on biological identification cross authentication | |
| CN107832976B (en) | Classroom teaching quality analysis system based on perception analysis | |
| CN116341983A (en) | Concentration evaluation and early warning method, system, electronic equipment and medium | |
| CN113506196A (en) | One-way video interaction based simulated driving training course making method | |
| CN112750057A (en) | Student learning behavior database establishing, analyzing and processing method based on big data and cloud computing and cloud data platform | |
| CN115409413A (en) | Multi-source data management method, system and storage medium for student teaching and research | |
| CN112951019A (en) | Presentation method for ideological and political education |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) |