CN109572816A - A kind of steering order processing method and vehicle - Google Patents
A kind of steering order processing method and vehicle Download PDFInfo
- Publication number
- CN109572816A CN109572816A CN201811639547.0A CN201811639547A CN109572816A CN 109572816 A CN109572816 A CN 109572816A CN 201811639547 A CN201811639547 A CN 201811639547A CN 109572816 A CN109572816 A CN 109572816A
- Authority
- CN
- China
- Prior art keywords
- steering
- time
- image data
- steering order
- sample
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
- B62D15/025—Active steering aids, e.g. helping the driver by actively influencing the steering system after environment evaluation
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The embodiment of the present invention provides a kind of steering order processing method and vehicle, this method comprises: acquisition image data；Described image data are input to steering model processing, to predict the steering order of object time, wherein, the object time specific duration more late than the acquisition time of described image data, the specific duration is corresponding with response delay, and the response delay is the time delay that the steering order predicted time responds the steering order to steering wheel；The steering order is transmitted to the steering wheel, so that the steering wheel responds the steering order.The steering behaviour of vehicle can be improved in the embodiment of the present invention.
Description
Technical field
The present invention relates to automatic Pilot technical field more particularly to a kind of steering order processing method and vehicles.
Background technique
With the rapid development of depth learning technology and the further investigation of artificial intelligence, vehicle is from pilot steering at present
It is changed to the trend of automatic Pilot.Wherein, realize that automatic Pilot is current automatic Pilot by deep learning end to end
One main direction of studying in field.However, current vehicle, which responds the steering order to steering wheel from prediction steering order, to be deposited
In time delay, because steering order needs are transferred to steering wheel in vehicle.In this way, causing Vehicular turn performance poor.
Summary of the invention
The embodiment of the present invention provides a kind of steering order processing method and vehicle, poor to solve Vehicular turn performance
Problem.
The embodiment of the present invention provides a kind of steering order processing method, is applied to vehicle, comprising:
Acquire image data；
Described image data are input to steering model processing, to predict the steering order of object time, wherein the mesh
Time specific duration more late than the acquisition time of described image data is marked, the specific duration is corresponding with response delay, the response
Time delay is the time delay that the steering order predicted time responds the steering order to steering wheel；
The steering order is transmitted to the steering wheel, so that the steering wheel responds the steering order.
Optionally, the steering model be input be image data output be steering order end to end model, described turn
Include: to the training sample data of model
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering refers to
The predicted time of the order specific duration more late than the acquisition time of the sample image data.
Optionally, the sample image data and the sample steering order are chosen from data acquisition system, wherein institute
State includes multiple image data and multiple steering orders in data acquisition system, wherein the predicted time of the multiple steering order
The acquisition time of the respectively equal to described multiple image data.
Optionally, the specific duration be equal to N number of image time-consuming total duration, wherein the response delay with it is described N number of
The total duration of image time-consuming matches, and described image time-consuming is the inverse for the frequency that the steering model handles image data, the N
For more than or equal to 1 integer.
Optionally, the N is equal to the integer that response delay is obtained divided by described image time-consuming；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
The embodiment of the present invention also provides a kind of vehicle, comprising:
Acquisition module, for acquiring image data；
Processing module, for described image data to be input to steering model processing, to predict that the steering of object time refers to
It enables, wherein the object time specific duration more late than the acquisition time of described image data, the specific duration and response delay
Corresponding, the response delay is the time delay that the steering order predicted time responds the steering order to steering wheel；
Execution module, for transmitting the steering order to the steering wheel, so that the steering wheel responds the steering
Instruction.
Optionally, the steering model be input be image data output be steering order end to end model, described turn
Include: to the training sample data of model
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering refers to
The predicted time of the order specific duration more late than the acquisition time of the sample image data.
Optionally, the sample image data and the sample steering order are chosen from data acquisition system, wherein institute
State includes multiple image data and multiple steering orders in data acquisition system, wherein the predicted time of the multiple steering order
The acquisition time of the respectively equal to described multiple image data.
Optionally, the specific duration be equal to N number of image time-consuming total duration, wherein the response delay with it is described N number of
The total duration of image time-consuming matches, and described image time-consuming is the inverse for the frequency that the steering model handles image data, the N
For more than or equal to 1 integer.
Optionally, the N is equal to the integer that response delay is obtained divided by described image time-consuming；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
The embodiment of the present invention also provides a kind of vehicle, including processor, memory and is stored on the memory and can
The computer program run on the processor realizes that the present invention is implemented when the computer program is executed by the processor
The step of steering order processing method that example provides.
The embodiment of the present invention also provides a kind of computer readable storage medium, stores on the computer readable storage medium
There is computer program, the computer program realizes steering order processing side provided in an embodiment of the present invention when being executed by processor
The step of method.
In the embodiment of the present invention, image data is acquired；Described image data are input to steering model processing, to predict mesh
Mark the steering order of time, wherein the object time specific duration more late than the acquisition time of described image data, it is described specific
Duration is corresponding with response delay, and the response delay responds the steering order for the steering order predicted time to steering wheel
Time delay；The steering order is transmitted to the steering wheel, so that the steering wheel responds the steering order.Due to predicting mesh
The steering order for marking the time, so as to reduce influence of the above-mentioned response delay to steering order, to improve the steering of vehicle
Performance.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, needed in being described below to the embodiment of the present invention
Attached drawing to be used is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention,
For those of ordinary skill in the art, without any creative labor, it can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of flow chart of steering order processing method provided in an embodiment of the present invention；
Fig. 2 is a kind of structure chart of vehicle provided in an embodiment of the present invention；
Fig. 3 is the structure chart of another vehicle provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Term " includes " and its any deformation in the description and claims of this application, it is intended that covering
Non-exclusive includes, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to clearly
Those of list to Chu step or unit, but may include be not clearly listed or for these process, methods, product or
The intrinsic other step or units of equipment.In addition, indicating institute's connecting object using "and/or" in specification and claim
At least one, such as A and/or B, indicate to include independent A, independent B and A and B have three kinds of situations.
In embodiments of the present invention, " illustrative " or " such as " etc. words for indicate make example, illustration or explanation.This
Be described as in inventive embodiments " illustrative " or " such as " any embodiment or design scheme be not necessarily to be construed as comparing
Other embodiments or design scheme more preferably or more advantage.Specifically, use " illustrative " or " such as " etc. words purport
Related notion is being presented in specific ways.
Referring to Figure 1, Fig. 1 is a kind of flow chart of steering order processing method provided in an embodiment of the present invention, this method
Applied to vehicle, as shown in Figure 1, comprising the following steps:
Step 101, acquisition image data.
Wherein, the image data that above-mentioned acquisition image data vehicle is acquired by the camera installed on vehicle, such as: on
Camera acquisition video data is stated, and above-mentioned image data can be a certain frame image data in the video data.
It should be noted that above-mentioned vehicle, which can be autonomous driving vehicle or other, to be led in the embodiment of the present invention
The automobile for crossing image data prediction steering order, is not construed as limiting this embodiment of the present invention.
Described image data are input to steering model processing by step 102, to predict the steering order of object time,
In, the object time specific duration more late than the acquisition time of described image data, the specific duration is corresponding with response delay,
The response delay is the time delay that the steering order predicted time responds the steering order to steering wheel.
Wherein, above-mentioned steering model can be the end to end model obtained in advance, such as: the end-to-end mould of training in advance
Type, the mode input are that image data output is steering order.Preferably, corresponding steering is exported for every frame image data
Instruction.
Above-mentioned steering order can be the instruction for controlling wheel steering.
It should be noted that the steering order of above-mentioned object time can be, above-mentioned steering model output is used for
State the steering order that the object time turned to.And specific duration more late than the acquisition time of described image data of above-mentioned object time
It can be, the above-mentioned object time, there are the time migrations (offset) of above-mentioned specific duration with above-mentioned acquisition time.
Above-mentioned steering order predicted time to steering wheel respond the steering order time delay it is also understood that vehicle to
Steering wheel transmitting steering order (i.e. sending steering order) responds the time delay of the steering order, and the response delay to steering wheel
It may also be referred to as transverse response delay time.
It can be in addition, above-mentioned specific duration is corresponding with response delay, above-mentioned specific duration is identical as above-mentioned response delay
It is or close, wherein here close can be understood as the time difference of specific duration and above-mentioned response delay in particular range.
In addition, above-mentioned response delay, which can carry out response test to vehicle, obtains response delay.
Step 103, Xiang Suoshu steering wheel transmit the steering order, so that the steering wheel responds the steering order.
Step 103 can be when step 102 predicts above-mentioned steering order, transmit steering order to steering wheel, thus
Steering wheel responds the steering order.
Due to predicting the steering order of object time according to above-mentioned image data, and the object time is than described image data
The steering order of object time may be implemented similar in the object time or object time in acquisition time evening specific duration in this way
Moment is responded by steering wheel, that is to say, that look-ahead steering order, and the steering order is sent to steering wheel in advance, thus
The influence for even being eliminated above-mentioned response delay is reduced, to improve the steering behaviour of vehicle.
Such as: the acquisition time of above-mentioned image data is t, and it is above-mentioned specific when a length of offset=200ms, above-mentioned response
For time delay is 200ms, then the above-mentioned object time is t+200ms, i.e., predicts t+200ms according to the image data of t moment acquisition
Steering order, and transmit the steering order to steering wheel, the steering order for predicting the following 200ms may be implemented in this way, and mention
Forward direction disk transmits the instruction, to reduce the influence for even being eliminated above-mentioned response delay.
As an alternative embodiment, steering model described above be input be image data output be steering order
End to end model, the training sample data of the steering model include:
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering refers to
The predicted time of the order specific duration more late than the acquisition time of the sample image data.
Wherein, above-mentioned sample image data and the corresponding sample steering order of the sample image data it is to be understood that
A pair of of training sample [image_t, steering_ (t+offset)], wherein image_t indicates the picture number of time t acquisition
According to steering_ (t+offset) indicates the steering order of time t+offset.Above-mentioned training sample data may include multipair
Training sample, each pair of training sample are all satisfied the relationship of above-mentioned sample image data and sample steering order.
Above-mentioned steering model, which can be, is trained basic end to end model using above-mentioned training sample data, to obtain
Above-mentioned steering model.Such as: using above-mentioned sample image data as input, using above-mentioned sample steering order as legitimate reading,
In the training process, a prediction result, prediction result meeting compared with legitimate reading can be obtained from input terminal to output end
Obtain an error, this error can each layer of transmitting (such as: backpropagation) in a model, each layer can basis
This error adjusts, and restraining or get a desired effect until model just terminates, to obtain above-mentioned steering model.
It should be noted that being not construed as limiting to the training process of model, and training process can be in the embodiment of the present invention
It is to carry out in computer.Such as: training obtains above-mentioned steering model on computers, then the steering model is allocated to above-mentioned
Vehicle.Certainly, the smart machine training for being also not excluded for vehicle obtains above-mentioned steering model.
In the embodiment, due to using sample image data and above-mentioned sample steering order as training sample, thus
Can accurately train and obtain input is the steering model above-mentioned end to end that image data output is steering order.
Optionally, the sample image data and the sample steering order are chosen from data acquisition system, wherein institute
State includes multiple image data and multiple steering orders in data acquisition system, wherein the predicted time of the multiple steering order
The acquisition time of the respectively equal to described multiple image data.
Wherein, above-mentioned data acquisition system can be allocation of computer, or carries out the mode of testing etc. to test vehicle and obtain
Data acquisition system.Such as: above-mentioned data acquisition system includes following data:
Sample data t0- steering order t0；
Sample data t1- steering order t1；
Sample data t2- steering order t2；
Sample data t3- steering order t3；
Wherein, above-mentioned sample data t0- steering order t0 indicates to time acquired image data and to time prediction
Steering order, above-mentioned sample data t1- steering order t1 indicates t1 time acquired image data and t1 time prediction
Steering order is not listed one by one herein.
With it is above-mentioned specific when a length of t2 and t0 time difference, and above-mentioned specific duration is equal to for above-mentioned response delay, from
And above-mentioned sample image data and the sample steering order include:
Sample data t0 and steering order t2；
Sample data t1 and steering order t3.
It is trained in this way using these sample datas, so as to obtain exporting the steering of t2 according to the image data of to
Instruction, in this way when predicting the steering order, transmits the steering order to steering wheel, can make steering wheel should in t2 response
Steering order.
In the embodiment, it may be implemented to receive control (i.e. steering wheel response according to image data acquiring time and vehicle
Steering order) between offset, training data is provided, so as to more accurately training obtain input be image data export
For the steering model above-mentioned end to end of steering order.
As an alternative embodiment, above-mentioned specific duration is equal to the total duration of N number of image time-consuming, wherein described
Response delay is matched with the total duration of N number of image time-consuming, and described image time-consuming is that the steering model handles image data
Frequency inverse, the N be more than or equal to 1 integer.
In the embodiment, it can be vehicle and carry out response test, find out above-mentioned response delay, such as: it is used for
Steering_delay_time is indicated.And determining that the frequency of steering model processing image data is p, i.e. steering model is predicted
Frequency, and above-mentioned image time-consuming is 1/p, i.e. a frame image time-consuming is 1/p, wherein p can be using the second as unit, i.e., in one second
Handle the quantity of image data, or the quantity of referred to as one second interior prediction steering order.
And it may include as follows that above-mentioned response delay is matched with the total duration of N number of image time-consuming:
The N is equal to the integer that response delay is obtained divided by described image time-consuming；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
Specifically, above-mentioned N can be understood as the number that above-mentioned response delay accounts for image time-consuming, it should be noted that above-mentioned N
The integer and above-mentioned N to round up equal to response delay divided by described image time-consuming is equal to response delay divided by described
The integer that image time-consuming rounds up is it is to be understood that take from above-mentioned response delay except nearest image time-consuming number.With
Above-mentioned response delay is 200ms, and above-mentioned p is using the second as unit, and value is 10 citings, then above-mentioned 1/p is equal to 100ms, i.e., above-mentioned N etc.
In 2；Above-mentioned response delay be 190ms, above-mentioned p using the second as unit, value be 10 citing, then above-mentioned 1/p be equal to 100ms, then to
Upper rounding, i.e., above-mentioned N are equal to 2；Above-mentioned response delay is 120ms, and in seconds, value is 10 citings to above-mentioned p, then above-mentioned 1/
P is equal to 100ms, then is rounded downwards, i.e., above-mentioned N is equal to 1.
The total duration that above-mentioned N number of image time-consuming may be implemented in above-mentioned three kinds of modes is interpreted as, the offset of steering order, example
Such as: being used for steering_offset, it is preferred that steering_offset=steering_delay_time/ (1/p),
In, above-mentioned steering_delay_time indicates above-mentioned response delay.The steering order of i.e. above-mentioned object time can be understood as
Above-mentioned image data deviates N number of steering order backward.
In the embodiment, since the corresponding sample steering order of each sample image data can be obtained by offset, from
Without being individually for the corresponding sample steering order of each image data, and then trained complexity can be reduced.Such as: with
N is equal to for 2, and sample data t0 deviates 2 steering orders, to obtain steering order t2.
In the embodiment of the present invention, image data is acquired；Described image data are input to steering model processing, to predict mesh
Mark the steering order of time, wherein the object time specific duration more late than the acquisition time of described image data, it is described specific
Duration is corresponding with response delay, and the response delay responds the steering order for the steering order predicted time to steering wheel
Time delay；The steering order is transmitted to the steering wheel, so that the steering wheel responds the steering order.Due to predicting mesh
The steering order for marking the time, so as to reduce influence of the above-mentioned response delay to steering order, to improve the steering of vehicle
Performance.
Fig. 2 is referred to, Fig. 2 is a kind of structure chart of vehicle provided in an embodiment of the present invention, as shown in Fig. 2, vehicle 200,
Include:
Acquisition module 201, for acquiring image data；
Processing module 202, for described image data to be input to steering model processing, to predict the steering of object time
Instruction, wherein when the object time specific duration more late than the acquisition time of described image data, the specific duration and response
Prolong correspondence, the response delay is the time delay that the steering order predicted time responds the steering order to steering wheel；
Execution module 203 turns for transmitting the steering order to the steering wheel so that steering wheel response is described
To instruction.
Optionally, the steering model be input be image data output be steering order end to end model, described turn
Include: to the training sample data of model
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering refers to
The predicted time of the order specific duration more late than the acquisition time of the sample image data.
Optionally, the sample image data and the sample steering order are chosen from data acquisition system, wherein institute
State includes multiple image data and multiple steering orders in data acquisition system, wherein the predicted time of the multiple steering order
The acquisition time of the respectively equal to described multiple image data.
Optionally, the specific duration be equal to N number of image time-consuming total duration, wherein the response delay with it is described N number of
The total duration of image time-consuming matches, and described image time-consuming is the inverse for the frequency that the steering model handles image data, the N
For more than or equal to 1 integer.
Optionally, the N is equal to the integer that response delay is obtained divided by described image time-consuming；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
Vehicle provided in an embodiment of the present invention can be realized each process that vehicle is realized in the embodiment of the method for Fig. 1, and
It can achieve identical beneficial effect, to avoid repeating, which is not described herein again.
Fig. 3 is referred to, Fig. 3 is the structure chart of another vehicle provided in an embodiment of the present invention, as shown in figure 3, vehicle 300
Including processor 301, memory 302 and it is stored in the computer that can be run on the memory 302 and on the processor
Program.
Wherein, following steps are realized when the computer program is executed by the processor 301:
Acquire image data；
Described image data are input to steering model processing, to predict the steering order of object time, wherein the mesh
Time specific duration more late than the acquisition time of described image data is marked, the specific duration is corresponding with response delay, the response
Time delay is the time delay that the steering order predicted time responds the steering order to steering wheel；
The steering order is transmitted to the steering wheel, so that the steering wheel responds the steering order.
It should be noted that the above-mentioned acquisition image data that processor 301 executes, which can be processor 301, controls vehicle
Camera collection image data.
Optionally, the steering model be input be image data output be steering order end to end model, described turn
Include: to the training sample data of model
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering refers to
The predicted time of the order specific duration more late than the acquisition time of the sample image data.
Optionally, the sample image data and the sample steering order are chosen from data acquisition system, wherein institute
State includes multiple image data and multiple steering orders in data acquisition system, wherein the predicted time of the multiple steering order
The acquisition time of the respectively equal to described multiple image data.
Optionally, the specific duration be equal to N number of image time-consuming total duration, wherein the response delay with it is described N number of
The total duration of image time-consuming matches, and described image time-consuming is the inverse for the frequency that the steering model handles image data, the N
For more than or equal to 1 integer.
Optionally, the N is equal to the integer that response delay is obtained divided by described image time-consuming；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
Vehicle provided in an embodiment of the present invention can be realized each process that vehicle is realized in the embodiment of the method for Fig. 1, and
It can achieve identical beneficial effect, to avoid repeating, which is not described herein again.
The embodiment of the present invention also provides a kind of computer readable storage medium, stores on the computer readable storage medium
There is computer program, the computer program realizes steering order processing side provided in an embodiment of the present invention when being executed by processor
The step of method.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, service
Device, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form belongs within protection of the invention.
Claims (12)
1. a kind of steering order processing method is applied to vehicle characterized by comprising
Acquire image data；
Described image data are input to steering model processing, to predict the steering order of object time, wherein when the target
Between specific duration more late than the acquisition time of described image data, the specific duration is corresponding with response delay, the response delay
The time delay of the steering order is responded to steering wheel for the steering order predicted time；
The steering order is transmitted to the steering wheel, so that the steering wheel responds the steering order.
2. the method as described in claim 1, which is characterized in that the steering model be input be image data output be steering
The training sample data of the end to end model of instruction, the steering model include:
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering order
The predicted time specific duration more late than the acquisition time of the sample image data.
3. method according to claim 2, which is characterized in that the sample image data and the sample steering order be from
It is chosen in data acquisition system, wherein include multiple image data and multiple steering orders in the data acquisition system, wherein institute
The predicted time for stating multiple steering orders is respectively equal to the acquisition time of the multiple image data.
4. method according to any one of claims 1 to 3, which is characterized in that it is time-consuming that the specific duration is equal to N number of image
Total duration, wherein the response delay is matched with the total duration of N number of image time-consuming, and described image time-consuming is described turns
To the inverse of the frequency of model treatment image data, the N is more than or equal to 1 integer.
5. method as claimed in claim 4, which is characterized in that the N is equal to response delay and obtains divided by described image time-consuming
Integer；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
6. a kind of vehicle characterized by comprising
Acquisition module, for acquiring image data；
Processing module, for described image data to be input to steering model processing, to predict the steering order of object time,
In, the object time specific duration more late than the acquisition time of described image data, the specific duration is corresponding with response delay,
The response delay is the time delay that the steering order predicted time responds the steering order to steering wheel；
Execution module, for transmitting the steering order to the steering wheel, so that the steering wheel responds the steering order.
7. vehicle as claimed in claim 6, which is characterized in that the steering model be input be image data output be steering
The training sample data of the end to end model of instruction, the steering model include:
Sample image data and the corresponding sample steering order of the sample image data, wherein the sample steering order
The predicted time specific duration more late than the acquisition time of the sample image data.
8. vehicle as claimed in claim 7, which is characterized in that the sample image data and the sample steering order be from
It is chosen in data acquisition system, wherein include multiple image data and multiple steering orders in the data acquisition system, wherein institute
The predicted time for stating multiple steering orders is respectively equal to the acquisition time of the multiple image data.
9. the vehicle as described in any one of claim 6 to 8, which is characterized in that it is time-consuming that the specific duration is equal to N number of image
Total duration, wherein the response delay is matched with the total duration of N number of image time-consuming, and described image time-consuming is described turns
To the inverse of the frequency of model treatment image data, the N is more than or equal to 1 integer.
10. vehicle as claimed in claim 9, which is characterized in that the N is equal to response delay and obtains divided by described image time-consuming
Integer；Or
The N is equal to the integer that response delay rounds up divided by described image time-consuming；Or
The N is equal to response delay and is rounded obtained integer downwards divided by described image is time-consuming.
11. a kind of vehicle, which is characterized in that including processor, memory and be stored on the memory and can be at the place
The computer program run on reason device is realized when the computer program is executed by the processor as appointed in claim 1 to 5
The step of steering order processing method described in one.
12. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the steering order processing as described in any one of claims 1 to 5 when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811639547.0A CN109572816B (en) | 2018-12-29 | 2018-12-29 | Steering instruction processing method and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811639547.0A CN109572816B (en) | 2018-12-29 | 2018-12-29 | Steering instruction processing method and vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109572816A true CN109572816A (en) | 2019-04-05 |
| CN109572816B CN109572816B (en) | 2020-08-14 |
Family
ID=65933578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811639547.0A Active CN109572816B (en) | 2018-12-29 | 2018-12-29 | Steering instruction processing method and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109572816B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000352502A (en) * | 1999-04-07 | 2000-12-19 | Koyo Seiko Co Ltd | Rotational angle detection device, torque sensor and steering device |
| US8036781B2 (en) * | 2004-11-26 | 2011-10-11 | Nissan Motor Co., Ltd. | Driving operation assisting system, method and vehicle incorporating the system |
| CN103415406A (en) * | 2011-03-16 | 2013-11-27 | 日产自动车株式会社 | Suspension device for vehicle, method for adjusting geometry of same, and automobile |
| CN103974873A (en) * | 2011-12-09 | 2014-08-06 | 丰田自动车株式会社 | Electric power steering device |
| CN104554434A (en) * | 2013-10-23 | 2015-04-29 | 株式会社捷太格特 | Warning device for vehicle |
| CN105122166A (en) * | 2013-01-31 | 2015-12-02 | 菲力尔系统公司 | Stabilized directional control systems and methods |
| US20160288831A1 (en) * | 2013-12-06 | 2016-10-06 | GM Global Technology Operations LLC | PRE-ALERT OF LCC's STEERING TORQUE LIMIT EXCEED |
| CN205930709U (en) * | 2016-07-22 | 2017-02-08 | 北京兴科迪科技有限公司 | Lane departure early warning system |
| DE102017128003A1 (en) * | 2016-11-30 | 2018-05-30 | Steering Solutions Ip Holding Corporation | SPEED ESTIMATION FOR ELECTRIC POWER STEERING SYSTEMS |
| CN108137006A (en) * | 2016-09-28 | 2018-06-08 | 百度（美国）有限责任公司 | For the system delay Corrective control method of automatic driving vehicle |
-
2018
- 2018-12-29 CN CN201811639547.0A patent/CN109572816B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000352502A (en) * | 1999-04-07 | 2000-12-19 | Koyo Seiko Co Ltd | Rotational angle detection device, torque sensor and steering device |
| US8036781B2 (en) * | 2004-11-26 | 2011-10-11 | Nissan Motor Co., Ltd. | Driving operation assisting system, method and vehicle incorporating the system |
| CN103415406A (en) * | 2011-03-16 | 2013-11-27 | 日产自动车株式会社 | Suspension device for vehicle, method for adjusting geometry of same, and automobile |
| CN103974873A (en) * | 2011-12-09 | 2014-08-06 | 丰田自动车株式会社 | Electric power steering device |
| CN105122166A (en) * | 2013-01-31 | 2015-12-02 | 菲力尔系统公司 | Stabilized directional control systems and methods |
| CN104554434A (en) * | 2013-10-23 | 2015-04-29 | 株式会社捷太格特 | Warning device for vehicle |
| US20160288831A1 (en) * | 2013-12-06 | 2016-10-06 | GM Global Technology Operations LLC | PRE-ALERT OF LCC's STEERING TORQUE LIMIT EXCEED |
| CN205930709U (en) * | 2016-07-22 | 2017-02-08 | 北京兴科迪科技有限公司 | Lane departure early warning system |
| CN108137006A (en) * | 2016-09-28 | 2018-06-08 | 百度（美国）有限责任公司 | For the system delay Corrective control method of automatic driving vehicle |
| DE102017128003A1 (en) * | 2016-11-30 | 2018-05-30 | Steering Solutions Ip Holding Corporation | SPEED ESTIMATION FOR ELECTRIC POWER STEERING SYSTEMS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109572816B (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110146100B (en) | Trajectory prediction method, apparatus and storage medium | |
| CN107491073B (en) | Data training method and device for unmanned vehicle | |
| CN106652515B (en) | Automatic vehicle control method, device and system | |
| CN108122027B (en) | Training method, device and chip of neural network model | |
| CN107609502A (en) | Method and apparatus for controlling automatic driving vehicle | |
| CN104008642A (en) | Vehicle apparatus and system for controlling platoon travel and method for selecting lead vehicle | |
| CN104851280B (en) | A kind of vehicle travel control method, device, system and relevant device | |
| US11586203B2 (en) | Method for training a central artificial intelligence module | |
| CN111372217B (en) | Method, medium, and apparatus for offloading computing tasks in an internet of vehicles environment | |
| CN109785611B (en) | Unmanned vehicle control method, device, server and storage medium | |
| EP3786925A1 (en) | Systems and methods for training a neural network to control an aircraft | |
| CN111291984B (en) | Multi-unmanned aerial vehicle distributed edge task selection and trajectory design method and device | |
| EP3739494A3 (en) | Method, apparatus, system, and program for optimizing solid electrolytes for li-ion batteries using bayesian optimization | |
| CN110481536A (en) | A kind of control method and equipment applied to hybrid vehicle | |
| JP2022080280A (en) | Method for predicting turnaround intention of driver based on hybrid learning | |
| CN115330095A (en) | Mine car dispatching model training method, device, chip, terminal, equipment and medium | |
| CN111967163B (en) | Vehicle simulation control method and device, computer equipment and storage medium | |
| US20210403054A1 (en) | Vehicle allocation method in automated vehicle and highway system and apparatus therefor | |
| CN109703566A (en) | A kind of rate control instruction processing method and vehicle | |
| CN109572816A (en) | A kind of steering order processing method and vehicle | |
| CN109976153A (en) | Control the method, apparatus and electronic equipment of unmanned equipment and model training | |
| CN110478911A (en) | The unmanned method of intelligent game vehicle and intelligent vehicle, equipment based on machine learning | |
| CN110654395A (en) | Vehicle-mounted control system, vehicle and method | |
| CN109606467A (en) | A kind of vehicle steering method and vehicle | |
| CN115715021A (en) | Internet of vehicles resource allocation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |