CN110335484A - Control the method and device of vehicle driving - Google Patents
Control the method and device of vehicle driving Download PDFInfo
- Publication number
- CN110335484A CN110335484A CN201910731308.6A CN201910731308A CN110335484A CN 110335484 A CN110335484 A CN 110335484A CN 201910731308 A CN201910731308 A CN 201910731308A CN 110335484 A CN110335484 A CN 110335484A
- Authority
- CN
- China
- Prior art keywords
- instruction state
- state
- instruction
- vehicle
- traffic lights
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/09623—Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
This application provides a kind of method and devices for controlling vehicle driving, wherein, this method comprises: when carrying out traffic lights identification, collect the state of multiple traffic lights at crossing, it is not only the traffic lights of vehicle heading, also according to the logical relation between multiple traffic lights, judge the traffic light status of vehicle heading, the vehicle drive traffic accident as caused by the traffic light status of the scenes wrong identification driving direction such as backlight is avoided, is solved the problems, such as in the related technology since the lower caused vehicle control of traffic lights recognition accuracy is easy error.
Description
Technical field
This application involves but be not limited to intelligent driving field, in particular to a kind of method for controlling vehicle driving and
Device.
Background technique
In the related art, in automated driving system, traffic lights identification is an important functional module, and identification is quasi-
True rate is related to the safety of automated driving system.Commonplace way is computer vision methods at present, collect in advance or
The image data for acquiring a large amount of traffic lights, obtaining a traffic lights identification model by training (can select various machine learning
Method or deep learning network), this model is then loaded into automated driving system vehicle-mounted end, vehicle driving to traffic lights
Behind crossing, the image input model that camera is acquired in real time, be calculated " red ", " green ", " Huang ", " can not identify " knot
Fruit, then other modules use of automated driving system is presented the result to, for example, path planning module, is learning that front is red
In the case where lamp, need to cook up the route that vehicle is gradually slowed down and stopped before stop line.Fig. 1 is according in the related technology
Typical traffic light identification method flow chart, as shown in Figure 1, by car-mounted computer camera obtain traffic lights photo, connect
Carry out photo segmentation, carry out image recognition using the good model of cloud computer aid training, identify the traffic light status.Cloud meter
Calculation machine uses picture training pattern, obtains model result, then carries out image recognition using model result.
Traffic light identification method in the related technology, due to the limitation of model training data, it cannot be guaranteed that recognition result one
It is fixed correct, there is certain error rate, and for automated driving system, if traffic lights identification is likely to result in serious traffic
Accident endangers passenger and pedestrains safety.Identification for single lamp, with better model, mistake can be reduced by increasing more data
Accidentally rate, but after reducing to a certain extent, the difficulty for continuing to reduce error rate can be increasing.Especially for some special feelings
Condition, human eye are all difficult to differentiate, and the method for computer vision is also difficult identification accurately, such as: backlight, lamp damage, lamp have spot, rain
Greasy weather gas is avenged, is blocked.
Aiming at the problem that being easy error due to the lower caused vehicle control of traffic lights recognition accuracy in the related technology, mesh
Preceding effective solution scheme not yet.
Summary of the invention
The embodiment of the present application provide it is a kind of control vehicle driving method and device, at least solve in the related technology by
The vehicle control caused by traffic lights recognition accuracy is lower is easy the problem of error.
According to one embodiment of the application, a kind of method for controlling vehicle driving is provided, comprising: in vehicle by working as
Before preceding crossing, the vehicle is obtained in the first instruction shape of the corresponding traffic lights of vehicle heading at the current crossing
Second instruction state of the corresponding traffic lights of the non-vehicle heading at state and the current crossing；Use described
Two instruction states or first instruction state and second instruction state are corrected first instruction state, obtain
To the final instruction state of the corresponding traffic lights of the vehicle heading；It determines according to the final instruction state for controlling
Whether the vehicle continues the control signal of traveling；The vehicle driving is controlled according to the control signal.
According to another embodiment of the application, a kind of device for controlling vehicle driving is additionally provided, comprising: identification mould
Block, for it is corresponding to obtain vehicle heading of the vehicle at the current crossing before vehicle is by current crossing
The second of the corresponding traffic lights of the non-vehicle heading at the first instruction state of traffic lights and the current crossing refers to
Show state；Module is obtained, for using second instruction state or first instruction state and second instruction state
First instruction state is corrected, the final instruction state of the corresponding traffic lights of the vehicle heading is obtained；Really
Cover half block, for determining the control signal for whether continuing traveling for controlling the vehicle according to the final instruction state；Control
Molding block, for controlling the vehicle driving according to the control signal.
According to another embodiment of the application, a kind of storage medium is additionally provided, meter is stored in the storage medium
Calculation machine program, wherein the computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
According to another embodiment of the application, a kind of electronic device, including memory and processor are additionally provided, it is described
Computer program is stored in memory, the processor is arranged to run the computer program to execute any of the above-described
Step in embodiment of the method.
The vehicle is obtained in the vehicle row at the current crossing before vehicle is by current crossing by the application
The non-vehicle heading of the first instruction state and the current crossing of sailing the corresponding traffic lights in direction is corresponding red
Second instruction state of green light；Use second instruction state or first instruction state and second instruction state
First instruction state is corrected, the final instruction state of the corresponding traffic lights of the vehicle heading is obtained；According to
The control signal for whether continuing traveling for controlling the vehicle is determined according to the final instruction state；According to the control signal
Control the vehicle driving.Using the above scheme, when carrying out traffic lights identification, the shape of multiple traffic lights at crossing is collected
State is not only the traffic lights of vehicle heading also according to the logical relation between multiple traffic lights and judges vehicle driving side
To the traffic light status, avoid the vehicle drive as caused by the traffic light status of the scenes wrong identification driving direction such as backlight
Traffic accident solves in the related technology since the lower caused vehicle control of traffic lights recognition accuracy is easy asking for error
Topic.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 is according to typical traffic light identification method flow chart in the related technology；
Fig. 2 is a kind of hardware block diagram of the terminal of the method for control vehicle driving of the embodiment of the present application；
Fig. 3 is the flow chart according to the method for the control vehicle driving of the embodiment of the present application；
Fig. 4 is the schematic diagram of a scenario for passing through traffic light intersection according to the vehicle of the embodiment of the present application.
Specific embodiment
The application is described in detail below with reference to attached drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
Embodiment one
Embodiment of the method provided by the embodiment of the present application one can be in terminal, terminal or similar
It is executed in arithmetic unit.For running on computer terminals, Fig. 2 is a kind of control vehicle driving of the embodiment of the present application
The hardware block diagram of the terminal of method, as shown in Fig. 2, terminal may include it is one or more (in Fig. 2 only
Showing one) (processor 202 can include but is not limited to Micro-processor MCV or programmable logic device FPGA etc. to processor 202
Processing unit) and memory 204 for storing data, optionally, above-mentioned terminal can also include for communicating
The transmitting device 206 and input-output equipment 208 of function.It will appreciated by the skilled person that structure shown in Fig. 2
Only illustrate, the structure of above-mentioned terminal is not caused to limit.For example, terminal may also include than in Fig. 2
Shown more perhaps less component or with the configuration different from shown in Fig. 2.
Memory 204 can be used for storing the software program and module of application software, such as the control in the embodiment of the present application
Corresponding program instruction/the module of vehicle driving method, the software program that processor 202 is stored in memory 204 by operation
And module realizes above-mentioned method thereby executing various function application and data processing.Memory 204 may include height
Fast random access memory, may also include nonvolatile memory, as one or more magnetic storage device, flash memory or other
Non-volatile solid state memory.In some instances, memory 204 can further comprise remotely located relative to processor 202
Memory, these remote memories can pass through network connection to terminal.The example of above-mentioned network includes but unlimited
In internet, intranet, local area network, mobile radio communication and combinations thereof.
Transmitting device 206 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of terminal provide.In an example, transmitting device 206 includes a Network adaptation
Device (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to it is mutual
Networking is communicated.In an example, transmitting device 206 can be radio frequency (Radio Frequency, RF) module, use
In wirelessly being communicated with internet.
A kind of method of control vehicle driving for running on above-mentioned terminal, Fig. 3 are provided in the present embodiment
It is according to the flow chart of the method for the control vehicle driving of the embodiment of the present application, as shown in figure 3, the process includes the following steps:
Step S302 obtains the vehicle in the vehicle driving at the current crossing before vehicle is by current crossing
The non-vehicle heading at the first instruction state of the corresponding traffic lights in direction and the current crossing is corresponding red green
Second instruction state of lamp；
The traffic light status may include red light, green light, amber light and can not identification state, such as situations such as branch blocks.
The traffic light status can be obtained by way of shooting traffic lights photo, roadside traffic lights can also be obtained by car networking technology
The traffic light status that frame is sent automatically.
The terminal for executing the program can integrate on vehicle, also can be set on server beyond the clouds, still
From the point of view of the real-time of communication, setting can more timely make a response to the traffic light status on vehicle.
Step S304 uses second instruction state or first instruction state and second instruction state pair
First instruction state is corrected, and obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
When the first instruction state, which is, to be identified, 0 can be set by the weight of the first instruction state, i.e., not consider the
One instruction state determines the final instruction state of the traffic lights of vehicle heading according to multiple second instruction states.
Foundation when being corrected to the first instruction state can be calculation formula, be different traffic lights settings in formula
There is different weights, the state of the different probability of the same traffic lights also has different weights, for example, clear in shooting photo
In the case of, identify that current driving direction be the probability of red light is 99%, the probability of green light is 1%, at this time, it is only necessary to less weight
The considerations of non-vehicle driving direction the traffic light status the output of model can be obtained.On the contrary, if due to originals such as shooting backlight
Cause identifies that the red light green light probability of driving direction respectively has percent 40%, needs that greater weight is arranged at this time to consider other
The traffic light status of non-vehicle driving direction increases green light on current driving direction if being red light in non-driving direction
Probability may finally be determined to control vehicle and continue to travel for green light.It is only for example, is also conceivable in timing herein
More parameters, such as the traffic lights delay of road intersection etc..
Step S306 determines the control letter for whether continuing traveling for controlling the vehicle according to the final instruction state
Number, the vehicle driving is controlled according to the control signal.
This method can be used for the scene of automatic Pilot, or be used for navigation scenarios, be mentioned by voice prompting for driver
Awake the traffic light status.
Through the above steps, before vehicle is by current crossing, the vehicle is obtained in the vehicle at the current crossing
The non-vehicle heading at the first instruction state of the corresponding traffic lights of driving direction and the current crossing is corresponding
Second instruction state of traffic lights；Use second instruction state or first instruction state and the second instruction shape
State is corrected first instruction state, obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
The control signal for whether continuing traveling for controlling the vehicle is determined according to the final instruction state；Believe according to the control
Number control vehicle driving.Using the above scheme, when carrying out traffic lights identification, the shape of multiple traffic lights at crossing is collected
State is not only the traffic lights of vehicle heading, according to the logical relation between multiple traffic lights, judges vehicle heading
The traffic light status, avoid the vehicle drive as caused by the traffic light status of the scenes wrong identification driving direction such as backlight friendship
Interpreter's event solves the problems, such as in the related technology since the lower caused vehicle control of traffic lights recognition accuracy is easy error
Optionally, described to use second instruction state or first instruction state and second instruction state
First instruction state is corrected, the final instruction state of the corresponding traffic lights of the vehicle heading is obtained, is wrapped
Include: using second instruction state and logical relation or first instruction state and second instruction state and
The logical relation is corrected first instruction state, obtains the final of the corresponding traffic lights of the vehicle heading
Instruction state, wherein the logical relation is the relationship between the display state of the different traffic lights at the current crossing, described
Final instruction state is one of the instruction state of traffic lights instruction state, the instruction state of the traffic lights include it is following it
One: red light phase, green light phase, amber light state, can not identification state.Using the program, corrected using preset logical relation
First instruction state, to increase the accuracy of traffic lights identification.
Optionally, described to use second instruction state or first instruction state and second instruction state
First instruction state is corrected, the final instruction state for obtaining the corresponding traffic lights of the vehicle heading includes
At least one of: logical operation is negated to second instruction state execution, wherein negate logical operation described in the execution
When, it is obtained from default mapping relations to the result for negating logical operation described in second instruction state progress；To described
Two instruction states, which execute, is equal to logical operation, wherein execute it is described be equal to logical operation when, obtained from default mapping relations
The result for being equal to logical operation is carried out to second instruction state；To first instruction state and second instruction
State executes ballot logical operation, wherein the first instruction state and described second described in when executing the ballot logical operation
Weight corresponding to instruction state is respectively according to first instruction state and second instruction state is corresponding pre-sets
Reliability determination obtains；Weighted average logical operation is executed to first instruction state and second instruction state, wherein
Weight corresponding to first instruction state described in when executing the weighted average logical operation and second instruction state is point
It is not obtained according to the corresponding default confidence level determination of first instruction state and second instruction state；Refer to described first
Show that state and second instruction state execute and operation, wherein execute it is described with operation when obtain from default mapping relations
It takes and the result with operation is carried out to first instruction state and second instruction state；To first instruction state
With second instruction state execution or operation, wherein obtained from default mapping relations to institute when executing described or operation
It states the first instruction state and second instruction state carries out described or operation result.Using the program, for different directions
The traffic light status have Different treatments, for example the traffic lights of road intersection are carried out negating operation, for opposite direction
The traffic lights of road carry out being equal to operation etc., be only for example herein.In the related technology setting traffic lights logical relation compared with
For complexity, such as the green time of unidirectional crossing is shorter than the time of car lane etc., also it is contemplated that pre-
In if.
Optionally, described that logical operation is negated to second instruction state execution, comprising: in second instruction state
In the case where instruction state for the corresponding traffic lights in direction intersected with the vehicle heading, closed from the default mapping
In system obtain to second instruction state carry out described in negate logical operation as a result, obtaining third instruction state, wherein institute
Stating default mapping relations indicates: it is the red light phase to the result that logical operation obtains is negated described in green light phase execution, it is right
Amber light state negates the result that logical operation obtains described in executing as red light phase, transports to logic is negated described in red light phase execution
Obtained result is amber light state or green light phase；Not being in first instruction state can not identification state and described
When three instruction states are identical as first instruction state, first instruction state is determined as the final instruction state；
Alternatively, first instruction state be not it is described can not identification state, and the third instruction state and first instruction
When state difference, first instruction state is determined as the final instruction state；Alternatively, being in first instruction state
It is described can not identification state, the third instruction state be not can not identification state when, the third instruction state is determined as
The final instruction state.The result for negate logical operation to every kind of instruction state in above-described embodiment is only for example
It is bright, there can also be other plans of establishment.
Optionally, described that the control for whether continuing traveling for controlling the vehicle is determined according to the final instruction state
Signal, comprising: when the third instruction state is non-green light phase, controls the vehicle and stop traveling；Refer in the third
When showing that state is green light phase, when the final instruction state is red light phase, it is subsequent in pre-set delay to control the vehicle
It continues and sails.Using the program, the traffic lights delay of opposite direction road is fully considered, such as detecting East and West direction road as red light
When, it increases after the crossing commonly postpones, determines that north-south road just shows green light.Pass through this kind of mode and traffic lights
Actual setting mode be perfectly combined, ensure traffic safety.
Optionally, described execute to second instruction state is equal to logical operation, comprising: in second instruction state
For the direction corresponding traffic lights opposite with the vehicle heading instruction state when, obtained from the default mapping relations
Take to second instruction state carry out it is described equal to logical operation as a result, obtaining the 4th instruction state, wherein to described red
The result that the execution of lamp state is equal to logical operation is red light phase, and the result for being equal to logical operation to amber light state execution is
Amber light state, the result for being equal to logical operation to green light phase execution is green light phase；The 4th instruction state with
When first instruction state is identical, which is determined as the final instruction state；Alternatively, described first
Instruction state it is non-can not identification state, and the 4th instruction state and when the first instruction state difference, by described first
Instruction state is determined as the final instruction state；Alternatively, first instruction state be can not identification state when, will be described
4th instruction state is determined as the final instruction state.
Optionally, the second instruction of the corresponding traffic lights of the non-vehicle heading for obtaining the current crossing
State, comprising: obtain the described of the corresponding traffic lights of multiple directions in the non-vehicle heading at the current crossing
Second instruction state.
Optionally, ballot logical operation is executed to first instruction state and second instruction state, comprising: to institute
It states each instruction state in the first instruction state and second instruction state and executes respectively and described be equal to logical operation or institute
It states and negates logical operation, obtain multiple operation results, wherein by first instruction state or the power of second instruction state
It is respectively corresponding to respective operation result again；In the multiple operation result correspondence to different instruction state, every kind is obtained
The number of the corresponding operation result of instruction state, with the largest number of instruction states for the final instruction state；Alternatively, institute
When stating multiple operation results correspondences to different instruction state, the sum of the weight of the corresponding operation result of every kind of instruction state is obtained
Value with weight and is worth maximum instruction state for the final instruction state.Using the program, selected by way of ballot
Final instruction state, so that the final instruction state determined is more accurate.
Optionally, weighted average logical operation is executed to first instruction state and second instruction state, comprising:
When obtaining the instruction state of multiple traffic lights including first instruction state and second instruction state, by institute
It states the red light phase in the instruction state of multiple traffic lights and is denoted as the first numerical value, it will be in the instruction state of the multiple traffic lights
Green light phase is denoted as second value；Third value is obtained after being weighted and averaged to the first all numerical value and second value,
In, the corresponding weight of each numerical value is the weight of the instruction state used when obtaining the numerical value；Obtain first numerical value and institute
State the first absolute value of the difference of third value and the difference of the second value and the third value second is absolute
Value；When first absolute value is less than second absolute value, the final instruction state is determined as red light phase, in institute
When stating the first absolute value greater than second absolute value, the final instruction state is determined as green light phase.
Optionally, described that the control for whether continuing traveling for controlling the vehicle is determined according to the final instruction state
Signal, comprising: when the final instruction state is green light phase, determine the letter for continuing traveling for controlling the vehicle
Number；When the final instruction state is red light phase or amber light state, determine to stop traveling for controlling the vehicle
Signal.
Optionally, it is described obtain the vehicle the current crossing the corresponding traffic lights of vehicle heading the
Second instruction state of the corresponding traffic lights of the non-vehicle heading at one instruction state and the current crossing it
Before, at the current crossing, there are lanes when multiple traffic lights, being currently located according to the vehicle and/or the vehicle driving
Direction determines the corresponding traffic lights of the vehicle heading and the corresponding traffic lights of the non-vehicle heading.
Optionally, described before vehicle is by current crossing, the vehicle is obtained in the vehicle row at the current crossing
The non-vehicle heading of the first instruction state and the current crossing of sailing the corresponding traffic lights in direction is corresponding red
Before second instruction state of green light, the mark at the current crossing is obtained；From server or it is set in the vehicle
Logical relation corresponding with the mark is read in local storage.Different crossings possesses different logical relations, same
The different time sections at crossing can also have a different logical relations, such as the logical relation and non-peak period of vehicle flowrate peak period
Logical relation is different.
Optionally, in state of the accuracy rate greater than threshold value for identifying first instruction state and second instruction state
Under, detect the display state between first instruction state and second instruction state actual logic relationship whether with school
The logical relation of just described first instruction state is identical；In the actual logic relationship and the logical relation difference,
Start the correction mechanism to the logical relation；Modify the logical relation according to following manner: artificial nucleus close the logic
System, alternatively, the actual logic relationship according to the acquisition of multiple vehicles corrects the logical relation.Using the above scheme, it is provided with road
The correction mechanism of the logical relation of mouth, the correction logic relationship by way of artificial nucleus couple, or the letter according to more vehicles feedback
Cease correction logic relationship.
Optionally, one of the in the following manner state of identification traffic lights: shooting the photo of the traffic lights, described in analysis
Photo obtains the state of the traffic lights；It is described red that being used to indicate for crossroads traffic light equipment transmission is obtained by car networking technology
The indication signal of green light phase identifies the state of the traffic lights according to the instruction information.
It is illustrated below with reference to another embodiment of the application.
This programme does not change the recognition methods of single traffic lights, but all identifies to multiple lamps for having logical relation,
Identification error rate and original method to single lamp maintain an equal level, and single lamp recognition methods in the method can be any side in other words
Method, without limitation, and this method can play the role of very big improvement.
Fig. 4 is the schematic diagram of a scenario according to the vehicle of the embodiment of the present application by traffic light intersection, as shown in figure 4, such as allusion quotation
It shown in type schematic diagram of a scenario, when vehicle V advances to crossing, needs to keep straight on, usual way is the red of identification control straight trip direction
Green light T1, to decide whether to pass through crossing.The method that we design can also identify T2, because of T2 and T1 in addition to identifying T1
State have certain logical relation, for example when T2 is green light, T1 must be red light, pass through certain Logical Deriving after obtaining T2 state
It calculates available T1 and achievees the purpose that improve recognition accuracy as a result, carrying out synthesis with T1 recognition result again.And so on also
Many methods (being not limited to these logics) for passing through traffic lights logical relation:
Vehicle V straight trip, T11 are that (there is the instruction of multiple groups lamp at many crossings to another traffic lights being consistent with the T1 moment
Same state), the state of T11 is equal to T1 state, this information can greatly improve recognition accuracy.Vehicle V straight trip, additionally
Identify the pavement T4 lamp, when T4 is green light, T1 must be red light；
Vehicle V turns left, and additionally identifies T3, and when T3 green light, T1 left-hand rotation lamp must be green light；
It should be strongly noted that in order to reserve buffering, the logical relation of some lamps to having entered crossing vehicle and pedestrian
There is delay, for example, T1 will also keep the red light of a period of time, usually several seconds when T2 is by green redden, then greening makes
This factor is taken into account with needs when logical relation.
Illustrate the scheme of the present embodiment by following formula:
Status=L (T1, T2 ..., Ti)；
Wherein, Status represents the final the traffic light status that we need to know, i.e., current automatic driving vehicle will go
Into direction whether can pass through；T1~Ti, which is represented, identifies that helpful all traffic lights (are not limited to vehicle to current state Status
The direction of face)；L represents logic calculation, including but not limited to: it is equal to, negates, votes, weighted average etc.；It is summing it up and is voting
When can also assign Ti to different weights according to confidence level, obtain more accurate result；
Optionally, the logical relation of lamp and lamp is relatively fixed at some crossing, but crossing and crossing may be different, together
One crossing may be also slightly different in different time sections, these information can collect in advance, is key according to crossing position and time
It is deposited into memory, is transferred after advancing to some crossing, a part that this type of information becomes high-precision map is wherein
A kind of way (but not limited to this, can also store in other forms).
Optionally, visual identity traffic lights accuracy rate has bottleneck, using car networking V2X technology, directly passes through and traffic lights
Wireless communication or obtain the traffic light status from the road network information of cloud and will have higher stability and an accuracy, but it is big at present
Most roads do not have this condition.
Using the above scheme, the present invention carries out more lamp identifications using logical relation, can greatly improve accuracy rate；Such as: it is right
Scene in Fig. 4, if single lamp recognition accuracy is 99%, T1 and T11 simple vote, recognition accuracy will be improved
To 99.99%；The accuracy rate of all traffic light identification methods based on single lamp can be substantially improved for the method, not limit a certain kind
Recognition methods.
In backlight, lamp damage, lamp has a spot, sleet mist bad weather, in the case that lamp is blocked, the recognition methods of single lamp
Can not identify or obtain mistake can not continue to travel as a result, can not identify and will lead to automatic driving vehicle, the result of mistake
It will lead to running red light for vehicle and then accident even occur.The recognition result that the present invention can use other lamps obtains current red green
Lamp state, so that enabling automatic driving vehicle in these cases can continue to travel and safety is greatly improved.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, the technical solution of the application is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server or network equipment etc.) execute method described in each embodiment of the application.
Embodiment two
Additionally provide a kind of device for controlling vehicle driving in the present embodiment, the device for realizing above-described embodiment and
Preferred embodiment, the descriptions that have already been made will not be repeated.As used below, predetermined function may be implemented in term " module "
The combination of the software and/or hardware of energy.It is hard although device described in following embodiment is preferably realized with software
The realization of the combination of part or software and hardware is also that may and be contemplated.
According to one embodiment of the application, a kind of device for controlling vehicle driving is provided, comprising:
Identification module, for obtaining the vehicle in the vehicle at the current crossing before vehicle is by current crossing
The non-vehicle heading at the first instruction state of the corresponding traffic lights of driving direction and the current crossing is corresponding
Second instruction state of traffic lights；
Module is obtained, for using second instruction state or first instruction state and the second instruction shape
State is corrected first instruction state, obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
Determining module, for determining the control for whether continuing traveling for controlling the vehicle according to the final instruction state
Signal processed；
Control module, for controlling the vehicle driving according to the control signal.
Using the above scheme, when carrying out traffic lights identification, the state of multiple traffic lights at crossing is collected, is not only vehicle
The traffic lights of driving direction judge the traffic lights shape of vehicle heading according to the logical relation between multiple traffic lights
State avoids the vehicle drive traffic accident as caused by the traffic light status of the scenes wrong identification driving direction such as backlight, solution
It has determined in the related technology since the lower caused vehicle control of traffic lights recognition accuracy is easy the problem of malfunctioning.
It should be noted that above-mentioned modules can be realized by software or hardware, for the latter, Ke Yitong
Following manner realization is crossed, but not limited to this: above-mentioned module is respectively positioned in same processor；Alternatively, above-mentioned modules are with any
Combined form is located in different processors.
Embodiment three
Embodiments herein additionally provides a kind of storage medium.Optionally, in the present embodiment, above-mentioned storage medium can
To be arranged to store the program code for executing following steps:
S1 obtains the vehicle in the vehicle heading pair at the current crossing before vehicle is by current crossing
The of the corresponding traffic lights of the non-vehicle heading at the first instruction state of the traffic lights answered and the current crossing
Two instruction states；
S2, using second instruction state or first instruction state and second instruction state to described
One instruction state is corrected, and obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
S3 determines the control signal for whether continuing traveling for controlling the vehicle according to the final instruction state, according to
The vehicle driving is controlled according to the control signal.
Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or
The various media that can store program code such as CD.
Embodiments herein additionally provides a kind of electronic device, including memory and processor, stores in the memory
There is computer program, which is arranged to run computer program to execute the step in any of the above-described embodiment of the method
Suddenly.
Optionally, above-mentioned electronic device can also include transmitting device and input-output equipment, wherein the transmitting device
It is connected with above-mentioned processor, which connects with above-mentioned processor.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S1 obtains the vehicle in the vehicle heading pair at the current crossing before vehicle is by current crossing
The of the corresponding traffic lights of the non-vehicle heading at the first instruction state of the traffic lights answered and the current crossing
Two instruction states；
S2, using second instruction state or first instruction state and second instruction state to described
One instruction state is corrected, and obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
S3 determines the control signal for whether continuing traveling for controlling the vehicle according to the final instruction state, according to
The vehicle driving is controlled according to the control signal.
Optionally, the specific example in the present embodiment can be with reference to described in above-described embodiment and optional embodiment
Example, details are not described herein for the present embodiment.
Optionally, the specific example in the present embodiment can be with reference to described in above-described embodiment and optional embodiment
Example, details are not described herein for the present embodiment.
Obviously, those skilled in the art should be understood that each module of above-mentioned the application or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.It is combined in this way, the application is not limited to any specific hardware and software.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (16)
1. a kind of method for controlling vehicle driving characterized by comprising
Before vehicle is by current crossing, it is corresponding red green to obtain vehicle heading of the vehicle at the current crossing
Second instruction shape of the corresponding traffic lights of the non-vehicle heading at the first instruction state of lamp and the current crossing
State；
Using second instruction state or first instruction state and second instruction state to the first instruction shape
State is corrected, and obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
The control signal for whether continuing traveling for controlling the vehicle is determined according to the final instruction state；
The vehicle driving is controlled according to the control signal.
2. the method according to claim 1, wherein described use second instruction state or described first
Instruction state and second instruction state are corrected first instruction state, and it is corresponding to obtain the vehicle heading
Traffic lights final instruction state, comprising:
Using second instruction state and logical relation or first instruction state and second instruction state with
And the logical relation is corrected first instruction state, obtains the corresponding traffic lights of the vehicle heading most
Whole instruction state, wherein the logical relation is the relationship between the display state of the different traffic lights at the current crossing, institute
It includes following for stating one of the instruction state that final instruction state is traffic lights instruction state, the instruction state of the traffic lights
One of: red light phase, green light phase, amber light state, can not identification state.
3. the method according to claim 1, wherein described use second instruction state or described first
Instruction state and second instruction state are corrected first instruction state, and it is corresponding to obtain the vehicle heading
The final instruction states of traffic lights include at least one of:
Logical operation is negated to second instruction state execution, wherein when negating logical operation described in the execution, reflect from default
The result obtained to logical operation is negated described in second instruction state progress is penetrated in relationship；
Second instruction state is executed and is equal to logical operation, wherein execute it is described be equal to logical operation when, reflected from default
It penetrates in relationship to obtain and the result for being equal to logical operation is carried out to second instruction state；
Ballot logical operation is executed to first instruction state and second instruction state, wherein executing the ballot
Weight corresponding to first instruction state described in when logical operation and second instruction state is to refer to respectively according to described first
Show that state and the corresponding default confidence level determination of second instruction state obtain；
Weighted average logical operation is executed to first instruction state and second instruction state, wherein described in execution
Weight corresponding to first instruction state described in when weighted average logical operation and second instruction state is respectively according to institute
It states the first instruction state and the corresponding default confidence level determination of second instruction state obtains；
First instruction state and second instruction state are executed and operation, wherein execute it is described with operation when from
It is obtained in default mapping relations and the result with operation is carried out to first instruction state and second instruction state；
First instruction state and second instruction state are executed or operation, wherein when executing described or operation from
It is obtained in default mapping relations and described or operation result is carried out to first instruction state and second instruction state.
4. according to the method described in claim 3, it is characterized in that, described negate logic fortune to second instruction state execution
It calculates, comprising:
In the instruction state that second instruction state is the corresponding traffic lights in direction intersected with the vehicle heading
In the case of, from the default mapping relations obtain to second instruction state carry out described in negate logical operation as a result,
It obtains third instruction state, wherein the default mapping relations indicate: being obtained to logical operation is negated described in green light phase execution
Result be red light phase, to amber light state execute described in negate result that logical operation obtains be red light phase, to red light shape
State negates the result that logical operation obtains described in executing as amber light state or green light phase；
Not being in first instruction state can not identification state and the third instruction state and the first instruction state phase
Meanwhile first instruction state is determined as the final instruction state；Alternatively, not being described in first instruction state
Can not identification state, and the third instruction state and when the first instruction state difference is true by first instruction state
It is set to the final instruction state；Alternatively, first instruction state be it is described can not identification state, the third indicate shape
State be not can not identification state when, the third instruction state is determined as the final instruction state.
5. according to the method described in claim 4, it is characterized in that, described determine according to the final instruction state for controlling
Whether the vehicle continues the control signal of traveling, comprising:
When the third instruction state is non-green light phase, controls the vehicle and stop traveling；
When the third instruction state is green light phase, when the final instruction state is red light phase, the vehicle is controlled
It is sailed in subsequent continue of pre-set delay.
6. according to the method described in claim 3, it is characterized in that, described execute to second instruction state is equal to logic fortune
It calculates, comprising:
When second instruction state is the instruction state of the direction corresponding traffic lights opposite with the vehicle heading,
Obtained from the default mapping relations to second instruction state carry out it is described equal to logical operation as a result, obtaining the 4th
Instruction state, wherein the result for being equal to logical operation to red light phase execution is red light phase, executes to be equal to amber light state and patrol
The result for collecting operation is amber light state, and the result for being equal to logical operation to green light phase execution is green light phase；
When the 4th instruction state is identical as first instruction state, which is determined as described final
Instruction state；Alternatively, first instruction state it is non-can not identification state, and the 4th instruction state and it is described first refer to
When showing state difference, first instruction state is determined as the final instruction state；Alternatively, in first instruction state
For can not identification state when, the 4th instruction state is determined as the final instruction state.
7. according to the method described in claim 3, it is characterized in that, the non-vehicle driving for obtaining the current crossing
Second instruction state of the corresponding traffic lights in direction, comprising:
Obtain the corresponding traffic lights of multiple directions in the non-vehicle heading at the current crossing described second refers to
Show state.
8. the method according to the description of claim 7 is characterized in that first instruction state and second instruction state
Execute ballot logical operation, comprising:
Each instruction state in first instruction state and second instruction state is executed respectively described equal to logic
Operation or it is described negate logical operation, obtain multiple operation results, wherein by first instruction state or it is described second instruction
The weight of state is respectively corresponding to respective operation result；
In the multiple operation result correspondence to different instruction state, the corresponding operation result of every kind of instruction state is obtained
Number, with the largest number of instruction states for the final instruction state；Alternatively, corresponding to difference in the multiple operation result
Instruction state when, obtain the weight of the corresponding operation result of every kind of instruction state and value, with weight and be worth maximum instruction
State is the final instruction state.
9. according to the method described in claim 4, it is characterized in that, to first instruction state and second instruction state
Execute weighted average logical operation, comprising:
When obtaining the instruction state of multiple traffic lights including first instruction state and second instruction state,
Red light phase in the instruction state of the multiple traffic lights is denoted as the first numerical value, by the instruction state of the multiple traffic lights
In green light phase be denoted as second value；
Third value is obtained after being weighted and averaged to the first all numerical value and second value, wherein each numerical value is corresponding
Weight is the weight of the instruction state used when obtaining the numerical value；
Obtain the first absolute value and the second value and described of the difference of first numerical value and the third value
Second absolute value of the difference of three numerical value；
When first absolute value is less than second absolute value, the final instruction state is determined as red light phase,
When first absolute value is greater than second absolute value, the final instruction state is determined as green light phase.
10. the method according to claim 1, wherein described determine according to the final instruction state for controlling
Make the control the signal whether vehicle continues traveling, comprising:
When the final instruction state is green light phase, the signal for continuing traveling for controlling the vehicle is determined；
When the final instruction state is red light phase or amber light state, determine to stop traveling for controlling the vehicle
Signal.
11. the method according to claim 1, wherein described obtain the vehicle in the vehicle at the current crossing
First instruction state of corresponding traffic lights of driving direction and the non-vehicle heading at the current crossing are corresponding
Traffic lights the second instruction state before, the method also includes:
At the current crossing, there are lanes when multiple traffic lights, being currently located according to the vehicle and/or the vehicle row
Direction is sailed, determines that the corresponding traffic lights of the vehicle heading and the non-vehicle heading are corresponding red green
Lamp.
12. according to the method described in claim 2, it is characterized in that, it is described in vehicle by before current crossing, described in acquisition
First instruction state and the current crossing of the vehicle in the corresponding traffic lights of vehicle heading at the current crossing
Before second instruction state of the corresponding traffic lights of the non-vehicle heading, the method also includes:
Obtain the mark at the current crossing；
Logical relation corresponding with the mark is read from server or the local storage being set in the vehicle.
13. according to the method described in claim 2, it is characterized in that, the method also includes:
In the state of identifying that the accuracy rate of first instruction state and second instruction state is greater than threshold value, described in detection
The actual logic relationship of display state between first instruction state and second instruction state whether with correction described first
The logical relation of instruction state is identical；
In the actual logic relationship and the logical relation difference, start the correction mechanism to the logical relation；
Modify the logical relation according to following manner: artificial nucleus are to the logical relation, alternatively, according to the acquisition of multiple vehicles
Actual logic relationship corrects the logical relation.
14. a kind of device for controlling vehicle driving characterized by comprising
Identification module, for obtaining the vehicle in the vehicle driving at the current crossing before vehicle is by current crossing
The non-vehicle heading at the first instruction state of the corresponding traffic lights in direction and the current crossing is corresponding red green
Second instruction state of lamp；
Module is obtained, for using second instruction state or first instruction state and second instruction state pair
First instruction state is corrected, and obtains the final instruction state of the corresponding traffic lights of the vehicle heading；
Determining module, for determining the control letter for whether continuing traveling for controlling the vehicle according to the final instruction state
Number；
Control module, for controlling the vehicle driving according to the control signal.
15. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to execute method described in any one of claim 1 to 13 when operation.
16. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to run the computer program to execute described in any one of claim 1 to 13
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910731308.6A CN110335484B (en) | 2019-08-08 | 2019-08-08 | Method and device for controlling vehicle to run |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910731308.6A CN110335484B (en) | 2019-08-08 | 2019-08-08 | Method and device for controlling vehicle to run |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110335484A true CN110335484A (en) | 2019-10-15 |
| CN110335484B CN110335484B (en) | 2021-03-12 |
Family
ID=68148937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910731308.6A Active CN110335484B (en) | 2019-08-08 | 2019-08-08 | Method and device for controlling vehicle to run |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110335484B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111289003A (en) * | 2020-02-06 | 2020-06-16 | 广州小马智行科技有限公司 | Path planning method, device, system, storage medium and processor |
| CN111932918A (en) * | 2020-10-14 | 2020-11-13 | 之江实验室 | Traffic signal lamp information fusion decision method for intelligent internet vehicle |
| CN112991791A (en) * | 2019-12-13 | 2021-06-18 | 上海商汤临港智能科技有限公司 | Traffic information identification and intelligent driving method, device, equipment and storage medium |
| CN113947917A (en) * | 2021-09-23 | 2022-01-18 | 联想(北京)有限公司 | Prompting method and device of signal display device, equipment and storage medium |
| WO2023231087A1 (en) * | 2022-05-31 | 2023-12-07 | 魔门塔(苏州)科技有限公司 | Traffic light status detection method and apparatus, storage medium, device, and vehicle |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102176287A (en) * | 2011-02-28 | 2011-09-07 | 无锡中星微电子有限公司 | Traffic signal lamp identifying system and method |
| JP2012098967A (en) * | 2010-11-02 | 2012-05-24 | Aisin Seiki Co Ltd | Traffic light detector, traffic light detection method and program |
| WO2014044272A1 (en) * | 2012-09-20 | 2014-03-27 | Conti Temic Microelectronic Gmbh | Method for calibrating a plurality of environment sensors in a vehicle |
| CN103729863A (en) * | 2013-12-06 | 2014-04-16 | 南京金智视讯技术有限公司 | Traffic light full-automatic positioning and recognizing method based on self-regulated learning |
| CN204087506U (en) * | 2014-09-17 | 2015-01-07 | 深圳市林润实业有限公司 | A kind of Combined traffic signal lamp indicating device |
| CN104346623A (en) * | 2013-08-05 | 2015-02-11 | 富士重工业株式会社 | Vehicle exterior environment recognition device |
| CN104537857A (en) * | 2014-12-11 | 2015-04-22 | 广东好帮手电子科技股份有限公司 | Reminding method and system for recognizing traffic lights on basis of automobile video recorder |
| CN104574960A (en) * | 2014-12-25 | 2015-04-29 | 宁波中国科学院信息技术应用研究院 | Traffic light recognition method |
| CN105678316A (en) * | 2015-12-29 | 2016-06-15 | 大连楼兰科技股份有限公司 | Active driving method based on multi-information fusion |
| CN106004883A (en) * | 2016-05-24 | 2016-10-12 | 北京小米移动软件有限公司 | Vehicle violation reminding method and device |
| CN106023619A (en) * | 2016-06-17 | 2016-10-12 | 乐视控股（北京）有限公司 | Traffic signal lamp information obtaining method, device and vehicle |
| CN106504554A (en) * | 2016-09-30 | 2017-03-15 | 乐视控股（北京）有限公司 | The method and device of identification traffic light status information |
| US9707960B2 (en) * | 2014-07-31 | 2017-07-18 | Waymo Llc | Traffic signal response for autonomous vehicles |
| CN107221176A (en) * | 2017-06-23 | 2017-09-29 | 安徽超清科技股份有限公司 | intelligent vehicle safety traffic system |
| EP3340204A1 (en) * | 2016-12-22 | 2018-06-27 | Urban Software Institute GmbH | Computer system and method for determining reliable vehicle control instructions |
| CN108510760A (en) * | 2018-05-28 | 2018-09-07 | 深圳市零度智控科技有限公司 | Communication control method, device based on traffic lights and computer readable storage medium |
| CN108629999A (en) * | 2018-05-17 | 2018-10-09 | 淘然视界(杭州)科技有限公司 | A kind of automobile identification traffic lights method, electronic equipment, storage medium and system |
| CN109035831A (en) * | 2018-09-07 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Recognition methods, device, equipment, storage medium and the vehicle of traffic light |
| CN109389836A (en) * | 2017-08-03 | 2019-02-26 | 杭州海康威视数字技术股份有限公司 | Control method, device, system and the controller of traffic lights |
| CN109544955A (en) * | 2018-12-26 | 2019-03-29 | 广州小鹏汽车科技有限公司 | A kind of state acquiring method and system of traffic lights |
| CN109671286A (en) * | 2018-12-26 | 2019-04-23 | 东软睿驰汽车技术（沈阳）有限公司 | A kind for the treatment of method and apparatus of road information and Traffic Information |
-
2019
- 2019-08-08 CN CN201910731308.6A patent/CN110335484B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012098967A (en) * | 2010-11-02 | 2012-05-24 | Aisin Seiki Co Ltd | Traffic light detector, traffic light detection method and program |
| CN102176287A (en) * | 2011-02-28 | 2011-09-07 | 无锡中星微电子有限公司 | Traffic signal lamp identifying system and method |
| WO2014044272A1 (en) * | 2012-09-20 | 2014-03-27 | Conti Temic Microelectronic Gmbh | Method for calibrating a plurality of environment sensors in a vehicle |
| CN104346623A (en) * | 2013-08-05 | 2015-02-11 | 富士重工业株式会社 | Vehicle exterior environment recognition device |
| CN103729863A (en) * | 2013-12-06 | 2014-04-16 | 南京金智视讯技术有限公司 | Traffic light full-automatic positioning and recognizing method based on self-regulated learning |
| US9707960B2 (en) * | 2014-07-31 | 2017-07-18 | Waymo Llc | Traffic signal response for autonomous vehicles |
| CN204087506U (en) * | 2014-09-17 | 2015-01-07 | 深圳市林润实业有限公司 | A kind of Combined traffic signal lamp indicating device |
| CN104537857A (en) * | 2014-12-11 | 2015-04-22 | 广东好帮手电子科技股份有限公司 | Reminding method and system for recognizing traffic lights on basis of automobile video recorder |
| CN104574960A (en) * | 2014-12-25 | 2015-04-29 | 宁波中国科学院信息技术应用研究院 | Traffic light recognition method |
| CN105678316A (en) * | 2015-12-29 | 2016-06-15 | 大连楼兰科技股份有限公司 | Active driving method based on multi-information fusion |
| CN106004883A (en) * | 2016-05-24 | 2016-10-12 | 北京小米移动软件有限公司 | Vehicle violation reminding method and device |
| CN106023619A (en) * | 2016-06-17 | 2016-10-12 | 乐视控股（北京）有限公司 | Traffic signal lamp information obtaining method, device and vehicle |
| CN106504554A (en) * | 2016-09-30 | 2017-03-15 | 乐视控股（北京）有限公司 | The method and device of identification traffic light status information |
| EP3340204A1 (en) * | 2016-12-22 | 2018-06-27 | Urban Software Institute GmbH | Computer system and method for determining reliable vehicle control instructions |
| CN107221176A (en) * | 2017-06-23 | 2017-09-29 | 安徽超清科技股份有限公司 | intelligent vehicle safety traffic system |
| CN109389836A (en) * | 2017-08-03 | 2019-02-26 | 杭州海康威视数字技术股份有限公司 | Control method, device, system and the controller of traffic lights |
| CN108629999A (en) * | 2018-05-17 | 2018-10-09 | 淘然视界(杭州)科技有限公司 | A kind of automobile identification traffic lights method, electronic equipment, storage medium and system |
| CN108510760A (en) * | 2018-05-28 | 2018-09-07 | 深圳市零度智控科技有限公司 | Communication control method, device based on traffic lights and computer readable storage medium |
| CN109035831A (en) * | 2018-09-07 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Recognition methods, device, equipment, storage medium and the vehicle of traffic light |
| CN109544955A (en) * | 2018-12-26 | 2019-03-29 | 广州小鹏汽车科技有限公司 | A kind of state acquiring method and system of traffic lights |
| CN109671286A (en) * | 2018-12-26 | 2019-04-23 | 东软睿驰汽车技术（沈阳）有限公司 | A kind for the treatment of method and apparatus of road information and Traffic Information |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991791A (en) * | 2019-12-13 | 2021-06-18 | 上海商汤临港智能科技有限公司 | Traffic information identification and intelligent driving method, device, equipment and storage medium |
| CN112991791B (en) * | 2019-12-13 | 2022-07-26 | 上海商汤临港智能科技有限公司 | Traffic information identification and intelligent driving method, device, equipment and storage medium |
| CN111289003A (en) * | 2020-02-06 | 2020-06-16 | 广州小马智行科技有限公司 | Path planning method, device, system, storage medium and processor |
| CN111932918A (en) * | 2020-10-14 | 2020-11-13 | 之江实验室 | Traffic signal lamp information fusion decision method for intelligent internet vehicle |
| CN111932918B (en) * | 2020-10-14 | 2020-12-18 | 之江实验室 | Traffic signal lamp information fusion decision method for intelligent internet vehicle |
| CN113947917A (en) * | 2021-09-23 | 2022-01-18 | 联想(北京)有限公司 | Prompting method and device of signal display device, equipment and storage medium |
| CN113947917B (en) * | 2021-09-23 | 2023-10-24 | 联想(北京)有限公司 | Prompting method and device for signal display device, equipment and storage medium |
| WO2023231087A1 (en) * | 2022-05-31 | 2023-12-07 | 魔门塔(苏州)科技有限公司 | Traffic light status detection method and apparatus, storage medium, device, and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110335484B (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335484A (en) | Control the method and device of vehicle driving | |
| CN107571864B (en) | The collecting method and device of automatic driving vehicle | |
| CN111695546B (en) | Traffic signal lamp identification method and device for unmanned vehicle | |
| CN105719499B (en) | Traffic Sign Recognition test method and device | |
| CN109035832A (en) | Signal lamp intersection intelligence traffic system based on V2X communication | |
| CN113781808A (en) | Method and system for passing internet-connected automatic driving vehicle at traffic light intersection | |
| CN108961803A (en) | Vehicle drive assisting method, device, system and terminal device | |
| CN110782673A (en) | Vehicle violation identification and detection system based on unmanned aerial vehicle shooting cloud computing | |
| CN106297342A (en) | A kind of in advance, the alarm set of real-time prompting traffic light information and method | |
| CN111178735B (en) | Test evaluation method, device and system for automatic driving function | |
| CN107024927A (en) | A kind of automated driving system and method | |
| CN106154834A (en) | For the method and apparatus controlling automatic driving vehicle | |
| CN109084794A (en) | A kind of paths planning method | |
| CN105096631A (en) | Traffic condition prompting method, device and system | |
| CN104794883A (en) | Taxi calling method and device | |
| CN107813830A (en) | A kind of method and device for aiding in vehicle drive | |
| CN109544940A (en) | Bus special lane road occupying capturing system and its grasp shoot method based on trinocular vision | |
| CN108734976B (en) | Traffic navigation prompting method and system | |
| CN110400480A (en) | Information processing method, device, equipment and medium based on traffic communication station | |
| CN116010854B (en) | Abnormality cause determination method, abnormality cause determination device, electronic device and storage medium | |
| CN108082218A (en) | A kind of locomotive shunting device, method and system | |
| WO2023005636A1 (en) | Sensing capability information generation method, and use method and apparatus | |
| CN110239518A (en) | A kind of lateral direction of car position control method and device | |
| WO2022170540A1 (en) | Method and device for traffic light detection | |
| CN111532282B (en) | Automatic driving coordination method, device and storage medium based on external environment and vehicle condition |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210203 Address after: 100094 19 / F, block A1, Zhongguancun No.1, 81 Beiqing Road, Haidian District, Beijing Applicant after: BEIJING XIAOMA HUIXING TECHNOLOGY Co.,Ltd. Address before: 100094 room 01, 1st floor, building 2, yard 68, Beiqing Road, Haidian District, Beijing Applicant before: BEIJING PONY.AI SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |