CN110335484B - Method and device for controlling vehicle to run - Google Patents
Method and device for controlling vehicle to run Download PDFInfo
- Publication number
- CN110335484B CN110335484B CN201910731308.6A CN201910731308A CN110335484B CN 110335484 B CN110335484 B CN 110335484B CN 201910731308 A CN201910731308 A CN 201910731308A CN 110335484 B CN110335484 B CN 110335484B
- Authority
- CN
- China
- Prior art keywords
- state
- indication state
- indication
- vehicle
- final
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
The application provides a method and a device for controlling a vehicle to run, wherein the method comprises the following steps: when the traffic lights are identified, the states of the traffic lights at the intersection are collected, the traffic lights in the vehicle running direction are judged according to the logical relation among the traffic lights, the vehicle driving traffic accidents caused by the condition that scenes such as backlight and the like wrongly identify the traffic light state in the vehicle running direction are avoided, and the problem that the vehicle control is easy to make mistakes due to the low identification accuracy of the traffic lights in the related technology is solved.
Description
Technical Field
The present application relates to, but is not limited to, the field of intelligent driving, and in particular, to a method and an apparatus for controlling vehicle driving.
Background
In the related art, traffic light identification is an important functional module in an automatic driving system, and the identification accuracy of the traffic light identification is related to the safety of the automatic driving system. At present, a computer vision method is commonly used, image data of a large number of traffic lights are collected or acquired in advance, a traffic light identification model (various machine learning methods or deep learning networks can be selected) is obtained through training, then the model is loaded to a vehicle-mounted end of an automatic driving system, after a vehicle runs to a traffic light intersection, images acquired by a camera in real time are input into the model, results of 'red', 'green', 'yellow', 'unrecognizable' are obtained through calculation, and the results are provided for other modules of the automatic driving system for use, for example, a path planning module needs to plan a route for gradually decelerating and stopping the vehicle before a stopping line under the condition that the front is a red light. Fig. 1 is a flowchart of a typical traffic light recognition method in the related art, and as shown in fig. 1, a camera of a vehicle-mounted computer acquires a traffic light photo, then the photo is segmented, and a model trained by a cloud computer is used for image recognition to recognize a traffic light state. And the cloud computer uses the picture training model to obtain a model result, and then uses the model result to perform image recognition.
In the traffic light identification method in the related art, due to the limitation of model training data, the identification result cannot be guaranteed to be correct, and a certain error rate exists, and for an automatic driving system, if traffic light identification is carried out, serious traffic accidents can be caused, and the safety of passengers and pedestrians is harmed. For the identification of a single lamp, the error rate can be reduced by adding more data with a better model, but when the error rate is reduced to a certain degree, the difficulty of continuously reducing the error rate is increased. Especially for some special cases, the human eye can hardly distinguish, and the computer vision method can hardly identify accurately, such as: backlighting, lamp damage, lamp smudges, rain, snow, fog weather, being blocked, etc.
Aiming at the problem that vehicle control is easy to make mistakes due to low identification accuracy of traffic lights in the related art, no effective solution is available at present.
Disclosure of Invention
The embodiment of the application provides a method and a device for controlling a vehicle to run, and aims to at least solve the problem that vehicle control is prone to making mistakes due to low traffic light identification accuracy in the related art.
According to an embodiment of the present application, there is provided a method of controlling travel of a vehicle, including: before a vehicle passes through a current intersection, acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the vehicle driving direction at the current intersection; correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction; determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state; and controlling the vehicle to run according to the control signal.
According to another embodiment of the present application, there is also provided an apparatus for controlling running of a vehicle, including: the identification module is used for acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the non-vehicle driving direction at the current intersection before the vehicle passes through the current intersection; the acquisition module is used for correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction; the determining module is used for determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state; and the control module is used for controlling the vehicle to run according to the control signal.
According to a further embodiment of the present application, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present application, there is also provided an electronic device, comprising a memory in which a computer program is stored and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
According to the method and the device, before the vehicle passes through the current intersection, a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the vehicle driving direction of the current intersection are obtained; correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction; determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state; and controlling the vehicle to run according to the control signal. By adopting the scheme, when the traffic lights are identified, the states of the plurality of traffic lights at the intersection are collected, not only are the traffic lights in the vehicle running direction, but also the traffic light states in the vehicle running direction are judged according to the logical relation among the plurality of traffic lights, so that the traffic accidents of vehicle driving caused by the wrong identification of the traffic light states in the running direction by scenes such as backlight and the like are avoided, and the problem that the vehicle control is easy to make mistakes due to the low identification accuracy of the traffic lights in the related technology is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a typical traffic light recognition method according to the related art;
fig. 2 is a block diagram of a hardware configuration of a computer terminal of a method of controlling a vehicle to travel according to an embodiment of the present application;
FIG. 3 is a flow chart of a method of controlling travel of a vehicle according to an embodiment of the present application;
fig. 4 is a schematic view of a scene in which a vehicle passes through a traffic light intersection according to an embodiment of the present application.
Detailed Description
The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Example one
The method provided by the first embodiment of the present application may be executed in a computer terminal, or a similar computing device. Taking a computer terminal as an example, fig. 2 is a hardware structure block diagram of a computer terminal of a method for controlling vehicle driving according to an embodiment of the present application, and as shown in fig. 2, the computer terminal may include one or more processors 202 (only one is shown in fig. 2) (the processor 202 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), and a memory 204 for storing data, and optionally, the computer terminal may further include a transmission device 206 for communication function and an input/output device 208. It will be understood by those skilled in the art that the structure shown in fig. 2 is only an illustration, and is not intended to limit the structure of the computer terminal. For example, the computer terminal may also include more or fewer components than shown in FIG. 2, or have a different configuration than shown in FIG. 2.
The memory 204 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the method for controlling the vehicle to run in the embodiment of the present application, and the processor 202 executes various functional applications and data processing by running the software programs and modules stored in the memory 204, so as to implement the method described above. Memory 204 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 204 may further include memory located remotely from the processor 202, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 206 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 206 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 206 can be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In the present embodiment, a method for controlling vehicle running, which is executed on the computer terminal, is provided, and fig. 3 is a flowchart of the method for controlling vehicle running according to the embodiment of the present application, and as shown in fig. 3, the flowchart includes the following steps:
step S302, before a vehicle passes through a current intersection, acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the vehicle driving direction of the current intersection;
traffic light states may include red, green, yellow, and unrecognizable states, such as branch occlusion. The traffic light state can be obtained by shooting a traffic light picture, and the traffic light state automatically sent by roadside traffic light brackets can also be obtained by the Internet of vehicles technology.
The computer terminal for executing the scheme can be integrated on the vehicle and also can be arranged on the cloud server, but the computer terminal can be arranged on the vehicle to react to the traffic light state more timely in view of the real-time performance of communication.
Step S304, correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction;
when the first indication state is unrecognizable, the weight of the first indication state may be set to 0, that is, the final indication state of the traffic light in the vehicle traveling direction is determined according to the plurality of second indication states regardless of the first indication state.
The basis for correcting the first indication state may be a calculation formula, different weights are set for different traffic lights in the formula, and states of different probabilities of the same traffic light have different weights, for example, when a picture is clearly taken, the probability that the current driving direction is the red light is identified to be 99%, the probability of the green light is 1%, and at this time, the output of the model can be obtained only by considering the traffic light state of the non-vehicle driving direction with less weight. On the contrary, if the red light and green light probabilities in the driving direction are respectively 40% for shooting the backlight and other reasons, a larger weight needs to be set to consider the traffic light states in other non-vehicle driving directions, if the red light is in the non-driving direction, the probability of the green light in the current driving direction is increased, and finally the red light can be determined to be the green light to control the vehicle to continue driving. Here, by way of example only, further parameters, such as traffic light delay of intersecting roads, etc., may also be considered in the correction.
And step S306, determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state, and controlling the vehicle to run according to the control signal.
The method can be used in an automatic driving scene or a navigation scene, and reminds a driver of the state of the traffic light through voice prompt.
Through the steps, before a vehicle passes through a current intersection, a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the non-vehicle driving direction at the current intersection are obtained; correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction; determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state; and controlling the vehicle to run according to the control signal. By adopting the scheme, when the traffic lights are identified, the states of the plurality of traffic lights at the intersection are collected, not only the traffic lights in the vehicle running direction, but also the traffic lights in the vehicle running direction are judged according to the logical relation among the plurality of traffic lights, so that the traffic accidents caused by the wrong identification of the traffic light state in the running direction by scenes such as backlight and the like are avoided, and the problem that the vehicle control is easy to make mistakes due to the low identification accuracy of the traffic lights in the related technology is solved
Optionally, the correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction includes: correcting the first indication state by using the second indication state and the logical relationship, or the first indication state, the second indication state and the logical relationship to obtain a final indication state of a traffic light corresponding to the vehicle driving direction, wherein the logical relationship is a relationship between display states of different traffic lights at the current intersection, the final indication state is one of the indication states of the traffic lights, and the indication states of the traffic lights comprise one of the following states: red light state, green light state, yellow light state, unrecognizable state. By adopting the scheme, the first indication state is corrected by using the preset logical relation so as to increase the accuracy of traffic light identification.
Optionally, the correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction includes at least one of: performing an inversion logical operation on the second indication state, wherein when the inversion logical operation is performed, a result of performing the inversion logical operation on the second indication state is obtained from a preset mapping relation; executing an equal logical operation on the second indication state, wherein when the equal logical operation is executed, a result of the equal logical operation on the second indication state is obtained from a preset mapping relation; executing voting logic operation on the first indication state and the second indication state, wherein weights corresponding to the first indication state and the second indication state are determined according to preset confidence degrees corresponding to the first indication state and the second indication state respectively when the voting logic operation is executed; executing weighted average logic operation on the first indication state and the second indication state, wherein weights corresponding to the first indication state and the second indication state are determined according to preset confidence degrees corresponding to the first indication state and the second indication state respectively when the weighted average logic operation is executed; performing an and operation on the first indication state and the second indication state, wherein a result of performing the and operation on the first indication state and the second indication state is obtained from a preset mapping relation when the and operation is performed; and executing OR operation on the first indication state and the second indication state, wherein the result of the OR operation on the first indication state and the second indication state is obtained from a preset mapping relation when the OR operation is executed. By adopting the scheme, different processing modes are provided for the traffic light states in different directions, for example, the negation operation is performed on the traffic light of the intersected road, the equality operation is performed on the traffic light of the road in the opposite direction, and the like, which are only examples. The logic relationship of setting the traffic lights in the related art is complex, for example, the green light time of the pedestrian crossing in the same direction is shorter than the time of the motor vehicle lane, and the like, and the setting can be considered in the presetting.
Optionally, the performing an inverting logic operation on the second indication state includes: under the condition that the second indication state is an indication state of a traffic light corresponding to a direction intersecting with the vehicle driving direction, obtaining a result of performing the negation logic operation on the second indication state from the preset mapping relation to obtain a third indication state, wherein the preset mapping relation represents that: the result obtained by executing the negation logic operation on the green light state is the red light state, the result obtained by executing the negation logic operation on the yellow light state is the red light state, and the result obtained by executing the negation logic operation on the red light state is the yellow light state or the green light state; determining the first indication state as the final indication state when the first indication state is not an unrecognizable state and the third indication state is the same as the first indication state; or, when the first indication state is not the unrecognizable state and the third indication state is different from the first indication state, determining the first indication state as the final indication state; or when the first indication state is the unrecognizable state and the third indication state is not the unrecognizable state, determining the third indication state as the final indication state. The result of performing the negation logic operation on each indication state in the above embodiments is only an example, and other setting schemes may be provided.
Optionally, the determining a control signal for controlling whether the vehicle continues to run according to the final indication state includes: when the third indication state is a non-green light state, controlling the vehicle to stop running; and when the third indication state is a green light state and the final indication state is a red light state, controlling the vehicle to continue running after a preset delay. By adopting the scheme, traffic light delay of roads in opposite directions is fully considered, for example, when the red light is detected on the east-west direction road, the green light is displayed only after a delay commonly used by the intersection is added, and the south-north direction road is determined. Through the perfect integration of this kind of mode and the actual setting mode of traffic lights, guarantee traffic safety.
Optionally, the performing an equal to logical operation on the second indication state includes: when the second indication state is an indication state of a traffic light corresponding to a direction opposite to the vehicle running direction, obtaining a result of performing the logical operation on the second indication state from the preset mapping relation to obtain a fourth indication state, wherein the result of performing the logical operation on the red light state is the red light state, the result of performing the logical operation on the yellow light state is the yellow light state, and the result of performing the logical operation on the green light state is the green light state; when the fourth indication state is the same as the first indication state, determining the same indication state as the final indication state; or, when the first indication state is not a non-recognizable state and the fourth indication state is different from the first indication state, determining the first indication state as the final indication state; or, when the first indication state is the unrecognizable state, determining the fourth indication state as the final indication state.
Optionally, the obtaining a second indication state of the traffic light at the current intersection, which is not corresponding to the vehicle driving direction, includes: and acquiring the second indication states of the traffic lights corresponding to a plurality of directions in the current intersection, which are not the vehicle driving directions.
Optionally, performing a voting logic operation on the first indication state and the second indication state includes: performing the equality logic operation or the negation logic operation on each of the first indication state and the second indication state respectively to obtain a plurality of operation results, wherein weights of the first indication state or the second indication state respectively correspond to the respective operation results; when the plurality of operation results correspond to different indication states, acquiring the number of operation results corresponding to each indication state, and taking the indication state with the largest number as the final indication state; or when the plurality of operation results correspond to different indication states, acquiring a sum of weights of the operation results corresponding to each indication state, and taking the indication state with the largest weight sum as the final indication state. By adopting the scheme, the final indication state is selected in a voting mode, so that the determined final indication state is more accurate.
Optionally, performing a weighted average logical operation on the first indication state and the second indication state includes: when the indicating states of a plurality of traffic lights including the first indicating state and the second indicating state are obtained, recording a red light state in the indicating states of the plurality of traffic lights as a first numerical value, and recording a green light state in the indicating states of the plurality of traffic lights as a second numerical value; carrying out weighted average on all the first numerical values and the second numerical values to obtain third numerical values, wherein the weight corresponding to each numerical value is the weight of the indication state used when the numerical value is obtained; acquiring a first absolute value of a difference value between the first numerical value and the third numerical value and a second absolute value of a difference value between the second numerical value and the third numerical value; and when the first absolute value is smaller than the second absolute value, determining the final indication state as a red light state, and when the first absolute value is larger than the second absolute value, determining the final indication state as a green light state.
Optionally, the determining a control signal for controlling whether the vehicle continues to run according to the final indication state includes: when the final indication state is a green light state, determining a signal for controlling the vehicle to continuously run; and when the final indication state is a red light state or a yellow light state, determining a signal for controlling the vehicle to stop running.
Optionally, before the first indication state of the traffic lights corresponding to the vehicle driving direction of the vehicle at the current intersection and the second indication state of the traffic lights not corresponding to the vehicle driving direction at the current intersection are obtained, when a plurality of traffic lights exist at the current intersection, the traffic lights corresponding to the vehicle driving direction and the traffic lights not corresponding to the vehicle driving direction are determined according to the lane where the vehicle is currently located and/or the vehicle driving direction.
Optionally, before the vehicle passes through the current intersection, acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection, and acquiring an identifier of the current intersection before a second indication state of the traffic light corresponding to the vehicle non-driving direction at the current intersection; and reading the logic relation corresponding to the identification from a server or a local storage arranged in the vehicle. Different intersections have different logical relations, and different time periods of the same intersection can also have different logical relations, for example, the logical relation of the traffic flow in the peak period is different from the logical relation of the traffic flow in the non-peak period.
Optionally, in a state where the accuracy of identifying the first indication state and the second indication state is greater than a threshold, detecting whether an actual logical relationship of a display state between the first indication state and the second indication state is the same as the logical relationship of correcting the first indication state; when the actual logical relationship is different from the logical relationship, starting a correction mechanism of the logical relationship; modifying the logical relationship in accordance with: and manually checking the logical relationship, or correcting the logical relationship according to the actual logical relationship collected by a plurality of vehicles. By adopting the scheme, a correction mechanism of the logic relationship of the intersection is arranged, and the logic relationship is corrected in a manual checking mode or according to information fed back by a plurality of vehicles.
Optionally, the status of the traffic light is identified by one of the following: shooting a picture of the traffic light, and analyzing the picture to obtain the state of the traffic light; and acquiring an indicating signal which is sent by intersection traffic light equipment and used for indicating the state of the traffic light through the Internet of vehicles technology, and identifying the state of the traffic light according to the indicating signal.
The following description is made in conjunction with another embodiment of the present application.
The scheme does not change the identification method of a single traffic light, but identifies a plurality of lights with logical relations, and the identification error rate of the single light is equal to that of the original method, or the identification method of the single light in the method can be any method without limitation, and the method can play a great improvement role.
Fig. 4 is a schematic view of a scene that a vehicle passes through a traffic light intersection according to an embodiment of the present application, as shown in fig. 4, as shown in a typical scene schematic view, when the vehicle V travels to the intersection, it needs to go straight, and a general method is to identify a traffic light T1 controlling the straight direction, so as to determine whether to pass through the intersection. The designed method can identify T2 besides T1, because the states of T2 and T1 have a certain logical relationship, for example, when T2 is a green light, T1 is a red light, a T1 result can be obtained by certain logical calculation after the T2 state is obtained, and the T1 result and the T1 identification result are synthesized to achieve the purpose of improving the identification accuracy. By analogy, there are many methods of passing traffic light logical relationships (not limited to these logics):
the vehicle V moves straight, the T11 is another traffic light (multiple groups of lights indicate the same state) which is consistent with the T1 time, the state of the T11 is equal to the state of the T1, and the identification accuracy can be greatly improved by the information. The vehicle V travels straight, the T4 sidewalk lamp is additionally identified, and when the T4 is a green lamp, the T1 is a red lamp;
when the vehicle V turns left and additionally recognizes the T3 and the T3 green light, the T1 left turn light is a green light;
it should be noted that in order to provide a buffer for vehicles and pedestrians that have entered the intersection, there is a delay in the logical relationship of some lights, for example, when T2 changes from green to red, T1 will also keep the red light for a period of time, typically a few seconds, and then change to green, which factor needs to be taken into account when using the logical relationship.
The scheme of this example is illustrated by the following formula:
Status＝L(T1,T2,…,Ti)；
wherein Status represents the traffic light state which needs to be known finally, namely whether the current direction of the automatic driving vehicle to travel can pass or not; T1-Ti represent all traffic lights (not limited to the direction in which the vehicle is facing) that are helpful in identifying the current state Status; l represents a logical calculation, including but not limited to: equaling, negating, voting, and equal weighting average; different weights can be given to Ti according to the confidence coefficient during the addition and voting, so that a more accurate result is obtained;
alternatively, the logical relationship between the lamp and the lamp is relatively fixed at a certain intersection, but the intersection may be different from the intersection, and the same intersection may also be slightly different at different time periods, and these information may be collected in advance, stored into the memory according to the position and time of the intersection as key, and retrieved after traveling to a certain intersection, and this kind of information becomes a part of the high-precision map (but is not limited to this, and may also be stored in other forms).
Optionally, the accuracy of visual identification of the traffic light is a bottleneck, and using the internet of vehicles V2X technology, obtaining the traffic light state directly through wireless communication with the traffic light or from the cloud road network information will have higher stability and accuracy, but most roads do not have this condition at present.
By adopting the scheme, the invention utilizes the logical relation to carry out multi-lamp identification, and can greatly improve the accuracy; for example: for the scenario in fig. 4, if the single-light recognition accuracy is 99%, then T1 and T11 simply vote, and the recognition accuracy will increase to 99.99%; the method can greatly improve the accuracy of all traffic light identification methods based on single light, and does not limit a certain identification method.
Under the conditions of backlight, lamp damage, lamp dirt, severe weather of rain, snow and fog and lamp shielding, the single-lamp identification method cannot identify or obtain wrong results, the automatic driving vehicle cannot continue to run due to the incapability of identifying, and the vehicle runs through red light due to the wrong results, so that even accidents occur. The invention can obtain the current traffic light state by using the identification results of other lights, thereby enabling the automatic driving vehicle to continue driving under the above conditions and greatly improving the safety.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.
Example two
In this embodiment, a device for controlling the vehicle to run is also provided, and the device is used to implement the above embodiments and preferred embodiments, which have already been described and will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
According to an embodiment of the present application, there is provided an apparatus for controlling running of a vehicle, including:
the identification module is used for acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the non-vehicle driving direction at the current intersection before the vehicle passes through the current intersection;
the acquisition module is used for correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction;
the determining module is used for determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state;
and the control module is used for controlling the vehicle to run according to the control signal.
By adopting the scheme, when the traffic lights are identified, the states of the plurality of traffic lights at the intersection are collected, not only the traffic lights in the vehicle running direction, but also the traffic light states in the vehicle running direction are judged according to the logical relation among the plurality of traffic lights, so that the traffic accidents of vehicle driving caused by the condition that the traffic lights in the running direction are identified by mistake in scenes such as backlight and the like are avoided, and the problem that the vehicle control is easy to make mistakes due to the lower identification accuracy of the traffic lights in the related technology is solved.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
EXAMPLE III
Embodiments of the present application also provide a storage medium. Alternatively, in the present embodiment, the storage medium may be configured to store program codes for performing the following steps:
s1, before a vehicle passes through a current intersection, acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the non-vehicle driving direction at the current intersection;
s2, correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction;
and S3, determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state, and controlling the vehicle to run according to the control signal.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Embodiments of the present application further provide an electronic device comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, before a vehicle passes through a current intersection, acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the non-vehicle driving direction at the current intersection;
s2, correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction;
and S3, determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state, and controlling the vehicle to run according to the control signal.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (15)
1. A method of controlling travel of a vehicle, comprising:
before a vehicle passes through a current intersection, acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the vehicle driving direction at the current intersection;
correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction;
determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state;
controlling the vehicle to run according to the control signal,
the correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction includes:
correcting the first indication state by using the second indication state and the logical relationship, or the first indication state, the second indication state and the logical relationship to obtain a final indication state of a traffic light corresponding to the vehicle driving direction, wherein the logical relationship is a relationship between display states of different traffic lights at the current intersection, the final indication state is one of the indication states of the traffic lights, and the indication states of the traffic lights comprise one of the following states: red light state, green light state, yellow light state, unrecognizable state.
2. The method according to claim 1, wherein the correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction comprises at least one of:
performing an inversion logical operation on the second indication state, wherein when the inversion logical operation is performed, a result of performing the inversion logical operation on the second indication state is obtained from a preset mapping relation;
executing an equal logical operation on the second indication state, wherein when the equal logical operation is executed, a result of the equal logical operation on the second indication state is obtained from a preset mapping relation;
executing voting logic operation on the first indication state and the second indication state, wherein weights corresponding to the first indication state and the second indication state are determined according to preset confidence degrees corresponding to the first indication state and the second indication state respectively when the voting logic operation is executed;
executing weighted average logic operation on the first indication state and the second indication state, wherein weights corresponding to the first indication state and the second indication state are determined according to preset confidence degrees corresponding to the first indication state and the second indication state respectively when the weighted average logic operation is executed;
performing an and operation on the first indication state and the second indication state, wherein a result of performing the and operation on the first indication state and the second indication state is obtained from a preset mapping relation when the and operation is performed;
and executing OR operation on the first indication state and the second indication state, wherein the result of the OR operation on the first indication state and the second indication state is obtained from a preset mapping relation when the OR operation is executed.
3. The method of claim 2, wherein said performing an inversion logic operation on said second indication state comprises:
under the condition that the second indication state is an indication state of a traffic light corresponding to a direction intersecting with the vehicle driving direction, obtaining a result of performing the negation logic operation on the second indication state from the preset mapping relation to obtain a third indication state, wherein the preset mapping relation represents that: the result obtained by executing the negation logic operation on the green light state is the red light state, the result obtained by executing the negation logic operation on the yellow light state is the red light state, and the result obtained by executing the negation logic operation on the red light state is the yellow light state or the green light state;
determining the first indication state as the final indication state when the first indication state is not an unrecognizable state and the third indication state is the same as the first indication state; or, when the first indication state is not the unrecognizable state and the third indication state is different from the first indication state, determining the first indication state as the final indication state; or when the first indication state is the unrecognizable state and the third indication state is not the unrecognizable state, determining the third indication state as the final indication state.
4. The method of claim 3, wherein determining a control signal for controlling whether the vehicle continues to travel based on the final indication state comprises:
when the third indication state is a non-green light state, controlling the vehicle to stop running;
and when the third indication state is a green light state and the final indication state is a red light state, controlling the vehicle to continue running after a preset delay.
5. The method of claim 2, wherein performing an equality logic operation on the second indication state comprises:
when the second indication state is the indication state of the traffic light corresponding to the direction opposite to the vehicle running direction, obtaining a result of performing the logical operation on the second indication state from the preset mapping relation to obtain a fourth indication state, wherein the result of performing the logical operation on the red light state is the red light state, the result of performing the logical operation on the yellow light state is the yellow light state, and the result of performing the logical operation on the green light state is the green light state;
when the fourth indication state is the same as the first indication state, determining the same indication state as the final indication state; or, when the first indication state is not a non-recognizable state and the fourth indication state is different from the first indication state, determining the first indication state as the final indication state; or, when the first indication state is the unrecognizable state, determining the fourth indication state as the final indication state.
6. The method of claim 2, wherein said obtaining a second indication state of a traffic light at the current intersection that does not correspond to the direction of travel of the vehicle comprises:
and acquiring the second indication states of the traffic lights corresponding to a plurality of directions in the current intersection, which are not the vehicle driving directions.
7. The method of claim 6, wherein performing a voting logic operation on the first indication state and the second indication state comprises:
performing the equality logic operation or the negation logic operation on each of the first indication state and the second indication state respectively to obtain a plurality of operation results, wherein weights of the first indication state or the second indication state respectively correspond to the respective operation results;
when the plurality of operation results correspond to different indication states, acquiring the number of operation results corresponding to each indication state, and taking the indication state with the largest number as the final indication state; or when the plurality of operation results correspond to different indication states, acquiring a sum of weights of the operation results corresponding to each indication state, and taking the indication state with the largest weight sum as the final indication state.
8. The method of claim 3, wherein performing a weighted average logical operation on the first indication state and the second indication state comprises:
when the indicating states of a plurality of traffic lights including the first indicating state and the second indicating state are obtained, recording a red light state in the indicating states of the plurality of traffic lights as a first numerical value, and recording a green light state in the indicating states of the plurality of traffic lights as a second numerical value;
carrying out weighted average on all the first numerical values and the second numerical values to obtain third numerical values, wherein the weight corresponding to each numerical value is the weight of the indication state used when the numerical value is obtained;
acquiring a first absolute value of a difference value between the first numerical value and the third numerical value and a second absolute value of a difference value between the second numerical value and the third numerical value;
and when the first absolute value is smaller than the second absolute value, determining the final indication state as a red light state, and when the first absolute value is larger than the second absolute value, determining the final indication state as a green light state.
9. The method of claim 1, wherein determining a control signal for controlling whether the vehicle continues to travel based on the final indication state comprises:
when the final indication state is a green light state, determining a signal for controlling the vehicle to continuously run;
and when the final indication state is a red light state or a yellow light state, determining a signal for controlling the vehicle to stop running.
10. The method of claim 1, wherein before obtaining a first indication state of a traffic light corresponding to a vehicle driving direction of the vehicle at the current intersection and a second indication state of a traffic light corresponding to a non-vehicle driving direction of the current intersection, the method further comprises:
when a plurality of traffic lights exist at the current intersection, according to the current lane of the vehicle and/or the vehicle running direction, the traffic light corresponding to the vehicle running direction and the traffic light corresponding to the non-vehicle running direction are determined.
11. The method of claim 1, wherein before the vehicle passes through the current intersection, a first indication state of a traffic light corresponding to a vehicle driving direction of the vehicle at the current intersection and a second indication state of a traffic light corresponding to a non-vehicle driving direction of the current intersection are obtained, and the method further comprises:
acquiring the identifier of the current intersection;
and reading the logic relation corresponding to the identification from a server or a local storage arranged in the vehicle.
12. The method of claim 1, further comprising:
detecting whether an actual logical relationship of a display state between the first indication state and the second indication state is the same as the logical relationship correcting the first indication state in a state where it is identified that accuracy of the first indication state and the second indication state is greater than a threshold value;
when the actual logical relationship is different from the logical relationship, starting a correction mechanism of the logical relationship;
modifying the logical relationship in accordance with: and manually checking the logical relationship, or correcting the logical relationship according to the actual logical relationship collected by a plurality of vehicles.
13. An apparatus for controlling running of a vehicle, characterized by comprising:
the identification module is used for acquiring a first indication state of a traffic light corresponding to the vehicle driving direction of the vehicle at the current intersection and a second indication state of the traffic light corresponding to the non-vehicle driving direction at the current intersection before the vehicle passes through the current intersection;
the acquisition module is used for correcting the first indication state by using the second indication state or the first indication state and the second indication state to obtain a final indication state of a traffic light corresponding to the vehicle driving direction;
the determining module is used for determining a control signal for controlling whether the vehicle continues to run or not according to the final indication state;
a control module for controlling the vehicle to run according to the control signal,
the obtaining module comprises an obtaining submodule, and the obtaining submodule is used for correcting the first indication state by using the second indication state and the logic relationship, or the first indication state, the second indication state and the logic relationship, so as to obtain a final indication state of a traffic light corresponding to the vehicle driving direction, wherein the logic relationship is a relationship between display states of different traffic lights at the current intersection, the final indication state is one of the indication states of the traffic lights, and the indication states of the traffic lights comprise one of the following states: red light state, green light state, yellow light state, unrecognizable state.
14. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 12 when executed.
15. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 12.
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 CN110335484A (en) | 2019-10-15 |
| CN110335484B true 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) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111932918B (en) * | 2020-10-14 | 2020-12-18 | 之江实验室 | Traffic signal lamp information fusion decision method for intelligent internet vehicle |
| 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 |
| CN117218822A (en) * | 2022-05-31 | 2023-12-12 | 魔门塔(苏州)科技有限公司 | Method and device for detecting state of traffic light, storage medium, equipment and vehicle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
Family Cites Families (10)
| 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 |
| CN102176287B (en) * | 2011-02-28 | 2013-11-20 | 无锡中星微电子有限公司 | Traffic signal lamp identifying system and method |
| DE102012108862A1 (en) * | 2012-09-20 | 2014-05-28 | Continental Teves Ag & Co. Ohg | Method for calibrating several environment sensors in a vehicle |
| CN103729863B (en) * | 2013-12-06 | 2016-05-25 | 南京金智视讯技术有限公司 | Traffic lights automatic location based on autonomous learning is known method for distinguishing |
| CN104537857B (en) * | 2014-12-11 | 2017-06-23 | 广东好帮手电子科技股份有限公司 | Based reminding method and system based on driving video instrument identification traffic-control device |
| CN104574960B (en) * | 2014-12-25 | 2016-08-24 | 宁波中国科学院信息技术应用研究院 | A kind of traffic lights recognition methods |
| CN105678316B (en) * | 2015-12-29 | 2019-08-27 | 大连楼兰科技股份有限公司 | Active drive manner based on multi-information fusion |
| CN106004883B (en) * | 2016-05-24 | 2018-12-11 | 北京小米移动软件有限公司 | The method and device that rule-breaking vehicle is reminded |
| 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 |
| 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 (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346623A (en) * | 2013-08-05 | 2015-02-11 | 富士重工业株式会社 | Vehicle exterior environment recognition device |
| 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 |
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110335484A (en) | 2019-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335484B (en) | Method and device for controlling vehicle to run | |
| CN110146097B (en) | Method and system for generating automatic driving navigation map, vehicle-mounted terminal and server | |
| US20190004517A1 (en) | Method and apparatus for generating automatic driving strategy | |
| CN111046709A (en) | Vehicle lane level positioning method and system, vehicle and storage medium | |
| CN111178735B (en) | Test evaluation method, device and system for automatic driving function | |
| CN110174110B (en) | Map corresponding method and device, electronic equipment and computer readable medium | |
| JP5522475B2 (en) | Navigation device | |
| CN110162589B (en) | Road speed limit value assignment method and device, electronic equipment and computer readable medium | |
| CN110765224A (en) | Processing method of electronic map, vehicle vision repositioning method and vehicle-mounted equipment | |
| CN108415051A (en) | Method for correcting error, device and the storage medium of vehicle position information | |
| US11312393B2 (en) | Artificially falsifying sensor data to initiate a safety action for an autonomous vehicle | |
| CN116010854B (en) | Abnormality cause determination method, abnormality cause determination device, electronic device and storage medium | |
| CN111661054B (en) | Vehicle control method, device, electronic device and storage medium | |
| CN112215042A (en) | Parking space limiter identification method and system and computer equipment | |
| WO2022170540A1 (en) | Method and device for traffic light detection | |
| CN111400531B (en) | Target labeling method, device, equipment and computer readable storage medium | |
| CN116052119A (en) | Traffic light detection method and device, electronic equipment and computer readable storage medium | |
| CN114972731A (en) | Traffic light detection and identification method and device, moving tool and storage medium | |
| CN112101177A (en) | Map construction method and device and carrier | |
| CN112721935A (en) | Vehicle control model training method, vehicle control method and device | |
| CN114127823A (en) | Determining signal status of traffic light device | |
| CN112733675A (en) | Vehicle driving behavior monitoring method, system, electronic device and storage medium | |
| CN113295181B (en) | Vehicle path planning method, device and system | |
| CN112669638A (en) | Vehicle safety passing method, system, terminal equipment and computer storage medium | |
| US11433920B2 (en) | Map-based prediction and mitigation of performance limitations for autonomous vehicles |
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 |