CN113665573B

CN113665573B - Vehicle running method, device, equipment and medium under unprotected left-turn working condition

Info

Publication number: CN113665573B
Application number: CN202111042812.9A
Authority: CN
Inventors: 李丰军; 周剑光; 谷俊
Original assignee: China Automotive Innovation Co Ltd
Current assignee: China Automotive Innovation Co Ltd
Priority date: 2021-09-07
Filing date: 2021-09-07
Publication date: 2023-02-28
Anticipated expiration: 2041-09-07
Also published as: CN113665573A

Abstract

The method comprises the steps of planning a running track point set of the current vehicle when the current vehicle drives into an intersection without a traffic indication sign and drives leftwards; acquiring left image data, right image data and front image data through image acquisition equipment; determining a first time parameter of the vehicle on the left side of the current vehicle driving to a first track point based on the acquired left image data; when the first time parameter is larger than a preset first preset time threshold value, controlling the vehicle to run to a first track point; determining a second time parameter of the current vehicle right side vehicle and the current vehicle opposite vehicle running to a second track point based on the acquired right side image data and the front image data; and when all the second time parameters are greater than the preset second time threshold value, controlling the vehicle to run to a second track point until the left turn is finished. The safety of the vehicle running under the working condition of left turn without protection is improved.

Description

Vehicle running method, device, equipment and medium under unprotected left-turn working condition

Technical Field

The invention relates to the technical field of vehicle control, in particular to a vehicle running method, a device, equipment and a medium under an unprotected left-turn working condition.

Background

With the rapid development of intelligent driving technology, advanced driving assistance functions such as lane change assistance LCA, automatic following ACC, lane keeping LKA, traffic congestion assistance TJA and the like are continuously applied to mass production of intelligent driving vehicles at present, but the above-mentioned intelligent driving functions are mostly performed on straight roads, and only the collision risk of a vehicle in front needs to be concerned, and the collision risk of an oncoming vehicle cannot be predicted.

Unprotected left turn refers to the process of making a left turn at an intersection without traffic lights or other guidance signs. Under the operating mode of driving without protection and turning left, the lateral collision risk of the self-vehicle is far greater than that of other driving operating modes, and the above-mentioned auxiliary driving function can not play a role in prompting the lateral risk.

When the vehicle runs under the working condition of left turn without protection, because the intersection has no traffic lights and guide signs, the coming vehicles in all directions can not stop according to the traffic and the like or the traffic sign indication, and a driver needs to pay attention to the coming vehicle states in at least three running directions of the left side, the right front and the right side in the driving process of left turn without protection and carefully drive and tentatively pass, so certain challenges and risks are brought to the driver with insufficient driving experience.

Disclosure of Invention

In order to solve the technical problems, the specific technical scheme is as follows:

in one aspect, a method of vehicle operation in an unprotected left turn condition is provided herein, the method comprising:

when a current vehicle enters a crossing without a traffic indication sign and the current vehicle drives to the left, planning a driving track point set of the current vehicle, wherein the driving track point set at least comprises: the first track point is a track point which is concentrated on the running track point and intersected with the running direction of the coming vehicle on the left side of the current vehicle, and the second track point is a track point which is concentrated on the running track point and intersected with the running direction of the coming vehicle opposite to the current vehicle;

continuously acquiring left-side image data on the left side of the current vehicle, right-side image data on the right side of the current vehicle and front image data in front of the current vehicle through image acquisition equipment arranged on two sides and in front of the current vehicle;

determining a first time parameter of the left vehicle of the current vehicle running to a first track point based on continuously acquired left image data;

when the first time parameter is larger than a preset first preset time threshold value, controlling the vehicle to run to the first track point;

determining a second time parameter of the current vehicle right side vehicle and the current vehicle opposite vehicle driving to a second track point based on continuously acquired right side image data and front image data;

and when all the second time parameters are greater than a second preset time threshold value, controlling the vehicle to run to the second track point until the current vehicle turns left.

Further, the image acquisition device that passes through setting up in present vehicle both sides and the place ahead is the left image data of continuous collection present vehicle left side, right side image data and the place ahead image data in right side, later still include:

constructing a grid map according to the continuously acquired left image data, the right image data and the front image data;

the method for determining the first time parameter of the vehicle on the left side of the current vehicle driving to the first track point based on the continuously acquired left side image data comprises the following steps:

determining continuous contour information of the vehicle on the left side of the current vehicle according to the continuously acquired left image data;

mapping continuous contour information of the vehicle on the left side of the current vehicle and the first track point to the grid map;

calculating first speed information of a vehicle on the left side of the current vehicle based on continuous contour information of the vehicle on the left side of the current vehicle in the grid map;

and determining a first time parameter of the current vehicle left side when the current vehicle runs to the first track point according to the first speed information and the distance information between the current vehicle left side vehicle and the first track point in the grid map.

Further, the constructing a grid map according to the continuously acquired left image data, the right image data and the front image data includes:

and mapping the pixels in the collected left image data, the right image data and the front image data to a pre-constructed grid model based on a homography transformation principle to obtain the grid map.

Further, the method further comprises:

acquiring attitude information of a current vehicle;

correcting the mapping relation of mapping pixels in the grid map according to the attitude information;

the step of mapping the continuous contour information of the vehicle on the left side of the current vehicle and the first track point into the grid map comprises the following steps:

and mapping continuous contour information of the vehicle on the left side of the current vehicle and the first track point into the grid map based on the mapping relation.

Further, the determining continuous contour information of the vehicle on the left side of the current vehicle according to the continuously acquired left side image data includes:

and inputting the continuously acquired left image data into a pre-constructed neural network model, and carrying out image recognition on the continuously acquired left image data to obtain continuous contour information of the left vehicle of the current vehicle.

Further, the method further comprises:

and when the first time parameter is not greater than a preset first preset time threshold or when the second time parameter is not greater than a preset second preset time threshold, generating prompt information to prompt the driver to wait in place.

Further, the prompt message is a voice prompt message and/or a light prompt message.

In another aspect, the present disclosure provides a vehicle driving apparatus in an unprotected left turn condition, the apparatus comprising:

the driving track point planning module is used for planning a driving track point set of the current vehicle when the current vehicle drives into a crossing without a traffic indication sign and the current vehicle drives leftwards, and the driving track point set at least comprises: the first track point is a track point which is concentrated in the running track point and intersected with the running direction of the coming vehicle on the left side of the current vehicle, and the first track point is a track point which is concentrated in the running track point and intersected with the running direction of the coming vehicle opposite to the current vehicle;

the image acquisition module is used for continuously acquiring left image data on the left side of the current vehicle, right image data on the right side of the current vehicle and front image data in front of the current vehicle through image acquisition equipment arranged on the two sides and in front of the current vehicle;

the first time parameter determining module is used for determining a first time parameter of the left vehicle of the current vehicle driving to a first track point based on continuously acquired left image data;

the first time parameter judging module is used for controlling the vehicle to run to the first track point when the first time parameter is greater than a preset first preset time threshold value;

the second time parameter determining module is used for determining a second time parameter of the current vehicle right side vehicle and the current vehicle opposite vehicle running to a second track point based on the continuously acquired right side image data and the front image data;

and the traveling module is used for controlling the vehicle to travel to the second track point when all the second time parameters are greater than a second preset time threshold value until the current vehicle turns left.

In yet another aspect, a computer-readable storage medium having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded by and executed by a processor to implement a method for vehicle driving in unprotected left-turn conditions as described above is provided.

In yet another aspect, provided herein is an electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the at least one processor implements the method for driving the vehicle under the unprotected left-turn condition by executing the instructions stored in the memory.

By adopting the technical scheme, the vehicle running method, the device, the equipment and the medium under the unprotected left-turn working condition can determine the running track of the left-turn of the current vehicle by planning the running track point set of the current vehicle when the current vehicle runs into the intersection without the traffic indication mark and the current vehicle runs leftwards, and continuously collect left-side image data, right-side image data and front-side image data of the left side of the current vehicle through the image collecting equipment arranged at the two sides and the front of the current vehicle; and determining whether the current vehicle can run according to the track with concentrated running track points through the continuously acquired image data so as to finish the left turning of the current vehicle. According to the method and the device, the time and distance information of the vehicles coming from different directions on the current vehicle running track can be determined only through image data, compared with the laser radar and millimeter wave radar schemes, the camera sensor is lower in cost, automatic driving under special driving scenes is achieved, and user satisfaction is improved.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments or technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic diagram illustrating steps of a vehicle driving method under an unprotected left turn condition provided in an embodiment herein;

FIG. 2 is a schematic diagram illustrating a vehicle driving scenario under an unprotected left turn condition provided in an embodiment herein;

fig. 3 illustrates a horizontal field angle schematic diagram of an image capture device provided in embodiments herein;

FIG. 4 is a schematic diagram illustrating steps of a vehicle driving method under an unprotected left turn condition provided in an embodiment herein;

FIG. 5 illustrates a schematic diagram of a left vehicle mapping to a grid map provided in embodiments herein;

FIG. 6 illustrates a schematic diagram of a right side vehicle and a front vehicle mapped to a grid map provided in embodiments herein;

FIG. 7 is a schematic diagram illustrating an unprotected left turn vehicle drive in accordance with an embodiment of the present invention;

fig. 8 shows a schematic structural diagram of an electronic device for driving a vehicle in an unprotected left-turn condition according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments herein without making any creative effort, shall fall within the scope of protection.

It should be noted that the terms "first," "second," and the like in the description and claims herein and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments herein described are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or device.

In order to solve the above problem, an embodiment of the present disclosure provides a method for driving a vehicle in an unprotected left-turn condition, where fig. 1 illustrates a schematic step diagram of the method for driving the vehicle in the unprotected left-turn condition provided in the embodiment of the present disclosure, and fig. 2 illustrates a schematic view of a scene in which the vehicle is driven in the unprotected left-turn condition provided in the embodiment of the present disclosure, as shown in fig. 1 and 2, the method is applied to a vehicle provided with at least three cameras in different directions, and the method may include the following steps:

step S102, when the current vehicle enters the intersection without the traffic indication sign and the current vehicle drives to the left, planning a driving track point set of the current vehicle, wherein the driving track point set at least comprises: first track point and second track point, first track point does travel track point concentrate with current vehicle left side come the crossing track point of direction of travel, second track point does travel track point concentrate with current vehicle subtend come the crossing track point of direction of travel.

In a specific implementation process, when the current vehicle enters the intersection without the traffic indication sign and the current vehicle drives to the left, the current vehicle can be determined by the navigation device inside the current vehicle and the real-time acquired front image data in front of the current vehicle, or determined according to the intention of the driver and the real-time acquired left side image data, right side image data and front image data in front of the current vehicle on the left side of the current vehicle. If the current vehicle drives to the intersection, the driver indicates that the driver has the intention of left steering by turning on the left steering lamp, and when the collected front image data is identified to have no traffic indication mark (traffic light and the like), the current vehicle can be determined to be about to drive to the intersection without the traffic indication mark, and the current vehicle drives to the left.

When the current vehicle drives into the crossing that does not have traffic indication sign and the current vehicle traveles to left, the vehicle computer of vehicle can confirm the environmental information at current crossing according to the image data of gathering, be the cross if current crossing, every side all has two rows of lanes, the vehicle computer of vehicle can plan the driving track point set that the current vehicle drove through current crossing according to the environmental information of gathering, including continuous a plurality of track points in the driving track point set, driving track point set still includes two at least orbit characteristic points: first track point and second track point. First track point does go track point concentrate with current vehicle left side arrival driving direction crossing track point, second track point does go track point concentrate with current vehicle opposite direction arrival driving direction crossing track point.

It is understood that the number of the track feature points may be determined according to the environment information, for example, when the number of lanes at the front intersection is large, the number of the track feature points may also be increased.

The driving track point set mentioned herein can have a plurality of track points, and when the vehicle drives to the next track point, the time parameter can be judged for other vehicles by adopting the method, and the vehicle continues to drive according to the next track point set in the driving track point set under the condition of meeting the requirement until the left turn is finished. As shown in fig. 2, the set of driving trace points may include at least 4 trace points, which are an initial trace point S0, a first trace point S1, a second trace point S2, and a third trace point S3.

And step S104, continuously acquiring left-side image data on the left side, right-side image data and front image data of the front of the current vehicle through image acquisition equipment arranged on the two sides and the front of the current vehicle.

The vehicle body can be provided with at least three image acquisition devices which can be cameras, wherein one front-view camera and two side front-view cameras are arranged. The front-view camera can be arranged behind a front windshield and used for collecting front image data in front of a vehicle, and the left and right rearview mirror supports can be respectively provided with a side front-view camera and used for collecting left-side image data on the left side of the vehicle and right-side image data on the right side of the vehicle, specifically, a horizontal view angle schematic diagram of the cameras at the three positions is shown in fig. 3, and fig. 3 shows a horizontal view angle schematic diagram of an image collecting device provided in the embodiment of the present disclosure.

It is understood that the three image capturing devices can capture the video data of the corresponding direction in real time, the video data may include a plurality of consecutive video image frames (image data), and adjacent video image frames may include the same content.

And S106, determining a first time parameter of the left vehicle driving to a first track point of the current vehicle based on continuously acquired left image data.

Specifically, the continuously acquired left image data may include vehicle image data of the left side of the current vehicle, and the vehicle speed information of the left side of the current vehicle may be determined by the continuously acquired left image data. It can be understood that the sampling time of the adjacently acquired left image data is known by the image acquisition device, and the relative position of the vehicle in the adjacent left image data can determine the phase displacement of the vehicle on the left side of the current vehicle corresponding to the sampling time according to an image transformation mode, so that the vehicle speed information on the left side of the current vehicle can be determined.

The first track point can be projected to the front image in a projection mode, the relative distance between the position of the vehicle on the left side of the current vehicle and the first track point is calculated, and the first time parameter can be determined based on the calculated vehicle speed information on the left side of the current vehicle and the relative distance between the position of the vehicle on the left side of the current vehicle and the first track point.

In some possible embodiments, the continuously acquiring left-side image data on the left side, right-side image data on the right side, and front-side image data on the front side of the current vehicle by the image acquisition devices arranged on both sides and in front of the current vehicle further comprises:

and constructing a grid map according to the continuously acquired left image data, the right image data and the front image data.

Specifically, pixels in the collected left image data, the collected right image data and the collected front image data are mapped to a pre-constructed grid model based on a homography transformation principle, so that the grid map is obtained.

The grid model may be a coordinate system at the bird's-eye view angle with the own vehicle as an origin, the length and width of the grid correspond to the physical world distance, and the current vehicle may be located at the right center below the boundary of the grid. According to the principle of homography transformation, a pixel region in a two-dimensional image acquired by three cameras and each grid in a grid model have a mutual mapping relation. The mapping relation can be calibrated by using ranging tools such as laser radar and the like. The mapping relation can be calibrated in advance, and the acquired left image data, right image data and front image data can be mapped to the grid model by using the mapping relation in practical application so as to complete the construction of the grid map. It will be appreciated that the grid map is also updated simultaneously with the captured image data, i.e. as the captured image data changes, the grid map is updated accordingly.

In some possible embodiments, fig. 4 shows a schematic step diagram of a vehicle driving method under an unprotected left-turn condition provided in an embodiment herein, and as shown in fig. 4, the determining a first time parameter for the vehicle on the left side of the current vehicle to drive to the first track point based on the continuously acquired left-side image data includes:

and S1062, determining continuous contour information of the vehicle on the left side of the current vehicle according to the continuously acquired left side image data.

Specifically, the continuously acquired left image data may be input to a pre-constructed neural network model, and the continuously acquired left image data may be subjected to image recognition to obtain continuous contour information of the vehicle on the left side of the current vehicle.

Specifically, the neural network model may be a trained deep learning network model, and the neural network model may detect a vehicle appearing in image data acquired by image acquisition devices corresponding to front-view images, left-view images and right-view images in a two-dimensional original image, and mark the detected vehicle with contour information of the vehicle in a position-marking manner, where the marked contour information may be a rectangular detection frame [ x, y, w, h ], where x is an abscissa of an upper left corner of the rectangular frame, y is an ordinate of the upper left corner of the rectangular frame, w is a width of the rectangular frame, and h is a height of the rectangular frame.

And S1064, mapping the continuous contour information of the vehicle on the left side of the current vehicle and the first track point to the grid map.

Specifically, fig. 5 shows a schematic diagram of a left vehicle mapped to a grid map provided in an embodiment of the present disclosure, fig. 6 shows a schematic diagram of a right vehicle and a front vehicle mapped to a grid map provided in an embodiment of the present disclosure, as shown in fig. 5 and 6, according to a principle of homography transformation, continuous contour information of a left vehicle of a current vehicle may be mapped to the grid map, and continuous contour information of a right vehicle and a front vehicle may be mapped to the grid map.

Step S1066, calculating first speed information of the vehicle on the left side of the current vehicle based on the continuous contour information of the vehicle on the left side of the current vehicle in the grid map.

And S1068, determining a first time parameter when the vehicle on the left side of the current vehicle runs to the first track point according to the first speed information and the distance information between the vehicle on the left side of the current vehicle and the first track point in the grid map.

The first track point can be mapped to the grid map in a projection mode, the relative distance between the vehicle on the left side of the current vehicle and the first track point can be determined on the grid map, the distance in the grid map is the same as the world distance (real distance), the relative distance between the vehicle on the left side of the current vehicle and the first track point in the grid map can be measured in a measuring mode, and the first time parameter can be determined based on the calculated vehicle speed information on the left side of the current vehicle and the calculated relative distance between the position of the vehicle on the left side of the current vehicle and the first track point.

And S108, when the first time parameter is larger than a preset first preset time threshold value, controlling the vehicle to run to the first track point.

Specifically, the preset first preset time threshold may be a time when the current vehicle moves to the first track point, or may be a preset time length. Only when the first time parameter is larger than a preset first preset time threshold value, it can be shown that the current vehicle does not collide with the vehicle on the left side of the current vehicle when the current vehicle runs to the first track point.

And when the first time parameter is greater than a preset first preset time threshold value, controlling the vehicle to run to a first track point by a driver or an automatic driving system of the vehicle. When the automatic driving function is turned off, when the first time parameter is greater than a preset first preset time threshold value, the driver can be prompted to drive to the first track point in a prompting mode. The prompting mode can be voice prompting, the moving distance of the current vehicle is detected, and when the current vehicle moves to the first track point and cannot drive forwards, the driver is prompted to park and wait for passing.

And step S110, determining a second time parameter of the right vehicle of the current vehicle and the second time parameter of the vehicle running to the second track point opposite to the current vehicle based on the continuously collected right image data and the front image data.

Specifically, based on the same manner of detecting the vehicle on the left side of the current vehicle, after the current vehicle moves to the first track point, a second time parameter of the vehicle on the right side of the current vehicle and the second time parameter of the vehicle opposite to the current vehicle running to the second track point can be calculated. It will be appreciated that each vehicle corresponds to a second time parameter.

And S112, when all the second time parameters are larger than a second preset time threshold value, controlling the vehicle to run to the second track point until the current vehicle turns left.

Specifically, the preset second preset time threshold may be a time when the current vehicle moves to the second track point, or may be a preset time length. And only when the second time parameter is greater than a preset second preset time threshold value, the fact that the current vehicle does not collide with the vehicle on the right side of the current vehicle and the oncoming vehicle when the current vehicle runs to the second track point can be indicated.

And when all the second time parameters are greater than a preset second preset time threshold value, the driver or an automatic driving system of the vehicle controls the vehicle to run to a second track point. When the automatic driving function is closed, when the second time parameter is greater than a preset second preset time threshold value, the driver can be prompted to drive to the second track point in a prompting mode. The prompting mode can be voice prompting, the moving distance of the current vehicle is detected, and when the current vehicle moves to the second track point, the current vehicle can be determined to turn completely.

On the basis of the above embodiment, in an embodiment of the present specification, the method further includes:

acquiring attitude information of a current vehicle;

and correcting the mapping relation of the mapping pixels in the grid map according to the attitude information.

Specifically, the grid map is a plane map based on a horizontal plane, and when the vehicle is in different postures, the grid map transmission is inclined, so that the grid model can receive posture information transmitted by a vehicle posture sensor and can be used for correcting grid and original pixel mapping errors caused by vehicle bump. Wherein the attitude information may include: the current steering wheel angle of the vehicle, the driving moment, the actual working moment, etc.

Specifically, when the posture of the vehicle is changed, the continuous contour information and the first track point of the vehicle on the left side of the current vehicle can be mapped into the grid map based on the corrected mapping relation, so that the dangerous driving of the vehicle caused by errors generated in distance calculation is avoided.

and when the first time parameter is not greater than a preset first preset time threshold or when the second time parameter is not greater than a preset second preset time threshold, generating prompt information to prompt a driver to wait in place.

Specifically, when the first time parameter is not greater than a preset first preset time threshold or when the second time parameter is not greater than a preset second preset time threshold, the vehicle is characterized to send a collision with other vehicles, and in order to avoid the collision, a driver is prompted to wait in place by a prompt message in a prompt mode, so that the collision is avoided. Wherein, the prompt message is a voice prompt message and/or a light prompt message.

For example, before the driver drives the vehicle to enter the S0 area first, it may be determined that the road condition is a road condition indicating that the vehicle runs without an indicator light, when the driver drives the vehicle to enter the S0 area first, the left-side forward-looking camera may collect the left-side direction coming vehicle, for example, A0 in fig. 2, the contour information of the left-side vehicle (for example, a rectangular detection frame) may be obtained through the neural network model, and the time T1 required for the vehicle A0 to reach S1 may be calculated by continuously collecting left-side image data. When T1 is smaller than a preset first time threshold, a prompt message can be sent to prompt a driver to wait in an S0 area in place, otherwise, the driver can be prompted to drive a vehicle to slowly move to an intersection to enter the S1 area, in the S1 area, a front-view camera of the vehicle can monitor a front oncoming vehicle, such as A2, meanwhile, a front-right camera of the vehicle can monitor an oncoming vehicle A1, the time T21 required by the vehicle A1 to reach the area S2 is calculated, the vehicle A2 to reach T22 is calculated, when the time T21 and the time T22 are not both larger than a second preset time threshold, an early warning prompt can be sent to prompt the driver to wait in the S1 area in place, and when the time T21 and the time T22 are both larger than the second preset time threshold, the driver drives the vehicle to slowly move to the S2 area and continuously move to the S3 area to finally complete an unprotected left turn process.

It can be understood that there may be a plurality of travel track point sets mentioned herein, and when the vehicle travels to the next track point, the above method may be adopted to determine the time parameter of other vehicles, and when the time parameter is satisfied, the vehicle continues to travel according to the next track point in the travel track point set until the left turn is completed. As shown in fig. 2, the travel track point set may include at least 4 track points, which are an initial track point S0, a first track point S1, a second track point S2, and a third track point S3.

When a current vehicle drives into an intersection without a traffic indication sign and the current vehicle drives leftwards, determining a left-turning driving track of the current vehicle by planning a driving track point set of the current vehicle, and continuously acquiring left-side image data on the left side, right-side image data and front-side image data of the current vehicle by image acquisition equipment arranged on the two sides and in front of the current vehicle; and determining whether the current vehicle can run according to the track with concentrated running track points through the continuously acquired image data so as to finish the left turning of the current vehicle. According to the method and the device, the time and distance information of the vehicles coming from different directions on the current vehicle running track can be determined only through image data, compared with the laser radar and millimeter wave radar schemes, the camera sensor is lower in cost, automatic driving under special driving scenes is achieved, and user satisfaction is improved.

In another aspect, the present invention provides a vehicle driving apparatus under an unprotected left turn condition, and fig. 7 shows a schematic structural diagram of the vehicle driving apparatus under an unprotected left turn condition in an embodiment of the present invention, as shown in fig. 7, the apparatus may include:

the driving track point planning module 11 is configured to plan a driving track point set of a current vehicle when the current vehicle drives into a crossing without a traffic indication sign and the current vehicle drives to the left, where the driving track point set at least includes: the first track point is a track point which is concentrated in the running track point and intersected with the running direction of the coming vehicle on the left side of the current vehicle, and the first track point is a track point which is concentrated in the running track point and intersected with the running direction of the coming vehicle opposite to the current vehicle;

the image acquisition module 12 is used for continuously acquiring left-side image data on the left side, right-side image data on the right side and front image data on the front side of the current vehicle through image acquisition equipment arranged on the two sides and the front of the current vehicle;

the first time parameter determining module 13 is configured to determine a first time parameter when a vehicle on the left side of the current vehicle travels to a first track point based on continuously acquired left side image data;

the first time parameter judging module 14 is configured to control the vehicle to travel to the first track point when the first time parameter is greater than a preset first preset time threshold;

the second time parameter determining module 15 is configured to determine a second time parameter when the current vehicle on the right side and the current vehicle heading vehicle travel to a second track point based on the continuously acquired right side image data and front image data;

and the traveling module 16 is used for controlling the vehicle to travel to the second track point when all the second time parameters are greater than a second preset time threshold value until the current vehicle turns left.

In another aspect, the present specification provides a computer-readable storage medium having at least one instruction or at least one program stored therein, where the at least one instruction or the at least one program is loaded into and executed by a processor to implement the method for driving a vehicle in an unprotected left-turn condition as described above.

In still another aspect, an embodiment of the present specification provides an electronic device for vehicle driving under an unprotected left-turn condition, and fig. 8 shows a schematic structural diagram of the electronic device for vehicle driving under an unprotected left-turn condition provided in an embodiment of the present specification, and as shown in fig. 8, the device includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for vehicle driving under an unprotected left-turn condition as described in any one of the above.

Since the technical effects of the vehicle driving method and apparatus under the unprotected left turn condition, the computer readable storage medium and the vehicle driving device under the unprotected left turn condition are the same as those of the vehicle driving method under the unprotected left turn condition, they are not described herein again.

On the other hand, this application provides a vehicle, the vehicle is provided with vehicle running device under the operating mode of turning left unprotected, and track point planning module traveles for when current vehicle drives into no traffic direction mark's crossing and current vehicle and traveles to the left, plans the track point set of traveling of current vehicle, the track point set of traveling includes at least: the first track point is a track point which is concentrated in the running track point and intersected with the running direction of the coming vehicle on the left side of the current vehicle, and the first track point is a track point which is concentrated in the running track point and intersected with the running direction of the coming vehicle opposite to the current vehicle;

the first time parameter determining module is used for determining a first time parameter of the left vehicle of the current vehicle, which runs to a first track point, based on the continuously acquired left image data;

the first time parameter judging module is used for controlling the vehicle to run to the first track point when the first time parameter is larger than a preset first preset time threshold value;

the second time parameter determining module is used for determining a second time parameter of the current vehicle right side vehicle and the current vehicle opposite vehicle driving to a second track point based on continuously acquired right side image data and front image data;

and the traveling module is used for controlling the vehicle to travel to the second track point until the current vehicle turns left when all the second time parameters are greater than a second preset time threshold value.

It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The implementation principle and the generated technical effect of the testing method provided by the embodiment of the invention are the same as those of the system embodiment, and for the sake of brief description, the corresponding contents in the system embodiment can be referred to where the method embodiment is not mentioned.

It should be understood that, in various embodiments herein, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments herein.

It should also be understood that, in the embodiments herein, the term "and/or" is only one kind of association relation describing an associated object, meaning that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided herein, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments herein.

In addition, functional units in the embodiments herein may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present invention may be implemented in a form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The principles and embodiments of this document are explained herein using specific examples, which are presented only to aid in understanding the methods and their core concepts; meanwhile, for the general technical personnel in the field, according to the idea of this document, there may be changes in the concrete implementation and the application scope, in summary, this description should not be understood as the limitation of this document.

Claims

1. A method of operating a vehicle in an unprotected left turn condition, said method comprising:

continuously acquiring left image data on the left side of the current vehicle, right image data on the right side of the current vehicle and front image data of the front of the current vehicle by image acquisition equipment arranged on two sides and in front of the current vehicle;

2. The method for driving a vehicle under unprotected left-turn conditions according to claim 1, wherein the left image data on the left side, the right image data on the right side and the front image data on the front side of the current vehicle are continuously collected by image collecting devices arranged on the two sides and the front of the current vehicle, and then the method further comprises:

determining continuous contour information of the vehicle on the left side of the current vehicle according to the continuously acquired left side image data;

and determining a first time parameter of the vehicle on the left side of the current vehicle running to the first track point according to the first speed information and the distance information between the vehicle on the left side of the current vehicle and the first track point in the grid map.

3. The vehicle driving method under the unprotected left-turn condition according to claim 2, wherein the constructing the grid map according to the continuously acquired left image data, the right image data and the front image data comprises:

4. The method of claim 3, further comprising:

acquiring attitude information of a current vehicle;

5. The method for driving a vehicle under an unprotected left-turn condition according to claim 2, wherein the step of determining continuous contour information of the vehicle on the left side of the current vehicle according to the continuously acquired left-side image data comprises the steps of:

6. The method of operating a vehicle under unprotected left turn conditions according to any of claims 1-5, further comprising:

7. The method for driving a vehicle under an unprotected left-turn condition as claimed in claim 6, wherein the prompt message is a voice prompt message and/or a light prompt message.

8. A vehicle travel arrangement under unprotected left turn conditions, the arrangement comprising:

9. A computer-readable storage medium, wherein at least one instruction or at least one program is stored, which is loaded and executed by a processor to implement the method for driving a vehicle under an unprotected left-turn condition as claimed in any one of claims 1 to 7.

10. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement a method of vehicle operation in an unprotected left turn condition according to any of claims 1-7 by executing the instructions stored by the memory.