CN115410384A - Roadside Traffic Scheduling Method and Assisted Driving Method at Intersection - Google Patents

Abstract

The disclosure relates to a road side traffic scheduling method and an auxiliary driving method for an intersection. The roadside traffic scheduling method comprises the following steps: acquiring an image and a point cloud of an intersection acquired by road side sensing equipment in real time; determining real-time sensing results of a plurality of traffic participation objects at the intersection according to the image and the point cloud of the intersection, wherein the real-time sensing results comprise positions, moving states and related traffic identifications of the corresponding traffic participation objects; determining a candidate driving path of each traffic participant in the traffic participants according to the real-time perception result of the traffic participants; and carrying out traffic scheduling on the plurality of traffic participation objects according to the candidate driving paths of the traffic participation objects to obtain the optimal driving path of each traffic participation object. By the roadside traffic scheduling method provided by the embodiment of the disclosure, the road conditions of the intersection can be acquired in real time, vehicles at the intersection are guided to pass quickly, and the passing efficiency is improved.

Description

Roadside Traffic Scheduling Method and Assisted Driving Method at Intersection

technical field

The present disclosure generally relates to the technical field of traffic dispatching. More specifically, the present disclosure relates to a roadside traffic scheduling method at an intersection and a driving assistance method.

Background technique

For a long time, most of the intersections of urban roads use traffic lights to control vehicles to dispatch vehicles. Usually, large intersections equipped with traffic lights are often traffic hubs with large traffic volume, many non-motorized vehicles and pedestrians, and complex and changeable road conditions. There are often a large number of emergency stops, emergency starts and congestion. . This not only causes waste of energy and environmental pollution, but also greatly increases the incidence of traffic accidents at intersections, resulting in lower traffic efficiency at intersections.

Therefore, it is necessary to study a traffic scheduling method at intersections to improve the problem of low traffic efficiency at intersections.

Contents of the invention

In order to solve one or more technical problems mentioned above, the present disclosure provides a roadside traffic dispatching method at an intersection, so as to improve the problem of low traffic efficiency at the intersection.

In a first aspect, an embodiment of the present disclosure provides a roadside traffic dispatching method at an intersection, the method comprising: acquiring in real time the image and point cloud of the intersection collected by the roadside sensing device; Image and point cloud, determine the real-time perception results of multiple traffic participation objects at the intersection, the real-time perception results include the position, movement status and related traffic signs of the corresponding traffic participation objects; according to the real-time perception results of the multiple traffic participation objects Determining the candidate driving route of each traffic participating object in the plurality of traffic participating objects according to the sensing result; and performing traffic scheduling on the plurality of traffic participating objects according to the candidate driving route of each traffic participating object, and obtaining each of the traffic participating objects preferred driving route.

In some embodiments, according to the image and point cloud of the intersection, determining the real-time perception results of multiple traffic participants at the intersection includes: performing target recognition on the image and point cloud respectively to obtain an image recognition result and point cloud recognition results; and using the system calibration parameters of the roadside sensing device to fuse the image recognition results and point cloud recognition results to obtain real-time perception results of multiple traffic participants at the intersection.

In some embodiments, according to the image and point cloud of the intersection, determining the real-time perception results of multiple traffic participants at the intersection includes: obtaining the vehicle-side perception results, wherein the vehicle-side perception results are consistent with the The image and the point cloud are obtained at the same time by the vehicle-side sensor data collected by the vehicle-side sensor; the road-side perception result is obtained according to the image and point cloud of the intersection; and the vehicle-side perception result and the road-side perception result are converted to The world coordinate system is used for fusion processing to obtain the real-time perception results of multiple traffic participants at the intersection.

In some embodiments, the candidate driving route is a lane-level driving route, and determining the candidate driving route of each traffic participating object in the plurality of traffic participating objects according to the real-time sensing results of the plurality of traffic participating objects includes: according to The real-time perception results of each of the traffic participation objects determine the current driving section of each of the traffic participation objects; according to the current position of each of the traffic participation objects and the relative direction of the terminal position, determine the optional driving distance of each of the traffic participation objects. an entry road section; and determining a candidate travel route for each traffic participation object according to the current travel section of each of the traffic participation objects and the lane information of the optional entry road section.

In some embodiments, according to the current driving section of each traffic participating object and the lane information of the optional driving section, determining the candidate driving route of each traffic participating object includes: based on the traffic of the current lane of each traffic participating object Rule information, to obtain the current optional lanes of each of the traffic participating objects in the current driving road section; determine the corresponding optional driving road section according to the traffic rule information of each current optional lane, and the traffic rule information includes lane change information and driving Direction information; and combining each current optional lane with the corresponding target lane of the corresponding optional entry road section to obtain the candidate driving path of each traffic participant object, and the target lane is the relative direction on the optional entry road section Matching lanes.

In some embodiments, according to the candidate driving routes of each traffic participating object, traffic scheduling is performed on the plurality of traffic participating objects to obtain the preferred driving route of each of the traffic participating objects, including: The real-time perception results of participating objects determine the average vehicle speed on each candidate driving path; determine the passing time of each candidate driving path according to the average vehicle speed and the signal light phase information at the intersection; and determine the passing time of each candidate driving path according to the Time determines the preferred driving route of each of the traffic participating objects.

In some embodiments, determining the passing time of each candidate driving route according to the average vehicle speed and the signal light phase information of the intersection includes: determining that the traffic participating object passes through the intersection according to the position of the traffic participating object The required travel distance; according to the travel distance and the average speed of the vehicle, determine the travel time required for the traffic participation object to pass through the intersection on each candidate travel route; according to the signal light phase information, determine the The waiting time required by the traffic participating objects; and determining the passing time of each candidate driving route according to the driving time and the waiting time.

In the second aspect, an embodiment of the present disclosure further provides a method for assisted driving, which is characterized in that it includes: receiving a assisted driving request sent by a smart terminal; A driving route; wherein, the preferred driving route is obtained by using the roadside traffic scheduling method in any embodiment of the first aspect of the present disclosure.

In some embodiments, sending the preferred driving route of the target vehicle to the smart terminal based on the assisted driving request includes: parsing the assisted driving request to obtain the location information of the smart terminal; determining multiple A target vehicle in the traffic participation object; and sending the preferred driving route of the target vehicle to the smart terminal.

In a third aspect, an embodiment of the present disclosure further provides a method for assisted driving, which is characterized by comprising: sending a request for assisted driving to the smart base station; and receiving the preferred driving route of the current vehicle returned by the smart base station based on the assisted driving request ; Wherein, the preferred driving route is obtained by using the roadside traffic scheduling method in any embodiment of the first aspect of the present disclosure.

In a fourth aspect, an embodiment of the present disclosure also provides a roadside traffic dispatching device at an intersection, characterized in that the device includes: an acquisition unit, configured to acquire images of intersections collected by roadside sensing devices in real time and point cloud; the perception result determination unit is used to determine the real-time perception results of multiple traffic participation objects at the intersection according to the image and point cloud of the intersection, and the real-time perception results include the positions of the corresponding traffic participation objects, A moving state and related traffic signs; a candidate route determination unit, configured to determine a candidate driving route for each traffic participation object in the plurality of traffic participation objects according to the real-time perception results of the plurality of traffic participation objects; and a preferred route determination unit, The method is used for performing traffic scheduling on the plurality of traffic participating objects according to the candidate driving routes of each traffic participating object, so as to obtain the optimal driving route of each of the traffic participating objects.

In the fifth aspect, an embodiment of the present disclosure also provides a driving assistance device, which is characterized by comprising: a receiving unit, configured to receive a driving assistance request sent by a smart terminal; and a sending unit, configured to Sending the preferred driving route of the target vehicle to the smart terminal; wherein, the preferred driving route is obtained by using the roadside traffic dispatching method at an intersection according to any embodiment of the aforementioned first aspect.

In the sixth aspect, an embodiment of the present disclosure further provides a driving assistance device, which is characterized by comprising: a sending unit, configured to send a driving assistance request to a smart base station; and a receiving unit, configured to receive The preferred driving route of the current vehicle returned by the driving request; wherein, the preferred driving route is obtained by using the roadside traffic dispatching method at an intersection described in any embodiment of the aforementioned first aspect.

In the seventh aspect, the embodiments of the present disclosure also provide a computer-readable storage medium, in which program instructions are stored. When the program instructions are loaded and executed by a processor, the processor executes the program according to the aforementioned first aspect. , the method described in any embodiment of the second aspect or the third aspect.

In the eighth invention, an embodiment of the present disclosure further provides a roadside device, including: a processor configured to execute program instructions; and a memory configured to store the program instructions, when the program instructions are executed by When the processor is loaded and executed, the computing device is made to execute the method according to any embodiment of the first aspect or the second aspect.

Through the roadside traffic dispatching method and assisted driving method provided above, the embodiment of the present disclosure uses roadside sensing equipment to sense information such as the location of traffic participating objects in real time, and determines the optimal driving route for each traffic participating object, thereby guiding vehicles to pass quickly , improve traffic efficiency. In some embodiments, the use of point cloud and image data can realize accurate identification of information such as traffic volume, vehicle speed, and traffic position of each lane at the intersection. Furthermore, in some embodiments, based on the accurate identification of lane information at intersections, driving route recommendations at the lane level can be implemented, so as to achieve fast passing.

Description of drawings

The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are shown by way of illustration and not limitation, and the same or corresponding reference numerals indicate the same or corresponding parts, wherein:

FIG. 1 illustrates an exemplary intersection to which the traffic dispatching scheme of an embodiment of the present disclosure may be applied;

FIG. 2 shows a schematic diagram of a roadside traffic dispatching system according to an embodiment of the present disclosure;

FIG. 3 shows a schematic flowchart of a roadside traffic scheduling method at an intersection according to an embodiment of the disclosure;

Fig. 4 shows an exemplary flowchart of a method for determining a candidate driving route according to an embodiment of the present disclosure;

Fig. 5 shows a schematic flowchart of a method for determining a preferred driving route according to an embodiment of the present disclosure; and

Fig. 6 shows an exemplary interaction flowchart of a driving assistance method according to an embodiment of the present disclosure.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are part of the embodiments of the present disclosure, not all of them. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present disclosure.

Explanations of technical terms that may be used in the present disclosure are given first.

Intersection: Refers to the part where two or more roads intersect on the same plane.

Fork: The road contained in the intersection.

One-way road: A road with only one direction of travel.

Two-way road: A road with two directions of travel.

Driving road: A road with a certain driving direction, which can be a one-way road or a road in any direction of a two-way road, and each driving road can include one or more lanes.

Lane: The narrowest road width unit for vehicles, usually a lane is only for one vehicle in width.

Road section: refers to a section of road on the driving path in the embodiments of the present disclosure. The driving path may include multiple road sections, and each road section may include one or more lanes.

FIG. 1 illustrates an exemplary intersection to which the traffic dispatching scheme of an embodiment of the present disclosure may be applied. As shown in the figure, the intersection 100 includes four forks 110, 120, 130, and 140, each of which is a two-way road, that is, includes two-way driving roads, which are for example separated by barriers, fences or roads. Traffic signs separated by lines.

When a vehicle passes through an intersection, the area it passes through can generally be divided into: the area where the vehicle travels before passing through the intersection, the area where the vehicle travels when passing through the intersection, and the area where the vehicle travels after passing through the intersection.

In the example in the figure, the area where the vehicle travels before passing the intersection includes the four traveling roads 111 , 121 , 131 and 141 facing the intersection among the four forks. Specifically, the traveling road 111 includes lanes c11, c12, and c13, the traveling road 121 includes lanes c24, c25, and c26, the traveling road 131 includes lanes c31, c32, and the traveling road 141 includes lanes c41, c42. The ground of each lane is painted with traffic direction signs, such as turn left, go straight, turn right, etc. Some lanes can have multiple driving directions at the same time, such as turning left + going straight, going straight + turning right, and so on.

The area in which the vehicle travels through the intersection generally includes the intersection center area 150 shown in the figure. It can be understood that in different driving directions, such as going straight, turning left, turning right or turning around, different parts of the central area 150 will be occupied, and the driving distances will also be different.

The area where the vehicle travels after passing the intersection includes the four driving roads 112 , 122 , 132 and 142 facing away from the intersection among the four forks. Specifically, the traveling road 112 includes lanes c14, c15, and c16, the traveling road 122 includes lanes c21, c22, and c23, the traveling road 132 includes a lane c33, and the traveling road 142 includes a lane c43.

Although the illustration takes an intersection as an example, those skilled in the art can understand that the traffic dispatching scheme of the embodiments of the present disclosure can also be applied to intersections with more or fewer forks. In addition, the driving road on each branch, and the number of lanes and driving direction included in the driving road may be different. Embodiments of the present disclosure are not limited in this respect.

Based on the above intersection scene, the embodiment of the present disclosure uses the roadside sensing device arranged at the intersection to sense the overall traffic distribution of the intersection in real time, dispatches the vehicles at the intersection based on the perception information, and plans the optimal traffic path, thereby improving traffic efficiency.

FIG. 2 shows a schematic diagram of a roadside traffic dispatching system 200 according to an embodiment of the present disclosure. The roadside traffic dispatching system 200 in the embodiment of the present disclosure may also be called a multi-source fusion sensing system, a smart base station, a roadside fusion sensing system or a roadside base station. The system can be installed on both sides of the road, collect sensing data in the coverage area through different types of sensors, and perform target detection on the collected sensing data to obtain various corresponding detection results, and then use the various detection results according to the preset The fusion strategy is fused and corrected to obtain the final target detection result.

As shown in the figure, the roadside traffic dispatching system 200 may include roadside sensing devices 201 , 202 and a server 203 . The roadside sensing devices 201 and 202 communicate with the server 203 in a wired or wireless manner, respectively. The roadside sensing devices 201 and 202 are installed on traffic poles or traffic crossbars on the side of the road. Optionally, the position offset between the roadside sensing devices 201 and 202 is smaller than the offset threshold, so that the roadside sensing devices 201 and 202 are approximately installed at the same position. The server 203 may be one server, or a server cluster composed of multiple servers.

The roadside perception device may include an image collection device 201 and a point cloud collection device 202 . The image collection device 201 is used to collect image data of the traffic scene at the intersection, and the point cloud collection device 202 is used to collect the point cloud data of the traffic scene at the intersection. Specifically, the image collection device may include a video camera and/or a camera, and the point cloud collection device may include a radar device. The type of the camera may be a bullet camera, a dome camera, or a spherical camera. The radar device may include at least one of lidar, millimeter wave radar, microwave radar, and the like. Further, the category of lidar may include multi-line lidar, for example may include 8-line, 16-line, 24-line, 32-line, 64-line or 128-line lidar.

The server 203 acquires the image data and point cloud data correspondingly at the same time and in the same scene through the image acquisition device 201 and the point cloud acquisition device 202, performs object detection on the image data to obtain the first detection result, and performs object detection on the point cloud data to obtain the second detection result. second detection result, and fuse the first detection result and the second detection result to obtain an initial fusion result. These fusion results can be applied to the roadside traffic dispatching scheme of the embodiments of the present disclosure.

It can be understood that the figure is only a block diagram of a part of the structure related to the embodiment of the present disclosure, and does not constitute a limitation on the smart base station to which the embodiment of the present disclosure is applied. A specific smart base station may include more than shown in the figure. or fewer components, or combine certain components, or have a different arrangement of components.

Fig. 3 shows a schematic flowchart of a roadside traffic scheduling method 300 at an intersection according to an embodiment of the present disclosure. The method can be implemented by the roadside traffic dispatching system shown in FIG. 2 .

As shown in the figure, the roadside traffic dispatching method 300 may include step S301, acquiring images and point clouds of intersections collected by roadside sensing devices in real time. The roadside sensing device can be installed at an appropriate position of the intersection, such as the roadside traffic pole or traffic crossbar on each fork of the intersection, so as to facilitate the collection of traffic conditions on each fork in the intersection. As described in FIG. 2 , the roadside sensing device may include an image acquisition device for collecting image data and a point cloud collection device for collecting point cloud data. These roadside sensing devices respectively acquire image data and point cloud data at the same time and in the same scene for subsequent fusion processing.

In an exemplary embodiment, the roadside sensing device may collect images and point clouds at preset time intervals, and send these images and point cloud data to it periodically or based on a server's request. The preset time interval and cycle here can be set correspondingly according to the frequency of vehicle guidance. For example, the preset time interval can be set to 0.5s or 1s. Correspondingly, the sending cycle can be set to 0.7s or 1.2s, etc.

After the image and point cloud of the intersection are obtained, the process proceeds to step S302, and the real-time perception results of multiple traffic participating objects at the intersection are determined according to the image and point cloud of the intersection. The real-time perception results can include the location, movement status and related traffic signs of the corresponding traffic participating objects. The traffic participation objects in this paper refer to all objects related to road activities/traffic activities, such as motor vehicles, pedestrians, roadside equipment, non-motor vehicles, and so on. Motor vehicles, pedestrians, non-motor vehicles and roadside equipment can communicate through V2X/5G/4G technology to realize data transmission.

In some embodiments, the real-time perception results of multiple traffic participants at the intersection can be obtained only through the images and point clouds of the intersection collected by the roadside sensing device, that is, only based on the roadside sensing results.

In these embodiments, target recognition can be performed on the image and point cloud respectively to obtain image recognition results and point cloud recognition results, and then use the system calibration parameters of the roadside sensing device to fuse the image recognition results and point cloud recognition results Finally, the real-time perception results of multiple traffic participants at the intersection are obtained.

In a specific implementation scenario, the image target recognition algorithm can be used to recognize each target in the image to obtain the image recognition result, and the point cloud target recognition algorithm can be used to recognize each target in the point cloud to obtain the point cloud recognition result. In order to improve the accuracy of image recognition and point cloud recognition, in an exemplary embodiment, the image target recognition algorithm and the point cloud target recognition algorithm can be respectively implemented through corresponding neural network models. For example, the image target detection algorithm can be realized by the YOLO v3 deep learning model, and the point cloud target detection algorithm can be realized by the SECOND deep learning model. Alternatively or additionally, in another exemplary embodiment, it is also possible to use a tracking algorithm such as the Kalman algorithm in combination with target identification information (such as a target ID) to perform target tracking on images and/or point clouds, so as to obtain Image recognition results and/or point cloud recognition results.

In an exemplary application scenario, the image recognition result may include the characteristics (such as category, color, and/or texture), position, and moving state (such as flow and/or speed) of each image object in the road scene collected by the camera. ) and related traffic signs (such as lane markings and/or signal lights at intersections) and other information. Here, it can be understood that the image target may refer to the target in the image recognition result obtained by performing target recognition on the image. In another exemplary application scenario, the point cloud recognition result may include the position, feature (such as size and/or category) and movement state (such as heading angle) of each point cloud object in the road scene collected by lidar and other information. Similarly, it can be understood that the point cloud target may refer to the target in the point cloud recognition result obtained by performing point cloud target recognition on the point cloud.

After obtaining the above image recognition results and point cloud recognition results, the system calibration parameters of the roadside sensing equipment can be used to fuse the image recognition results and point cloud recognition results to obtain real-time perception results of multiple traffic participants at the intersection. In some embodiments, the fused real-time perception result can be obtained by projecting the image recognition result into the point cloud recognition result. In other embodiments, the fused real-time perception result can also be obtained by projecting the point cloud recognition result into the image recognition result.

Taking the real-time perception result obtained by projecting the point cloud recognition result into the image recognition result as an example, the point cloud target in the point cloud recognition result can be converted into the image recognition result by using the system calibration parameters of the roadside sensing device The two-dimensional coordinate system where the image target is located, and then determine the measured target in the real-time perception result according to the point cloud target and the image target in the two-dimensional coordinate system. The system calibration parameters may include an internal reference matrix and an external parameter matrix of the roadside sensing device. For example, for an embodiment where the roadside sensing device includes an image acquisition device and a point cloud detection device, the internal reference matrix may be the internal reference matrix of the image acquisition device, and the external reference matrix may be The parameter matrix may be an external parameter matrix between the image acquisition device and the point cloud detection device.

In a specific application scenario, the above-mentioned coordinate conversion can be realized by the following formula.

Z=P*T*Q

Among them, Z is the coordinates of a point cloud object in the point cloud projected into the image recognition result, P is the internal reference matrix of the image acquisition device, and T is the 3D space coordinate rotation and translation between the image acquisition device and the point cloud detection device matrix, Q is the three-dimensional coordinates of the above-mentioned point cloud target in the point cloud.

Through the system calibration parameters of the roadside sensing equipment, the point cloud target in the point cloud recognition result and the image target in the image recognition result are converted to the same dimension, and then fused, which can improve the accuracy of point cloud recognition result and image recognition result fusion .

After converting each point cloud target in the point cloud to the image recognition result, the measured target in the real-time perception result can be determined through the information matching probability, where the information matching probability is used to represent the position overlap between the point cloud target and the image target . For example, point cloud targets and image targets whose information matching probability is greater than or equal to the matching threshold can be set as the same measured target, while point cloud targets and image targets whose information matching probability is less than the matching threshold can be set as different measured targets. Further, if the point cloud object and any image object are not the same measured object, then the point cloud object is taken as a separate measured object. Similarly, if the image object and any point cloud object are not the same object to be measured, then the image object is regarded as a separate object to be measured. Through the fusion method, each measured target in the real-time perception result can be obtained.

There may be multiple methods for obtaining the above-mentioned information matching probability. For example, in a specific implementation scenario, the above-mentioned information matching probability can be obtained by calculating the degree of position overlap between the detection frame of the point cloud object in the point cloud recognition result and the detection frame of the image object in the image recognition result. In an implementation scenario, the detection frame of the point cloud object can be converted to the two-dimensional coordinate system where the image object is located for calculation. Then, the position overlap between the detection frame of the point cloud target and the detection frame of the image target is calculated by the method of Intersectionover Union (IOU), and it is used as the information between the point cloud target and the image target match probability.

The method of fusing the point cloud recognition result and the image recognition result by using the information matching probability has been described above. In another embodiment, the point cloud recognition result and the image recognition result can also be fused according to the position of the point cloud target in the point cloud recognition result and the position of the image target in the image recognition result, so as to obtain multiple target. Exemplarily, the distance between each point cloud object in the point cloud recognition result and each image object in the image recognition result can be calculated. If the distance between a point cloud object in the point cloud recognition result and an image object in the image recognition result is less than or equal to the preset distance threshold, the point cloud object and the image object can be determined as the same measured object Target. Correspondingly, if the distance between the point cloud object and the image object is greater than a preset distance threshold, it is determined that the point cloud object and the image object are different measured objects.

Further, if the distance between the point cloud target in the point cloud recognition result and any image target in the image recognition result is greater than a preset distance threshold, the point cloud target can be used as a separate measured target. Similarly, if the distance between the image target in the image recognition result and any point cloud target in the point cloud recognition result is greater than a preset distance threshold, the image target can be used as a separate measured target. Through the fusion method, each measured target in the real-time perception result can be obtained.

According to the above descriptions about the information included in the image recognition results and point cloud detection results, the fused real-time perception results can contain a variety of traffic information corresponding to the traffic participating objects, such as location, movement status (such as traffic and/or speed) and relevant traffic signs (such as lane markings and/or signal lights at intersections), etc. Based on this, by fusing the point cloud recognition results and image recognition results, it is possible to accurately recognize the traffic flow, speed, and location of traffic in each lane of the intersection. Furthermore, based on the accurate recognition of lane information at intersections, lane-level driving route recommendations can be realized, thereby realizing fast traffic.

Optionally or additionally, in some embodiments, in order to further improve the accuracy of target recognition, the vehicle-side perception results can also be obtained, and multiple Real-time perception results of traffic participants. In order to ensure the synchronization of target recognition, thereby improving the accuracy of target recognition, the vehicle-side perception result may be a perception result obtained from vehicle-side data collected by the vehicle-side sensor at the same time as the image and point cloud. The same moment here can be understood as the same timestamp or the same frame. Based on this, it is possible to synchronize the sampling frequency and time of the roadside sensing device and the vehicle-side sensor.

Vehicle-side sensors can include vehicle-mounted cameras and/or vehicle-mounted lidars. Further, vehicle-side image perception results can be obtained through vehicle-mounted cameras, and vehicle-side point cloud perception results can be obtained through vehicle-mounted lidars. In some embodiments, the car-end image sensing result and the car-end point cloud sensing result may be fused to obtain the car-end sensing result.

Furthermore, the vehicle-side perception results and road-side perception results can be converted to the world coordinate system for fusion processing to obtain real-time perception results of multiple traffic participants at the intersection. Based on the road-side sensing results and vehicle-side sensing results at the same time, subsequent traffic dispatching can be carried out based on the comprehensive sensing results with a larger sensing range, so that the dispatching plan can be determined more accurately. In addition, combined with the perception results of the vehicle-end equipment, it is possible to achieve no dead-spot coverage of intersections, which greatly improves safety.

Continuing with Fig. 3, after obtaining the real-time sensing results of multiple traffic participating objects at the intersection, the flow proceeds to step S303, and determining the candidate of each traffic participating object among the multiple traffic participating objects according to the real-time sensing results of the multiple traffic participating objects driving path. Finally, in step S304, according to the candidate driving routes of each traffic participating object, traffic scheduling is performed on the plurality of traffic participating objects, and the optimal driving route of each traffic participating object is obtained.

In some embodiments, the candidate driving route is a lane-level driving route, and the preferred driving route selected therefrom is also a lane-level driving route. As defined earlier, a lane is the narrowest unit of road width for vehicles to travel on. Therefore, by providing the optimal driving route at the lane level, the traffic participants can be dispatched more carefully and accurately, and the traffic efficiency can be improved.

The roadside traffic dispatching method of the intersection according to the embodiment of the present disclosure has been described above in conjunction with FIG. 3 . Those skilled in the art can understand that the method of the embodiment of the present disclosure can dispatch traffic at the intersection at least based on the roadside perception results. Traffic participation objects, thereby improving the accuracy and reliability of scheduling, and quickly solving intersection traffic problems. The scheduling scheme of the preferred driving route will be described in more detail below with reference to the accompanying drawings.

Fig. 4 shows an exemplary flowchart of a method for determining a candidate driving route according to an embodiment of the present disclosure. As described above in conjunction with Figure 1, when a vehicle passes through an intersection, the area it travels through can generally be divided into: the area where the vehicle travels before passing the intersection, the area where the vehicle travels when passing the intersection, and the area that the vehicle travels after passing the intersection. area. Therefore, the candidate driving route can generally include: the current driving section (that is, the driving section when the traffic participant does not pass through the intersection), the passing section (that is, the driving area when passing the intersection, for example, from a bifurcated zebra crossing to Another bifurcated zebra crossing), and the target entry road section (that is, the road section that is about to enter after passing through the intersection). Therefore, the candidate driving route can be determined according to the above several road sections.

As shown in the figure, in step S401, the current driving section of each traffic participation object is determined according to the real-time sensing results of each traffic participation object. From the previous description of the real-time sensing results of the roadside sensing device, it can be seen that the real-time sensing results include the location, movement status and related traffic signs of the traffic participating objects. Thus, based on the location of the traffic participating object, its current driving section can be determined.

Take the five traffic participation objects (d1-d5) shown in FIG. 1 as an example to illustrate here. FIG. 1 shows the current positions of the five traffic participating objects. According to the current position of the traffic participation object d1, its current driving section is the driving road 121 in the fork 120, including three lanes c24, c25 and c26. According to the current position of the traffic participation object d2, its current driving section is also the driving road 121 in the fork 120 . According to the current positions of the traffic participation objects d3 and d4, it can be known that their current driving sections are the driving road 141 in the fork 140, including two lanes c41 and c42. According to the current position of the traffic participation object d5, its current driving section is the driving road 111 in the branch 110, including three lanes c11, c12 and c13.

Continuing with Fig. 4, in order to determine the road section that the traffic participation object is about to enter after passing through the intersection, that is, the target entry road section, so as to obtain a complete driving path, then in step S402, the current position and the end point of each traffic participation object can be The relative direction of the position determines the optional entry road segment of each traffic participating object.

According to different application scenarios, different methods may be adopted to determine the end position.

In an implementation scenario, the destination location can be sent to the roadside smart base station by the smart terminal of the traffic participant. For example, the on-board intelligent terminal of the vehicle may send an assisted driving request, wherein the assisted driving request carries the destination location information. The destination location information may be, for example, the destination address of the vehicle, or simply the traffic direction information of the intersection, such as going straight, turning left, turning right, and the like.

In another implementation scenario, the traffic participant does not interact with the roadside smart base station, so its end position is predicted by the roadside smart base station based on the traffic rule information of the current driving section. The traffic rule information can include lane change information and driving direction information.

After the terminal position of the traffic participating object is determined, the optional driving section of each traffic participating object can be determined according to the relative direction of the current position of the traffic participating object and the terminal position.

Figure 1 is still taken as an example for illustration. Assume that the traffic participant d1 in Figure 1 sends an assisted driving request to the roadside smart base station, including its end position A1. The roadside smart base station judges that d1 can choose to turn left at the intersection or go straight to reach the end position according to the current position and end position of d1. Therefore, it can be determined that the optional entry road section of d1 includes the bifurcation 130 that enters through the left turn. , and the travel road 112 in the fork 110 entered via a straight line.

Assuming that the traffic participant d2 in Figure 1 does not interact with the roadside smart base station, the roadside smart base station can predict its end position based on the current location of d2. Specifically, according to the fact that the current lane of d2 is a straight-going and right-turning lane, and there is a solid line between the adjacent lanes, it can be predicted that the end position of d2 is a place that can be reached by going straight or turning right. Therefore, it can be determined that the optional driving road section of d2 includes the driving road 112 in the fork 110 entering via going straight, and the driving road 142 in the fork 140 entering via a right turn.

Returning to FIG. 4 , finally in step S403 , according to the current driving road segment of each traffic participating object and the lane information of the optional driving road segment, the candidate driving route of each traffic participating object is determined.

As mentioned above, the candidate driving route in the embodiments of the present disclosure may be a lane-level route, so the lanes of the current driving road segment and the optional entering road segment can be further determined.

Specifically, in some embodiments, based on the traffic rule information of the current lane of each traffic participating object, the current optional lane of each traffic participating object on the current driving section is acquired.

Still taking the above five traffic participation objects (traffic participation objects d1-d5) shown in FIG. 1 as an example to illustrate the method for obtaining the current optional lane here. The current lane of the traffic participation object d1 is lane c25, and the lane lines between it and adjacent lanes (lane c24 and lane c26) are dashed lines. According to the traffic rule information, it can drive on the lane c24, the lane c25 and the lane c26, so its current optional lanes can include the lane c24, the lane c25 and the lane c26. The current lane of the traffic participation object d2 is lane c26, and the lane line between it and the adjacent lane (lane c25) is a solid line. According to the traffic rule information, it can only drive on the lane c26 at present, so its current optional lane is only the lane c26.

Similarly, the current lane of the traffic participant d3 is lane c42, and the lane line between it and the adjacent lane (lane c41) is a solid line, so its current selectable lane can only be lane c42. The current lane of the traffic participant d4 is lane c41, and the lane line between it and the adjacent lane (lane c42) is a solid line, so its current selectable lane can only be lane c41. The current lane of traffic participant d5 is lane c12, the lane line between it and one of the adjacent lanes c11 is a solid line, and the lane line between it and another adjacent lane c12 is a dashed line, so its current optional lane can be for lanes c12 and c13.

As mentioned above, there may be multiple current optional lanes for each traffic participant, and there may also be multiple optional entry road segments, which need to be matched and combined according to traffic rule information. Therefore, in some embodiments, the corresponding optional entry road section is determined according to the traffic rule information of each currently optional lane, and the traffic rule information includes, for example, lane change information and driving direction information. Finally, each current optional lane can be combined with the corresponding target lane of the optional entry section to obtain the candidate driving route of each traffic participant object. Here, the target lane is a lane matching the traveling direction of the vehicle (that is, the relative direction between the current position and the terminal position) on the optional entry road segment.

Take the traffic participation object d1 in Figure 1 as an example. As can be seen from the foregoing description, the current optional lanes include lane c24, lane c25, and lane c26, and in the preceding example, the optional entry road segment determined according to the assisted driving request includes the travel in the fork 130 via a left turn. road 132, and the travel road 112 in the fork 110 entered via a straight line. Therefore, the corresponding optional entry section of the currently optional left-turn lane c24 is the driving road 132, which has only one lane c33, that is, one candidate driving route c24+c33 can be obtained. The currently optional through lane c25 corresponds to the driving road 112, which has three lanes c14, c15 and c16, so three candidate driving routes c25+c14, c25+c15 and c25+c16 can be obtained. The corresponding optional entry section of the currently optional straight-going + right-turn lane c26 is also the driving road 112, because d1 cannot turn right due to the relative direction of the end position. From this, three candidate driving routes c26+c14, c26+c15 and c26+c16 can also be obtained.

Through the above analysis, it can be determined that the traffic participant d1 has a total of seven candidate driving routes. Candidate driving routes of other traffic participating objects can be determined similarly, and will not be repeated here.

After obtaining the candidate driving routes of each traffic participating object, the solution of the embodiment of the present disclosure may perform traffic scheduling on multiple traffic participating objects based on these candidate driving routes, and obtain the optimal driving route of each traffic participating object.

FIG. 5 shows a schematic flowchart of a method for determining a preferred driving route according to an embodiment of the present disclosure. In this embodiment, the preferred driving route of each traffic participating object can be selected from the multiple candidate driving routes according to the transit time of each candidate driving route among the multiple candidate driving routes. For example, the candidate driving route with the shortest passing time can be determined as the preferred driving route of the traffic participating object, so as to realize the rapid passage of the traffic participating object at the intersection and ensure the passing efficiency.

As shown in the figure, in step S501, the average vehicle speed on each candidate driving route may be determined according to the real-time sensing results of multiple traffic participating objects at the intersection. For example, the average speed of the vehicle on the lane can be determined by the speed of the traffic participating objects on each lane in the real-time perception result.

Next, in step S502, the transit time of each candidate travel route is determined according to the average vehicle speed and the signal light phase information at the intersection. Specifically, according to the current position of the traffic participating object, the driving distance required for the traffic participating object to pass through the intersection may be determined. Then, according to the driving distance and the average speed of the vehicle, the driving time required by the traffic participants to pass through the intersection on each candidate driving route is determined. In addition, the possible waiting time of traffic participants can be determined according to the signal light phase information. Finally, the passing time of each candidate driving route can be determined according to the driving time and possible waiting time.

The following uses a specific example to describe the way of determining the passing time. The passing time through the intersection may include the travel time required to reach the current zebra crossing at the intersection, the travel time to cross the intersection, and the possible time to wait for traffic lights before crossing the intersection.

Assuming that there is a target vehicle driving on the straight lane, there are N vehicles in front of it, and the distance between the current position of the target vehicle and the current zebra crossing (the zebra crossing on the same side as the target vehicle at the intersection) is L1, the current zebra crossing to The distance from the zebra crossing on the opposite side of the intersection is L2.

Based on the above settings, in a scene, if the signal light at the current zebra crossing is currently red, and the time for the distance to turn green is s1. The current average speed V1 of N vehicles can be calculated according to the real-time perception results. If the average speed V1 is close to 0, it means that the vehicles on this lane are currently in a waiting state. After the light turns green, the vehicle will move off and drive through the intersection. If the universal starting speed V2 is the speed at which the vehicle starts and passes through the intersection, then the time for the target vehicle to pass through the intersection (that is, the time from the current position to the zebra crossing on the opposite side of the intersection) is T ₁

T ₁ =L1/V2+s1+L2/V2.

In another scenario, if the signal light at the current zebra crossing is green, the time for the distance to change to red is s2. According to the real-time perception results, the current average speed V1 of N vehicles can be calculated, and the time when the target vehicle reaches the current zebra crossing at the average speed V1 is predicted to be t1

t1=L1/V1

If t1<s2, the target vehicle can pass through the intersection directly without waiting, and its total passing time is T ₂

T ₂ =t1+L2/V1.

If t1≥s2, the target vehicle will stop again at the intersection, and at this time, the time for the target vehicle to pass through the intersection can be calculated by the above-mentioned calculation method when the signal light is red.

In other scenarios, the transit time can be estimated similarly to the above method.

After the passing time of each candidate driving route is determined, finally in step S503, the preferred driving route of each traffic participation object is determined according to the passing time of each candidate driving route. In a specific implementation scenario, the candidate driving route with the shortest passing time is used as the preferred driving route of the traffic participant, so that vehicles can be guided to quickly pass through the intersection, thereby improving the passing efficiency of the intersection. As can be seen from the above description, the transit time is only calculated until the vehicle reaches the zebra crossing on the target side. When the target entry road section includes multiple lanes, the traffic volume of these lanes can also be calculated, and the lane with the smallest traffic volume can be output.

For example, for the seven candidate driving routes of the traffic participant object d1 in Fig. 1 above, if the passage time of the lane c24+c33 route is 2.5 minutes, the passage time of the lane c25+c14 route is 1.2 minutes, and the passage time of the lane c25+c15 route The passing time is 1.2 minutes, the passing time of the lane c25+c16 path is 1.2 minutes, the passing time of the lane c26+c14 path is 2 minutes, the passing time of the lane c26+c15 path is 2 minutes, the passing time of the lane c26+c16 path for 2 minutes. Among the passage times of the above seven candidate driving routes, the passage times of lanes c25+c14, c25+c15 and c25+c16 are the shortest and are all 1.2 minutes. At this time, the traffic flow of the target lanes c14, c15 and c16 may be further considered, and the candidate driving route including the target lane with the smallest traffic flow may be output as the optimal driving route. This method can not only ensure the efficiency of traffic participants passing through the intersection, but also further ensure their driving efficiency in the target lane, thereby improving the driving efficiency of traffic participants on the entire optimal driving route.

In some embodiments, the determined optimal driving route information may be sent to corresponding traffic participants to guide them to quickly pass through the intersection. The preferred driving route information may include various lanes in the preferred driving route, such as the lanes of the current driving route segment and the lanes of the target driving route segment. Optionally or additionally, the preferred driving route information further includes the estimated transit time of the preferred driving route. In addition, as mentioned above, in some embodiments, there may be multiple driving directions, for example, going straight and turning left, and correspondingly multiple optional driving sections. In these embodiments, preferred driving route information may be provided for each traffic direction, for example, a preferred driving route is provided for going straight, and a preferred driving route is provided for turning left.

It can be seen from the above description that depending on the sensing range of the roadside sensing device, traffic scheduling and guidance can be performed for each traffic participant near the intersection area and within its sensing range. For example, it is possible to guide the traffic participating objects that stop at the zebra crossing at the intersection, and also guide the traffic participating objects that are far away from the zebra crossing at the intersection, so that each traffic participating object can be guided in real time, and then The traffic efficiency at the intersection can be further improved. Furthermore, the use of point cloud and image data can realize accurate identification of information such as traffic volume, vehicle speed, and traffic position of each lane at the intersection. Furthermore, based on the accurate identification of lane information at intersections, lane-level driving route recommendations can be realized, thereby achieving fast traffic.

The embodiment of the present disclosure also provides an assisted driving method, which can assist the vehicle to quickly pass through an intersection with complex traffic conditions through the interaction between the intelligent terminal on the vehicle and the roadside intelligent base station, realize efficient traffic guidance of the vehicle, and greatly improve traffic. efficiency and reduce traffic congestion.

Fig. 6 shows an exemplary interactive flow chart of a driving assistance method according to an embodiment of the present disclosure.

As shown in the figure, the smart terminal 610 of the vehicle may send S611 an assisted driving request to the smart base station 620 . The driving assistance request may include various information required for driving assistance, including but not limited to identification information of the vehicle, location information of the vehicle, and destination location information of the vehicle. The identification information of the vehicle and the location information of the vehicle can be used by the smart base station 620 to identify the target vehicle sending the request.

Then, in response to receiving the assisted driving request, the smart base station 620 may send the preferred driving route of the target vehicle to the smart terminal 610 based on the assisted driving request.

Specifically, the smart base station 620 can analyze the assisted driving request, obtain the location information of the smart terminal, and determine the target vehicle among multiple traffic participants according to the location information of the smart terminal (S621). Next, for the target vehicle, the optimal driving route may be determined by using the roadside traffic scheduling method for cross road conditions described above in conjunction with the accompanying drawings (S622). Finally, the smart base station 620 may send the determined optimal driving route to the smart terminal 610 (S623).

At this time, the smart terminal 610 of the vehicle receives the current preferred driving route of the vehicle returned by the smart base station 620 in response to its assisted driving request. The current vehicle can drive through the intersection with reference to the optimal driving route recommended by the smart base station 620 (S612).

Through the above descriptions of the roadside traffic dispatching method and the assisted driving method at the intersection of the embodiments of the present disclosure and the description of multiple embodiments, those skilled in the art can understand that the embodiments of the present disclosure are at least based on the perception results of the roadside sensing device , each traffic participant can be accurately guided, not limited to vehicles close to the stop line. Furthermore, it can guide the optimal driving route of each traffic participant at each moment, and the route can be accurate to the lane level, for example, so it is more practical to assist driving. In addition, the selection of the optimal driving route not only combines the selection of the current own lane and adjacent lanes, but also combines the selection of lanes after crossing intersections (such as traffic lights).

It can be seen from the above description that the embodiments of the present disclosure may be implemented as a system, method or computer program product. Therefore, the present disclosure can be embodied in the form of complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as "circuit", " module" or "system". Furthermore, in some embodiments, the present invention can also be implemented in the form of a computer program product embodied in one or more computer-readable media having computer-readable program code embodied therein. Any combination of one or more computer readable medium(s) may be utilized. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out the operations of the present invention may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider). connect).

It should be understood that each block in the method flowcharts and/or block diagrams of the embodiments of the present disclosure and combinations of blocks in the flowcharts and/or block diagrams can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, and these computer program instructions are executed by the computer or other programmable data processing apparatus to produce a flow diagram of the implementation and/or means for the functions/operations specified in the blocks in the block diagrams. These computer program instructions can also be stored in a computer-readable medium that can cause a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable medium can generate a program including implementation flowcharts and and/or the product of the instruction device for the function/operation specified in the box in the block diagram. It is also possible to load computer program instructions onto a computer, other programmable data processing apparatus, or other equipment, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process, thereby Instructions that enable execution on a computer or other programmable device provide a process for implementing the functions/operations specified in the flowcharts and/or blocks in the block diagrams.

Although the embodiments of the present disclosure are as above, the content is only the embodiments adopted for the convenience of understanding the present disclosure, and is not intended to limit the scope and application scenarios of the present disclosure. Anyone skilled in the technical field described in the present disclosure can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the patent protection scope of the present disclosure , must still be subject to the scope defined by the appended claims.

Claims (15)

1. A method for roadside traffic scheduling at an intersection, the method comprising:

acquiring an image and a point cloud of an intersection acquired by road side sensing equipment in real time;

determining real-time sensing results of a plurality of traffic participation objects at the intersection according to the image and the point cloud of the intersection, wherein the real-time sensing results comprise positions, moving states and related traffic identifications of the corresponding traffic participation objects;

determining a candidate driving path of each traffic participant in the traffic participants according to the real-time perception result of the traffic participants; and

and carrying out traffic scheduling on the plurality of traffic participating objects according to the candidate running paths of the traffic participating objects to obtain the optimal running path of each traffic participating object.

2. The method of claim 1, wherein determining real-time perception of a plurality of traffic-engaging objects at the intersection based on the image and point cloud of the intersection comprises:

respectively carrying out target identification on the image and the point cloud to obtain an image identification result and a point cloud identification result; and

and fusing the image recognition result and the point cloud recognition result by using system calibration parameters of road side sensing equipment to obtain real-time sensing results of a plurality of traffic participation objects at the intersection.

3. The method of claim 1, wherein determining real-time perception of a plurality of traffic-engaging objects at the intersection from the image and the point cloud of the intersection comprises:

acquiring a vehicle end sensing result, wherein the vehicle end sensing result is a sensing result obtained by vehicle end data acquired by a vehicle end sensor at the same time as the image and the point cloud;

obtaining a road end sensing result according to the image and the point cloud of the intersection; and

and converting the vehicle end sensing result and the road end sensing result into a world coordinate system for fusion processing to obtain real-time sensing results of a plurality of traffic participation objects at the intersection.

4. The method according to claim 1, wherein the candidate driving route is a lane-level driving route, and determining the candidate driving route of each traffic participant object in the traffic participant objects according to the real-time perception result of the traffic participant objects comprises:

determining the current driving road section of each traffic participating object according to the real-time perception result of each traffic participating object;

determining selectable access road sections of the traffic participation objects according to the relative directions of the current positions and the end positions of the traffic participation objects; and

and determining the candidate driving paths of the traffic participating objects according to the current driving road section of the traffic participating objects and the lane information of the selectable driving road section.

5. The method of claim 4, wherein determining the candidate driving path of each traffic participant according to the current driving section and the lane information of the selectable driving section of each traffic participant comprises:

acquiring a current selectable lane of each traffic participating object on a current driving road section based on traffic rule information of the current lane of each traffic participating object;

determining a corresponding selectable entering road section according to traffic regulation information of each current selectable lane, wherein the traffic regulation information comprises lane change information and driving direction information; and

and combining each current selectable lane with a target lane of the corresponding selectable entry road section to obtain a candidate driving path of each traffic participating object, wherein the target lane is a lane matched with the relative direction on the selectable entry road section.

6. The method according to claim 4 or 5, wherein performing traffic scheduling on the plurality of traffic-participating objects according to the candidate driving paths of the traffic-participating objects to obtain the preferred driving path of each traffic-participating object comprises:

determining the average speed of the vehicles on each candidate driving path according to the real-time perception results of a plurality of traffic participation objects at the intersection;

determining the passing time of each candidate running path according to the average speed of the vehicle and the signal lamp phase information of the intersection; and

and determining the optimal running path of each traffic participant according to the passing time.

7. The method of claim 6, wherein determining the transit time for each candidate travel path based on the average vehicle speed and signal light phase information for the intersection comprises:

determining the driving distance required by the traffic participant to pass through an intersection according to the position of the traffic participant;

determining the driving time required by the traffic participation object to pass through the intersection on each candidate driving path according to the driving distance and the average speed of the vehicle;

determining the waiting time required by the traffic participation object according to the signal lamp phase information; and

and determining the passing time of each candidate running path according to the running time and the waiting time.

8. A driving assistance method characterized by comprising:

receiving an auxiliary driving request sent by an intelligent terminal; and

sending a preferred running path of a target vehicle to the intelligent terminal based on the auxiliary driving request; wherein the preferred travel path is acquired by the roadside traffic scheduling method at the intersection of any one of claims 1 to 7.

9. The method of claim 8, wherein sending a preferred travel path for a target vehicle to the smart terminal based on the assisted driving request comprises:

analyzing the auxiliary driving request to obtain the position information of the intelligent terminal;

determining target vehicles in a plurality of traffic participation objects according to the position information of the intelligent terminal; and

and sending the optimal running path of the target vehicle to the intelligent terminal.

10. A driving assistance method characterized by comprising:

sending a driving assistance request to the intelligent base station; and

receiving a preferred driving path of the current vehicle returned by the intelligent base station based on the driving assisting request; wherein the preferred travel path is acquired by the road-side traffic scheduling method at the intersection according to any one of claims 1 to 7.

11. A roadside traffic scheduling device at an intersection, the device comprising:

the acquisition unit is used for acquiring images and point clouds of the intersection acquired by the roadside sensing equipment in real time;

the sensing result determining unit is used for determining real-time sensing results of a plurality of traffic participating objects at the intersection according to the image and the point cloud of the intersection, and the real-time sensing results comprise positions, moving states and related traffic identifications of the corresponding traffic participating objects;

the candidate path determining unit is used for determining a candidate driving path of each traffic participant object in the traffic participants according to the real-time perception result of the traffic participants; and

and the preferred path determining unit is used for carrying out traffic scheduling on the plurality of traffic participating objects according to the candidate running paths of the traffic participating objects to obtain the preferred running paths of the traffic participating objects.

12. A driving assist apparatus, characterized by comprising:

the intelligent terminal comprises a receiving unit, a judging unit and a judging unit, wherein the receiving unit is used for receiving an auxiliary driving request sent by the intelligent terminal; and

a sending unit, configured to send a preferred driving path of a target vehicle to the intelligent terminal based on the driving assistance request; wherein the preferred driving path is obtained by the road side traffic dispatching method of the intersection according to any one of claims 1 to 7.

13. A driving assistance apparatus characterized by comprising:

the transmitting unit is used for transmitting a driving assistance request to the intelligent base station; and

the receiving unit is used for receiving the optimal running path of the current vehicle returned by the intelligent base station based on the driving assisting request; wherein the preferred driving path is obtained by using the road side traffic dispatching method of the intersection according to any one of claims 1 to 7.

14. A computer readable storage medium having stored therein program instructions which, when loaded and executed by a processor, cause the processor to carry out the method according to any one of claims 1 to 10.

15. A roadside apparatus comprising:

a processor configured to execute program instructions; and

a memory configured to store the program instructions, which when loaded and executed by the processor, cause the processor to perform the method of any of claims 1-9.

Images