Method, device and equipment for identifying lane traffic state and storage medium

Abstract

The present disclosure provides a method, device and equipment for identifying lane traffic state, and a storage medium, relates to the field of artificial intelligence, in particular to the technical field of automatic driving, intelligent traffic and the like. The specific implementation scheme is as follows: obtaining driving data of a second vehicle, and predicting a target lane corresponding to the second vehicle based on the driving data of the second vehicle. Then, determining the traffic state of the target lane based on the obstacle situation of the target lane. Finally, determining the driving strategy of a first vehicle based on the traffic state of the target lane.

Description

TECHNICAL FIELD

[0001] The present disclosure pertains to the field of artificial intelligence, and particularly relates to the technical field of automatic driving, intelligent traffic, and the like. Specifically, it relates to a method and device for identifying a lane traffic state, an apparatus, and a storage medium. BACKGROUND

[0002] Intelligent driving is a vehicle control technology that integrates advanced information control technology, environmental perception, multi-level auxiliary driving, and other functions. Intelligent driving can improve road traffic efficiency and vehicle driving safety, greatly benefiting people's lives.

[0003] In the intelligent driving scenario, understanding the traffic state of the lane in front of the surrounding vehicles of the driving vehicle can help predict the driving behavior of the surrounding vehicles, thereby facilitating the driving vehicle to make correct driving decisions. SUMMARY

[0004] The present disclosure provides a method and device for identifying a lane traffic state, an apparatus, and a storage medium.

[0005] According to a first aspect of the present disclosure, a method for identifying a lane traffic state is provided, applied to a first vehicle; the method comprises:

[0006] obtaining driving data of at least one second vehicle within a preset range of the first vehicle; predicting a target lane corresponding to the second vehicle based on the driving data of the second vehicle; determining a traffic state of the target lane based on an obstacle situation of the target lane; and determining a driving strategy of the first vehicle based on the traffic state of the target lane.

[0007] According to a second aspect of the present disclosure, a device for identifying a lane traffic state is provided, applied to a first vehicle; the device comprises: an obtaining unit configured to obtain driving data of at least one second vehicle within a preset range of the first vehicle; a prediction unit configured to predict a target lane corresponding to the second vehicle based on the driving data of the second vehicle; a first determination unit configured to determine a traffic state of the target lane based on an obstacle situation of the target lane; and a second determination unit configured to determine a driving strategy of the first vehicle based on the traffic state of the target lane.

[0008] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0009] at least one processor; and

[0010] a memory in communication with the at least one processor; wherein

[0011] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any of the methods in the first aspect.

[0012] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform any of the methods of the first aspect.

[0013] According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program, the computer program being configured to cause a processor to perform any of the methods of the first aspect.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0016] Figure 1 is a traffic road plane schematic diagram provided by an embodiment of the present disclosure;

[0017] Figure 2 is another traffic road plane schematic diagram provided by an embodiment of the present disclosure;

[0018] Figure 3 is a flowchart of a method for identifying a lane passing state provided by some embodiments of the present disclosure;

[0019] Figure 4 is a position schematic diagram of a plurality of lane segments on a lane provided by an embodiment of the present disclosure;

[0020] Figure 5 is a position schematic diagram of lane segments corresponding to a lane sequence provided by an embodiment of the present disclosure;

[0021] Figure 6 is another position schematic diagram of lane segments corresponding to a lane sequence provided by an embodiment of the present disclosure;

[0022] Figure 7 is a schematic diagram of a predicted trajectory provided by an embodiment of the present disclosure;

[0023] Figure 8 is a schematic diagram of a corrected predicted trajectory provided by an embodiment of the present disclosure;

[0024] Figure 9 is a position schematic diagram of a detection blind area existing on a traffic road provided by an embodiment of the present disclosure;

[0025] Figure 10is a flowchart of a method for identifying a lane traffic state according to some embodiments of the present disclosure;

[0026] Figure 11 is a structural diagram of a device for identifying a lane traffic state according to some embodiments of the present disclosure;

[0027] Figure 12 is a structural diagram of an electronic device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0028] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are provided to assist in the understanding of the present disclosure, and which include various details of the embodiments of the present disclosure in order to assist in that understanding. Accordingly, those skilled in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0029] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solutions comply with relevant laws and regulations and do not violate public order and good customs.

[0030] Figure 1 is a traffic road plane diagram according to an embodiment of the present disclosure; Figure 2 is another traffic road plane diagram according to an embodiment of the present disclosure. A plurality of vehicles are driving on the traffic road, and the plurality of vehicles on the same road are driving on the road based on their respective destinations. The plurality of vehicles on the road can include a first vehicle 100 and a second vehicle 200. The first vehicle can be an autonomous vehicle or a manually driven vehicle. The second vehicle can be a manually driven vehicle or an autonomous vehicle.

[0031] The driving of the first vehicle 100 on the road will be affected by the second vehicle 200. Understandably, the driving decision of the first vehicle 100 will change because the second vehicle 200 adopts a different driving mode.

[0032] In some examples, as Figure 1As shown, the second vehicle 200 can be a vehicle located in the periphery of the first vehicle 100, and the distance between the second vehicle 200 and the first vehicle 100 is less than a threshold, i.e., the second vehicle 200 is a vehicle within a preset range of the first vehicle 100. For example, the preset range is a circular range with the first vehicle as the center and a preset distance as the radius, and the radius can be 1 m, 2 m, 3 m, 5 m, 8 m, 10 m, 12 m, 15 m, 17 m, 20 m, etc. For another example, taking the second vehicle 200 as a vehicle 201 driving on the road where the first vehicle 100 is located and located in front of the first vehicle 100, if the vehicle 201 drives at a deceleration, the first vehicle 100 will make a driving decision to step on the brake; if the vehicle 201 drives at a constant speed, the first vehicle 100 will make a driving decision to maintain the vehicle speed. For another example, taking the second vehicle 200 as a vehicle 202 driving on the adjacent lane on the right side of the road where the first vehicle 100 is located, if the vehicle 202 drives to the left lane, the first vehicle 100 will make a driving decision to step on the brake.

[0033] In other examples, the second vehicle 200 can also be a vehicle that is predicted to have an interaction with the first vehicle 100 based on the relative position of the first vehicle 100 and the second vehicle 200 and the driving state (such as driving direction and / or driving speed) of the first vehicle 100 and the second vehicle 200. The interaction between the first vehicle and the second vehicle can include the second vehicle driving side by side with the first vehicle in a direction perpendicular to the extension of the road, the second vehicle driving in front of or behind the first vehicle on the road, and other suitable interactions, which are not limited here.

[0034] In theory, other vehicles on the road can have an impact on the driving decision of the first vehicle. Therefore, in other examples, as shown in FIG. 1B, the second vehicle can also be all vehicles except the first vehicle. Figure 2

[0035] The first vehicle can be provided with various detection devices. The first vehicle can perceive objects (such as cars, bicycles, pedestrians, roadblocks, etc.) in the surrounding road environment by means of the detection devices, so that the first vehicle can obtain more abundant actual road information to make correct driving decisions.

[0036] For example, the detection device on the first vehicle can include a camera. The camera can be a fixed camera, and multiple fixed cameras can be respectively arranged on the outer wall of the vehicle body and outwardly arranged to collect environmental image information of the surrounding road of the first vehicle. The camera can also be a rotating camera, which can be arranged at the top of the vehicle body and collect environmental image information of the surrounding road of the first vehicle during rotation.

[0037] ​Exemplarily, the detection device on the first vehicle can also include an ultrasonic probe. During driving of the first vehicle, the ultrasonic probe emits ultrasonic signals and receives ultrasonic signals reflected back from objects in the surrounding environment of the first vehicle. By analyzing the reflection positions of the ultrasonic signals, the objects in the surrounding road environment of the first vehicle are learned.

[0038] The detection device on the first vehicle can also include other sensors with detection functions, such as a laser sensor and the like, which are not limited herein.

[0039] As has been described above, the second vehicle has an impact on the driving decision of the first vehicle, and therefore the traffic state of the road in front of the second vehicle is particularly important. Accurate identification of whether the road in front of the second vehicle is in a smooth state or in a congested state, prediction of the future driving behavior of the second vehicle, and thus assistance of the first vehicle in making a correct driving decision based on the predicted driving behavior of the second vehicle.

[0040] Based on this, embodiments of the present disclosure provide a method and device for identifying a traffic state of a lane, equipment and a storage medium. To help the first vehicle accurately identify the traffic state of the road in front of the second vehicle, improve the accuracy of the prediction of the future driving behavior of the second vehicle, and thus assist the first vehicle in making a correct driving decision. The following are described respectively.

[0041] The method for identifying a traffic state of a lane provided by the embodiments of the present disclosure can be applied to the first vehicle described above, such as the device for identifying a traffic state of a lane in the first vehicle. It should be understood that the device for identifying a traffic state of a lane that executes the method of the present disclosure is not limited to being deployed in the first vehicle, but can also be deployed in other equipment, such as a roadside unit or other servers. After the other equipment identifies the traffic state of the road in front of the second vehicle, the identification result is sent to the first vehicle, so that the first vehicle makes a driving decision according to the identification result. The following is described by way of example applied to the first vehicle.

[0042] In the case where the number of second vehicles is multiple, the first vehicle can identify the traffic states of the roads in front of multiple second vehicles at the same time, and the method for identifying a traffic state of a lane described below Figure 3 The method for identifying a traffic state of a lane described below

[0043] Figure 3 is a flowchart of the method for identifying a traffic state of a lane provided by some embodiments of the present disclosure. The method is executed by the first vehicle, specifically by the device for identifying a traffic state of a lane in the first vehicle, as Figure 3 illustred, the method for identifying a traffic state of a lane includes steps S301-S304.

[0044] Step S301: Obtain driving data of the second vehicle.

[0045] In some examples, the driving data of the second vehicle can include attitude information of the second vehicle. For example, the direction of the body tilt (head orientation) of the second vehicle. For another example, the deflection direction of the tire of the second vehicle.

[0046] In yet other examples, the driving data of the second vehicle can also include the prompt information emitted by the second vehicle. For example, the prompt information emitted by the turn signal of the second vehicle. For another example, the prompt information emitted by the brake warning light of the second vehicle.

[0047] In still other examples, the driving data of the second vehicle can also include the driving state of the second vehicle, such as the current driving road of the second vehicle, the driving speed of the second vehicle, and the movement information of the second vehicle. The movement information of the second vehicle includes the movement direction of the second vehicle in the lateral direction (the direction perpendicular to the lane extension direction). For another example, the lateral speed when the second vehicle moves to the left.

[0048] Of course, the driving data of the second vehicle can also be other suitable information. For example, the driving data described in step S500 can be the historical driving data (or the driving data at the historical moment, which is the moment before the current moment) of the second vehicle, the driving data of the second vehicle at the current moment, or the driving data of the second vehicle within a preset time period, which includes the current moment and a plurality of continuous moments before the current moment, and the present disclosure does not limit this.

[0049] For example, the first vehicle can obtain the driving data of the second vehicle through the above-mentioned detection device. For example, the first vehicle can obtain the attitude information of the second vehicle through the ultrasonic probe; and / or, the first vehicle can obtain the prompt information emitted by the second vehicle through the camera.

[0050] Step S302: Based on the driving data of the second vehicle, predict the target lane corresponding to the second vehicle.

[0051] In the high-definition map, a large amount of road information is generally included, such as sidewalk, lane, intersection, signboard, traffic signal, etc. The map data is composed of a plurality of data segments. For example, the lane generation device of the high-definition map divides the lane into a plurality of continuous lane segments. In some examples, the lane segment can be divided according to the extension direction of the lane and its change trend. For example, the straight lane is divided into a plurality of lane segments according to the extension direction of the lane and its change trend. Figure 4As shown, one straight lane includes at least two road segments 40 with different extension directions, one road segment with an extension direction is one lane segment 41, and the other road segment with an extension direction in the straight lane is another lane segment 42. That is, the road generation apparatus of the high-definition map can segment the lane into different lane segments according to the change of the extension direction of the lane. In other examples, the road generation apparatus of the high-definition map can also segment the lane into different lane segments according to the change of the lateral width of the lane, and can also segment the lane into different lane segments according to other suitable factors, which are not limited here.

[0052] It can be understood that the longitudinal (parallel to the extension direction of the lane) length of different lane segments can be different. The longitudinal length of one lane segment can be several meters or several hundred meters, which is not limited here.

[0053] The target lane corresponding to the second vehicle refers to the lane segment that the second vehicle will enter in the future predicted by the first vehicle. The target lane can be a lane segment of the current lane of the second vehicle, or a lane segment of a lane adjacent to the current lane of the second vehicle.

[0054] After obtaining the driving data of the second vehicle, the first vehicle predicts the target lane of the second vehicle based on the driving data of the second vehicle. It should be noted that the driving data of the second vehicle is not constant, and the driving data of the second vehicle changes. After the driving data of the second vehicle changes, the target lane of the second vehicle predicted by the first vehicle can also change accordingly. For example, the driving data of the second vehicle at the first time is different from the driving data of the second vehicle at the second time, and the target lane of the second vehicle predicted by the first vehicle at the first time can be different from the target lane of the second vehicle predicted by the first vehicle at the second time.

[0055] Step S303: determining the passing state of the target lane based on the obstacle situation of the target lane.

[0056] The first vehicle can detect whether there is an object other than the second vehicle on the determined target lane by means of its own detection equipment. If there is an object other than the second vehicle on the target lane, it can be considered that there is an obstacle on the target lane. The obstacle can be a car, a bicycle, an electric vehicle, a pedestrian, an animal, a roadblock, etc., which is not limited here.

[0057] The obstacle situation output by the first vehicle at least includes an obstacle existing on the target lane or an obstacle not existing on the target lane. In some examples, the obstacle situation output by the first vehicle only includes an obstacle existing on the target lane or an obstacle not existing on the target lane. In other examples, the obstacle situation output by the first vehicle can further include a moving speed of the obstacle in the longitudinal direction, an obstacle width of the obstacle in the lateral direction, and the like suitable obstacle information, which is not limited here.

[0058] The traffic state of the target lane represents a traffic state of a future road of the second vehicle. The traffic state can be simply divided into congestion or smooth, or can be graded according to different degrees of congestion in the case that the target lane is in a congestion state.

[0059] The determination manner of the traffic state of the target lane can be determined by detecting the target lane through the detection device of the first vehicle, can be determined based on the monitoring data of the actual road condition of the high-precision map in real time, or can be determined through other suitable manners, which is not limited here.

[0060] Step S304: determining the driving strategy of the first vehicle based on the traffic state of the target lane.

[0061] It should be noted that, in the case that the first vehicle is a manually driven vehicle, the recognition result of the traffic state of the target lane can be conveyed to the driver of the first vehicle through screen display or voice prompt, so as to facilitate the driving decision of the driver. In the case that the first vehicle is an automatic driving vehicle, the driving control unit of the automatic driving vehicle can receive and automatically make a driving decision based on the traffic state of the target lane.

[0062] In the embodiments of the present disclosure, the method of recognizing the traffic state of the lane predicts the target lane of the second vehicle through the driving data of the second vehicle, and recognizes the traffic state of the target lane by detecting the obstacle of the target lane. The first vehicle can obtain more rich and comprehensive actual road information, which is helpful for the driving decision of the first vehicle, so as to improve the safety and driving efficiency of the first vehicle.

[0063] In some embodiments, the method of recognizing the traffic state of the lane can further include: obtaining a lane set of the second vehicle before step S302.

[0064] The lane set includes a plurality of lane segment sequences, each lane segment sequence corresponds to a driving behavior of the second vehicle, and each lane segment sequence includes a sequence composed of identification information of a plurality of continuously spliced lane segments.

[0065] The lane set for the second vehicle can be created by other devices and sent to the first vehicle, or it can be created by the first vehicle itself; there is no limitation here.

[0066] For example, a lane segment sequence refers to a sequence of lane segment identification information arranged and combined according to the driving order of the second vehicle. A lane segment sequence is used to represent a driving route that will occur after the second vehicle performs a certain driving behavior on a real road. This driving route can be divided into multiple lane segments, each lane segment corresponding to one identification information. The identification information of multiple lane segments corresponding to this driving route is combined together according to the driving order of the second vehicle to form a lane segment sequence.

[0067] The aforementioned driving actions can include braking, U-turns, left turns, right turns, changing lanes to the left, changing lanes to the right, etc., without limitation. Understandably, any operation that adjusts the vehicle's driving mode can be considered a driving action.

[0068] In some examples, a lane segment sequence includes (p1, p2, p3, p4). For example... Figure 5 As shown, lane segment p1 represents the lane currently being driven by the second vehicle on the real road, lane segment p2 represents the lane to the right of the current lane being driven by the second vehicle, lane segment p3 represents the right turn lane at the intersection, and lane segment p4 represents the lane after crossing the intersection. Lane segments p1 to p4 are sequentially spliced ​​together to form a driving route that will occur after the second vehicle makes a right turn.

[0069] In other examples, a lane segment sequence includes (p5, p6, p7). For example... Figure 6 As shown, this represents lane segment p5 of the second vehicle's current lane, lane segment p6 for making a U-turn, and lane segment p7 on the opposite side after the U-turn. Lane segments p5 to p7 are sequentially spliced ​​together to form a driving route that the second vehicle will generate after making a U-turn.

[0070] The lane set of the second vehicle can include all possible lane segment sequences for the second vehicle. For example, if the second vehicle can perform driving actions such as turning left, going straight, turning right, and making a U-turn, the lane set of the second vehicle can include lane segment sequences corresponding to the second vehicle turning left, lane segment sequences corresponding to the second vehicle going straight, lane segment sequences corresponding to the second vehicle turning right, and lane segment sequences corresponding to the second vehicle making a U-turn. Understandably, the lane set of the second vehicle includes lane segments that the second vehicle will enter in the future.

[0071] For example, the first vehicle creates a lane set of the second vehicle, the first vehicle determines all the possible driving behaviors of the second vehicle, and then determines the driving routes of the second vehicle under each possible driving behavior. The first vehicle determines the lane segments contained in each driving route, and combines the identification information of the lane segments on a driving route in the order of driving to obtain a lane segment sequence of the second vehicle, and further obtains all the lane segment sequences of the second vehicle, thereby successfully creating the lane set of the second vehicle.

[0072] For example, as shown in FIG. 1, the first vehicle determines all the possible driving behaviors of the second vehicle, and then determines the driving routes of the second vehicle under each possible driving behavior. The first vehicle determines the lane segments contained in each driving route, and combines the identification information of the lane segments on a driving route in the order of driving to obtain a lane segment sequence of the second vehicle, and further obtains all the lane segment sequences of the second vehicle, thereby successfully creating the lane set of the second vehicle. Figure 5 Figure 6 For example, as shown in FIG. 1, the first vehicle determines all the possible driving behaviors of the second vehicle, and then determines the driving routes of the second vehicle under each possible driving behavior. The first vehicle determines the lane segments contained in each driving route, and combines the identification information of the lane segments on a driving route in the order of driving to obtain a lane segment sequence of the second vehicle, and further obtains all the lane segment sequences of the second vehicle, thereby successfully creating the lane set of the second vehicle.

[0073] On this basis, step S302 can include: predicting a target driving behavior of the second vehicle based on driving data of the second vehicle; determining a target lane segment sequence corresponding to the target driving behavior from the lane set; and selecting at least one lane segment in the target lane segment sequence as a target lane.

[0074] In some examples, the driving data of the second vehicle includes data capable of reflecting the current driving condition of the second vehicle. For example, the tire of the second vehicle is deflected to the left, which can reflect that the second vehicle wants to move to the left. For another example, the left turn indicator of the second vehicle is flashing, which can also reflect that the second vehicle wants to move to the left.

[0075] In other examples, the driving data of the second vehicle includes data capable of reflecting the driving habits of the driver in the second vehicle. For another example, the driving data of the second vehicle includes historical driving data of the second vehicle. Based on the historical driving data of the second vehicle, the proportion of different driving behaviors of the second vehicle on the current lane in the past can be obtained.

[0076] The target driving behavior of the second vehicle can be predicted based on data in one or more dimensions (the deflection direction of the tire of the second vehicle, the indicator information of the second vehicle, the historical driving data of the second vehicle, etc.) in the driving data of the second vehicle.

[0077] As mentioned earlier, each lane segment sequence in the lane set corresponds to a driving behavior of the second vehicle. After the target driving behavior of the second vehicle is predicted, the target lane segment sequence corresponding to the target driving behavior can be found in the lane set.

[0078] ​The target lane may include at least the lane segment in which the second vehicle is currently located in the target lane segment sequence, and may also include other lane segments in the target lane segment sequence that are connected to that lane segment. Embodiments of this disclosure do not limit the number of lane segments in the target lane.

[0079] In this embodiment, the lane set for the second vehicle includes lane segments that the second vehicle will likely enter in the future. At least one lane segment is selected as the target lane from the lane set based on the most likely driving behavior of the second vehicle. This allows for the selection of the lane segment with the highest accuracy from a limited number of lane segments as the target lane, thereby improving the accuracy of target lane prediction.

[0080] In some embodiments, predicting the target driving behavior of the second vehicle based on the driving data of the second vehicle may specifically include: using the driving data of the second vehicle as input data to a trajectory prediction algorithm and obtaining the predicted trajectory output by the trajectory prediction algorithm; and determining the target driving behavior of the second vehicle based on the predicted trajectory.

[0081] Trajectory prediction algorithms, after undergoing deep learning, can achieve better prediction accuracy. Suitable trajectory prediction algorithms can include VectorNet, Multipath++, etc., and are not limited here.

[0082] In this embodiment, the driving data of the second vehicle includes at least the input data required by the trajectory prediction algorithm. Thus, by using the driving data of the second vehicle as input data for the trajectory prediction algorithm, the algorithm can output predicted data correctly.

[0083] The trajectory prediction algorithm outputs prediction data consisting of multiple trajectory points. By connecting adjacent trajectory points, the predicted trajectory output by the trajectory prediction algorithm can be obtained.

[0084] By knowing the current location of the second vehicle and the predicted trajectory output by the trajectory prediction algorithm, we can know the future driving route predicted by the trajectory prediction algorithm, and thus determine the target driving behavior corresponding to the driving route.

[0085] For example, such as Figure 7 As shown, the second vehicle is in the second lane from the left, and the trajectory prediction algorithm outputs the predicted trajectory ( Figure 7 (As shown by the thick black dashed line) Passing through the second lane from the left, then the third lane from the left, and continuing straight through the intersection ahead, it can be determined that the target driving behavior corresponding to this route is changing lanes to the right.

[0086] It can be understood that, in the scheme in which the method of identifying the lane passing state determines the target lane segment sequence by using the prediction trajectory algorithm, the steps of determining the target driving behavior of the second vehicle based on the prediction trajectory and determining the target lane segment sequence corresponding to the target driving behavior from the lane set can be regarded as a process of matching the prediction trajectory output by the prediction trajectory algorithm and the plurality of lane sequences in the lane set.

[0087] In this embodiment, the target driving behavior of the second vehicle is predicted by using the prediction trajectory algorithm that has completed deep learning. Because the prediction trajectory algorithm that has completed deep learning has high prediction accuracy, the prediction accuracy of the first vehicle in predicting the target driving behavior of the second vehicle can be improved.

[0088] The blocking object that can exist in front of the second vehicle can affect the actual driving trajectory of the second vehicle, so that the actual driving trajectory of the second vehicle is inconsistent with the prediction trajectory.

[0089] Therefore, in some embodiments, based on the prediction trajectory, the target driving behavior of the second vehicle can be determined specifically by detecting the shape and size of the blocking object located at least in front of the second vehicle and representing the blocking object by using a convex hull; in the case where the prediction trajectory overlaps with the position data of the convex hull, the prediction trajectory is corrected; and the target driving behavior of the second vehicle is determined based on the corrected prediction trajectory.

[0090] The convex hull is a kind of geometric figure that can represent the shape and area size in the high-definition map. The convex hull can be a closed polygon formed by connecting a plurality of points on the periphery. The convex hull can represent the range of the orthographic projection (i.e., the horizontal and vertical projection range) of the blocking object on the actual lane on the road surface in the high-definition map, and the position data of the convex hull in the high-definition map represents the position of the blocking object on the road surface.

[0091] After the first vehicle detects the shape and size of the blocking object located at least in front of the second vehicle by using its own detection device, a corresponding convex hull can be simulated in the high-definition map based on the shape and size of the blocking object, for representing the blocking object on the lane.

[0092] Compared with the way of representing the blocking object by using a center point, the way of representing the blocking object by using the convex hull can enable the first vehicle to more comprehensively and specifically understand the influence of the blocking object on the lane and the vehicle passing in the actual environment.

[0093] The overlapping of the prediction trajectory output by the trajectory prediction algorithm and the position data of the convex hull indicates that the driving trajectory of the second vehicle predicted by the trajectory prediction algorithm will pass through the blocking object, which is obviously not in line with the actual situation.

[0094] Therefore, in this case, the prediction trajectory output by the trajectory prediction algorithm can be corrected by using the correction algorithm, so that the corrected prediction trajectory does not overlap with the position data of the convex hull, which indicates that the second vehicle will bypass the front obstacle and continue to drive.

[0095] As shown in Figure 8 , Figure 8 The black filling in the middle is a convex hull, indicating that the two vehicles cannot move temporarily after the collision and constitute an obstacle in the lane, and occupy the left first lane and the second lane. The trajectory prediction algorithm predicts that the second vehicle needs to drive into the left first lane in order for the second vehicle to make a subsequent left turn, and therefore outputs prediction trajectory I. However, prediction trajectory I overlaps with the position data of the convex hull, which indicates that the second vehicle will pass through the obstacle, which is obviously not in line with the actual situation.

[0096] The correction algorithm can correct prediction trajectory I based on the position data of the convex hull, thereby obtaining prediction trajectory II, which will bypass the front obstacle, drive into the left first lane and continue to drive. In the case where the trajectory prediction algorithm predicts that the driving behavior of the second vehicle is correct, prediction trajectory II is obviously more in line with the actual situation than prediction trajectory I, and is the actual trajectory that the second vehicle will drive.

[0097] In this embodiment, by using a convex hull to represent the obstacle in front of the second vehicle, and correcting the prediction trajectory output by the trajectory prediction algorithm in the case where the prediction trajectory overlaps with the position data of the convex hull, a prediction trajectory that is more in line with the actual situation is obtained, thereby being able to more comprehensively and specifically predict the target driving behavior of the second vehicle in the actual environment, and improving the accuracy of predicting the target driving behavior.

[0098] In some embodiments, the method of identifying the lane traffic state can further include, before step S302, acquiring road traffic information.

[0099] The first vehicle can acquire road traffic information by using its own detection equipment. Illustratively, the first vehicle can acquire traffic signal information by using a camera to capture an image of a traffic signal.

[0100] The road traffic information at least includes traffic signal information, and can further include road obstacle information, road water information, etc., which are not limited here.

[0101] The above prediction of the target driving behavior of the second vehicle based on the driving information of the second vehicle can specifically include predicting the target driving behavior of the second vehicle based on the driving data of the second vehicle and the road traffic information.

[0102] Exemplarily, when the vehicle head of the second vehicle is left-biased and there is a leftward transverse speed, the first vehicle can predict that the target driving behavior of the second vehicle is to change lanes from the lane where the second vehicle is located to the left side.

[0103] Exemplarily, when the vehicle head of the second vehicle is straight, the vehicle speed decreases, and the front traffic signal light is red, the first vehicle can predict that the target driving behavior of the second vehicle is to brake.

[0104] In this embodiment, the road traffic information is further combined on the basis of the driving data of the second vehicle, so that the first vehicle can obtain richer and more comprehensive actual road information, thereby improving the accuracy of the prediction of the target driving behavior of the second vehicle by the first vehicle.

[0105] It should be noted that the embodiments and the embodiments using the prediction trajectory algorithm can be used to respectively and independently predict the target driving behavior of the second vehicle, or can be used to jointly predict the target driving behavior of the second vehicle.

[0106] In some embodiments, the number of lane segments in the target lane can be determined based on the vehicle speed of the second vehicle. The driving data of the second vehicle obtained above includes the vehicle speed of the second vehicle. The vehicle speed can refer to the speed of the second vehicle in the longitudinal direction, or can refer to the speed of the second vehicle in the actual driving direction. The above selecting at least one lane segment in the target lane segment sequence as the target lane can specifically include: determining a distance threshold based on the vehicle speed of the second vehicle; the distance threshold is positively correlated with the vehicle speed of the second vehicle; and selecting at least one lane segment from the plurality of lane segments in the target lane segment sequence, the interval distance between which and the second vehicle in the lane extension direction is less than or equal to the distance threshold, as the target lane.

[0107] The distance threshold is a reference tool for selecting the lane segment in the target lane. The distance threshold can be close to or equal to the driving distance of the second vehicle within a preset time length. For example, the distance threshold can be equal to the distance traveled by the second vehicle within 20 seconds, or can be equal to the distance traveled by the second vehicle within 30 seconds. The embodiments of the present disclosure do not limit the preset time length.

[0108] The faster the vehicle speed of the second vehicle, the farther the driving distance of the second vehicle within the preset time length, so that the distance threshold can be larger. Understandably, the distance threshold is used to select the lane segment in the target lane, so that the target lane can include the lane segment where the second vehicle is currently located and the lane segments passed within the preset time length thereafter.

[0109] As Figure 5As shown, taking the example of the target lane segment sequence including lane segments p1-p4, in the case that the second vehicle is at a low speed, the distance threshold can be d1, and the first vehicle can select lane segments p1 and p2 as the target lane; in the case that the second vehicle is at a high speed, the distance threshold can be d2, and the first vehicle can select lane segments p1-p3 as the target lane.

[0110] It should be noted that when the target lane includes multiple lane segments, the multiple lane segments are continuous with each other.

[0111] In this embodiment, the lane segments in the target lane are selected by using the distance threshold that is positively correlated with the vehicle speed, so that the target lane includes the lane segment in which the second vehicle is currently located and the lane segments that will be passed through within a preset time period. This facilitates subsequent identification of the lane communication condition of the second vehicle within the preset time period.

[0112] In some examples, the traffic state of the target lane can be directly determined according to the obstacle condition. For example, if the obstacle condition indicates that there is an obstacle on the target lane, the traffic state of the target lane indicates that the target lane is in a congested state; if the obstacle condition indicates that there is no obstacle on the target lane, the traffic state of the target lane indicates that the target lane is in a smooth state. The congested state indicates that there is an obstacle in front of the second vehicle on the target lane; the smooth state indicates that there is no obstacle in front of the second vehicle on the target lane.

[0113] In this example, the difficulty of determining the traffic state of the target lane is simplified, and the identification efficiency of the first vehicle for the traffic state of the target lane is improved, thereby improving the prediction efficiency of the first vehicle for the future driving behavior of the second vehicle based on the traffic state of the target lane.

[0114] In some embodiments, the obstacle condition indicates that there is an obstacle on the target lane and an attribute feature of the obstacle, and the attribute feature includes a moving speed. The traffic state of the target lane can further indicate a congestion level of the target lane. The above determination of the traffic state of the target lane according to the obstacle condition can include: determining a moving speed of the obstacle on the target lane in the extension direction of the target lane based on the obstacle condition; and obtaining the congestion level of the target lane according to the moving speed of the obstacle in the extension direction of the target lane. The moving speed of the obstacle in the extension direction of the target lane can be negatively correlated with the congestion level of the target lane.

[0115] The moving speed of the obstacle in the extending direction of the target lane can reflect the congestion degree of the target lane. For example, the moving speed of the obstacle in the longitudinal direction is slow, and the vehicle cannot pass through the obstacle, so the speed reduction of all vehicles (including the second vehicle) on the target lane is serious, and thus the congestion degree of the target lane is serious. For another example, the moving speed of the obstacle in the longitudinal direction is fast, and the speed reduction of the vehicle behind the obstacle is slight, and thus the moving speed of all vehicles (including the second vehicle) on the target lane can be fast, and thus the congestion degree of the target lane is slight.

[0116] In some examples, the congestion state of the first lane to the target lane is divided into three levels, including a first congestion state, a second congestion state and a third congestion state, and the congestion degrees gradually increase. The first congestion state corresponds to a slight congestion degree, and the third congestion state corresponds to a serious congestion degree.

[0117] In a case where the obstacle situation includes that the moving speed of the obstacle in the extending direction of the lane is greater than or equal to the speed of the second vehicle in the extending direction of the lane in the driving data of the second vehicle, it can be considered that the second vehicle is in a following state with a high probability, the driving behavior of the second vehicle is likely to not change suddenly, the speed reduction of the second vehicle caused by the obstacle is slight, and thus it is determined that the target lane is in the first congestion state. In this way, the first vehicle can output the identification result that the target lane is in a congestion state, which can include that the target lane is in the first congestion state.

[0118] In a case where the obstacle situation includes that the moving speed of the obstacle in the extending direction of the lane is greater than zero and less than the speed of the second vehicle in the extending direction of the lane in the driving data of the second vehicle, it can be considered that the speed reduction of the second vehicle caused by the obstacle is moderate, and thus it is determined that the target lane is in the second congestion state. In this way, the first vehicle can output the identification result that the target lane is in a congestion state, which can include that the target lane is in the second congestion state.

[0119] In a case where the obstacle situation includes that the moving speed of the obstacle in the extending direction of the lane is zero, it can be considered that the obstacle is a static object of a non-traffic participant, such as a cone, a fence, etc., and the speed reduction of the second vehicle caused by the obstacle is serious, and thus it is determined that the target lane is in the third congestion state. In this way, the first vehicle can output the identification result that the target lane is in a congestion state, which can include that the target lane is in the third congestion state.

[0120] In other examples, the first vehicle can divide the congestion state of the target lane into two levels, four levels, etc., without limitation. In addition, the determination factor of the influence of the moving speed of the obstacle in the lane extension direction on the speed reduction of the second vehicle can also be different. For example, it can be considered that the moving speed of the obstacle in the lane extension direction is greater than or equal to 50 km / h, the influence of the obstacle on the speed reduction of the second vehicle is slight, and thus it is determined that the target lane is in a first level of congestion state; it can be considered that the moving speed of the obstacle in the lane extension direction is less than 10 km / h, the influence of the obstacle on the speed reduction of the second vehicle is serious, and thus it is determined that the target lane is in a third level of congestion state.

[0121] In this embodiment, the congestion state of the target lane is classified by the moving speed of the obstacle in the longitudinal direction, which can enable the first vehicle to obtain richer and more comprehensive actual road information, and is helpful for the first vehicle to make driving decisions.

[0122] In other embodiments, the obstacle situation represents that there is an obstacle on the target lane and the attribute characteristics of the existing obstacle, and the attribute characteristics include the size of the obstacle in the lateral direction. The traffic state of the target lane can also represent the congestion level of the target lane. The above determination of the traffic state of the target lane according to the obstacle situation can include: determining the size of the obstacle in the lateral direction on the target lane based on the obstacle situation; and obtaining the congestion level of the target lane according to the size of the obstacle in the lateral direction. The size of the obstacle in the lateral direction can be positively correlated with the congestion level of the target lane.

[0123] In this embodiment, the convex hull can represent the range of the orthographic projection of the obstacle on the actual lane on the road surface in the high-definition map, and the position data of the convex hull in the high-definition map represents the position of the obstacle on the road surface.

[0124] The size of the obstacle in the lateral direction can directly affect the time and distance required for the vehicle to bypass the obstacle, and thus affect the degree of congestion on the target lane. For example, the size of the obstacle in the lateral direction is long, the time and distance required for the vehicle to bypass the obstacle are long, and thus the speed reduction of all vehicles (including the second vehicle) on the target lane is serious, and thus the degree of congestion on the target lane is serious. For another example, the size of the obstacle in the lateral direction is short, the time and distance required for the vehicle to bypass the obstacle are short, and thus the speed reduction of all vehicles (including the second vehicle) on the target lane is slight, and thus the degree of congestion on the target lane is slight.

[0125] In this embodiment, the congestion state of the target lane is classified by the size of the obstacle in the lateral direction, which can enable the first vehicle to obtain richer and more comprehensive actual road information, and is helpful for the first vehicle to make driving decisions.

[0126] In some road scenarios, the first vehicle can have a detection blind zone for the target lane. For example, as shown in FIG. 8, there is a large vehicle (e.g., a heavy truck, a bus, etc.) between the first vehicle and the target lane, which blocks the detection device of the first vehicle from detecting the target lane, resulting in a detection blind zone for the target lane. Figure 9

[0127] In a case where the first vehicle determines that there is a detection blind zone for the target lane and identifies that the target lane is in a free state, the judgment of the first vehicle for the target lane about the free state can be inaccurate.

[0128] Therefore, in some embodiments, the first vehicle determines the traffic state of the target lane at a first time to represent a case where the target lane is in a free state, as shown in FIG. 9, the method of identifying the traffic state of the lane further includes steps S305-S307. Figure 10

[0129] Step S305: Determine whether there is a detection blind zone for the target lane for the first vehicle.

[0130] It should be noted that after the detection device of the first vehicle receives the feedback detection signal, the first vehicle can determine whether there is a detection blind zone in the actual road environment based on the feedback detection signal.

[0131] For example, by judging whether the detection blind zone overlaps with the target lane, in a case where the detection blind zone overlaps with the target lane, it is determined that the target lane has a detection blind zone.

[0132] Step S306: In a case where the first vehicle has a detection blind zone for the target lane, based on the driving data of the second vehicle, monitor whether the speed of the second vehicle at a second time is lower than the speed of the second vehicle at a first time.

[0133] In a case where the first vehicle determines that there is a detection blind zone for the target lane and identifies that the target lane is in a free state, the first vehicle continuously monitors whether the speed of the second vehicle is reduced compared to the speed at the time when the target lane is determined to be in a free state by obtaining the driving data of the second vehicle.

[0134] Step S307: If the speed of the second vehicle at the second time is lower than the speed of the second vehicle at the first time, the traffic state of the target lane represents that the target lane is in a congested state.

[0135] If the speed of the second vehicle at the second time is lower than the speed of the second vehicle at the first time, it indicates that the detection blind zone in the target lane can have an obstacle that affects the speed of the second vehicle. Therefore, the traffic state of the target lane represents that the target lane is in a congested state.

[0136] ​​In the embodiment, in the case that the first vehicle determines that there is a detection blind area for the target lane and identifies that the target lane is in a smooth state, in order to avoid the problem of inaccurate identification result caused by the detection blind area of the first vehicle, the identification result is corrected to the congested state of the target lane in the case that the second vehicle speed is monitored to be reduced, so as to improve the accuracy of the identification result, and further to help the first vehicle to make driving decision based on the identification result of the traffic state of the target lane.

[0137] Figure 11 is a structural schematic diagram of the device for identifying lane traffic provided by some embodiments of the present disclosure. The device for identifying lane traffic state is applied to a first vehicle. As shown in Figure 11 , the device comprises:

[0138] The acquisition unit 401 is configured to acquire driving data of at least one second vehicle in a preset range of the first vehicle. The prediction unit 402 is configured to predict a target lane corresponding to the second vehicle based on the driving data of the second vehicle. The first determination unit 403 is configured to determine a traffic state of the target lane based on an obstacle condition of the target lane. The second determination unit 404 is configured to determine a driving strategy of the first vehicle based on the traffic state of the target lane.

[0139] Optionally, the prediction unit 402 is specifically configured to predict a target driving behavior of the second vehicle based on the driving data of the second vehicle; determine a target lane segment sequence corresponding to the target driving behavior from a lane set; the lane set comprises a plurality of lane segment sequences, each lane segment sequence corresponds to a driving behavior of the second vehicle; each lane segment sequence comprises a plurality of continuously spliced lane segments; and at least one lane segment in the target lane segment sequence is selected as the target lane.

[0140] Optionally, the driving data of the second vehicle comprises a vehicle speed of the second vehicle. The prediction unit 402 is further configured to determine a distance threshold based on the vehicle speed of the second vehicle; the distance threshold is positively correlated with the vehicle speed of the second vehicle; and at least one lane segment between the second vehicle and the target lane in the lane extension direction and having an interval distance less than or equal to the distance threshold is selected from a plurality of lane segments of the target lane segment sequence as the target lane.

[0141] Optionally, the prediction unit 402 is further configured to take the driving data of the second vehicle as input data of a trajectory prediction algorithm, and acquire a predicted trajectory output by the trajectory prediction algorithm; and determine the target driving behavior of the second vehicle based on the predicted trajectory.

[0142] Optionally, the acquisition unit 401 is further configured to acquire road traffic information; the road traffic information at least comprises traffic signal information. The prediction unit 402 is further configured to predict the target driving behavior of the second vehicle based on the driving data of the second vehicle and the road traffic information.

[0143] Optionally, the prediction unit 402 is further configured to detect an outline and a size of the blocking object located at least in front of the second vehicle, and represent the blocking object by a convex hull; correct the predicted trajectory in a case that the predicted trajectory overlaps with position data of the convex hull; determine the target driving behavior of the second vehicle based on the corrected predicted trajectory; and the corrected predicted trajectory does not overlap with the position data of the convex hull.

[0144] Optionally, the obstacle situation represents whether there is an obstacle. The first determination unit 403 is specifically configured to: if the obstacle situation represents that there is an obstacle on the target lane, the recognition result represents that the target lane is in a congested state; and if the obstacle situation represents that there is no obstacle on the target lane, the recognition result represents that the target lane is in a smooth state.

[0145] Optionally, the obstacle situation represents that there is an obstacle on the target lane and attribute features of the obstacle, and the attribute features include a moving speed. The first determination unit 403 is further configured to: determine a moving speed of the obstacle on the target lane in an extension direction of the target lane based on the obstacle situation; and obtain a congestion level of the target lane according to the moving speed of the obstacle in the extension direction of the target lane, wherein the moving speed of the obstacle in the extension direction of the target lane is negatively correlated with the congestion level of the target lane.

[0146] Optionally, in a case that the traffic state of the target lane at the first time represents that the target lane is in a smooth state. The first determination unit 403 is further configured to: determine whether there is a detection blind area of the target lane for the first vehicle; in a case that there is the detection blind area of the target lane for the first vehicle, monitor whether a vehicle speed of the second vehicle at a second time is lower than a vehicle speed of the second vehicle at the first time based on driving data of the second vehicle; and if the vehicle speed of the second vehicle at the second time is lower than the vehicle speed of the second vehicle at the first time, the traffic state of the target lane represents that the target lane is in a congested state.

[0147] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0148] Figure 12 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0149] like Figure 12 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the electronic device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0150] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0151] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method of identifying lane passage status. For example, in some embodiments, the method of identifying lane passage status may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the method of identifying lane passage status described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the method of identifying lane passage status by any other suitable means (e.g., by means of firmware).

[0152] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0153] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or server.

[0154] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical conductors, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0156] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0157] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0158] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution provided in this disclosure can be achieved, and this is not limited herein.

[0159] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for identifying lane traffic status, applied to a first vehicle; The method includes: Acquire driving data of at least one second vehicle within a preset range of the first vehicle; Based on the driving data of the second vehicle, predict the target lane corresponding to the second vehicle; The traffic status of the target lane is determined based on the obstacle situation of the target lane; the obstacle situation indicates whether there is an obstacle; the determination of the traffic status of the target lane based on the obstacle situation of the target lane includes: if the obstacle situation indicates that there is an obstacle in the target lane, then the target lane is determined to be in a congested state; if the obstacle situation indicates that there is no obstacle in the target lane, then the target lane is determined to be in a free state. The driving strategy of the first vehicle is determined based on the traffic status of the target lane; Wherein, the traffic status of the target lane at the first moment is used to characterize the situation where the target lane is in a free-flowing state; the method further includes: Determine whether the first vehicle has a detection blind spot in the target lane; If the first vehicle has a blind spot in the target lane, based on the driving data of the second vehicle, it is monitored whether the speed of the second vehicle at the second moment is lower than the speed of the second vehicle at the first moment; the second moment is later than the first moment. If the speed of the second vehicle at the second moment is lower than the speed of the second vehicle at the first moment, then the traffic status of the target lane is used to indicate that the target lane is in a congested state.

2. The method according to claim 1, wherein, The step of predicting the target lane corresponding to the second vehicle based on the driving data of the second vehicle includes: Based on the driving data of the second vehicle, predict the target driving behavior of the second vehicle; From the lane set, a target lane segment sequence corresponding to the target driving behavior is determined; the lane set includes multiple lane segment sequences, each lane segment sequence corresponds to a driving behavior of the second vehicle; each lane segment sequence includes multiple consecutively spliced ​​lane segments. At least one lane segment from the target lane segment sequence is selected as the target lane.

3. The method according to claim 2, wherein, The driving data of the second vehicle, including the vehicle speed; selecting at least one lane segment from the target lane segment sequence as the target lane includes: A distance threshold is determined based on the speed of the second vehicle; the distance threshold is positively correlated with the speed of the second vehicle. From the multiple lane segments in the target lane segment sequence, at least one lane segment whose interval distance with the second vehicle in the lane extension direction is less than or equal to the distance threshold is selected as the target lane.

4. The method according to claim 2, wherein, The step of predicting the target driving behavior of the second vehicle based on the driving information of the second vehicle includes: The driving data of the second vehicle is used as input data for the trajectory prediction algorithm, and the predicted trajectory output by the trajectory prediction algorithm is obtained. Based on the predicted trajectory, the target driving behavior of the second vehicle is determined.

5. The method according to claim 2, further comprising: Obtain road traffic information; The road traffic information includes at least traffic light information; The step of predicting the target driving behavior of the second vehicle based on the driving information of the second vehicle includes: Based on the driving data of the second vehicle and the road traffic information, the target driving behavior of the second vehicle is predicted.

6. The method according to claim 4, wherein, Determining the target driving behavior of the second vehicle based on the predicted trajectory includes: The shape and size of an obstruction located at least in front of the second vehicle are detected, and the obstruction is represented using a convex hull. If the predicted trajectory overlaps with the position data of the convex hull, the predicted trajectory is corrected. Based on the corrected predicted trajectory, the target driving behavior of the second vehicle is determined; the corrected predicted trajectory does not overlap with the position data of the convex hull.

7. The method according to any one of claims 1 to 6, wherein, The obstacle situation characterizes the presence of obstacles in the target lane and the attribute characteristics of the existing obstacles, including movement speed; determining the traffic status of the target lane based on the obstacle situation includes: Based on the obstacle situation in the target lane, determine the moving speed of the obstacles in the target lane in the direction of the target lane extension; The congestion level of the target lane is obtained based on the moving speed of the obstacle in the direction of extension of the target lane, wherein the moving speed of the obstacle in the direction of extension of the target lane is negatively correlated with the congestion level of the target lane.

8. A device for identifying lane passage status, applied to a first vehicle; The device includes: The acquisition unit is used to acquire driving data of at least one second vehicle within a preset range of the first vehicle; The prediction unit is used to predict the target lane corresponding to the second vehicle based on the driving data of the second vehicle. The first determining unit is configured to determine the traffic status of the target lane based on the obstacle situation of the target lane; the obstacle situation indicates whether there is an obstacle; determining the traffic status of the target lane based on the obstacle situation includes: if the obstacle situation indicates that there is an obstacle in the target lane, then determining that the target lane is in a congested state; if the obstacle situation indicates that there is no obstacle in the target lane, then determining that the target lane is in a free-flowing state. The second determining unit is used to determine the driving strategy of the first vehicle based on the traffic status of the target lane; The first determining unit is further configured to determine whether the first vehicle has a detection blind spot in the target lane; if the first vehicle has a detection blind spot in the target lane, based on the driving data of the second vehicle, monitor whether the speed of the second vehicle at a second moment is lower than the speed of the second vehicle at a first moment; the second moment is later than the first moment; if the speed of the second vehicle at the second moment is lower than the speed of the second vehicle at the first moment, then the traffic status of the target lane is used to characterize that the target lane is in a congested state; At the first moment, the target lane is in a state of unobstructed traffic.

9. The apparatus according to claim 8, wherein, The prediction unit is specifically used to predict the target driving behavior of the second vehicle based on the driving data of the second vehicle. From the lane set, a target lane segment sequence corresponding to the target driving behavior is determined; the lane set includes multiple lane segment sequences, and each lane segment sequence corresponds to a driving behavior of the second vehicle. Each lane segment sequence consists of multiple consecutively spliced ​​lane segments; At least one lane segment from the target lane segment sequence is selected as the target lane.

10. The apparatus according to claim 9, wherein, The driving data of the second vehicle includes the speed of the second vehicle; the prediction unit is further configured to determine a distance threshold based on the speed of the second vehicle; the distance threshold is positively correlated with the speed of the second vehicle; and from multiple lane segments of the target lane segment sequence, at least one lane segment whose interval distance with the second vehicle in the lane extension direction is less than or equal to the distance threshold is selected as the target lane.

11. The apparatus according to claim 9, wherein, The prediction unit is further configured to use the driving data of the second vehicle as input data for the trajectory prediction algorithm, and obtain the predicted trajectory output by the trajectory prediction algorithm; and determine the target driving behavior of the second vehicle based on the predicted trajectory.

12. The apparatus according to claim 11, wherein, The prediction unit is also configured to detect the shape and size of an obstacle located at least in front of the second vehicle, and represent the obstacle using a convex hull; correct the prediction trajectory if the predicted trajectory overlaps with the position data of the convex hull; and determine the target driving behavior of the second vehicle based on the corrected prediction trajectory. The corrected predicted trajectory does not overlap with the position data of the convex hull.

13. The apparatus according to any one of claims 8 to 12, wherein, The obstacle situation characterizes the presence of obstacles on the target lane and the attribute characteristics of the existing obstacles, including movement speed; The determining unit is further configured to determine the moving speed of the obstacles in the target lane in the direction of extension of the target lane based on the obstacle situation of the target lane; and to obtain the congestion level of the target lane based on the moving speed of the obstacles in the direction of extension of the target lane, wherein the moving speed of the obstacles in the direction of extension of the target lane is negatively correlated with the congestion level of the target lane.

14. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

16. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images