Prediction method and device for driving track of obstacle vehicle

Abstract

The invention provides a method and a device for predicting a driving track of an obstacle vehicle. In the scene that the obstacle vehicle does not enter the intersection or is located in the intersection, the driving intention of the obstacle vehicle is determined, and the driving intention comprises at least one of straight going, left turning, right turning and U-turn. And according to the driving intention, determining the next road where the obstacle vehicle is expected to drive after passing through the intersection. According to the current position of the obstacle vehicle, in at least one lane in the next road, determining a target lane into which the obstacle vehicle is expected to run after passing through the intersection; and generating a future driving track of the obstacle vehicle according to the current position of the obstacle vehicle and the position of the entrance of the target lane. The generated future driving track of the obstacle vehicle can be accurate to the lane, so that the accuracy of the generated future driving track of the obstacle vehicle can be improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular, to a method and device for predicting the driving trajectory of an obstacle vehicle. Background Art

[0002] In an autonomous driving scenario, an autonomous vehicle (ego vehicle) needs to predict the future driving trajectory of other obstacle vehicles in its vicinity, and then plan the subsequent drivable trajectory of the ego vehicle based on the predicted future driving trajectory of the other obstacle vehicles, and then control the ego vehicle to drive automatically according to the subsequent drivable trajectory of the ego vehicle. However, currently, the accuracy of generating the future driving trajectory of an obstacle vehicle is low. Summary of the Invention

[0003] This application discloses a method and device for predicting the driving trajectory of an obstacle vehicle.

[0004] In a first aspect, this application discloses a method for predicting the driving trajectory of an obstacle vehicle, the method including:

[0005] In a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, determining the driving intention of the obstacle vehicle, the driving intention including at least one of going straight, turning left, turning right, and making a U-turn;

[0006] According to the driving intention, determining the next road that the obstacle vehicle is expected to enter after passing through the intersection;

[0007] According to the current position of the obstacle vehicle, determining, in at least one lane of the next road, the target lane that the obstacle vehicle is expected to enter after passing through the intersection;

[0008] Generating the future driving trajectory of the obstacle vehicle according to the current position of the obstacle vehicle and the position of the entrance of the target lane.

[0009] In a second aspect, this application discloses a device for predicting the driving trajectory of an obstacle vehicle, the device including:

[0010] A first determination module, configured to determine the driving intention of the obstacle vehicle in a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, the driving intention including at least one of going straight, turning left, turning right, and making a U-turn;

[0011] A second determination module, configured to determine the next road that the obstacle vehicle is expected to enter after passing through the intersection according to the driving intention;

[0012] A third determination module, configured to determine, in at least one lane of the next road, the target lane that the obstacle vehicle is expected to enter after passing through the intersection according to the current position of the obstacle vehicle;

[0013] A generation module, configured to generate a future driving trajectory of an obstacle vehicle according to the current position of the obstacle vehicle and the position of the entrance of a target lane.

[0014] In a third aspect, the present application discloses an electronic device, which includes: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to execute the method described in any of the above aspects.

[0015] In a fourth aspect, the present application discloses a non-transitory computer-readable storage medium, which, when the instructions stored therein are executed by a processor of an electronic device, enables the electronic device to execute the method described in any of the above aspects.

[0016] In a fifth aspect, the present application discloses a computer program product, which, when the instructions stored therein are executed by a processor of an electronic device, enables the electronic device to execute the method described in any of the above aspects.

[0017] The technical solution provided by the present application may include the following beneficial effects:

[0018] In the present application, in a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, the driving intention of the obstacle vehicle is determined, and the driving intention includes at least one of going straight, turning left, turning right, and making a U-turn. According to the driving intention, the next road that the obstacle vehicle is expected to enter after passing through the intersection is determined. Based on the current position of the obstacle vehicle, in at least one lane of the next road, the target lane that the obstacle vehicle is expected to enter after passing through the intersection is determined; and a future driving trajectory of the obstacle vehicle is generated according to the current position of the obstacle vehicle and the position of the entrance of the target lane.

[0019] The present application can predict the driving trajectory of an obstacle vehicle in a multi-stage and multi-process manner for an intersection scenario, and can not only provide the driving intention of the obstacle vehicle when approaching the intersection and / or when within the intersection to the downstream of the project, but also provide one or more future driving trajectories of the obstacle vehicle to the downstream of the project, providing strong support for the decision-making and planning of the downstream of the project (such as other autonomous vehicles on the road, etc.).

[0020] Among them, the multi-stage includes: the stage when the obstacle vehicle is driving towards the intersection but has not entered the intersection and the stage when the obstacle vehicle is already within the intersection, and the stage when the obstacle vehicle is already within the intersection can be further divided into: the stage when the obstacle vehicle has just entered the intersection and the stage of "the obstacle vehicle approaching the center of the intersection and then driving towards the exit of the intersection".

[0021] Moreover, the multi-process includes: first determining the driving intention of the obstacle vehicle, then determining the target lane in the next road that the obstacle vehicle is expected to enter after passing through the intersection based on the driving intention, and then generating the future driving trajectory of the obstacle vehicle based on the target lane.

[0022] Among them, one or more future driving trajectories of the obstacle vehicle can be generated in the stage when the obstacle vehicle is driving towards the intersection but has not entered the intersection, and one future driving trajectory of the obstacle vehicle can be generated in the stage when the obstacle vehicle is already inside the intersection.

[0023] Since the driving intention of the obstacle vehicle is utilized when determining the target lane in the next road that the obstacle vehicle is expected to enter after passing through the intersection, and the target lane is utilized when generating the future driving trajectory of the obstacle vehicle, the generated future driving trajectory of the obstacle vehicle can be accurate to the lane, thereby improving the accuracy of the generated future driving trajectory of the obstacle vehicle.

[0024] Secondly, the solution of the present application can obtain the driving intention of the obstacle vehicle and the future driving trajectory of the obstacle vehicle, and subsequently, the driving intention of the obstacle vehicle and the future driving trajectory of the obstacle vehicle can be provided to the downstream of the project simultaneously, so as to better provide more powerful support for the decision-making and planning of the downstream of the project (such as other autonomous vehicles on the road, etc.). Description of the Drawings

[0025] Figure 1 is a flowchart of the steps of a method for predicting the driving trajectory of an obstacle vehicle according to the present application.

[0026] Figure 2 is a schematic diagram of a scenario according to the present application.

[0027] Figure 3 is a schematic diagram of a scenario according to the present application.

[0028] Figure 4 is a schematic diagram of a scenario according to the present application.

[0029] Figure 5 is a flowchart of the steps of a method for determining the driving intention of an obstacle vehicle according to the present application.

[0030] Figure 6 is a flowchart of the steps of a method for determining the driving intention of an obstacle vehicle according to the present application.

[0031] Figure 7 is a block diagram of the structure of a device for predicting the driving trajectory of an obstacle vehicle according to the present application.

[0032] Figure 8 is a block diagram of an electronic device according to the present application.

[0033] Figure 9 It is a block diagram of an electronic device of the present application. Detailed implementation manners

[0034] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without making creative efforts shall fall within the protection scope of the present application.

[0035] Referring to Figure 1 , a step flowchart of a method for predicting the driving trajectory of an obstacle vehicle of the present application is shown. This method can be applied to an electronic device, and the electronic device can include a terminal or a server, etc. The terminal can include an in-vehicle terminal on a vehicle, etc. Among them, this method can specifically include the following steps:

[0036] In step S101, in a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, determine the driving intention of the obstacle vehicle, and the driving intention includes at least one of going straight, turning left, turning right, and making a U-turn.

[0037] In the present application, in a scenario where the obstacle vehicle has not entered the intersection, the driving intention of the obstacle vehicle will be determined. Secondly, in a scenario where the obstacle vehicle is already within the intersection, the driving intention of the obstacle vehicle will also be determined.

[0038] The intersection can include a crossroads, a T-shaped intersection (three-way intersection), or a five-way intersection, etc.

[0039] The obstacle vehicle can include: a human-driven car or an autonomous car.

[0040] The straight-line main body in the present application is not the electronic device in the obstacle vehicle, but the electronic device (such as an in-vehicle terminal, etc.) in a vehicle (which can be regarded as the host vehicle, for example, another autonomous vehicle, etc.) near the obstacle vehicle. For example, a vehicle on the same road as the obstacle vehicle (the host vehicle may be in the same lane as the obstacle vehicle on the same road, or may be in a different lane from the obstacle vehicle on the same road).

[0041] In one example, the host vehicle is located at the left rear, or the right rear, or directly behind the obstacle vehicle, etc.

[0042] For the specific manner of determining the driving intention of the obstacle vehicle, reference can be made to the embodiments shown later, and details will not be elaborated here.

[0043] In step S102, according to the driving intention, determine the next road that the obstacle vehicle is expected to enter after passing through the intersection.

[0044] When the obstacle vehicle has not entered the intersection yet, the obstacle vehicle is on a road. For example, this road can be regarded as the current road. The obstacle vehicle will enter the intersection via the current road and then drive out of the intersection and enter the next road. The current road and the next road are different roads.

[0045] In this application, an intersection is connected to multiple roads. For example, a three-way intersection is connected to 6 roads (a total of 3 roads or 3 streets. In the same road or street, there are two roads with opposite driving directions, and the two roads with opposite driving directions can be regarded as different roads). Another example is that a crossroads is connected to 8 roads, etc.

[0046] The obstacle vehicle is driving on the current road, enters the intersection, then drives out of the intersection and enters another road. Which road the obstacle vehicle enters after driving out of the intersection is determined according to the driving intention of the obstacle vehicle.

[0047] For example, when the current road has been determined and the driving intention of the obstacle vehicle has been determined, which road the obstacle vehicle enters after driving out of the intersection can be determined.

[0048] In an example, when the current road has been determined, each driving intention corresponds to a different road connected to the intersection.

[0049] For example, going straight corresponds to one road, turning left corresponds to another road, turning right corresponds to yet another road, and making a U-turn corresponds to still another road.

[0050] For example, when the driving intention of the obstacle vehicle includes going straight, the next road that the obstacle vehicle is expected to enter after passing through the intersection is the road corresponding to going straight.

[0051] Or, when the driving intention of the obstacle vehicle includes turning left, the next road that the obstacle vehicle is expected to enter after passing through the intersection is the road corresponding to turning left.

[0052] Or, when the driving intention of the obstacle vehicle includes turning right, the next road that the obstacle vehicle is expected to enter after passing through the intersection is the road corresponding to turning right.

[0053] Or, when the driving intention of the obstacle vehicle includes making a U-turn, the next road that the obstacle vehicle is expected to enter after passing through the intersection is the road corresponding to making a U-turn.

[0054] For example, see Figure 2As shown, the obstacle vehicle is currently located in Road 1. The reverse road on the left side of Road 1 is Road 2. Road 3 is the road that the obstacle vehicle will enter after turning left. Road 4 is the road that the obstacle vehicle will enter after turning right. Road 5 is the road that the obstacle vehicle will enter after going straight.

[0055] Among them, the next road that the obstacle vehicle with a U-turn driving intention is expected to enter after passing through the intersection is Road 2 (shown as a dotted line in the figure). The next road that the obstacle vehicle with a left-turn driving intention is expected to enter after passing through the intersection is Road 3 (shown as a dotted line in the figure). The next road that the obstacle vehicle with a right-turn driving intention is expected to enter after passing through the intersection is Road 4 (not shown in the figure). The next road that the obstacle vehicle with a straight-ahead driving intention is expected to enter after passing through the intersection is Road 5 (shown as a dotted line in the figure).

[0056] In step S103, according to the current position of the obstacle vehicle, in at least one lane of the next road, determine the target lane that the obstacle vehicle is expected to enter after passing through the intersection.

[0057] In an embodiment of the present application, when the next road has one lane, determine the one lane in the next road as the target lane.

[0058] Alternatively, in another embodiment of the present application, when the next road has more than two lanes, among the more than two lanes in the next road, determine the lane closest to the current position of the obstacle vehicle, and determine the target lane according to the lane closest to the current position of the obstacle vehicle.

[0059] In an example, since the next road has more than two lanes, therefore, it is possible to virtually create within the intersection: "virtual lanes within the intersection" where the obstacle vehicle reaches the entrance of each lane in the next road from its current position. If the next road has several lanes, several virtual lanes within the intersection can be created. The position of the obstacle vehicle is located in one of the virtual lanes within the intersection, which can be regarded as the "current virtual lane within the intersection".

[0060] When the obstacle vehicle maintains the current virtual lane within the intersection, determine the target lane according to the current virtual lane within the intersection. For example, determine a lane in the next road connected to the current virtual lane within the intersection, and determine the lane in the next road connected to the current virtual lane within the intersection as the target lane.

[0061] Alternatively, in the case where the obstacle vehicle has an intention to change from the "virtual lane within the current intersection" to the "virtual lane within the adjacent intersection" adjacent to the virtual lane within the current intersection, determine the target lane according to the "virtual lane within the adjacent intersection". For example, determine a lane in the next road connected to the "virtual lane within the adjacent intersection", and determine a lane in the next road connected to the "virtual lane within the adjacent intersection" as the target lane.

[0062] Among them, the method for determining whether the obstacle vehicle has an intention to change from the "virtual lane within the current intersection" to the "virtual lane within the adjacent intersection" adjacent to the virtual lane within the current intersection may include:

[0063] In an embodiment of the present application, it may be determined whether the distance between the obstacle vehicle and the left boundary line of the virtual lane within the current intersection is gradually decreasing; in the case of gradual decrease, it is determined that the obstacle vehicle has an intention to change from the virtual lane within the current intersection to the virtual lane within the adjacent intersection on the left side of the virtual lane within the current intersection.

[0064] Among them, the camera on the vehicle can collect an image, which has the obstacle vehicle and the left boundary line of the virtual lane within the current intersection. The distance between the obstacle vehicle and the left boundary line of the virtual lane within the current intersection can be obtained by analyzing the image through the currently existing image analysis technology.

[0065] Alternatively, in another embodiment of the present application, it may be determined whether the distance between the obstacle vehicle and the right boundary line of the virtual lane within the current intersection is gradually decreasing; in the case of gradual decrease, it is determined that the obstacle vehicle has an intention to change from the virtual lane within the current intersection to the virtual lane within the adjacent intersection on the right side of the virtual lane within the current intersection.

[0066] Among them, the camera on the vehicle can collect an image, which has the obstacle vehicle and the right boundary line of the virtual lane within the current intersection. The distance between the obstacle vehicle and the right boundary line of the virtual lane within the current intersection can be obtained by analyzing the image through the currently existing image analysis technology.

[0067] Alternatively, in another embodiment of the present application, the current orientation of the front of the obstacle vehicle can be obtained, and in addition, the historical orientations of the front of the obstacle vehicle at multiple historical moments in the historical process can be obtained. The current orientation of the front of the obstacle vehicle is the orientation of the front of the obstacle vehicle obtained at the latest moment.

[0068] Among them, the camera on the vehicle can collect an image, which has the obstacle vehicle. The orientation of the front of the obstacle vehicle can be obtained by analyzing the image through the currently existing image analysis technology.

[0069] Taking the direction of the virtual lane within the current intersection as the reference direction, within the plane where the road surface is located, rotation to the right is the positive direction and rotation to the left is the negative direction.

[0070] It is possible to calculate the differences between the current orientation of the front of the obstacle vehicle and the historical orientations of the front of the obstacle vehicle at each historical moment. For every two adjacent moments (including the "latest moment" and each historical moment), if the "difference between the current orientation of the front of the obstacle vehicle and the historical orientation of the front of the obstacle vehicle at the adjacent previous historical moment" is greater than the "difference between the current orientation of the front of the obstacle vehicle and the historical orientation of the front of the obstacle vehicle at the adjacent next historical moment", and each difference is a positive value, then it can be determined that the obstacle vehicle has the intention to change from the virtual lane within the current intersection to the virtual lane within the intersection adjacent to the right of the virtual lane within the current intersection.

[0071] And / or, it is possible to calculate the differences between the historical orientations of the front of the obstacle vehicle at each historical moment and the current orientation of the front of the obstacle vehicle. For every two adjacent moments (including the "latest moment" and each historical moment), if the "difference between the historical orientation of the front of the obstacle vehicle at the adjacent previous historical moment and the current orientation of the front of the obstacle vehicle" is greater than the "difference between the historical orientation of the front of the obstacle vehicle at the adjacent next historical moment and the current orientation of the front of the obstacle vehicle", and each difference is a positive value, then it can be determined that the obstacle vehicle has the intention to change from the virtual lane within the current intersection to the virtual lane within the intersection adjacent to the left of the virtual lane within the current intersection.

[0072] Otherwise, it can be determined that the obstacle vehicle does not have the intention to change from the virtual lane within the current intersection to the virtual lane within the intersection adjacent to the virtual lane within the current intersection.

[0073] In step S104, based on the current position of the obstacle vehicle and the position of the entrance of the target lane, the future driving trajectory of the obstacle vehicle is generated.

[0074] After the target lane is determined, the position of the entrance of the target lane can be determined. Thus, based on the current position of the obstacle vehicle and the position of the entrance of the target lane, the future driving trajectory of the obstacle vehicle can be generated by means of the existing driving trajectory generation methods.

[0075] This application does not limit the trajectory generation method. For example, it may include a cubic polynomial model or a quintic polynomial model, etc.

[0076] The starting point of the future driving trajectory is the current position of the obstacle vehicle, and the ending point of the future driving trajectory is the position of the entrance of the target lane.

[0077] For example, referring to Figure 3 , assume that the next road is Road 5, which has three lanes, namely Lane A, Lane B, and Lane C.

[0078] Assume that the current road where the obstacle vehicle is located is Road 1, which includes 3 lanes, namely Lane D, Lane E, and Lane F, and the obstacle vehicle is in Lane D of Road 1.

[0079] Among Lane A, Lane B, and Lane C in Road 5, Lane A is the closest to the current position of the obstacle vehicle (the distance can be the Euclidean distance or the lateral distance, etc.). Therefore, Lane A can be used as the target lane in the next road.

[0080] The future driving trajectory of the obstacle vehicle can be seen as the dotted line in the figure, specifically: the current position of the obstacle vehicle in Lane D → intersection → the entrance of Lane A.

[0081] For example, referring to Figure 4 , assume that the next road is Road 3, which has three lanes, namely Lane H, Lane I, and Lane J.

[0082] Assume that the current road where the obstacle vehicle is located is Road 1, which includes 3 lanes, namely Lane D, Lane E, and Lane F, and the obstacle vehicle is in Lane D of Road 1.

[0083] Among Lane H, Lane I, and Lane J in Road 3, Lane J is the closest to the current position of the obstacle vehicle (the distance can be the Euclidean distance or the lateral distance, etc.). Therefore, Lane J can be used as the target lane in the next road.

[0084] The future driving trajectory of the obstacle vehicle can be seen as the dotted line in the figure, specifically: the current position of the obstacle vehicle in Lane D → intersection → the entrance of Lane J.

[0085] In this application, a kinematic method is used to generate the future driving trajectory of the obstacle vehicle. For example, when the state of the obstacle vehicle changes (such as suddenly detecting that the obstacle vehicle has an intention to change lanes, or detecting a change in the driving intention of the obstacle vehicle), or when a predefined time is reached (or understood as periodically or regularly), the future driving trajectory of the obstacle vehicle is automatically generated to overwrite the previously generated future driving trajectory of the obstacle vehicle, so that the host vehicle can take measures as early as possible according to the newly generated future driving trajectory of the obstacle vehicle, such as decelerating or changing lanes as early as possible, to avoid collisions.

[0086] In this application, in a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, the driving intention of the obstacle vehicle is determined. The driving intention includes at least one of going straight, turning left, turning right, and making a U-turn. According to the driving intention, the next road that the obstacle vehicle is expected to enter after passing through the intersection is determined. Based on the current position of the obstacle vehicle, in at least one lane of the next road, the target lane that the obstacle vehicle is expected to enter after passing through the intersection is determined; according to the current position of the obstacle vehicle and the position of the entrance of the target lane, the future driving trajectory of the obstacle vehicle is generated.

[0087] This application can predict the driving trajectory of the obstacle vehicle in a multi-stage and multi-process manner for the intersection scenario, and can not only provide the driving intention of the obstacle vehicle when approaching the intersection and / or when within the intersection to the downstream of the project, but also provide one or more future driving trajectories of the obstacle vehicle to the downstream of the project, providing strong support for the decision-making and planning of the downstream of the project (such as other autonomous vehicles on the road, etc.).

[0088] Among them, the multi-stage includes: the stage when the obstacle vehicle is driving towards the intersection but has not entered the intersection and the stage when the obstacle vehicle is already within the intersection. The stage when the obstacle vehicle is already within the intersection can be further divided into: the stage when the obstacle vehicle has just entered the intersection and the stage of "the obstacle vehicle approaching the center of the intersection and then driving towards the exit of the intersection".

[0089] And, the multi-process includes: first determining the driving intention of the obstacle vehicle, then determining the target lane in the next road that the obstacle vehicle is expected to enter after passing through the intersection according to the driving intention, and then generating the future driving trajectory of the obstacle vehicle according to the target lane.

[0090] Among them, one or more future driving trajectories of the obstacle vehicle can be generated in the stage when the obstacle vehicle is driving towards the intersection but has not entered the intersection, and one future driving trajectory of the obstacle vehicle can be generated in the stage when the obstacle vehicle is already within the intersection.

[0091] Since the target lane in the next road that the obstacle vehicle is expected to enter after passing through the intersection is determined by means of the driving intention of the obstacle vehicle, and the future driving trajectory of the obstacle vehicle is generated by means of the target lane, the generated future driving trajectory of the obstacle vehicle can be accurate to the lane, thereby improving the accuracy of the generated future driving trajectory of the obstacle vehicle.

[0092] Secondly, the solution of the present application can obtain the driving intention of the obstacle vehicle and the future driving trajectory of the obstacle vehicle, and subsequently, the driving intention of the obstacle vehicle and the future driving trajectory of the obstacle vehicle can be provided to the downstream of the project at the same time, so as to better provide more powerful support for the decision-making and planning of the downstream of the project (such as other autonomous vehicles in the road, etc.).

[0093] In an embodiment of the present application, refer to Figure 5 , in the scenario where the obstacle vehicle has not entered the intersection, the process of determining the driving intention of the obstacle vehicle may include:

[0094] In step S201, in the scenario where the obstacle vehicle has not entered the intersection, determine whether the obstacle vehicle has a lane-changing intention to change from the current lane where the obstacle vehicle is located to the adjacent lane of the current lane; the current lane and the adjacent lane are on the same road.

[0095] In the case of no lane-changing intention, execute step S202, or, in the case of having a lane-changing intention, execute step S203.

[0096] In an embodiment of the present application, the first distance between the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located may be determined; in the case where the first distance is less than the first preset threshold, it is determined that the obstacle vehicle has a lane-changing intention to change from the current lane where the obstacle vehicle is located to the left adjacent lane of the current lane.

[0097] The first preset distance can be set in the electronic device in advance by those skilled in the art according to the actual situation, and can be 10 cm, 11 cm, 12 cm, etc. The present application does not limit the value of the first preset distance.

[0098] Among them, the camera on the vehicle can collect images, and the images include the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located. The first distance between the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located can be obtained by analyzing the images through the existing image analysis technology.

[0099] Or, in another embodiment of the present application, the second distance between the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located may be determined; in the case where the second distance is less than the second preset threshold, it is determined that the obstacle vehicle has a lane-changing intention to change from the current lane where the obstacle vehicle is located to the right adjacent lane of the current lane.

[0100] The second preset threshold may be the same as or different from the first preset threshold.

[0101] The second preset distance can be set in the electronic device in advance by those skilled in the art according to the actual situation. It can be 10 cm, 11 cm, 12 cm, 13 cm, etc. The present application does not limit the value of the second preset distance.

[0102] Among them, the camera on the vehicle can collect an image, which has the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located. The second distance between the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located can be obtained by analyzing the image through the existing image analysis technology.

[0103] Alternatively, in another embodiment of the present application, it can be determined whether the distance between the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located is gradually decreasing; if it is gradually decreasing, it is determined that the obstacle vehicle has the intention of changing lanes from the current lane where the obstacle vehicle is located to the left adjacent lane of the current lane.

[0104] Alternatively, in another embodiment of the present application, it can be determined whether the distance between the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located is gradually decreasing; if it is gradually decreasing, it is determined that the obstacle vehicle has the intention of changing lanes from the current lane where the obstacle vehicle is located to the right adjacent lane of the current lane.

[0105] Alternatively, in another embodiment of the present application, the current orientation of the front of the obstacle vehicle can be obtained, and the orientation of the current lane where the obstacle vehicle is located can be obtained.

[0106] Among them, the camera on the vehicle can collect an image, which has the obstacle vehicle and the boundary line (left boundary line and / or right boundary line) of the current lane where the obstacle vehicle is located. The current orientation of the front of the obstacle vehicle and the orientation of the current lane where the obstacle vehicle is located can be obtained by analyzing the image through the existing image analysis technology.

[0107] Taking the orientation of the current lane as the reference orientation, on the plane where the ground of the road is located, if the current orientation of the front of the obstacle vehicle is rotated a certain angle to the right along the reference orientation, and the angle is greater than the preset angle and less than 90° (generally not driving in reverse in the current road), it can be determined that the obstacle vehicle has the intention of changing lanes from the current lane where the obstacle vehicle is located to the right adjacent lane of the current lane.

[0108] Alternatively, taking the orientation of the current lane as the reference orientation, on the plane where the ground of the road is located, if the current orientation of the front of the obstacle vehicle is rotated by a certain angle to the left along the reference orientation, and this angle is greater than the preset angle and less than 90° (generally not driving in reverse on the current road), it can be determined that the obstacle vehicle has the intention of changing lanes from the current lane where the obstacle vehicle is located to the adjacent lane on the left of the current lane.

[0109] The preset angle can be set in advance in the electronic device by those skilled in the art according to the actual situation. It can be 4°, 5°, or 6°, etc. The present application does not limit the value of the preset angle.

[0110] In the case where there is no intention of changing lanes, in step S202, the driving intention of the obstacle vehicle is determined according to the current lane.

[0111] In an embodiment of the present application, when the current lane is a straight lane, it is determined that the driving intention of the obstacle vehicle is to go straight, and the straight lane can be a lane for only straight driving.

[0112] Alternatively, when the current lane is a right-turn lane, it is determined that the driving intention of the obstacle vehicle is to turn right, and the right-turn lane can be a lane for only right-turning.

[0113] Alternatively, when the current lane is a left-turn lane, it is determined that the driving intention of the obstacle vehicle is to turn left, and the left-turn lane can be a lane for only left-turning.

[0114] Alternatively, when the current lane is a U-turn lane, it is determined that the driving intention of the obstacle vehicle is to make a U-turn, and the U-turn lane can be a lane for only U-turning.

[0115] Alternatively, when the current lane is a shared lane for straight and right turns, it is determined that the driving intention of the obstacle vehicle is to go straight and / or turn right.

[0116] The distance between the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located can be determined; when this distance is less than the third preset threshold, it is determined that the driving intention of the obstacle vehicle is to turn right, otherwise, it is determined that the driving intention of the obstacle vehicle is to go straight.

[0117] The third preset threshold can be the same as or different from the second preset threshold.

[0118] The second preset distance can be set in advance in the electronic device by those skilled in the art according to the actual situation. It can be 10 cm, 11 cm, 11.5 cm, 12 cm, or 13 cm, etc. The present application does not limit the value of the third preset distance.

[0119] Among them, the camera on the vehicle can collect images. The images include the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located. The distance between the obstacle vehicle and the right boundary line of the current lane where the obstacle vehicle is located can be obtained by analyzing the images through the existing image analysis technology.

[0120] The above embodiments show that the driving intention can be a result. For example, it can be either going straight or turning right. Or, both the driving intentions of going straight and turning right can be given at the same time.

[0121] Or, when the current lane is a shared lane for going straight and turning left, determine the driving intention of the obstacle vehicle as going straight and / or turning left.

[0122] The distance between the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located can be determined; when this distance is less than the fourth preset threshold, determine the driving intention of the obstacle vehicle as turning left, otherwise, determine the driving intention of the obstacle vehicle as going straight.

[0123] The fourth preset threshold can be the same as or different from the first preset threshold.

[0124] The fourth preset distance can be set in the electronic device in advance by technicians according to the actual situation. It can be 10 cm, 10.5 cm, 11 cm, 12 cm, 13 cm, etc. The present application does not limit the value of the fourth preset distance.

[0125] Among them, the camera on the vehicle can collect images. The images include the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located. The distance between the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located can be obtained by analyzing the images through the existing image analysis technology (for example, by means of a neural network model, etc.).

[0126] The above embodiments show that the driving intention can be a result. For example, it can be either going straight or turning left. Or, both the driving intentions of going straight and turning left can be given at the same time.

[0127] Or, when the current lane is a shared lane for turning left and U-turning, determine the driving intention of the obstacle vehicle as turning left and / or U-turning.

[0128] Among them, the camera on the vehicle can collect images. The images include the obstacle vehicle and the left boundary line of the current lane where the obstacle vehicle is located. The result that the driving intention of the obstacle vehicle is turning left or U-turning can be obtained by analyzing the images through the existing image analysis technology (such as by means of a neural network model, etc.).

[0129] Or, both the driving intentions of going straight and turning left can be given at the same time.

[0130] In the case of a lane-changing intention, in step S203, the driving intention of the obstacle vehicle is determined according to the adjacent lane.

[0131] In the present application, it may be after the obstacle vehicle enters the adjacent lane that the driving intention of the obstacle vehicle is determined according to the adjacent lane.

[0132] In an embodiment of the present application, when the adjacent lane is a straight lane, it is determined that the driving intention of the obstacle vehicle is straight, and the straight lane may be a lane for only straight driving.

[0133] Alternatively, when the adjacent lane is a right-turn lane, it is determined that the driving intention of the obstacle vehicle is to turn right, and the right-turn lane may be a lane for only right-turning.

[0134] Alternatively, when the adjacent lane is a left-turn lane, it is determined that the driving intention of the obstacle vehicle is to turn left, and the left-turn lane may be a lane for only left-turning.

[0135] Alternatively, when the adjacent lane is a U-turn lane, it is determined that the driving intention of the obstacle vehicle is to make a U-turn, and the U-turn lane may be a lane for only U-turning.

[0136] Alternatively, when the adjacent lane is a shared lane for straight and right turns, it is determined that the driving intention of the obstacle vehicle is straight and / or right turn.

[0137] The distance between the obstacle vehicle and the right boundary line of the adjacent lane can be determined; when the distance is less than the third preset threshold, it is determined that the driving intention of the obstacle vehicle is to turn right, otherwise, it is determined that the driving intention of the obstacle vehicle is straight.

[0138] The third preset threshold may be the same as or different from the second preset threshold.

[0139] The second preset distance can be set in the electronic device in advance by those skilled in the art according to the actual situation, and can be 10 cm, 11 cm, 11.5 cm, 12 cm or 13 cm, etc. The present application does not limit the value of the third preset distance.

[0140] Among them, the camera on the vehicle can collect an image, which has the obstacle vehicle and the right boundary line of the adjacent lane. The distance between the obstacle vehicle and the right boundary line of the adjacent lane can be obtained by analyzing the image through the currently existing image analysis technology.

[0141] The above embodiments give that the driving intention can be a result. For example, it can be either straight or right turn, or alternatively, both the driving intentions of straight and right turn can be given at the same time.

[0142] Alternatively, in the case where the adjacent lane is a shared lane for straight-ahead and left-turn, determine that the driving intention of the obstacle vehicle is straight-ahead and / or left-turn.

[0143] It is possible to determine the distance between the obstacle vehicle and the left boundary line of the adjacent lane; in the case where this distance is less than a fourth preset threshold, determine that the driving intention of the obstacle vehicle is left-turn, otherwise, determine that the driving intention of the obstacle vehicle is straight-ahead.

[0144] The fourth preset threshold may be the same as or different from the first preset threshold.

[0145] The fourth preset distance can be set in advance in the electronic device by a person skilled in the art according to the actual situation, and can be 10 cm, 10.5 cm, 11 cm, 12 cm, 13 cm, etc. The present application does not limit the value of the fourth preset distance.

[0146] Among them, the camera on the vehicle itself can collect an image, which has the obstacle vehicle and the right boundary line of the adjacent lane. The distance between the obstacle vehicle and the left boundary line of the adjacent lane can be obtained by analyzing the image through existing image analysis techniques.

[0147] In the above embodiments, the driving intention can be one result. For example, it can be either straight-ahead or left-turn, or both the driving intentions of straight-ahead and left-turn can be given at the same time.

[0148] Alternatively, in the case where the adjacent lane is a shared lane for left-turn and U-turn, determine that the driving intention of the obstacle vehicle is left-turn and / or U-turn.

[0149] Among them, the camera on the vehicle itself can collect an image, which has the obstacle vehicle and the left boundary line of the adjacent lane. The result that the driving intention of the obstacle vehicle is left-turn or U-turn can be obtained by analyzing the image through existing image analysis techniques (for example, by means of a neural network model, etc.).

[0150] Alternatively, both the driving intentions of straight-ahead and left-turn can be given at the same time.

[0151] In an embodiment of the present application, refer to Figure 6 , in the scenario where the obstacle vehicle is already inside the intersection, the process of determining the driving intention of the obstacle vehicle may include:

[0152] In step S301, in the scenario where the obstacle vehicle is already inside the intersection, determine the lane through which the obstacle vehicle enters the intersection.

[0153] For example, assuming that the obstacle vehicle enters the intersection from the straight-ahead lane, it can be determined that the lane through which the obstacle vehicle enters the intersection is the straight-ahead lane.

[0154] Alternatively, assuming that the obstacle vehicle enters the intersection from the right-turn lane, it can be determined that the lane through which the obstacle vehicle enters the intersection is the right-turn lane.

[0155] Alternatively, assuming that the obstacle vehicle enters the intersection from the left-turn lane, it can be determined that the lane through which the obstacle vehicle enters the intersection is the left-turn lane.

[0156] Alternatively, assuming that the obstacle vehicle enters the intersection from the U-turn lane, it can be determined that the lane through which the obstacle vehicle enters the intersection is the U-turn lane.

[0157] Alternatively, assuming that the obstacle vehicle enters the intersection from the shared lane for straight and right turns, it can be determined that the lane through which the obstacle vehicle enters the intersection is the shared lane for straight and right turns.

[0158] Alternatively, assuming that the obstacle vehicle enters the intersection from the shared lane for straight and left turns, it can be determined that the lane through which the obstacle vehicle enters the intersection is the shared lane for straight and left turns.

[0159] Alternatively, assuming that the obstacle vehicle enters the intersection from the shared lane for left turn and U-turn, it can be determined that the lane through which the obstacle vehicle enters the intersection is the shared lane for left turn and U-turn.

[0160] Alternatively, assuming that the obstacle vehicle enters the intersection from the shared lane for straight, left turn and U-turn, it can be determined that the lane through which the obstacle vehicle enters the intersection is the shared lane for straight, left turn and U-turn.

[0161] In step S302, determine the driving intention of the obstacle vehicle according to the lane through which it enters the intersection.

[0162] For example, when the lane through which the obstacle vehicle enters the intersection is the straight lane, determine that the driving intention of the obstacle vehicle is straight, and the straight lane can be a dedicated straight lane.

[0163] Alternatively, when the lane through which the obstacle vehicle enters the intersection is the right-turn lane, determine that the driving intention of the obstacle vehicle is right turn, and the right-turn lane can be a dedicated right-turn lane.

[0164] Alternatively, when the lane through which the obstacle vehicle enters the intersection is the left-turn lane, determine that the driving intention of the obstacle vehicle is left turn, and the left-turn lane can be a dedicated left-turn lane.

[0165] Alternatively, when the lane through which the obstacle vehicle enters the intersection is the U-turn lane, determine that the driving intention of the obstacle vehicle is U-turn, and the U-turn lane can be a dedicated U-turn lane.

[0166] Alternatively, when the lane through which the vehicle enters the intersection is a shared lane for straight and right turns, determine that the driving intention of the obstacle vehicle is straight or right turn.

[0167] For example, the current orientation of the front of the obstacle vehicle can be obtained, and the historical orientations of the front of the obstacle vehicle at multiple historical moments in the historical process can be obtained. The current orientation of the front of the obstacle vehicle is the orientation of the front of the obstacle vehicle obtained at the latest moment.

[0168] Taking the direction of the shared lane as the reference direction, in the plane of the road surface, the right rotation is the positive direction and the left rotation is the negative direction.

[0169] The difference between the current orientation of the front of the obstacle vehicle and the historical orientation of the front of the obstacle vehicle at each historical moment can be calculated.

[0170] For every two adjacent moments (including the "latest moment" and each historical moment), if the "difference between the current orientation of the front of the obstacle vehicle and the historical orientation of the front of the obstacle vehicle at the adjacent previous historical moment" is greater than the "difference between the current orientation of the front of the obstacle vehicle and the historical orientation of the front of the obstacle vehicle at the adjacent next historical moment", and each difference is a positive value, then it can be determined that the driving intention of the obstacle vehicle is a right turn; otherwise, it can be determined that the driving intention of the obstacle vehicle is a straight turn.

[0171] Alternatively, when the lane through which the vehicle enters the intersection is a shared lane for straight and left turns, determine that the driving intention of the obstacle vehicle is straight or left turn.

[0172] For example, the current orientation of the front of the obstacle vehicle can be obtained, and the historical orientations of the front of the obstacle vehicle at multiple historical moments in the historical process can be obtained. The current orientation of the front of the obstacle vehicle is the orientation of the front of the obstacle vehicle obtained at the latest moment.

[0173] Taking the direction of the shared lane as the reference direction, in the plane of the road surface, the right rotation is the positive direction and the left rotation is the negative direction.

[0174] The difference between the historical orientation of the front of the obstacle vehicle at each historical moment and the current orientation of the front of the obstacle vehicle can be calculated.

[0175] For every two adjacent moments (including the "latest moment" and each historical moment), if "the difference between the historical orientation of the front of the obstacle vehicle at the previous adjacent historical moment and the current orientation of the front of the obstacle vehicle" is greater than "the difference between the historical orientation of the front of the obstacle vehicle at the next adjacent historical moment and the current orientation of the front of the obstacle vehicle", and each difference is a positive value, then it can be determined that the driving intention of the obstacle vehicle is to turn left; otherwise, it can be determined that the driving intention of the obstacle vehicle is to go straight.

[0176] Alternatively, in the case where the lane through which the vehicle enters the intersection is a shared lane for left turn and U-turn, it is determined that the driving intention of the obstacle vehicle is to turn left or make a U-turn.

[0177] It can be determined whether the left vertex of the front of the obstacle vehicle crosses the boundary line of the left-turn waiting area within the intersection, where the boundary line of the left-turn waiting area within the intersection is: the boundary line of the left-turn waiting area where the left-turn lane through which the obstacle vehicle enters the intersection extends into the intersection.

[0178] In the case where the left vertex of the front of the obstacle vehicle crosses the boundary line of the left-turn waiting area within the intersection, it is determined that the driving intention of the obstacle vehicle is to make a U-turn.

[0179] Alternatively, in the case where the left vertex of the front of the obstacle vehicle does not cross the boundary line of the left-turn waiting area within the intersection, it is determined that the driving intention of the obstacle vehicle is to turn left.

[0180] Among them, the camera on the vehicle can collect images, and the images include the obstacle vehicle and the boundary line of the left-turn waiting area. The result of whether the left vertex of the front of the obstacle vehicle crosses the boundary line of the left-turn waiting area within the intersection can be obtained by analyzing the images through the currently existing image analysis technology.

[0181] Alternatively, in the case where the lane through which the vehicle enters the intersection is a shared lane for straight, left turn and U-turn, it is determined that the driving intention of the obstacle vehicle is to go straight, turn left or make a U-turn.

[0182] For example, the current orientation of the front of the obstacle vehicle can be obtained, and the historical orientations of the front of the obstacle vehicle at multiple historical moments during the historical process can be obtained. The current orientation of the front of the obstacle vehicle is the orientation of the front of the obstacle vehicle obtained at the latest moment.

[0183] Taking the direction of the shared lane as the reference direction, in the plane of the ground of the road, the right rotation is the positive direction and the left rotation is the negative direction.

[0184] The difference between the historical orientations of the front of the obstacle vehicle at each historical moment and the current orientation of the front of the obstacle vehicle can be calculated.

[0185] For every two adjacent moments (including the "latest moment" and each historical moment), if "the difference between the historical orientations of the front of the obstacle vehicle at the previous adjacent historical moment and the current orientation of the front of the obstacle vehicle" is greater than "the difference between the historical orientations of the front of the obstacle vehicle at the next adjacent historical moment and the current orientation of the front of the obstacle vehicle", and each difference is a positive value, then it can be determined that the driving intention of the obstacle vehicle is non-straight (left turn or U-turn); otherwise, it can be determined that the driving intention of the obstacle vehicle is straight.

[0186] If it is determined that the driving intention of the obstacle vehicle is non-straight (left turn or U-turn), then it can be determined whether the left vertex of the front of the obstacle vehicle crosses the boundary line of the left-turn waiting area within the intersection, where the boundary line of the left-turn waiting area within the intersection is: the boundary line of the left-turn waiting area obtained by extending the left-turn lane through which the obstacle vehicle enters the intersection into the intersection.

[0187] In the case where the left vertex of the front of the obstacle vehicle crosses the boundary line of the left-turn waiting area within the intersection, it is determined that the driving intention of the obstacle vehicle is a U-turn.

[0188] Or, in the case where the left vertex of the front of the obstacle vehicle does not cross the boundary line of the left-turn waiting area within the intersection, it is determined that the driving intention of the obstacle vehicle is a left turn.

[0189] Among them, the camera on the vehicle can collect images, and the images include the obstacle vehicle and the boundary line of the left-turn waiting area. The result of whether the left vertex of the front of the obstacle vehicle crosses the boundary line of the left-turn waiting area within the intersection can be obtained by analyzing the images through the currently existing image analysis technology.

[0190] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily required by the present application.

[0191] Refer to Figure 7 , which shows a structural block diagram of a prediction device for the driving trajectory of an obstacle vehicle according to the present application. The device includes:

[0192] The first determination module 11 is configured to determine the driving intention of the obstacle vehicle in a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, and the driving intention includes at least one of going straight, turning left, turning right, and making a U-turn;

[0193] The second determination module 12 is configured to determine the next road that the obstacle vehicle is expected to enter after passing through the intersection according to the driving intention;

[0194] The third determination module 13 is configured to determine the target lane that the obstacle vehicle is expected to enter after passing through the intersection in at least one lane of the next road according to the current position of the obstacle vehicle;

[0195] The generation module 14 is configured to generate the future driving trajectory of the obstacle vehicle according to the current position of the obstacle vehicle and the position of the entrance of the target lane.

[0196] In an optional implementation manner, the first determination module includes:

[0197] The first determination unit is configured to determine whether there is a lane-changing intention for the obstacle vehicle to change from the current lane where the obstacle vehicle is located to an adjacent lane of the current lane in a scenario where the obstacle vehicle has not entered the intersection; the current lane and the adjacent lane are on the same road;

[0198] The second determination unit is configured to determine the driving intention of the obstacle vehicle according to the current lane when there is no lane-changing intention;

[0199] Or,

[0200] The third determination unit is configured to determine the driving intention of the obstacle vehicle according to the adjacent lane when there is a lane-changing intention.

[0201] In an optional implementation manner, the second determination unit is specifically configured to:

[0202] When the current lane is a straight lane, determine that the driving intention of the obstacle vehicle is to go straight;

[0203] Or,

[0204] When the current lane is a right-turn lane, determine that the driving intention of the obstacle vehicle is to turn right;

[0205] Or,

[0206] When the current lane is a left-turn lane, determine that the driving intention of the obstacle vehicle is to turn left;

[0207] Or,

[0208] When the current lane is a U-turn lane, determine that the driving intention of the obstacle vehicle is to make a U-turn;

[0209] Or,

[0210] When the current lane is a shared lane for straight and right turns, determine that the driving intention of the obstacle vehicle is straight and / or right turn;

[0211] Or,

[0212] When the current lane is a shared lane for straight and left turns, determine that the driving intention of the obstacle vehicle is straight and / or left turn;

[0213] Or,

[0214] When the current lane is a shared lane for left turn and U-turn, determine that the driving intention of the obstacle vehicle is left turn and / or U-turn.

[0215] In an alternative implementation, the second determination unit is specifically configured to:

[0216] When the adjacent lane is a straight lane, determine that the driving intention of the obstacle vehicle is straight;

[0217] Or,

[0218] When the adjacent lane is a right turn lane, determine that the driving intention of the obstacle vehicle is right turn;

[0219] Or,

[0220] When the adjacent lane is a left turn lane, determine that the driving intention of the obstacle vehicle is left turn;

[0221] Or,

[0222] When the adjacent lane is a U-turn lane, determine that the driving intention of the obstacle vehicle is U-turn;

[0223] Or,

[0224] When the adjacent lane is a shared lane for straight and right turns, determine that the driving intention of the obstacle vehicle is straight and / or right turn;

[0225] Or,

[0226] When the adjacent lane is a shared lane for straight and left turns, determine that the driving intention of the obstacle vehicle is straight and / or left turn;

[0227] Or,

[0228] When the adjacent lane is a shared lane for left turn and U-turn, determine that the driving intention of the obstacle vehicle is left turn and / or U-turn.

[0229] In an alternative implementation, the first determination module includes:

[0230] A fourth determination unit, configured to determine a lane through which an obstacle vehicle enters an intersection in a scenario where the obstacle vehicle is already within the intersection;

[0231] A fifth determination unit, configured to determine the driving intention of the obstacle vehicle according to the lane through which the obstacle vehicle enters the intersection.

[0232] In an optional implementation manner, the fifth determination unit is specifically configured to:

[0233] When the lane through which the obstacle vehicle enters the intersection is a straight lane, determine that the driving intention of the obstacle vehicle is to go straight;

[0234] Or,

[0235] When the lane through which the obstacle vehicle enters the intersection is a right-turn lane, determine that the driving intention of the obstacle vehicle is to turn right;

[0236] Or,

[0237] When the lane through which the obstacle vehicle enters the intersection is a left-turn lane, determine that the driving intention of the obstacle vehicle is to turn left;

[0238] Or,

[0239] When the lane through which the obstacle vehicle enters the intersection is a U-turn lane, determine that the driving intention of the obstacle vehicle is to make a U-turn;

[0240] Or,

[0241] When the lane through which the obstacle vehicle enters the intersection is a shared lane for straight and right turns, determine that the driving intention of the obstacle vehicle is to go straight or turn right;

[0242] Or,

[0243] When the lane through which the obstacle vehicle enters the intersection is a shared lane for straight and left turns, determine that the driving intention of the obstacle vehicle is to go straight or turn left;

[0244] Or,

[0245] When the lane through which the obstacle vehicle enters the intersection is a shared lane for left turns and U-turns, determine that the driving intention of the obstacle vehicle is to turn left or make a U-turn;

[0246] Or,

[0247] When the lane through which the obstacle vehicle enters the intersection is a shared lane for straight, left turns, and U-turns, determine that the driving intention of the obstacle vehicle is to go straight, turn left, or make a U-turn.

[0248] In an optional implementation manner, the third determination module includes:

[0249] A sixth determination unit, configured to determine one lane in the next road as the target lane when the next road has one lane;

[0250] Or,

[0251] A seventh determination unit, configured to determine, among two or more lanes in the next road, the lane closest to the current position of the obstacle vehicle when the next road has two or more lanes, and determine the target lane according to the lane closest to the current position of the obstacle vehicle.

[0252] In this application, in a scenario where the obstacle vehicle has not entered the intersection or is already within the intersection, the driving intention of the obstacle vehicle is determined, and the driving intention includes at least one of going straight, turning left, turning right, and making a U-turn. According to the driving intention, the next road that the obstacle vehicle is expected to enter after passing through the intersection is determined. According to the current position of the obstacle vehicle, among at least one lane in the next road, the target lane that the obstacle vehicle is expected to enter after passing through the intersection is determined; according to the current position of the obstacle vehicle and the position of the entrance of the target lane, the future driving trajectory of the obstacle vehicle is generated.

[0253] This application can predict the driving trajectory of the obstacle vehicle in a multi-stage and multi-process manner for the intersection scenario, and can not only provide the driving intention of the obstacle vehicle when approaching the intersection and / or when within the intersection for the downstream of the project, but also provide one or more future driving trajectories of the obstacle vehicle for the downstream of the project, providing strong support for the decision-making and planning of the downstream of the project (such as other autonomous vehicles on the road, etc.).

[0254] Among them, the multi-stage includes: the stage when the obstacle vehicle is driving towards the intersection but has not entered the intersection and the stage when the obstacle vehicle is already within the intersection. The stage when the obstacle vehicle is already within the intersection can be further divided into: the stage when the obstacle vehicle has just entered the intersection, and the stage of "the obstacle vehicle approaching the center of the intersection and then driving towards the exit of the intersection".

[0255] And, the multi-process includes: first determining the driving intention of the obstacle vehicle, then determining the target lane in the next road that the obstacle vehicle is expected to enter after passing through the intersection according to the driving intention, and then generating the future driving trajectory of the obstacle vehicle according to the target lane.

[0256] Among them, one or more future driving trajectories of the obstacle vehicle can be generated in the stage when the obstacle vehicle is driving towards the intersection but has not entered the intersection, and one future driving trajectory of the obstacle vehicle can be generated in the stage when the obstacle vehicle is already within the intersection.

[0257] Since the driving intention of the obstacle vehicle is utilized when determining the target lane in the next road that the obstacle vehicle is expected to drive into after passing through the intersection, and the target lane is utilized when generating the future driving trajectory of the obstacle vehicle, the generated future driving trajectory of the obstacle vehicle can be accurate to the lane, thereby improving the accuracy of the generated future driving trajectory of the obstacle vehicle.

[0258] Secondly, the solution of the present application can obtain the driving intention of the obstacle vehicle and the future driving trajectory of the obstacle vehicle. Subsequently, the driving intention of the obstacle vehicle and the future driving trajectory of the obstacle vehicle can be provided to the downstream of the project simultaneously, so as to better provide more powerful support for the decision-making and planning of the downstream of the project (such as other autonomous driving vehicles on the road, etc.).

[0259] For the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, refer to the partial description of the method embodiment.

[0260] Optionally, the embodiment of the present application further provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements each process of the above method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0261] The embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, it implements each process of the above method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium, such as a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk, or an optical disc, etc.

[0262] Figure 8 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0263] Refer to Figure 8 , the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0264] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above methods. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0265] The memory 804 is configured to store various types of data to support the operation of the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, images, videos, and the like. The memory 804 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0266] The power component 806 provides power to various components of the electronic device 800. The power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0267] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundary lines of the touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operations. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each of the front camera and the rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0268] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

[0269] The I / O interface 812 provides an interface between the processing component 802 and a peripheral interface module, and the peripheral interface module may be a keyboard, a click wheel, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a power button, and a lock button.

[0270] The sensor component 814 includes one or more sensors for providing an assessment of various aspects of the status of the electronic device 800. For example, the sensor component 814 can detect the on / off state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor component 814 can also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor component 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 814 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 814 can further include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0271] The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices in a wired or wireless manner. The electronic device 800 can access a wireless network based on communication standards, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast operation information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0272] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above method.

[0273] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the above instructions can be executed by a processor 820 of the electronic device 800 to complete the above method. For example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0274] Figure 9 FIG. 7 is a block diagram of an electronic device 1900 shown in the present application. For example, the electronic device 1900 may be provided as a server.

[0275] Referring to Figure 9 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0276] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

[0277] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0278] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described method of the embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0279] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

[0280] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the embodiments of the present application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0281] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0282] In the embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0283] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0284] In addition, in each embodiment of the present application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0285] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0286] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting the driving trajectory of an obstacle vehicle, characterized in that: The method comprises: In a scenario where the obstructing vehicle has not yet entered the intersection or is already in the intersection, determining the driving intention of the obstructing vehicle, the driving intention including at least one of going straight, turning left, turning right, and making a U-turn; Determine, based on the driving intention, the next road that the obstacle vehicle is expected to enter after passing the intersection; According to the current position of the obstacle vehicle, determining, in at least one lane in the next road, a target lane into which the obstacle vehicle is expected to enter after passing the intersection; The future driving trajectory of the obstacle vehicle is generated according to the current position of the obstacle vehicle and the position of the entrance of the target lane.

2. The method according to claim 1, characterized in that The determining of the driving intention of the obstacle vehicle includes: In a scenario where the obstructing vehicle has not yet entered the intersection, determining whether the obstructing vehicle has an intention to change lanes from the current lane where the obstructing vehicle is located to an adjacent lane of the current lane; the current lane and the adjacent lane are located on the same road; In the absence of a lane change intention, the driving intention of the obstacle vehicle is determined based on the current lane; or, In the case of a lane change intention, the driving intention of the obstacle vehicle is determined based on the adjacent lanes.

3. The method according to claim 2, characterized in that The determining of the driving intention of the obstacle vehicle according to the current lane in the absence of a lane change intention includes: When the current lane is a straight lane, it is determined that the driving intention of the obstacle vehicle is to go straight; or, When the current lane is a right-turn lane, determining that the obstacle vehicle has a right-turn intention; or, When the current lane is a left-turn lane, determining that the obstacle vehicle has a driving intention of turning left; or, In the case where the current lane is a U-turn lane, determining that the driving intention of the obstacle vehicle is to make a U-turn; or, In the case where the current lane is a shared lane for going straight and turning right, determining that the driving intention of the obstacle vehicle is going straight and / or turning right; or, In the case where the current lane is a shared lane for going straight and turning left, determining that the driving intention of the obstacle vehicle is going straight and / or turning left; or, In the case that the current lane is a shared lane for left turns and U-turns, it is determined that the driving intention of the obstacle vehicle is to turn left and / or to make a U-turn.

4. The method according to claim 2, characterized in that: The method of determining the driving intention of the obstacle vehicle according to the adjacent lane when there is an intention to change lanes includes: When the adjacent lane is a through lane, it is determined that the driving intention of the obstacle vehicle is to go straight; or, In the case where the adjacent lane is a right-turn lane, it is determined that the driving intention of the obstacle vehicle is to turn right; or, In the case where the adjacent lane is a left-turn lane, it is determined that the driving intention of the obstructing vehicle is to turn left; or, In the case where the adjacent lane is a U-turn lane, it is determined that the driving intention of the obstructing vehicle is to make a U-turn; or, In the case where the adjacent lane is a shared lane for going straight and turning right, determining that the driving intention of the obstacle vehicle is going straight and / or turning right; or, In the case where the adjacent lane is a shared lane for going straight and turning left, determining that the driving intention of the obstacle vehicle is going straight and / or turning left; or, In the case that the adjacent lane is a shared lane for left turns and U-turns, it is determined that the driving intention of the obstacle vehicle is to turn left and / or to make a U-turn.

5. The method according to claim 1, characterized in that The determining of the driving intention of the obstacle vehicle includes: In a scenario where the obstructing vehicle is already in the intersection, determining the lane through which the obstructing vehicle enters the intersection; The driving intention of the obstacle vehicle is determined based on the lane it passes through to enter the intersection.

6. The method according to claim 5, characterized in that The method of determining the driving intention of the obstacle vehicle according to the lane through which the obstacle vehicle enters the intersection includes: In the case that the lane through which the vehicle enters the intersection is a straight lane, it is determined that the driving intention of the obstacle vehicle is to go straight; or, In the case where the lane through which the obstacle vehicle enters the intersection is a right-turn lane, determining that the obstacle vehicle has a right-turn intention; or, In the case where the lane through which the vehicle enters the intersection is a left-turn lane, determining that the driving intention of the obstructing vehicle is to turn left; or, In the case where the lane through which the vehicle enters the intersection is a U-turn lane, determining that the driving intention of the obstructing vehicle is to make a U-turn; or, In the case where the lane through which the vehicle enters the intersection is a shared lane for going straight and turning right, determining that the driving intention of the obstructing vehicle is to go straight or turn right; or, In the case where the lane through which the vehicle enters the intersection is a shared lane for going straight and turning left, determining that the driving intention of the obstructing vehicle is to go straight or turn left; or, In the case where the lane used to enter the intersection is a shared lane for left turns and U-turns, determining that the driving intention of the obstructing vehicle is to turn left or to make a U-turn; or, In the case that the lane through which the vehicle enters the intersection is a shared lane for going straight, turning left, and making a U-turn, it is determined that the driving intention of the obstacle vehicle is going straight, turning left, or making a U-turn.

7. The method according to claim 1, characterized in that The method of determining, according to the current position of the obstacle vehicle, a target lane in at least one lane in the next road that the obstacle vehicle is expected to enter after passing the intersection, comprises: In the case where the next road has one lane, determining one lane on the next road as the target lane; or, When the next road has two or more lanes, the lane closest to the current position of the obstacle vehicle is determined among the two or more lanes in the next road, and the target lane is determined based on the lane closest to the current position of the obstacle vehicle.

8. A device for predicting the driving trajectory of an obstacle vehicle, characterized in that: The device comprises: A first determination module is used to determine the driving intention of the obstacle vehicle in a scenario where the obstacle vehicle has not yet entered the intersection or is already in the intersection, the driving intention including at least one of going straight, turning left, turning right and turning around; A second determination module is used to determine the next road that the obstacle vehicle is expected to enter after passing the intersection according to the driving intention; A third determination module is used to determine, according to the current position of the obstacle vehicle, a target lane in at least one lane in the next road that the obstacle vehicle is expected to enter after passing the intersection; The generation module is used to generate the future driving trajectory of the obstacle vehicle according to the current position of the obstacle vehicle and the position of the entrance of the target lane.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images