Vehicle movement state recognition method and device

Abstract

This application discloses a vehicle motion state recognition method and device, which relate to the field of autonomous driving. This method predicts the driving trajectory of another vehicle based on position information and motion information of the other vehicle and at least two types of lane information: lane information for the lane in which the other vehicle is located, lane information for a first adjacent lane of the lane in which the other vehicle is located, and lane information for a second adjacent lane of the lane in which the other vehicle is located, and obtains at least two predicted driving trajectories corresponding to the at least two types of lane information. Next, the motion state of the other vehicle relative to the host vehicle is recognized based on the at least two predicted driving trajectories and the lane information for the lane in which the host vehicle is located, thereby effectively reducing sensitivity to instantaneous kinematic information of the other vehicle in monitoring the motion state of the other vehicle relative to the host vehicle and reducing misidentification of the motion state of the other vehicle.

Description

[Technical field]

[0001] This application claims priority to Chinese Patent Application No. 202010762012.3, entitled “VEHICLE MOTION STATUS IDENTIFICATION METHOD AND APPARATUS,” filed with the China National Intellectual Property Office on July 31, 2020, which is incorporated herein by reference in its entirety.

[0002] TECHNICAL FIELD Embodiments of the present application relate to the field of autonomous driving, and in particular to a method and apparatus for recognizing vehicle motion states. [Background technology]

[0003] In the field of autonomous driving and driving assistance, a vehicle needs to timely and accurately obtain the movement status of other vehicles on the road, for example, whether other vehicles change lanes, so that the vehicle can perform operations such as route planning, adaptive cruise control, appropriate deceleration in an emergency, etc. based on the movement status of other vehicles. Therefore, while driving, the vehicle needs to monitor the movement status of other vehicles on the road.

[0004] Currently, vehicles use sensors to detect the turn signals of other vehicles, the lane in which the other vehicles are located, and center The vehicle can collect information such as the horizontal distance between the lane line and the other vehicle, and the speed and acceleration of the other vehicle, and predict the driving trajectory of the other vehicle based on the collected information. Then, the vehicle can recognize whether the other vehicle is changing lanes based on the predicted driving trajectory of the other vehicle. Alternatively, the vehicle can use a sensor to detect the lane of the lane in which the other vehicle is located. center Line information, the lane of other vehicles and the lane in which the other vehicles are located centerThe vehicle can collect information such as the horizontal distance between the lane and the heading angle, and determine the actual driving path of the other vehicle based on the collected information. The vehicle can then compare the actual driving path of the other vehicle with the driving path of the vehicle that normally continues to drive in the lane in the vehicle driving database. If the distance between the actual driving path of the other vehicle and the driving path of the vehicle that normally continues to drive in the lane in the vehicle driving database is greater than a specified threshold, the vehicle determines that the other vehicle has changed lanes.

[0005] However, in the current method of monitoring the movement state of other vehicles as described above, when the vehicle predicts the driving trajectory of other vehicles or when the vehicle compares the actual driving trajectory of other vehicles with the driving trajectory of vehicles that normally continue to drive in lanes in the vehicle driving database, the host vehicle is very sensitive to the instantaneous kinematic information of other vehicles, and the host vehicle is prone to misinterpreting the movement state of other vehicles. Regarding prior art documents, the corresponding EP application (EP4180295) of this application cites 1. US2018 / 284785A1 (JP6837558B2), 2. US2019 / 389464A1 (JP6935813B2), and 3. CN109 583 151 as related art. Summary of the Invention

[0006] The embodiments of the present application provide a vehicle motion state recognition method and equipment for effectively reducing sensitivity to instantaneous kinematic information of other vehicles when monitoring the motion states of other vehicles, and reducing misidentification of the motion states of other vehicles.

[0007] According to a first aspect, an embodiment of the present application provides a vehicle motion state recognition method, which includes the steps of: acquiring first lane information, second lane information, and position information and motion information of a second vehicle, where the first lane information is lane information of a lane where the first vehicle is located, and the second lane information includes at least two of lane information of a lane where the second vehicle is located, lane information of a first adjacent lane of the lane where the second vehicle is located, and lane information of a second adjacent lane of the lane where the second vehicle is located; determining at least two predicted driving trajectories of the second vehicle based on the second lane information and the position information and motion information of the second vehicle, where each predicted driving trajectory corresponds to each type of lane information included in the second lane information; and determining a motion state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information.

[0008] The position information of the second vehicle may be a relative position of the second vehicle with respect to the first vehicle, e.g., a relative position coordinate. Alternatively, the position information of the second vehicle may be an absolute position of the second vehicle. For example, the actual (absolute) position coordinate of the second vehicle may be determined based on the position coordinate of the first vehicle and the relative position coordinate of the second vehicle with respect to the first vehicle.

[0009] The second vehicle motion information may include kinematic information such as the speed, acceleration, and trajectory curvature of the second vehicle.

[0010] Each predicted driving trajectory corresponds to each type of lane information included in the second lane information means that when the second lane information includes two types of lane information, two predicted driving trajectories having a one-to-one correspondence with the two types of lane information can be determined. When the second lane information includes three types of lane information, three predicted driving trajectories having a one-to-one correspondence with the three types of lane information can be determined.

[0011] For example, when the second lane information includes lane information of the lane in which the second vehicle is located and lane information of a first adjacent lane to the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle will maintain driving in the lane in which the second vehicle is currently located and a predicted driving trajectory in which the second vehicle will change lanes to the first adjacent lane to the lane in which the second vehicle is located can be determined in correspondence with each other.

[0012] Alternatively, when the second lane information includes lane information of the lane in which the second vehicle is located and lane information of a second adjacent lane to the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle will maintain driving in the lane in which the second vehicle is currently located and a predicted driving trajectory in which the second vehicle will change lanes to the second adjacent lane to the lane in which the second vehicle is located can be determined in correspondence with each other.

[0013] Alternatively, when the second lane information includes lane information of a first adjacent lane of the lane in which the second vehicle is located and lane information of a second adjacent lane of the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle changes lanes to the first adjacent lane of the lane in which the second vehicle is located and a predicted driving trajectory in which the second vehicle changes lanes to the second adjacent lane of the lane in which the second vehicle is located can be determined in correspondence with each other.

[0014] Alternatively, when the second lane information includes all three lane information, namely, lane information of the lane in which the second vehicle is located, lane information of a first adjacent lane to the lane in which the second vehicle is located, and lane information of a second adjacent lane to the lane in which the second vehicle is located, it is possible to determine in correspondence with a predicted driving trajectory in which the second vehicle will maintain traveling in the lane in which the second vehicle is currently located, a predicted driving trajectory in which the second vehicle will change lanes to the first adjacent lane to the lane in which the second vehicle is located, and a predicted driving trajectory in which the second vehicle will change lanes to the second adjacent lane to the lane in which the second vehicle is located.

[0015] In this method, based on the position information and motion information of the second vehicle and at least two types of lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located, the driving trajectory of the second vehicle can be predicted to obtain at least two predicted driving trajectories corresponding to the at least two types of lane information. Then, the motion state of the second vehicle relative to the first vehicle can be identified based on the at least two predicted driving trajectories and the lane information of the lane where the first vehicle is located, thereby effectively reducing the sensitivity to the instantaneous kinematic information of the second vehicle when monitoring the motion state of the second vehicle relative to the first vehicle, and reducing the misidentification of the motion state of the second vehicle.

[0016] The first vehicle may be understood as an autonomous or driver-assisted own vehicle, and the second vehicle may be understood as another vehicle traveling on the road relative to the vehicle.

[0017] In a possible design, the step of determining a movement state of the second vehicle relative to the first vehicle based on at least two predicted driving trajectories and the first lane information includes: determining a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and a similarity between each predicted driving trajectory of the second vehicle and the historical driving trajectory; and determining a movement state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information.

[0018] In this design, a target predicted driving trajectory of the second vehicle is determined based on at least two predicted driving trajectories and a similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle, so that the determined target predicted driving trajectory of the second vehicle may be closer to an actual driving trajectory of the second vehicle in the future, thereby improving the accuracy of the motion state of the second vehicle relative to the first vehicle that is subsequently determined based on the target predicted driving trajectory and the first lane information.

[0019] In a possible design, prior to the step of determining a target predicted driving trajectory of the second vehicle based on at least two predicted driving trajectories and a similarity between each predicted driving trajectory and a historical driving trajectory of the second vehicle, the method further includes a step of obtaining a first horizontal coordinate vector of the historical driving trajectory of the second vehicle during a first preset period, the first horizontal coordinate vector being a lateral distance between the historical driving trajectory and a lane in which the second vehicle is located. center obtaining a second horizontal coordinate vector of each predicted driving trajectory in a second preset period, and determining a similarity between each predicted driving trajectory and the historical driving trajectory based on the second horizontal coordinate vector and the first horizontal coordinate vector, wherein the second horizontal coordinate vector is used to indicate a distance vector between each predicted driving trajectory and a lane of a lane in which the second vehicle is located; center The method further includes the steps of:

[0020] The first horizontal coordinate vector of the historical driving trajectory of the second vehicle during the first preset time period includes a plurality of first horizontal coordinates of the historical driving trajectory of the second vehicle during the first preset time period. The second horizontal coordinate vector of each predicted driving trajectory during the second preset time period includes a plurality of second horizontal coordinates of the predicted driving trajectory during the second preset time period.

[0021] In some implementations, the first preset period may be a period including a plurality of consecutive first preset cycles, each of which may include at least one first horizontal coordinate, and the second preset period may be a period including a plurality of consecutive second preset cycles, each of which may include at least one second horizontal coordinate.

[0022] Alternatively, in some other possible designs, the similarity between each of the at least two predicted driving trajectories and the historical driving trajectory of the second vehicle may be determined by another similarity calculation method, which is not limited in the present specification.

[0023] In a possible design, the step of determining a target predicted driving trajectory of the second vehicle based on at least two predicted driving trajectories and a similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle includes: predicting a similarity between each predicted driving trajectory and an actual driving trajectory of the second vehicle based on a similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle; and determining a target predicted driving trajectory of the second vehicle based on at least two predicted driving trajectories and a similarity between each predicted driving trajectory and the actual driving trajectory of the second vehicle.

[0024] For example, the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle can be normalized, and a probability of each predicted driving trajectory can be predicted. The probability can indicate the similarity between each predicted driving trajectory and the actual driving trajectory of the second vehicle. A target predicted driving trajectory of the second vehicle is determined based on at least two predicted driving trajectories and the probability of each predicted driving trajectory.

[0025] In this design, the similarity between each of the at least two predicted driving trajectories and the actual driving trajectory of the second vehicle is predicted, and the at least two predicted driving trajectories are comprehensively considered based on the similarity between each predicted driving trajectory and the actual driving trajectory of the second vehicle to determine a target predicted driving trajectory of the second vehicle, which can ensure better continuity of cutting or changing the motion state of the second vehicle in the determined target predicted driving trajectory.

[0026] In a possible design, the step of determining a motion state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information includes: determining a motion state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information, the step of determining a motion state of the second vehicle relative to the first vehicle relative to the first lane information based on the target predicted driving trajectory and the first lane information, center The method includes the steps of: determining a minimum horizontal distance between the line and within a predetermined vertical length; and determining that the movement state of the second vehicle relative to the first vehicle is maintaining travel in a different lane from the first vehicle if the minimum horizontal distance is greater than a first threshold.

[0027] In this design, whether the motion state of the second vehicle relative to the first vehicle is maintaining driving in a different lane from the first vehicle is determined by comparing the target predicted driving trajectory and the lane in which the first vehicle is located. center The minimum horizontal distance between the lines within a preset vertical length can be determined by comparing it to a first threshold value.

[0028] In a possible design, the method includes: determining a lane of a lane in which the first vehicle is located based on the target predicted driving trajectory and the first lane information. center determining a maximum horizontal distance between the line within a preset vertical length; and determining that the movement state of the second vehicle relative to the first vehicle is crossing the lane in which the first vehicle is located, if the minimum horizontal distance is smaller than a first threshold and the maximum horizontal distance is greater than a second threshold, the second threshold being greater than the first threshold, or determining that the movement state of the second vehicle relative to the first vehicle is maintaining traveling in the same lane as the first vehicle, if the maximum horizontal distance is smaller than a third threshold, the third threshold being smaller than the first threshold, or determining that the movement state of the second vehicle relative to the first vehicle is cutting into or exiting the lane in which the first vehicle is located, if the minimum horizontal distance is smaller than the first threshold and the maximum horizontal distance is greater than the third threshold and less than the second threshold.

[0029] In this design, within a preset longitudinal length, the target predicted driving trajectory and the lane in which the first vehicle is located are aligned. center If the minimum horizontal distance between the lines is less than the first threshold, the movement state of the second vehicle relative to the first vehicle can be further refined by comparing the maximum horizontal distance with a second threshold and a third threshold.

[0030] In a possible design, the method further includes a step of obtaining a first longitudinal position corresponding to a minimum horizontal distance and a second longitudinal position corresponding to a maximum horizontal distance, and the step of determining that the movement state of the second vehicle relative to the first vehicle is entering or exiting the lane in which the first vehicle is located when the minimum horizontal distance is smaller than the first threshold and the maximum horizontal distance is greater than the third threshold and smaller than the second threshold includes a step of determining that the movement state of the second vehicle relative to the first vehicle is entering the lane in which the first vehicle is located when the time at which the second longitudinal position appears is earlier than the time at which the first longitudinal position appears in the target predicted driving trajectory, or a step of determining that the movement state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located when the time at which the first longitudinal position appears is earlier than the time at which the second longitudinal position appears in the target predicted driving trajectory.

[0031] In this design, the motion state of the second vehicle relative to the first vehicle can be distinguished as entering or exiting the lane in which the first vehicle is located based on the time series in which a first longitudinal position corresponding to a minimum horizontal distance appears in the target predicted driving trajectory and the time series in which a second longitudinal position corresponding to a maximum horizontal distance appears.

[0032] In a possible design, the method further comprises the step of obtaining a longitudinal distance between the first longitudinal position and a first end of a preset longitudinal length, the longitudinal distance being a distance between the first longitudinal position and the first end of the preset longitudinal length of a lane in which the first vehicle is located. centerThe method further includes the steps of: determining whether the movement state of the second vehicle relative to the first vehicle is either cutting into the lane in which the first vehicle is located in a first cutting-in state or exiting the lane in which the first vehicle is located in a second exit state, when the longitudinal distance is smaller than a fourth threshold; or determining whether the movement state of the second vehicle relative to the first vehicle is either cutting into the lane in which the first vehicle is located in a second cutting-in state or exiting the lane in which the first vehicle is located in a second exit state, when the longitudinal distance is greater than the fourth threshold.

[0033] For example, the first cutting-in state can be referred to as a close cutting-in state and the first cutting-out state can be referred to as a close cutting-out state. The second cutting-in state can be referred to as a general cutting-in state and the second cutting-out state can be referred to as a general cutting-out state. Alternatively, the first / second cutting-in state and the first / second cutting-out state can be referred to by different names.

[0034] For example, the first cutting-in state is called a close cut-in state, the first pull-out state is called a close cut-out state, the second cutting-in state is called a normal cutting-in state, and the second pull-out state is called a normal pull-out state. In this design, by comparing the longitudinal distance between the first longitudinal position and the first end of the preset longitudinal length with the fourth threshold, the movement state of the second vehicle relative to the first vehicle can be further narrowed down from cutting into the lane in which the first vehicle is located to close cut-in or normal cutting-in, or the movement state of the second vehicle relative to the first vehicle can be narrowed down from pulling out of the lane in which the first vehicle is located to close cut-out or normal pulling-out.

[0035] In a possible design, the movement information of the second vehicle includes a horizontal speed of the second vehicle, and prior to the step of determining at least two predicted driving trajectories of the second vehicle based on the second lane information and the position information and movement information of the second vehicle, the method further includes a step of correcting the horizontal speed included in the movement information of the second vehicle based on an average historical horizontal speed of the second vehicle.

[0036] In this design, the horizontal velocity included in the second vehicle's motion information is modified based on the average historical horizontal velocity of the second vehicle, thereby reducing disturbances caused by excessively large instantaneous current horizontal velocity when determining the second vehicle's predicted driving trajectory.

[0037] According to a second aspect, an embodiment of the present application provides a vehicle motion state recognition device, the device includes: an acquisition module configured to acquire first lane information, second lane information, and position information and motion information of a second vehicle, the first lane information being lane information of a lane where the first vehicle is located, and the second lane information including at least two types of lane information of a lane where the second vehicle is located, lane information of a first adjacent lane of the lane where the second vehicle is located, and a second adjacent lane of the lane where the second vehicle is located; a prediction module configured to determine at least two predicted driving trajectories of the second vehicle based on the second lane information and the position information and motion information of the second vehicle, each predicted driving trajectory corresponding to each type of lane information included in the second lane information; and a determination module configured to determine a motion state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information.

[0038] In a possible design, the determination module is particularly configured to: determine a target predicted driving trajectory of the second vehicle based on at least two predicted driving trajectories and a similarity between each predicted driving trajectory of the second vehicle and the historical driving trajectory; and determine a movement state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information.

[0039] In one possible design, the determination module is configured to obtain a first horizontal coordinate vector of a historical driving trajectory of the second vehicle during a first preset period, the first horizontal coordinate vector being a ratio of the historical driving trajectory to a lane in which the second vehicle is located. center and; obtaining a second horizontal coordinate vector of each predicted driving trajectory during a second preset period, and determining a similarity between each predicted driving trajectory and the historical driving trajectory based on the second horizontal coordinate vector and the first horizontal coordinate vector, wherein the second horizontal coordinate vector is used to indicate a distance vector between each predicted driving trajectory and a lane of a lane in which the second vehicle is located. center used to indicate a distance vector between the lines.

[0040] In a possible design, the determination module is particularly configured to: predict a similarity between each predicted driving trajectory and an actual driving trajectory of the second vehicle based on a similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle; and determine a target predicted driving trajectory of the second vehicle based on the similarity between the at least two predicted driving trajectories and each predicted driving trajectory and the actual driving trajectory of the second vehicle.

[0041] In a possible design, the determination module determines a lane of a lane where the first vehicle is located based on the target predicted driving trajectory and the first lane information. center The vehicle is particularly configured to: determine a minimum horizontal distance between the line and within a predetermined vertical length; and if the minimum horizontal distance is greater than a first threshold, determine that the movement state of the second vehicle relative to the first vehicle is maintaining travel in a different lane from the first vehicle.

[0042] In a possible design, the determination module determines a lane of a lane where the first vehicle is located based on the target predicted driving trajectory and the first lane information. centerand determining a maximum horizontal distance between the line within a preset vertical length; and determining that the movement state of the second vehicle relative to the first vehicle is crossing the lane in which the first vehicle is located if the minimum horizontal distance is smaller than a first threshold and the maximum horizontal distance is greater than a second threshold, the second threshold being greater than the first threshold, or determining that the movement state of the second vehicle relative to the first vehicle is maintaining traveling in the same lane as the first vehicle if the maximum horizontal distance is smaller than a third threshold, the third threshold being less than the first threshold, or determining that the movement state of the second vehicle relative to the first vehicle is cutting into or exiting the lane in which the first vehicle is located if the minimum horizontal distance is smaller than the first vehicle and the maximum horizontal distance is greater than the third threshold and less than the second threshold.

[0043] In a possible design, the determination module is further configured to obtain a first longitudinal position corresponding to a minimum horizontal distance and a second longitudinal position corresponding to a maximum horizontal distance, and; determine that the motion state of the second vehicle relative to the first vehicle is entering the lane in which the first vehicle is located if the minimum horizontal distance is smaller than the first threshold, the maximum horizontal distance is greater than the third threshold and smaller than the second threshold, and the time at which the second longitudinal position appears is earlier than the time at which the first longitudinal position appears in the target predicted driving trajectory, or; determine that the motion state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located if the time at which the first longitudinal position appears is earlier than the time at which the second longitudinal position is displayed in the target predicted driving trajectory.

[0044] In a possible design, the determination module is adapted to obtain a longitudinal distance between the first longitudinal position and a first end of the preset longitudinal length, the longitudinal distance being a lane distance of a lane in which the first vehicle is located between the first longitudinal position and the first end of the preset longitudinal length. centerthe first end of the predetermined longitudinal length being an end closer to the first vehicle; and if the longitudinal distance is smaller than a fourth threshold, determining whether the movement state of the second vehicle relative to the first vehicle is either cutting in to the lane in which the first vehicle is located based on a first cutting in state or exiting from the lane in which the first vehicle is located based on a first exit state; or if the longitudinal distance is greater than the fourth threshold, determining whether the movement state of the second vehicle relative to the first vehicle is either cutting in to the lane in which the first vehicle is located based on a second cutting in state or exiting from the lane in which the first vehicle is located based on a second exit state.

[0045] In a possible design, the second vehicle motion information includes a horizontal speed of the second vehicle, and the prediction module is further configured to modify the horizontal speed included in the second vehicle motion information based on an average historical horizontal speed of the second vehicle.

[0046] According to a third aspect, an embodiment of the present application further provides a vehicle motion state recognition device, the device including: an interface circuit configured to receive data transmitted by another device; and a processor connected to the interface circuit and configured to perform a method according to the first aspect or any one of the possible designs of the first aspect.

[0047] According to a fourth aspect, an embodiment of the present application provides a vehicle including a processor, the processor being configured to connect to a memory and to invoke a program stored in the memory to perform a method according to the first aspect or any one of the possible designs of the first aspect.

[0048] According to a fifth aspect, an embodiment of the present application provides a server including a processor, the processor being configured to connect to a memory and to invoke a program stored in the memory to perform a method according to the first aspect or any one of the possible designs of the first aspect.

[0049] According to a sixth aspect, an embodiment of the present application provides a vehicle driving system, which may be, for example, an autonomous driving system or an assisted driving system, comprising a processor, the processor being connected to a memory and configured to invoke a program stored in the memory to perform a method according to the first aspect or any one of the possible designs of the first aspect.

[0050] According to a seventh aspect, an embodiment of the present application provides a computer readable storage medium including computer software instructions, which when executed on a vehicle motion state recognition device or a chip integrated in the vehicle motion state recognition device, enable the vehicle motion state recognition device to perform a method according to the first aspect or any one of the possible designs of the first aspect.

[0051] According to an eighth aspect, an embodiment of the present application further provides a computer program product, which when executed is capable of performing a method according to the first aspect or any one of the possible designs of the first aspect.

[0052] According to a ninth aspect, an embodiment of the present application further provides a chip system. The chip system is applied to a vehicle, a server, or a driving system, and the chip system includes one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected via lines. The processor receives computer instructions from a memory of an electronic device via the interface circuits, and executes the computer instructions to implement the method according to the first aspect or any one of the possible designs of the first aspect.

[0053] It will be understood that the beneficial effects that can be achieved by the second to ninth aspects should refer to the beneficial effects in the first aspect and any one of the possible designs of the first aspect, and the details will not be described again here. [Brief description of the drawings]

[0054] [Figure 1] FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present application. [Diagram 2] 2 is a schematic diagram showing changes in the motion state of vehicle 2 relative to vehicle 1. FIG. [Diagram 3] FIG. 2 is a schematic diagram showing changes in the motion state of vehicle 4 relative to vehicle 1. [Figure 4] 1 is a schematic diagram showing how a vehicle A recognizes the motion state of a vehicle B by predicting a travel trajectory of the vehicle B. FIG. [Diagram 5] FIG. 11 is another schematic diagram illustrating how vehicle A recognizes the motion state of vehicle B by predicting the driving trajectory of vehicle B. [Figure 6] FIG. 1 is a schematic diagram showing how vehicle A recognizes the motion state of vehicle B by comparing the driving trajectory of a vehicle that continues to normally drive on a lane in a vehicle driving database. [Figure 7] FIG. 1 is a schematic diagram showing how vehicle A recognizes the motion state of vehicle B by comparing the driving trajectory of a vehicle that continues to normally drive on a lane in a vehicle driving database. [Figure 8] FIG. 1 is a schematic diagram of components of a vehicle according to an embodiment of the present application. [Figure 9] 1 is a schematic flowchart of a vehicle motion state recognition method according to an embodiment of the present application; [Figure 10] 4 is another schematic flowchart of a vehicle motion state recognition method according to an embodiment of the present application. [Figure 11] 1 is a schematic diagram illustrating a vehicle A recognizing a motion state of a vehicle B based on a target predicted driving trajectory of the vehicle B according to an embodiment of the present application. FIG. [Figure 12] FIG. 2 is another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application. [Figure 13] FIG. 2 is yet another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application. [Figure 14]FIG. 2 is yet another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application. [Figure 15] FIG. 2 is yet another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application. [Figure 16] FIG. 2 is yet another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application. [Figure 17] FIG. 2 is yet another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application. [Figure 18] FIG. 2 is a schematic diagram of the structure of a vehicle motion state recognition equipment according to an embodiment of the present application; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0055] FIG. 1 is a schematic diagram of an application scenario according to one embodiment of the present application.

[0056] As shown in Fig. 1, this application scenario of this embodiment of the present application may include multiple vehicles traveling on a road. For example, four vehicles are shown in Fig. 1, including vehicle 1, vehicle 2, vehicle 3, and vehicle 4. Different vehicles may travel on different lanes. For example, vehicle 1 travels on lane 1, vehicle 2 travels on lane 2, and vehicle 3 travels on lane 3. Alternatively, different vehicles may travel on the same lane. For example, vehicle 1 and vehicle 4 both travel on lane 1.

[0057] In the field of autonomous driving and driving assistance, for the vehicle in the application scenario shown in Figure 1, the vehicle needs to timely and accurately obtain the movement status of other vehicles on the road, such as whether other vehicles have changed lanes, in order to perform operations such as route planning, adaptive cruise control, and appropriate deceleration in emergency situations based on the movement status of other vehicles.

[0058] In the application scenario shown in Fig. 1, vehicle 1 monitors the motion state of vehicle 2. For example, Fig. 2 is a schematic diagram showing changes in the motion state of vehicle 2 relative to vehicle 1. As shown in Fig. 2, while vehicle 1 and vehicle 2 are traveling, vehicle 2 may cut into the lane in which vehicle 1 is located, for example, cut into lane 1 from lane 2. Vehicle 1 needs to timely monitor changes in the motion state of vehicle 2 and perform route planning and appropriate deceleration, etc., for its own vehicle.

[0059] Alternatively, in the application scenario shown in Fig. 1, the vehicle 1 monitors the motion state of the vehicle 4. For example, Fig. 3 is a schematic diagram showing changes in the motion state of the vehicle 4 relative to the vehicle 1. As shown in Fig. 3, while the vehicle 1 and the vehicle 4 are traveling, the vehicle 4 may exit from the lane in which the vehicle 1 is located to another lane, for example, from lane 1 to lane 2. In this case, the vehicle 1 also needs to monitor the changes in the motion state of the vehicle 4 in a timely manner to execute route planning for the vehicle.

[0060] Currently, there are two common methods for monitoring the movement of other vehicles, as described below.

[0061] In one method, a vehicle uses sensors to detect the turn signals of other vehicles, the lane of other vehicles and the lane in which the other vehicles are located. center The vehicle obtains the horizontal distance between the vehicle and the line, and the speed and acceleration of the other vehicle, and predicts the driving trajectory of the other vehicle based on the collected information. Then, the vehicle can recognize whether the other vehicle will change lanes based on the predicted driving trajectory of the other vehicle.

[0062] For example, the other vehicle is vehicle B, and the host vehicle is vehicle A. Fig. 4 is a schematic diagram in which vehicle A recognizes the motion state of vehicle B by predicting the travel trajectory of vehicle B. As shown in Fig. 4, when vehicle A recognizes that vehicle B is traveling from the lane in which vehicle B is located to another lane based on the predicted travel trajectory of vehicle B, vehicle A can consider that vehicle B may change lanes.

[0063] However, when the host vehicle predicts the driving trajectory of the other vehicle in this manner, the host vehicle may be sensitive to the instantaneous kinematic information of the other vehicle, and may possibly misinterpret the motion state of the other vehicle.

[0064] Similarly, for example, the other vehicle is vehicle B, and the host vehicle is vehicle A. FIG. 5 is another schematic diagram in which vehicle A recognizes the motion state of vehicle B by predicting the driving trajectory of vehicle B. As shown in FIG. 5, when vehicle B suddenly deviates due to an erroneous operation by the driver of vehicle B, vehicle A determines, based on the predicted driving trajectory of vehicle B, that vehicle B may change lanes, but in reality vehicle B may continue to drive in the original lane. Thus, vehicle A misidentifies the motion state of vehicle B.

[0065] Alternatively, the vehicle may use sensors to determine the lane in which the other vehicle is located. center Line information, the lane of other vehicles and the lane in which the other vehicles are located center The vehicle can collect information such as the horizontal distance between the lane and the lane and the travel angle, and determine the actual driving path of the other vehicle based on the collected information. The vehicle can then compare the actual driving path of the other vehicle with the driving path of the vehicle that continues to drive normally in the lane in the vehicle driving database. If the distance between the actual driving path of the other vehicle and the driving path of the vehicle that maintains normal driving in the lane in the vehicle driving database is greater than a predetermined threshold, the vehicle considers that the other vehicle has changed lanes.

[0066] For example, the other vehicle is vehicle B, and the host vehicle is vehicle A. Fig. 6 is a schematic diagram in which vehicle A recognizes the motion state of vehicle B by comparing the driving trajectory of a vehicle that continues to normally drive on a lane in the vehicle driving database. As shown in Fig. 6, when vehicle A recognizes that the distance between the actual driving trajectory of vehicle B and the driving trajectory of a vehicle that maintains normal driving on a lane in the vehicle driving database exceeds a specified threshold, vehicle A can consider that vehicle B may change lanes.

[0067] However, when the vehicle compares the actual driving trajectory of the other vehicle with the driving trajectory of a vehicle that continues to normally drive in the lane in the vehicle driving database in this manner, the vehicle is likely to misinterpret the motion state of the other vehicle because the vehicle is sensitive to the instantaneous kinematic information of the other vehicle.

[0068] Similarly, for example, the other vehicle is vehicle B, and the host vehicle is vehicle A. FIG. 7 is another schematic diagram in which vehicle A recognizes the motion state of vehicle B by comparing the driving trajectory of the vehicle that continues to normally drive in the lane in the vehicle driving database. As shown in FIG. 7, when vehicle B suddenly deviates due to an erroneous operation by the driver of vehicle B, the distance between the actual driving trajectory of vehicle B when vehicle B deviates and the driving trajectory of the vehicle that continues to normally drive in the lane in the vehicle driving database may exceed a certain threshold. Vehicle A may recognize that vehicle B may change lanes, but actually vehicle B may continue to drive in the original lane, so vehicle A misidentifies the motion state of vehicle B.

[0069] From the above, it can be seen that in the current method of recognizing the motion state of other vehicles, the host vehicle may possibly misrecognize the motion state of other vehicles because the host vehicle is sensitive to the instantaneous kinematic information of the other vehicles.

[0070] Based on this, one embodiment of the present application provides a vehicle motion state recognition method. According to this method, the travel trajectory of the other vehicle can be predicted based on at least two types of lane information of the lane in which the other vehicle is located, the lane information of a first adjacent lane (e.g., the adjacent lane on the left side) of the lane in which the other vehicle is located, and the lane information of a second adjacent lane (e.g., the adjacent lane on the right side) of the lane in which the other vehicle is located (combining the motion information and position information of the other vehicle), to obtain at least two predicted travel trajectories corresponding to the at least two types of lane information. Next, the motion state of the other vehicle relative to the host vehicle can be recognized based on the at least two predicted travel trajectories and the lane information of the lane in which the host vehicle is located. For example, it can be recognized whether there is a possibility that the other vehicle will change lanes into the lane in which the host vehicle is located.

[0071] For example, the host vehicle is a first vehicle, and the other vehicle is a second vehicle. The vehicle motion state recognition method may include the steps of: acquiring first lane information, second lane information, and position information and motion information of the second vehicle, where the first lane information is lane information of a lane in which the first vehicle is located, and the second lane information includes at least two types of lane information of a lane in which the second vehicle is located, lane information of a first adjacent lane of the lane in which the second vehicle is located, and lane information of a second adjacent lane of the lane in which the second vehicle is located; determining at least two predicted driving trajectories of the second vehicle based on the second lane information and the position information and motion information of the second vehicle, where each predicted driving trajectory corresponds to each type of lane information included in the second lane information; and determining a motion state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information.

[0072] In the vehicle motion state recognition method provided in this embodiment of the present application, the second lane information includes at least two types of lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located, so that at least two predicted driving trajectories having a one-to-one correspondence with each type of lane information included in the second lane information can be determined with reference to the position information and motion information of the second vehicle. When the motion state of the second vehicle relative to the first vehicle is determined based on the at least two predicted driving trajectories and the first lane information, the at least two predicted driving trajectories can perform mutual correction to reduce sensitivity to the instantaneous kinematic information of the second vehicle. This is to avoid misidentification of the motion state of the second vehicle relative to the first vehicle due to the instantaneous change of the kinematic information of the second vehicle.

[0073] Next, an example of a vehicle motion state recognition method provided in this embodiment of the present application will be described.

[0074] It should be noted that in the description of the present application, terms such as "first" and "second" are used merely to distinguish the description and are not intended to specifically limit the features. In the description of the embodiments of the present application, the term "and / or" describes an association relationship between associated objects and indicates that three relationships may exist. For example, A and / or B may indicate three cases: when only A exists, when both A and B exist, and when only B exists. The character " / " generally indicates an "or" relationship between associated objects. In the present application, "at least one" means one or more, and "multiple" means two or more.

[0075] 8 is a schematic diagram of components of a vehicle according to one embodiment of the present application. As shown in FIG. 8, the vehicle may include various subsystems, such as a driving system 102, a sensor system 104, a control system 106, one or more peripheral devices 108, a power source 110, a computer system 112, and a user interface 116.

[0076] Optionally, a vehicle may include more or fewer subsystems, and each subsystem may include multiple elements. Further, all of the subsystems and elements of a vehicle may be interconnected, either wired or wirelessly.

[0077] The traction system 102 may include components that power the vehicle for movement. In one embodiment, the traction system 102 may include an engine 118, an energy source 119, a transmission 120, and wheels / tires 121. The engine 118 may be an internal combustion engine, an electric motor, an air compression engine, or a combination of other types of engines, such as a hybrid engine including a gasoline engine and an electric motor, or a hybrid engine including an internal combustion engine and an air compression engine. The engine 118 converts the energy source 119 into mechanical energy.

[0078] Examples of energy source 119 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other power sources. Energy source 119 may also provide energy to other systems of the vehicle.

[0079] The transmission 120 may transmit mechanical power from the engine 118 to the wheels 121. The transmission 120 may include a gearbox, a differential, and a drive shaft. In one embodiment, the transmission 120 may further include other components, such as a clutch. The drive shaft may include one or more shafts that may be coupled to one or more wheels 121.

[0080] The sensor system 104 may include a number of sensors capable of sensing information about the vehicle's surrounding environment. For example, the sensor system 104 may include a positioning system 122 (which may be a GPS system, a BeiDou system, or other positioning system), an inertial measurement unit (IMU) 124, a radar 126, a laser range finder 128, and a camera 130. The sensor system 104 may further include sensors of the vehicle's internal systems (e.g., an on-board air quality monitor, a fuel gauge, or an engine oil temperature gauge). Sensor data from one or more of these sensors may be used to detect objects and corresponding characteristics of the objects (such as position, shape, orientation, and speed).

[0081] The positioning system 122 may be configured to estimate the geographic position of the vehicle. The IMU 124 is configured to sense changes in the position and orientation of the vehicle based on inertial acceleration. In one embodiment, the IMU 124 may be a combination of an accelerometer and a gyroscope.

[0082] The radar 126 may sense objects in the vehicle's environment via radio signals. In some embodiments, in addition to sensing objects, the radar 126 may be further configured to sense the speed and / or direction of movement of the objects.

[0083] The laser range finder 128 may use a laser to sense objects in the environment the vehicle is in. In some embodiments, the laser range finder 128 may include one or more laser sources, a laser scanner, one or more detectors, and other system components.

[0084] The camera 130 may be configured to capture multiple images of the vehicle's surrounding environment. The camera 130 may be a still camera or a video camera.

[0085] The control system 106 is an operating system that controls the vehicle and its components. The control system 106 may include a steering system 132, a throttle 134, a braking unit 136, a computer vision system 138, a route control system 140, and an obstacle avoidance system 142.

[0086] The steering system 132 may be manipulated to adjust the direction of travel of the vehicle. For example, in one embodiment, the steering system 132 may be a steering wheel system.

[0087] The throttle 134 is configured to control the operating speed of the engine 118, which in turn controls the speed of the vehicle.

[0088] The brake unit 136 is configured to control the deceleration of the vehicle. The brake unit 136 can use friction to decelerate the wheels 121. In another embodiment, the brake unit 136 can convert the kinetic energy of the wheels 121 into an electric current. Alternatively, the brake unit 136 can reduce the rotational speed of the wheels 121 in other ways to control the speed of the vehicle.

[0089] The computer vision system 138 may operate to process and analyze images captured by the camera 130 and recognize objects and / or features in the vehicle's environment. The objects and / or features may include traffic signals, road boundaries, and obstacles. The computer vision system 138 may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, the computer vision system 138 may be configured to draw a map of the environment, track objects, estimate the speed of objects, etc.

[0090] The route control system 140 is configured to determine a route for the vehicle to travel. In some embodiments, the route control system 140 may combine data from the sensors 104 with one or more predefined maps to determine a route for the vehicle to travel.

[0091] The obstacle avoidance system 142 is otherwise configured to identify, evaluate, and avoid or circumvent potential obstacles within the vehicle's environment.

[0092] Indeed, in one example, the control system 106 can include additional or alternative components in addition to those shown and described, or the control system 106 can omit some of the components shown above.

[0093] The vehicle interacts with external sensors, other vehicles, other computer systems, or a user via the peripherals 108. The peripherals 108 may include a wireless communication system 146, an on-board computer 148, a microphone 150, and / or a speaker 152.

[0094] In some embodiments, the peripherals 108 provide a means for a user of the vehicle to interact with the user interface 116. For example, the on-board computer 148 can provide information to the user of the vehicle 100. The interface 116 can further operate the on-board computer 148 to receive input from the user. The on-board computer 148 can be operated using a touch panel. In other cases, the peripherals 108 can provide a means for the vehicle to communicate with another device located within the vehicle. For example, the microphone 150 can receive audio (e.g., voice commands or other audio input) from the user of the vehicle. Similarly, the speaker 152 can output audio to the user of the vehicle.

[0095] The wireless communication system 146 can communicate with one or more devices directly or wirelessly through a communication network. For example, the wireless communication system 146 can communicate over a 3G cellular network such as code division multiple access (CDMA), EVDO, or GSM / GPRS, over a 4G cellular network such as LTE, or over a 5G cellular network. The wireless communication system 146 can communicate with a wireless local area network (WLAN) using Wi-Fi. In some embodiments, the wireless communication system 146 can communicate directly with devices using an infrared link, Bluetooth, or ZigBee. Various vehicle communication systems, such as other wireless protocols, such as the wireless communication system 146, can include one or more dedicated short range communication (DSRC) devices, which can include public and / or private data communications between the vehicles and / or roadside stations.

[0096] The power source 110 can provide power to various components of the vehicle. In one embodiment, the power source 110 can be a rechargeable lithium-ion or lead-acid battery. One or more battery packs of such batteries can be configured as a power source to provide power to various components of the vehicle. In some embodiments, the power source 110 and the energy source 119 can be implemented together, for example, in some pure electric vehicles.

[0097] Some or all of the vehicle's functions are controlled by a computer system 112. The computer system 112 may include at least one processor 113 that executes instructions 115 stored in a non-transitory computer-readable medium, such as a memory 114. Alternatively, the computer system 112 may be multiple computing devices that control individual components or subsystems of the vehicle in a distributed manner.

[0098] The processor 113 may be any conventional processor, such as a commercially available CPU. Alternatively, the processor may be a dedicated device, such as an ASIC or another hardware-based processor. While FIG. 8 illustrates the processor and memory functionally, one skilled in the art should understand that a processor or memory may actually include multiple processors or memories, which may or may not be stored in the same physical housing. For example, the memory may be a hard disk drive or another storage medium located in different physical housings. Thus, reference to a processor is understood to include reference to a set of processors or memories that may or may not operate in parallel. Unlike using a single processor to perform the steps described herein, some components, such as the steering and deceleration components, may each include a respective processor that performs only calculations related to the component's specific function.

[0099] In various aspects described herein, the processor may be located remotely from the vehicle and communicate wirelessly with the vehicle, In other aspects, some processes described herein are performed on a processor located within the vehicle, while other processes are performed by a remote processor, including performing steps necessary for a single operation.

[0100] In some embodiments, memory 114 may include instructions 115 (e.g., program logic) that may be executed by processor 113 to perform various functions of the vehicle, including the functions described above. Memory 114 may further include additional instructions, including instructions for transmitting data to, receiving data from, interacting with, and / or controlling one or more of driving system 102, sensor system 104, control system 106, and peripherals 108.

[0101] In addition to instructions 115, memory 114 may further store data, such as road maps, route information, position, direction, speed, and other vehicle data for the vehicle, and other information. Such information may be used by vehicle and computer system 112 when the vehicle is operating in autonomous, semi-autonomous, and / or manual modes.

[0102] The user interface 116 is used to provide information to or receive information from a user of the vehicle. Optionally, the user interface 116 may include one or more input / output devices in the set of peripherals 108, such as, for example, a wireless communication system 146, an on-board computer 148, a microphone 150, and a speaker 152.

[0103] The computer system 112 may control functions of the vehicle based on inputs received from various subsystems (e.g., the driving system 102, the sensor system 104, and the control system 106) and from the user interface 116. For example, the computer system 112 may access and use inputs from the control system 106 to control the steering unit 132 to avoid obstacles detected by the sensor system 104 and the obstacle avoidance system 144. In some embodiments, the computer system 112 may be operated to provide control over many aspects of the vehicle 100 and its subsystems.

[0104] Optionally, one or more of the aforementioned components may be located separate from or in association with the vehicle. For example, the memory 114 may exist partially or completely separate from the vehicle. The aforementioned components may be communicatively coupled to each other in a wired and / or wireless manner.

[0105] Optionally, the above components are merely examples. In practical applications, the components of the above modules can be added or removed based on practical requirements. Figure 8 should not be understood as a limitation to this embodiment of the present application.

[0106] An autonomous vehicle traveling on a road, such as a car, may recognize objects in the vehicle's surrounding environment and decide to adjust its current speed. The objects may be other vehicles, traffic control devices, or other types of other objects. In some examples, each recognized object may be considered independently and used to determine the speed to be adjusted by the autonomous vehicle based on characteristics of each object, such as the object's current speed, the object's acceleration, and the distance between the object and the vehicle.

[0107] Optionally, the vehicle or a computing device associated with the vehicle (such as the computer system 112, computer vision system 138, and processor 113 in FIG. 8) can predict the behavior of the recognized object based on the characteristics of the recognized object and the state of the surrounding environment (e.g., traffic volume, rain, icy road). Optionally, the recognized objects can be considered together to predict the behavior of a single recognized object, since each of the recognized objects depends on the behavior of the others. The vehicle can adjust the speed of the vehicle based on the predicted behavior of the recognized objects. In other words, the vehicle can determine the stable state (e.g., accelerate, decelerate, or stop) to which the vehicle needs to be adjusted based on the predicted behavior of the objects. In this process, the speed of the vehicle can also be determined taking into account other factors, such as the horizontal position of other vehicles on the road on which they travel, the curvature of the road, or the proximity between static and dynamic objects.

[0108] Optionally, the vehicle shown in Figure 8 may be a car, truck, motorcycle, bus, or amusement ride, etc., capable of traveling on public roads and highways with or without a driver, which is not particularly limited in this embodiment of the present application.

[0109] In an exemplary embodiment, the vehicle motion state recognition method provided in this embodiment of the present application may be applied to the vehicle shown in FIG. 8, for example, the method may be executed by a processor in the vehicle or may be executed by a computer system. Alternatively, in another exemplary embodiment, the vehicle motion state recognition method provided in this embodiment of the present application may also be applied to a server, for example, a cloud server, communicatively connected to the vehicle shown in FIG. 8. The server can remotely control the vehicle to perform autonomous driving. The application of the vehicle motion state recognition method is not limited in this application.

[0110] Similarly, for example, the own vehicle is the first vehicle, and the other vehicle is the second vehicle. Fig. 9 is a schematic flowchart of a vehicle motion state recognition method according to an embodiment of the present application.

[0111] As shown in FIG. 9, in this method, first, S901 to S903 are executed to obtain the first lane information, the second lane information, and the position information and movement information of the second vehicle.

[0112] S901: Obtain lane information of a lane in which a first vehicle is located, and use the information as first lane information.

[0113] The lane information of the lane in which the first vehicle is located is trajectory information of the lane center axis of the lane in which the first vehicle is located. For example, the first vehicle is vehicle 1 shown in Fig. 1. The lane information of the lane in which vehicle 1 is located is the trajectory of the lane center axis of lane 1 (shown by a dashed line in Fig. 1).

[0114] Next, the process of acquiring the first lane information will be described.

[0115] The first lane information can be expressed using the following curve equation: y ego,t (x)=a 3,t x 3 +a 2,t x 2 +a 1,t x+a 0,t Note that ego refers to the vehicle itself.

[0116] In this formula, a 3,t represents 1 / 6 of the curvature change rate of the trajectory of the lane center axis at time t in the first lane information. 2,t represents 1 / 2 of the curvature of the trajectory of the lane center axis of the first lane information at time t. 1,t represents the tangent gradient of the trajectory of the lane center axis at time t in the first lane information. 0,t represents the horizontal offset of the trajectory of the lane center axis at time t in the first lane information.

[0117] The trajectory of the lane center axis of the lane in which the first vehicle is located is fitted according to the above-mentioned curve equation to obtain lane information of the lane in which the first vehicle is located, i.e., first lane information.

[0118] S902: Obtain at least two types of lane information of a lane in which a second vehicle is located, lane information of a first adjacent lane of the lane in which the second vehicle is located, and lane information of a second adjacent lane of the lane in which the second vehicle is located, and use the information as second lane information.

[0119] For example, in one embodiment, the second lane information may include lane information of the lane in which the second vehicle is located and lane information of a first adjacent lane in which the second vehicle is located. In another embodiment, the second lane information may include lane information of the lane in which the second vehicle is located and lane information of a second adjacent lane in which the second vehicle is located. In yet another embodiment, the second lane information may include lane information of a first adjacent lane of the lane in which the second vehicle is located and lane information of a second adjacent lane of the lane in which the second vehicle is located. Alternatively, the second lane information may include all three types of lane information: lane information of the lane in which the second vehicle is located, lane information of a first adjacent lane of the lane in which the second vehicle is located, and lane information of a second adjacent lane of the lane in which the second vehicle is located.

[0120] The lane information of the lane in which the second vehicle is located is trajectory information of the lane center axis of the lane in which the second vehicle is located, the lane information of a first adjacent lane of the lane in which the second vehicle is located is trajectory information of the lane center axis of the first adjacent lane of the lane in which the second vehicle is located, and the lane information of a second adjacent lane of the lane in which the second vehicle is located is trajectory information of the lane center axis of the second adjacent lane of the lane in which the second vehicle is located.

[0121] 1, for example, the second vehicle is vehicle 4. The first adjacent lane of the lane (lane 1) in which vehicle 4 is located is lane 2, and the second adjacent lane is lane 3, or the first adjacent lane is lane 3 and the second adjacent lane is lane 2. In other words, the first adjacent lane and the second adjacent lane are the adjacent lanes on the left and right sides of the lane in which vehicle 4 is located. The lane information of lane 1, lane 2, and lane 3 are the trajectories of lane center axes corresponding to lane 1, lane 2, and lane 3, respectively.

[0122] The process of obtaining the second lane information is described below.

[0123] The second lane information can be expressed using the following curve equation: y i,t (x)=b i 3,t x 3 +b i 2,t x 2 +b i 1,t x+b i 0,t , i=0,1,2

[0124] When i=0, y i,t (x) is y 0,t (x), which represents the lane information of the lane in which the second vehicle is located. When i=1, y i,t (x) is y 1,t (x), which represents the lane information of the first adjacent lane of the lane in which the second vehicle is located. When i=2, y i,t (x) is y 2,t (x), which represents the lane information of the second adjacent lane of the lane in which the second vehicle is located; i 3,t represents 1 / 6 of the curvature change rate of the lane center axis at time t in the lane information corresponding to i. i 2,t represents half the curvature of the trajectory of the lane center axis at time t in the lane information corresponding to i. i 1,trepresents the tangent gradient of the trajectory of the lane center axis at time t in the lane information corresponding to i. i 0,t represents the horizontal offset of the trajectory of the lane center axis at time t in the lane information corresponding to i.

[0125] When the first adjacent lane (e.g., the left lane) does not exist in the lane in which the second vehicle is located, in the curve equation of the second lane information, when i=1, b i 3,t , b i 2,t , b i 1,t , and b i 0,t The corresponding parameter coefficients are all 255, or when the second adjacent lane (e.g., the right lane) does not exist in the lane where the second vehicle is located, in the curve equation of the second lane information, when i=2, b i 3,t , b i 2,t , b i 1,t , and b i 0,t The corresponding parameter coefficients of all are 255.

[0126] The trajectory of the lane center axis of the lane in which the second vehicle is located, the trajectory of the lane center axis of a first adjacent lane to the lane in which the second vehicle is located, and the trajectory of the lane center axis of a second adjacent lane to the lane in which the second vehicle is located are fitted according to a curve equation to obtain corresponding lane information of the lane in which the second vehicle is located, lane information of the first adjacent lane to the lane in which the second vehicle is located, and lane information of the second adjacent lane to the lane in which the second vehicle is located.

[0127] S903: Obtain location information and movement information of a second vehicle.

[0128] Optionally, the sensor system (e.g., radar or distance sensor) and the positioning system (e.g., GPS or BeiDou) of the first vehicle can collect the position information and movement information of the second vehicle based on a fixed cycle, and upload the position information and movement information of the second vehicle relative to the first vehicle. The position information of the second vehicle refers to the position information (x t ,y t ,θ t ) (x t represents the horizontal coordinate of the second vehicle, and y t represents the longitudinal coordinate of the second vehicle, and θ t represents the travel angle of the second vehicle). The position information of the second vehicle may be the relative position of the second vehicle with respect to the first vehicle, or may be the absolute position of the second vehicle. The motion information of the second vehicle may be the speed v of the second vehicle at time t of each cycle. x,t , acceleration a x,t , trajectory curvature γ t This refers to movement information such as:

[0129] It should be noted that the execution order of S901, S902, and S903 is not limited in the present application, and S901, S902, and S903 may be performed simultaneously, or any of S901, S902, and S903 may be performed first or later.

[0130] After the first lane information, the second lane information, and the position information and movement information of the second vehicle are obtained through the aforementioned S901-S903, the movement state of the second vehicle relative to the first vehicle can be determined as follows: S904-S907.

[0131] S904: Based on the second lane information and the position information and movement information of the second vehicle, determine at least two predicted driving trajectories of the second vehicle, each predicted driving trajectory corresponding to each type of lane information included in the second lane information.

[0132] For example, when the second lane information includes lane information of the lane in which the second vehicle is located and lane information of a first adjacent lane of the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle will maintain traveling in the lane in which the second vehicle is currently located and a predicted driving trajectory in which the second vehicle will change lanes to the first adjacent lane of the lane in which the second vehicle is located can be determined in correspondence with each other.

[0133] Alternatively, when the second lane information includes lane information of the lane in which the second vehicle is located and lane information of a second adjacent lane to the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle will maintain traveling in the lane in which the second vehicle is currently located and a predicted driving trajectory in which the second vehicle will change lanes to the second adjacent lane to the lane in which the second vehicle is located can be determined in correspondence with each other.

[0134] Alternatively, when the second lane information includes lane information of a first adjacent lane of the lane in which the second vehicle is located and lane information of a second adjacent lane of the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle changes lanes to the first adjacent lane of the lane in which the second vehicle is located and a predicted driving trajectory in which the second vehicle changes lanes to the second adjacent lane of the lane in which the second vehicle is located can be determined in correspondence with each other.

[0135] Alternatively, when the second lane information includes all three of lane information of the lane in which the second vehicle is located, lane information of a first adjacent lane of the lane in which the second vehicle is located, and lane information of a second adjacent lane of the lane in which the second vehicle is located, a predicted driving trajectory in which the second vehicle will maintain traveling in the lane in which the second vehicle is currently located, a predicted driving trajectory in which the second vehicle will change lanes to the first adjacent lane of the lane in which the second vehicle is located, and a predicted driving trajectory in which the second vehicle will change lanes to the second adjacent lane of the lane in which the second vehicle is located can be determined in correspondence with each other.

[0136] Below, a specific method for determining a predicted driving trajectory will be described using as an example a case in which the second lane information includes all three types of lane information: lane information of the lane in which the second vehicle is located, lane information of a first adjacent lane to the lane in which the second vehicle is located, and lane information of a second adjacent lane to the lane in which the second vehicle is located.

[0137] (1) Regarding a predicted driving trajectory that keeps the second vehicle traveling in the lane in which the second vehicle is currently located Assume that polynomial fitting can be used to plan a path for the second vehicle to adjust its steering and speed from its current position to return to near the lane center axis of the lane in which the second vehicle is located, while keeping the second vehicle traveling within the lane in which it is currently located.

[0138] For example, based on six conditions such as the current position of the second vehicle, the travel angle, the route curvature, the horizontal position, the linear compatibility satisfied by the lane center axis of the second vehicle returning to the lane in which the second vehicle is located, and the quadratic compatibility, the following equation (which may also be called a polynomial fitting model) can be obtained by performing quadratic polynomial fitting, which can represent a predicted driving trajectory that keeps the second vehicle driving within the lane in which the second vehicle is currently located. z 0,t (x)=c 0 4,t x 4 +c 0 3,t x 3 +c 0 2,t x 2 +c 0 1,t x+c 0 0,t

[0139] The polynomial satisfies the following conditions:

number

[0140] In the above formula, c 0 4,t , c 03,t , c 0 2,t , c 0 1,t , and c 0 0,t The five parameters above can be obtained by applying the compatibility conditions described above, and no special meaning is given to them here.

[0141] (2) Regarding a predicted driving trajectory in which the second vehicle changes lanes to the first adjacent lane or the second adjacent lane of the lane in which the second vehicle is located For example, the first adjacent lane is the left lane of the lane in which the second vehicle is located, and the second adjacent lane is the right lane of the lane in which the second vehicle is located, and when the second vehicle changes lanes from its current position to the left lane or the right lane, the following equation (or, what may be referred to as a polynomial fitting model) can be obtained by performing second-order polynomial fitting based on the lane information, kinematic information, and road information of the destination lane representing the predicted driving trajectory of the second vehicle changing lanes to the first adjacent lane or the second adjacent lane of the lane in which the second vehicle is located. z 1,t (x)=c i 4,t x 4 +c i 3,t x 3 +c i 2,t x 2 +c i 1,t x+c i 0,t , i=1,2

[0142] In this formula, i=1 indicates that the second vehicle changes lanes to the left lane, and i=2 indicates that the second vehicle changes lanes to the right lane.

[0143] The polynomial satisfies the following conditions:

number

[0144] In the above formula, ci 4,t , c i 3,t , c i 2,t , c i 1,t , and c i 0,t These five parameters can be obtained by applying the compatibility conditions described above, and no special meaning is given to them here.

[0145] Alternatively, in some embodiments, the polynomial fitting method described above may not be used, and another fitting function such as a Bessel function may be used, or extraction may be performed based on a driving database to obtain a second predicted driving trajectory in which the second vehicle maintains driving in the lane in which the second vehicle is currently located, and a predicted driving trajectory in which the second vehicle changes lanes to the first adjacent lane or the second adjacent lane of the lane in which the second vehicle is located, which is not limited in the present application.

[0146] After executing S904 to obtain at least two predicted driving trajectories, S905 and S906 can be first executed to determine a target predicted driving trajectory of the second vehicle based on the obtained at least two predicted driving trajectories, and then S907 can be executed to determine the movement state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory of the second vehicle and the first lane information.

[0147] S905: Determine a similarity between each projected driving trajectory and the historical driving trajectory of the second vehicle.

[0148] In some embodiments, a first horizontal coordinate vector of a historical driving trajectory of the second vehicle during a first preset time period can be obtained, the first horizontal coordinate vector being a function of a horizontal coordinate of the historical driving trajectory and a lane in which the second vehicle is located. center Next, for each of the at least two predicted driving trajectories, a second horizontal coordinate vector of the predicted driving trajectory during a second preset period is obtained, and the second horizontal coordinate vector is used to indicate a distance vector between each predicted driving trajectory and a lane of a lane in which the second vehicle is located. center The line is used to indicate a distance vector between the line and the historical driving trajectory, and a similarity between the predicted driving trajectory and the historical driving trajectory is determined based on the second horizontal coordinate vector and the first horizontal coordinate vector. In this manner, a similarity between each predicted driving trajectory of the second vehicle and the historical driving trajectory is obtained.

[0149] The first horizontal coordinate vector of the historical driving trajectory of the second vehicle during the first preset time period includes a plurality of first horizontal coordinates of the historical driving trajectory of the second vehicle during the first preset time period. The second horizontal coordinate vector of each predicted driving trajectory during the second preset time period includes a plurality of second horizontal coordinates of the predicted driving trajectory during the second preset time period.

[0150] In some implementations, the first preset period may be a period including a plurality of consecutive first preset cycles, each of which may include at least one first horizontal coordinate, and the second preset period may be a period including a plurality of consecutive second preset cycles, each of which may include at least one second horizontal coordinate.

[0151] For example, since the driver's keeping in a lane or changing lanes is a continuous process (the second vehicle is assumed to be the vehicle driven by the driver), the driver will make corresponding adjustments before obvious features appear in the corresponding scenario. In consideration of this, in the present application, a first horizontal coordinate time series (i.e., the above-mentioned first horizontal coordinate vector) including a plurality of first horizontal coordinates of the historical driving trajectory of the second vehicle in a first preset period and a second horizontal coordinate time series (i.e., the above-mentioned second horizontal coordinate vector) including a plurality of second horizontal coordinates of each predicted driving trajectory in a second preset period can be first determined. Then, the similarity between the first horizontal coordinate time series and the second horizontal coordinate time series can be calculated to obtain the similarity between the historical driving trajectory and the predicted driving trajectory of the second vehicle.

[0152] For example, the current time is t, the first preset period is an M+t-MΔT first preset cycle, such as (t-MΔT, t-(M-1)ΔT, ···, t), and the second preset period is an N+1 second preset cycle, such as (M+N, M+N-1, ···, M).

[0153] A first horizontal coordinate time series including a first horizontal coordinate of the historical driving trajectory during a first preset period is represented by Y t,h It can be expressed as: Y t,h =(y t-MΔT ,y t-(M-1)ΔT ,···,y t )

[0154] In this equation, Y t,h represents the time series of the first horizontal coordinate, and y t-MΔT represents the first horizontal coordinate at time t-MΔT, and the rest can be deduced by analogy.

[0155] In an exemplary embodiment, M may be 20, N may be 10, and ΔT is the sampling period, which may be an integer multiple of 0.02 s.

[0156] A second horizontal coordinate time series including second horizontal coordinates of the predicted driving trajectory during a second preset period is represented by Y i t,p It can be expressed as: Y i t,p =(z i N (t-MΔT),z i N (t-(M-1)ΔT), ,z i N (t)), i=0,1,2 z i N (t-MΔT)=z i,t-(M+N-j) (x t-(M-j)ΔT ), j=0,1,2,M

[0157] In the two equations, i=0 represents staying in the lane, i=1 represents changing to the left lane, and i=2 represents changing to the right lane. Y i t,p represents the second horizontal coordinate time series. z i N (t-MΔT) is the predicted longitudinal position of the second vehicle at a certain time t-(M-1)ΔT. t-(M-j)ΔT If so, then the horizontal position of the second vehicle is represented as:

[0158] Also, the first horizontal coordinate time series Y t,h and the second horizontal coordinate series Y i t,p The similarity between (i=0,1,2) is

number

number

[0159] In this formula, i=0 represents staying in the lane, i=1 represents changing to the left lane, and i=2 represents changing to the right lane.

number

number

number

[0160] a j a is the inverse of the time difference between each jth period corresponding to j After performing normalization on the initial value of a j Note that it is possible to determine the value of . The details will not be described again here.

[0161] In some other embodiments, other mathematical methods, such as cosine similarity, Mahalanobis distance, and Euclidean distance, may be used to determine the similarity between each of the at least two predicted driving trajectories of the second vehicle and the historical driving trajectory, which is not limited herein.

[0162] S906: Determine a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and a similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle.

[0163] In a possible design, determining a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and the similarity between each of the at least two predicted driving trajectories of the second vehicle and the historical driving trajectory determined in S905 may refer to selecting a predicted driving trajectory having the highest similarity to the historical driving trajectory of the second vehicle from the at least two predicted driving trajectories as a target predicted driving trajectory of the second vehicle. Since the selected target predicted driving trajectory has the highest similarity to the historical driving trajectory of the second vehicle, the target predicted driving trajectory is the predicted driving trajectory that is likely to be closest to the future actual driving trajectory of the second vehicle in the at least two predicted driving trajectories.

[0164] In another possible design, after determining the similarity between each of the at least two predicted driving trajectories of the second vehicle and the historical driving trajectory, a similarity between each predicted driving trajectory and an actual driving trajectory of the second vehicle may be first predicted based on the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle. Then, a target predicted driving trajectory of the second vehicle is determined based on the at least two predicted driving trajectories and the similarity between each predicted driving trajectory and the actual driving trajectory of the second vehicle.

[0165] For example, the similarity between each predicted driving trajectory of the second vehicle and the historical driving trajectory can be normalized, and the probability of each predicted driving trajectory can be predicted. The probability can indicate the similarity between each predicted driving trajectory of the second vehicle and the actual driving trajectory. Then, a comprehensive calculation may be performed with reference to the probability of each predicted driving trajectory and the at least two predicted driving trajectories to obtain a target predicted driving trajectory of the second vehicle.

[0166] Next, a process of determining a target predicted driving trajectory using three predicted driving trajectories, such as a predicted driving trajectory in which the second vehicle maintains driving in the lane in which the second vehicle is currently located, a predicted driving trajectory in which the second vehicle changes lanes to the left lane of the lane in which the second vehicle is located, and a predicted driving trajectory in which the second vehicle changes lanes to the right lane of the lane in which the second vehicle is located, will be described. However, it should be noted that in practice, the target predicted driving trajectory may be determined based on any two of the above three predicted driving trajectories. Details will not be described again here.

[0167] The aforementioned similarity

number

number

number

[0168] In this formula, i=0 represents staying in the lane, i=1 represents changing to the left lane, and i=2 represents changing to the right lane.

[0169] Furthermore, the probability that the predicted driving trajectory of the second vehicle will maintain the lane in which the second vehicle is currently located is P 0 t It can be expressed as:

number

[0170] The probability that the second vehicle will change lanes to the left of the lane in which the second vehicle is located is P 1 t It can be expressed as:

number

[0171] The probability that the second vehicle will change lanes to the right of the lane in which the second vehicle is located is P 2 t It can be expressed as:

number

[0172] The above probability P corresponding to the predicted driving trajectory 0 t , P 1 t , P 2 t After calculating the predicted driving trajectory, the target predicted driving trajectory may be calculated comprehensively by referring to the three predicted driving trajectories.

[0173] As described in the previous embodiment, z i,tLet (x) denote the predicted driving trajectory, where i=0 represents staying in the lane, i=1 represents a lane change to the left lane, and i=2 represents a lane change to the right lane. The target predicted driving trajectory is z t It can be expressed as (x).

number

[0174] Optionally, since the lane change to the left lane performed by the second vehicle or the lane change to the right lane performed by the second vehicle does not occur at the same time, in some embodiments of the present application, when the target predicted driving trajectory is determined based on the above three predicted driving trajectories, the minimum value of the probability corresponding to each of the three predicted driving trajectories is corrected to 0, so that the determined target predicted driving trajectory is closer to the actual driving trajectory, thereby improving the accuracy of the subsequent vehicle movement state recognition. For example, when the probability corresponding to the predicted driving trajectory in which the second vehicle changes lanes to the left lane is the smallest, the probability can be corrected to 0. The target predicted driving trajectory is determined based only on the predicted driving trajectory in which the second vehicle changes lanes to the right lane, the predicted driving trajectory in which the second vehicle maintains driving in that lane, and the probabilities corresponding to each of the two predicted driving trajectories.

[0175] In another possible design, after predicting the similarity between each predicted driving trajectory and the actual driving trajectory of the second vehicle based on the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle, the predicted driving trajectory that has the highest similarity to the actual driving trajectory of the second vehicle may be directly selected as the target predicted driving trajectory of the second vehicle.

[0176] For example, after determining the probability of each predicted driving trajectory of the second vehicle separately based on the similarity between each of at least two predicted driving trajectories of the second vehicle and the historical driving trajectory, the predicted driving trajectory with the maximum probability may be directly selected as the target predicted driving trajectory of the second vehicle.

[0177] This design is similar to the first method above, which directly selects the predicted driving trajectory with the highest similarity as the target predicted driving trajectory of the second vehicle, and the determined predicted driving trajectory is the predicted driving trajectory that is likely to be closest to the future actual driving trajectory of the second vehicle among the at least two predicted driving trajectories above.

[0178] It should be noted that the particular method of determining a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and the similarity between each of the at least two predicted driving trajectories of the second vehicle and the historical driving trajectory is not limited by this application.

[0179] S907: Determine a motion state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information.

[0180] As described above, the first lane information is trajectory information of the lane center axis of the lane in which the first vehicle is located. After obtaining the target predicted driving trajectory, the first lane information is referred to to determine the distance (e.g., the minimum horizontal distance or the maximum horizontal distance) between the target predicted driving trajectory and the lane center axis of the lane in which the first vehicle is located, thereby making it possible to determine, for example, whether the second vehicle will cut into the lane in which the first vehicle is located from another lane, or whether the second vehicle will cut into the lane in which the first vehicle is located from the lane in which the first vehicle is located, etc.

[0181] For example, FIG. 10 is another schematic flowchart of a vehicle motion state recognition method according to an embodiment of the present application.

[0182] As shown in FIG. 10, S907 may include S1001 to S1006.

[0183] S1001: Based on the target predicted driving trajectory and the first lane information, a target predicted driving trajectory and a lane in which a first vehicle is located are determined. centerA minimum horizontal distance between the lines and within a preset vertical length, a first vertical position corresponding to the minimum horizontal distance, a maximum horizontal distance, and a second vertical position corresponding to the maximum horizontal distance are determined.

[0184] As mentioned above, the first lane information may be the lane center axis of the lane in which the first vehicle is located.

[0185] For example, the first vehicle is vehicle A, and the second vehicle is vehicle B. Figure 11 is a schematic diagram of vehicle A recognizing the motion state of vehicle B based on the target predicted driving trajectory of vehicle B according to one embodiment of the present application.

[0186] As shown in Fig. 11, if the preset longitudinal length is [a, b], the position of a can be a position close to vehicle B in the direction along the lane central axis or the same position as the longitudinal coordinate of vehicle B. Correspondingly, the position of b is a position away from vehicle B in the direction along the lane central axis. It is understood that the preset longitudinal length [a, b] is only used to limit a certain range in the direction along the lane central axis.

[0187] Target predicted driving trajectory z t (x) and the lane center axis y of the lane in which vehicle A is located within a preset longitudinal length [a, b] ego,t The minimum horizontal distance d between min can be expressed as follows:

number

[0188] Target predicted driving trajectory z t (x) and the lane center axis y of the lane in which vehicle A is located within a preset longitudinal length [a, b] ego,t The maximum horizontal distance d between max can be expressed as follows:

number

[0189] The first vertical position corresponding to the minimum horizontal distance is d min The second longitudinal position is the position of d max This is the location.

[0190] S1002: When the minimum horizontal distance is greater than a first threshold, it is determined that the motion state of the second vehicle relative to the first vehicle maintains traveling in a different lane from the first vehicle.

[0191] Optionally, the value of the first threshold d1 may be half the width of the body of the first vehicle plus 30 centimeters, or may be a value close to half the width of the body of the first vehicle plus 30 centimeters.

[0192] minimum horizontal distance d min If d1 is greater than the first threshold d1, it can be determined that the second vehicle has not entered the lane in which the first vehicle is located, and the movement state of the second vehicle relative to the first vehicle can be considered to be that the second vehicle maintains a lane different from that of the first vehicle, which can be expressed, for example, as follows: objectState()=passby() objectState indicates the state of an object. Passby indicates passing by.

[0193] For example, Fig. 12 is another schematic diagram of a vehicle A recognizing the motion state of the vehicle B based on the target predicted driving trajectory of the vehicle B according to an embodiment of the present application. As shown in Fig. 12, the minimum horizontal distance d between the target predicted driving trajectory of the vehicle B and the lane center axis of the lane where the vehicle A is located is min If is greater than the first threshold d1, the motion state of vehicle B relative to vehicle A is determined to be objectState=passby.

[0194] S1003: Determine that the movement state of the second vehicle relative to the first vehicle is crossing the lane in which the first vehicle is located if the minimum horizontal distance is smaller than a first threshold and the maximum horizontal distance is greater than a second threshold, where the second threshold is greater than the first threshold.

[0195] Optionally, the value of the second threshold d2 may be equal to or close to the width of the lane in which the first vehicle is located plus 30 centimeters. It may be seen that the second threshold d2 is much larger than the first threshold d1.

[0196] minimum horizontal distance d min is smaller than the first threshold d1 and the maximum horizontal distance d max If d1 is greater than the second threshold d2, it is determined that the second vehicle may enter the lane in which the first vehicle is located and the horizontal offset is large, so the movement state of the second vehicle relative to the first vehicle can be considered as crossing the lane in which the first vehicle is located, which can be expressed, for example, as follows: objectState=cross(cross) Cross means to cross.

[0197] For example, Fig. 13 is yet another schematic diagram of a vehicle A recognizing the motion state of the vehicle B based on the target predicted driving trajectory of the vehicle B according to an embodiment of the present application. As shown in Fig. 13, the minimum horizontal distance d between the target predicted driving trajectory of the vehicle B and the lane center axis of the lane where the vehicle A is located is min is smaller than the first threshold d1 and the maximum horizontal distance d max If is greater than the second threshold d2, it is determined that vehicle B may enter the lane in which vehicle A is located and the horizontal offset is large, so the movement state of vehicle B relative to vehicle A can be considered to be crossing the lane in which vehicle A is located, which can be expressed as, for example, objectState=cross.

[0198] S1004: When the maximum horizontal distance is smaller than a third threshold, determine that the movement state of the second vehicle relative to the first vehicle is maintaining traveling in the same lane as the first vehicle, where the third threshold is smaller than the first threshold.

[0199] Optionally, the value of the third threshold d3 may be half the width of the body of the first vehicle minus 30 centimeters, or may be close to half the width of the body of the first vehicle minus 30 centimeters. It may be found that the third threshold d3 is smaller than the first threshold d1.

[0200] maximum horizontal distance d max If is less than the third threshold d3, it can be determined that the movement state of the second vehicle relative to the first vehicle is maintaining traveling in the same lane as the first vehicle, which can be expressed, for example, as follows: objectState=follow(follow) Follow means to follow (pursue).

[0201] Indeed, it will be appreciated that in S1004, the second vehicle may follow the first vehicle, or the first vehicle may follow the second vehicle.

[0202] For example, Fig. 14 is yet another schematic diagram according to an embodiment of the present application in which vehicle A recognizes the motion state of vehicle B based on the target predicted driving trajectory of vehicle B. As shown in Fig. 14, the maximum horizontal distance d between the target predicted driving trajectory of vehicle B and the lane center axis of the lane in which vehicle A is located is max If the minimum horizontal distance d is less than the third threshold d3, the motion state of vehicle B relative to vehicle A is determined to maintain the same lane as vehicle A, which can be expressed as, for example, objectState=follow. min is definitely smaller than the third threshold d3. Details will not be described again.

[0203] S1005: If the minimum horizontal distance is smaller than the first threshold, the maximum horizontal distance is greater than the third threshold and smaller than the second threshold, and the time at which the second longitudinal position appears is earlier than the time at which the first longitudinal position appears in the target predicted driving trajectory, it is determined that the movement state of the second vehicle relative to the first vehicle is intruding into the lane in which the first vehicle is located.

[0204] For example, Fig. 15 is yet another schematic diagram according to an embodiment of the present application in which vehicle A recognizes the motion state of vehicle B based on the target predicted driving trajectory of vehicle B. As shown in Fig. 15, the minimum horizontal distance d between the target predicted driving trajectory of vehicle B and the lane center axis of the lane in which vehicle A is located is min is smaller than the first threshold d1 and the maximum horizontal distance d max is greater than the third threshold d3 and less than the second threshold d2, and the second vertical position x max appears on the target predicted driving trajectory at the first longitudinal position x min appears earlier than the time when the vehicle B is in the lane where the vehicle A is located, the motion state of the vehicle B relative to the vehicle A can be determined to be in the lane where the vehicle A is located, which can be expressed as, for example, objectState=cut in (Cut in). (Cut in indicates cutting in.)

[0205] S1006: If the minimum horizontal distance is smaller than the first threshold, the maximum horizontal distance is greater than the third threshold and smaller than the second threshold, and the time at which the first longitudinal position appears is earlier than the time at which the second longitudinal position appears in the target predicted driving trajectory, it is determined that the movement state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located.

[0206] For example, Fig. 16 is yet another schematic diagram according to an embodiment of the present application in which vehicle A recognizes the motion state of vehicle B based on the target predicted driving trajectory of vehicle B. As shown in Fig. 16, the minimum horizontal distance d between the target predicted driving trajectory of vehicle B and the lane center axis of the lane in which vehicle A is located is min is smaller than the first threshold d1 and the maximum horizontal distance d maxis greater than the third threshold d3 and less than the second threshold d2, and the first vertical position x min appears on the target predicted driving trajectory at the second vertical position x max appears, the motion state of vehicle B relative to vehicle A is exiting the lane in which vehicle A is located, which can be expressed as, for example, objectState=cut out (cut out). (Cut out means exiting.)

[0207] In the above described example of S1002-S1006, the scenarios when the minimum horizontal distance is greater than or less than the threshold are used to distinguish the motion state of the second vehicle relative to the first vehicle, but in actual implementations, it may be necessary to further consider the scenario where the minimum distance is equal to the threshold. For example, in some implementations, the minimum horizontal distance d min is equal to the first threshold d1 and the minimum horizontal distance d min Scenarios in which the minimum horizontal distance d is greater than a first threshold d1 may be grouped together. Alternatively, in some other implementations, min is equal to the first threshold d1 and the minimum horizontal distance d min Scenarios in which d is less than the first threshold d1 can be grouped together. This is not a limitation in the present application. Comparisons with other thresholds are similar and will not be described in detail again.

[0208] In a possible design, when in S1005 it is determined that the movement state of the second vehicle relative to the first vehicle is intervening into the lane in which the first vehicle is located, the method can further refine the movement state of the second vehicle relative to the second vehicle to intervening into the lane in which the first vehicle is located in a first intervening state or intervening into the lane in which the first vehicle is located in a second intervening state based on the longitudinal distance between the first longitudinal position corresponding to the minimum horizontal distance and the end that is related to the preset longitudinal length and is closer to the first vehicle.

[0209] Alternatively, if in S1006 it is determined that the movement state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located, the method can further narrow down the movement state of the second vehicle relative to the first vehicle to exiting the lane in which the first vehicle is located in a first exit state or exiting the lane in which the first vehicle is located in a second exit state based on the longitudinal distance between the first longitudinal position corresponding to the minimum horizontal distance and the end related to the preset longitudinal length and closer to the first vehicle.

[0210] For example, the first interrupt state may be referred to as a closed cut-in state and the first extract state may be referred to as a closed cut-out state. The second interrupt state may be referred to as a normal interrupt state and the second extract state may be referred to as a normal extract state. Alternatively, the first / second interrupt state and the first / second extract state may be referred to by different names.

[0211] Hereinafter, for example, the first cut-in state is referred to as a close cut-in state, the first pull-out state is referred to as a close cut-out state, the second cut-in state is referred to as a normal cut-in state, and the second pull-out state is referred to as a cut-out state. Examples will be given to separately explain a case where the movement state of the second vehicle relative to the first vehicle is further narrowed down to a close cut-in state or a normal cut-in state, and a case where the movement state of the second vehicle relative to the first vehicle is further narrowed down to a close cut-out state or a normal cut-out state.

[0212] FIG. 17 is yet another schematic diagram of vehicle A recognizing the motion state of vehicle B based on a target predicted driving trajectory of vehicle B according to an embodiment of the present application.

[0213] For example, as shown in FIG. 17, the motion state of the second vehicle relative to the first vehicle is determined by the longitudinal distance between the first longitudinal position corresponding to the minimum horizontal distance and the end a of the preset longitudinal length, i.e., the longitudinal distance between the first longitudinal position and the lane of the lane in which the first vehicle is located. centerThe range may be further narrowed down based on the distance between the end a of the preset longitudinal length in the direction parallel to the line. When the movement state of the second vehicle relative to the first vehicle is determined to be cut into the lane in which the first vehicle is located, if the longitudinal distance is smaller than a fourth threshold (i.e., 1 m, 2 m, or 3 m, etc., not limited here), the movement state of the second vehicle relative to the first vehicle is determined to be close cut in the lane in which the first vehicle is located (close_cut_in). When the longitudinal distance is larger than the fourth threshold, the movement state of the second vehicle relative to the first vehicle is determined to be almost cut in the lane in which the first vehicle is located (general_cut_in).

[0214] It is easy to understand that when the longitudinal distance is equal to the fourth threshold, the motion state of the second vehicle relative to the first vehicle can be determined to be closely intervening in the lane in which the first vehicle is located, or nearly intervening in the lane in which the first vehicle is located, which is not limited in this specification.

[0215] Similarly, using an example, the motion state of the second vehicle relative to the first vehicle is determined by the longitudinal distance between the first longitudinal position corresponding to the minimum horizontal distance and the end a of the preset longitudinal length, i.e., the longitudinal distance between the first longitudinal position and the lane of the lane in which the first vehicle is located. centerBased on the distance between the end a of the preset longitudinal length in the direction parallel to the line, the state may be further narrowed down to be close to exiting or nearly exiting. For example, when the motion state of the second vehicle relative to the first vehicle is determined to be exiting the lane in which the first vehicle is located, if the longitudinal distance is smaller than the fourth threshold, the motion state of the second vehicle relative to the first vehicle is determined to be close to exiting the lane in which the first vehicle is located. If the longitudinal distance is greater than the fourth threshold, the motion state of the second vehicle relative to the first vehicle is determined to be nearly exiting the lane in which the first vehicle is located. Similarly, it is easy to understand that the motion state of the second vehicle relative to the first vehicle may be determined to be close to exiting the lane in which the first vehicle is located or nearly exiting the lane in which the first vehicle is located, if the longitudinal distance is equal to the fourth threshold. This is not limited in the present specification.

[0216] In some embodiments, in S904, before the predicted driving trajectory of the second vehicle is determined based on the second lane information, the position information, and the movement information of the second vehicle, the vehicle motion state recognition method may further include a step of correcting the movement information of the second vehicle.

[0217] For example, horizontal velocities for several (e.g., six) past time periods may be collected first, and an average value of the horizontal velocities for the several past time periods is calculated to obtain an average historical horizontal velocity of the second vehicle. The horizontal velocity included in the motion information of the second vehicle is then modified based on the average horizontal lateral velocity of the second vehicle.

[0218] Alternatively, a time-velocity polynomial fitting can be performed on the horizontal speeds in the aforementioned several past periods to obtain fitting coefficients (for the method of polynomial fitting, refer to the method of performing polynomial fitting on the predicted driving trajectory in which the second vehicle keeps driving in the lane or changes the lane in the aforementioned embodiment, and the details will not be described again here). Then, the current horizontal speed of the second vehicle is predicted based on the fitting coefficients to obtain a current predicted horizontal speed. Then, the horizontal speed included in the motion information of the second vehicle can be corrected based on the current predicted horizontal speed.

[0219] For example, the horizontal speed included in the motion information of the second vehicle is modified based on the current predicted horizontal speed (the same as the method of modification based on the average historical horizontal speed of the second vehicle). The collected horizontal speed of the second vehicle may be compared with the above-mentioned current predicted horizontal speed, and if the difference between the collected horizontal speed and the current predicted horizontal speed is greater than the fifth threshold, the collected horizontal speed is modified to reduce disturbances caused by excessively large instantaneous speed of the collected horizontal speed. For example, the horizontal speed may be increased or decreased, or a weighted combination of the collected horizontal speed and the current predicted horizontal speed is performed based on a preset weight to update the collected horizontal speed.

[0220] Optionally, the value of the fifth threshold is related to the driving stability of the second vehicle. The higher the stability of the second vehicle, the lower the fifth threshold, and the lower the driving stability of the second vehicle, the higher the fifth threshold. For example, the fifth threshold may be 0.2 meters per second (m / s), or 0.4 m / s, etc. This is not limited herein.

[0221] Further, in some embodiments, when the similarity between each of the at least two predicted driving trajectories of the second vehicle and the historical driving trajectory is determined in S905, a method is used in which a first horizontal coordinate time series including first historical coordinates of the historical driving trajectory of the second vehicle for a first preset period and a second historical coordinate time series including second transverse coordinates of each predicted driving trajectory for a second preset period are first determined, and then a similarity between the first historical coordinate time series and the second historical coordinate time series is calculated to obtain a similarity between the historical driving trajectory and the predicted driving trajectory of the second vehicle. In this manner, the durations of the first preset period and the second preset period may be further adjusted based on the difference between the collected horizontal speed of the second vehicle and the current predicted horizontal speed.

[0222] For example, if the difference is large, it indicates that the driving intention of the second vehicle is specific. The delay effect of the historical driving trajectory of the second vehicle on the predicted driving trajectory can be reduced by decreasing the duration of the first preset period and the second preset period. Alternatively, if the difference is small, the duration of the first preset period and the second preset period may be increased.

[0223] For the second vehicle, the polynomial fitting prediction result of the past horizontal speed, i.e., the aforementioned current predicted horizontal speed is v, the collected current horizontal speed is v0, and the first preset period is δ m and the second preset period is δ n Assume that (δ m and δ n is a calibration value, e.g., δ m can be 3, and δ n can be 2.5), and δ m and δ n The period can be changed as follows: Δ m =[v-v0]*δ m ;Δ n =[v-v0]*δ n

[0224] Optionally, use the δ m can refer to the quantity of first preset cycles included in the first preset period, and adjusting the duration of the first preset period refers to adjusting the quantity of first preset cycles included in the first preset period.

[0225] Similarly, the aforementioned δ n can refer to the quantity of second preset cycles included in the second preset period, and adjusting the duration of the second preset period refers to adjusting the quantity of second preset cycles included in the second preset period.

[0226] The above mainly describes the solutions provided in the embodiments of the present application from the perspective of a vehicle or a server. It should be understood that, to realize the functions described above, the vehicle or the server may include corresponding hardware structures and / or software modules for performing each function.

[0227] For example, an embodiment of the present application may further provide a vehicle motion state recognition device. Figure 18 is a schematic diagram of the structure of a vehicle motion state recognition device according to an embodiment of the present application. As shown in Figure 18, the vehicle motion state recognition device includes an acquisition module 1801 configured to acquire first lane information, second lane information, and position information and motion information of a second vehicle, where the first lane information is lane information of a lane where the first vehicle is located, and the second lane information includes at least two types of lane information of a lane where the second vehicle is located, lane information of a first adjacent lane of the lane where the second vehicle is located, and lane information of a second adjacent lane of the lane where the second vehicle is located. The system includes: a module 1801; a prediction module 1802 configured to determine at least two predicted driving trajectories of the second vehicle based on second lane information and position information and movement information of the second vehicle, each predicted driving trajectory corresponding to each type of lane information included in the second lane information; and a determination module 1803 configured to determine a movement state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information.

[0228] In a possible design, the determination module 1803 is particularly configured to determine a target predicted driving trajectory of the second vehicle based on at least two predicted driving trajectories and a similarity between at least each predicted driving trajectory of the second vehicle and a historical driving trajectory, and to determine a movement state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information.

[0229] In one possible design, the determining module 1803 obtains a first horizontal coordinate vector of a historical driving trajectory of the second vehicle during a first preset period, the first horizontal coordinate vector being a function of the historical driving trajectory and a lane of a lane in which the second vehicle is located. centerand obtaining a second horizontal coordinate vector of each of the predicted driving trajectories in a second preset period, and determining a similarity between each of the predicted driving trajectories and the historical driving trajectory based on the second horizontal coordinate vector and the first horizontal coordinate vector, wherein the second horizontal coordinate vector is used to indicate a distance vector between each of the predicted driving trajectories and a lane of a lane in which the second vehicle is located. center used to indicate a distance vector between the lines.

[0230] In a possible design, the determination module 1803 is particularly configured to predict a similarity between each predicted driving trajectory and an actual driving trajectory of the second vehicle based on a similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle, and to determine a target predicted driving trajectory of the second vehicle based on the similarity between at least two predicted driving trajectories and each predicted driving trajectory and the actual driving trajectory of the second vehicle.

[0231] In a possible design, the determination module 1803 determines a target predicted driving trajectory and a lane of a lane where the first vehicle is located based on the target predicted driving trajectory and the first lane information. center It is particularly configured to determine a minimum horizontal distance between the line and within a predetermined vertical length, and if the minimum horizontal distance is greater than a first threshold, determine that the movement state of the second vehicle relative to the first vehicle is to maintain traveling in a different lane from the first vehicle.

[0232] In a possible design, the determination module 1803 further determines, based on the target predicted driving trajectory and the first lane information, a lane in which the first vehicle is located within a preset longitudinal length of the target predicted driving trajectory. centerdetermine a maximum horizontal distance between the lane in which the first vehicle is located, and if the minimum horizontal distance is less than a first threshold and the maximum horizontal distance is greater than a second threshold, the second threshold being greater than the first threshold; or determine a movement state of the second vehicle relative to the first vehicle to remain in the same lane as the first vehicle, if the maximum horizontal distance is less than a third threshold, the third threshold being less than the first threshold; or determine a movement state of the second vehicle relative to the first vehicle to be cutting into or exiting the lane in which the first vehicle is located, if the minimum horizontal distance is less than the first threshold and the maximum horizontal distance is greater than the third threshold and less than the second threshold.

[0233] In a possible design, the determination module 1803 is further configured to: obtain a first longitudinal position corresponding to the minimum horizontal distance and a second longitudinal position corresponding to the maximum horizontal distance; and; determine that the motion state of the second vehicle relative to the first vehicle is entering the lane in which the first vehicle is located if the minimum horizontal distance is smaller than the first threshold, the maximum horizontal distance is greater than the third threshold and smaller than the second threshold, and the time at which the second longitudinal position appears is earlier than the time at which the first longitudinal position appears in the target predicted driving trajectory; or; determine that the motion state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located if the time at which the first longitudinal position appears is earlier than the time at which the second longitudinal position appears in the target predicted driving trajectory.

[0234] In a possible design, the determination module 1803 obtains a longitudinal distance between the first longitudinal position and a first end of a preset longitudinal length, the longitudinal distance being determined by determining a longitudinal distance between the first longitudinal position and a lane of a lane in which the first vehicle is located. centera distance between the first end of the predetermined longitudinal length in a direction parallel to the line, the first end of the predetermined longitudinal length being an end closer to the first vehicle; and, if the longitudinal distance is smaller than a fourth threshold, determining that the movement state of the second vehicle relative to the first vehicle is either cutting into the lane in which the first vehicle is located in a first cutting-in state or exiting from the lane in which the first vehicle is located in a first exit state, or, if the longitudinal distance is greater than the fourth threshold, determining that the movement state of the second vehicle relative to the first vehicle is either cutting into the lane in which the first vehicle is located in a second cutting-in state or exiting from the lane in which the first vehicle is located in a second exit state.

[0235] In a possible design, the second vehicle's motion information includes a horizontal speed of the second vehicle. The prediction module 1802 is further configured to modify the horizontal speed included in the second vehicle's motion information based on an average historical horizontal speed of the second vehicle.

[0236] It should be understood that the division into modules or units in the device is merely a logical division of functions. During actual implementation, all or some of the modules or units may be integrated into one physical entity or physically separated. Furthermore, all modules in the device may be implemented in the form of software called by a processing element, or in the form of hardware. Alternatively, some units may be implemented in the form of software called by a processing element, and some units may be implemented in the form of hardware.

[0237] For example, each unit may be an independently located processing element or may be integrated into a chip of the device for implementation. Alternatively, each unit may be stored in a memory in the form of a program that is called by a processing element of the device to execute the function of the unit. Furthermore, all or part of the units may be integrated or implemented independently. The processing element in this specification may be called a processor and may be an integrated circuit having signal processing capabilities. During implementation, the steps of the aforementioned method or the aforementioned units may be implemented using hardware integrated logic circuits in the processor element or in the form of software that is called by the processing element.

[0238] In one example, any one unit of the aforementioned apparatus may be one or more integrated circuits configured to perform the aforementioned method, such as one or more application-specific integrated circuits (ASICs), one or more microprocessors (digital signal processors (DSPs), one or more field programmable gate arrays (FPGAs), or a combination of at least two of these types of integrated circuits.

[0239] In another example, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or another processor capable of calling a program, where the unit in the device may be implemented in a form that schedules a program by the processing element. As yet another example, the unit may be integrated and implemented in the form of a system-on-a-chip (SOC).

[0240] For example, an embodiment of the present application further provides a vehicle motion state recognition device, the device including: an interface circuit configured to receive data transmitted by another device; and a processor connected to the interface circuit and configured to perform the steps of the aforementioned method. The processor may include one or more processors.

[0241] In one embodiment, the modules separately performing corresponding steps in the above-mentioned method can be implemented in the form of scheduling a program by a processing element. For example, a vehicle motion state recognition device can include a processing element and a storage element, and the processing element calls the program stored in the storage element to execute the method described in the above-mentioned method embodiment. The storage element may be a storage element disposed on the same chip as the processing element, i.e., an on-chip storage element.

[0242] In another embodiment, the programs for implementing the above-mentioned methods may be in a storage element on a different chip than the processing element, i.e., an off-chip storage element, in which case the processing element calls or loads the programs from the off-chip storage element to the on-chip storage element to call and execute the methods described in the above-mentioned method embodiments.

[0243] For example, an embodiment of the present application may further provide a vehicle including a processor, the processor being connected to the memory and configured to call a program stored in the memory to perform the method described in the method embodiment above.

[0244] Alternatively, an embodiment of the present application may further provide a server including a processor, the server being capable of remotely communicating with the vehicle, the processor being connected to the memory and configured to call a program stored in the memory to execute the method described in the previous method embodiment.

[0245] Alternatively, an embodiment of the present application may further provide a vehicle driving system, for example an autonomous driving system or a driving assistance system. The vehicle driving system may include a vehicle and a server, or may be independently deployed in the vehicle or the server. The vehicle driving system includes a processor, which is connected to a memory and configured to call a program stored in the memory to execute the method described in the above method embodiment.

[0246] In yet another embodiment, the modules configured to perform the steps of the aforementioned method may be configured as one or more processing elements, which may be located in a terminal. The processing elements here may be integrated circuits, such as one or more ASICs, one or more DSPs, one or more FPGAs, or a combination of these types of integrated circuits, which may be integrated together to form a chip.

[0247] In yet another embodiment, modules configured to perform steps of the aforementioned methods can be integrated together and implemented in the form of a SOC. The SOC chip is configured to perform the corresponding method. At least one processing element and a storage element can be integrated into the chip, and the processing element calls a program stored in the storage element to perform the corresponding method. Alternatively, at least one integrated circuit can be incorporated into the chip to perform the corresponding method. Alternatively, with reference to the aforementioned embodiment, the functions of some units can be realized in the form of a program called by the processing element, and the functions of some units are implemented in the form of an integrated circuit.

[0248] As mentioned above, the processing elements herein may be a general purpose processor, such as a CPU, or may be one or more integrated circuits configured to perform the methods described above, such as one or more AISCs, one or more microprocessors DSPs, one or more FPGAs, or a combination of at least two of the integrated circuits.

[0249] The storage element may be a single memory, or may be a collective term for multiple storage elements.

[0250] Based on the above description of the embodiments, those skilled in the art can clearly understand that the above division into functional modules is merely used as an example for explanation, for the sake of convenience and concise description. During actual application, the above functions can be allocated to different functional modules for implementation based on requirements. That is, the internal structure of the device is divided into different functional modules to realize all or part of the above functions.

[0251] In some embodiments provided in the present application, it should be understood that the disclosed devices and methods can be realized in other ways. For example, the described device embodiments are merely examples. For example, the division into modules or units is merely a logical division of functions, and may be divided differently in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some functions may be ignored or not performed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be implemented through some interfaces. Indirect couplings or communication connections between devices or units may be realized in electrical, mechanical, or other forms.

[0252] The units described as separate parts may or may not be physically separated, and the parts shown as units may be one or more physical units, and may be located in one place or distributed in different places. Some or all of the units may be selected according to actual requirements to achieve the objectives of the solutions of the embodiments.

[0253] Furthermore, the functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0254] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, the integrated unit may be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or in part contributing to the prior art, or all or part of the technical solutions may be implemented in the form of a software product, for example, a program. The software product may be a program product, for example, stored in a computer-readable storage medium, and may include some instructions for enabling an apparatus (which may be a single-chip microcomputer, or a chip, etc.) or a processor to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes any medium capable of storing program code, such as a USB flash drive, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0255] For example, an embodiment of the present application provides a computer-readable storage medium including computer software instructions, which, when executed on a vehicle motion state recognition device or a chip embedded in the vehicle motion state recognition device, enable the vehicle motion state recognition device to perform the method described in the above method embodiment.

[0256] The above description is merely a specific embodiment of the present application, and is not intended to limit the protection scope of the present application. Any modifications or replacements within the technical scope disclosed in the present application shall fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A vehicle motion state recognition method, the vehicle motion state recognition method comprising: acquiring first lane information, second lane information, and position information and movement information of a second vehicle relative to a first vehicle, wherein the first lane information is trajectory information of a center axis of a lane in which the first vehicle is located, and the second lane information includes at least two of trajectory information of a center axis of a lane in which the second vehicle is located, trajectory information of a center axis of a first adjacent lane adjacent to the lane in which the second vehicle is located, and trajectory information of a center axis of a second adjacent lane (i) adjacent to the lane in which the second vehicle is located and (ii) opposite to the first adjacent lane, and the lane in which the first vehicle is located is any one of the lane in which the second vehicle is located, the first adjacent lane, or the second adjacent lane; determining at least two predicted driving trajectories of the second vehicle based on the second lane information, the position information of the second vehicle, and the movement information of the second vehicle relative to the lane in which the second vehicle is located, the first adjacent lane, and the second adjacent lane, each predicted driving trajectory corresponding to each type of lane information included in the second lane information; determining a motion state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information; The step of determining a motion state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information includes: determining a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and a similarity between each predicted driving trajectory of the second vehicle and a historical driving trajectory of the second vehicle in a first preset period in the past, the target predicted driving trajectory being a predicted driving trajectory among the at least two predicted driving trajectories that shows the highest similarity to the historical driving trajectory of the second vehicle; determining the motion state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information; The similarity is [0010] and ρ i t is expressed as follows: [0025] where i=0 indicates that the second vehicle maintains driving within the lane, i=1 indicates that the second vehicle changes lanes to the left lane, and i=2 indicates that the second vehicle changes lanes to the right lane, Yt,h(j) indicates the jth component of Yt,h, Yit,p(j) indicates the jth component of Yit,p, and aj(j=0,...,M) respectively indicate weights of the difference between the predicted driving trajectory and the historical driving trajectory in the jth period from the current time to the past, [0030] Fulfill the conditions of A method for recognizing the motion state of a vehicle.

2. Prior to the step of determining a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and a similarity between each predicted driving trajectory of the second vehicle and a historical driving trajectory, the vehicle motion state recognition method includes: obtaining a first horizontal coordinate vector of the historical driving trajectory of the second vehicle during a first preset time period, the first horizontal coordinate vector being used to indicate a distance vector between the historical driving trajectory and a center axis of the lane in which the second vehicle is located; 2. The vehicle motion state recognition method of claim 1, further comprising: a step of acquiring a second horizontal coordinate vector of each predicted driving trajectory during a second preset period, and determining the similarity between each predicted driving trajectory and the historical driving trajectory based on the second horizontal coordinate vector and the first horizontal coordinate vector, wherein the second horizontal coordinate vector is used to indicate a distance vector between each predicted driving trajectory and the central axis of the lane in which the second vehicle is located.

3. The step of determining a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and a similarity between each predicted driving trajectory of the second vehicle and a historical driving trajectory includes: predicting a similarity between each predicted travel trajectory and an actual travel trajectory of the second vehicle based on a similarity between each predicted travel trajectory and the historical travel trajectory of the second vehicle; and determining the target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and the similarity between each predicted driving trajectory of the second vehicle and the actual driving trajectory.

4. The step of determining the motion state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information includes: determining a minimum horizontal distance between the target predicted driving trajectory and a central axis of the lane in which the first vehicle is located, the minimum horizontal distance being within a preset vertical length, based on the target predicted driving trajectory and the first lane information; 4. The vehicle motion state recognition method according to claim 1, further comprising a step of determining that the motion state of the second vehicle relative to the first vehicle is maintaining traveling in a different lane from the first vehicle when the minimum horizontal distance is greater than a first threshold, the first threshold being greater than half the width of the body of the first vehicle.

5. determining a maximum horizontal distance between the target predicted driving trajectory and the central axis of the lane in which the first vehicle is located within the preset longitudinal length based on the target predicted driving trajectory and the first lane information; and determining that the movement state of the second vehicle relative to the first vehicle is crossing the lane in which the first vehicle is located if the minimum horizontal distance is less than the first threshold and the maximum horizontal distance is greater than a second threshold, the second threshold being greater than the first threshold; or determining that the motion state of the second vehicle relative to the first vehicle is maintaining travel in the same lane as the first vehicle if the maximum horizontal distance is less than a third threshold, the third threshold being less than the first threshold; or 5. The vehicle motion state recognition method of claim 4, further comprising the step of determining that the motion state of the second vehicle relative to the first vehicle is entering the lane in which the first vehicle is located or exiting the lane in which the first vehicle is located when the minimum horizontal distance is smaller than the first threshold and the maximum horizontal distance is greater than the third threshold and smaller than the second threshold.

6. The vehicle motion state recognition method further includes a step of obtaining a first longitudinal position corresponding to the minimum horizontal distance and a second longitudinal position corresponding to the maximum horizontal distance; The step of determining that the movement state of the second vehicle relative to the first vehicle is entering the lane in which the first vehicle is located or exiting the lane in which the first vehicle is located when the minimum horizontal distance is smaller than the first threshold and the maximum horizontal distance is greater than the third threshold and smaller than the second threshold includes: determining that the motion state of the second vehicle relative to the first vehicle is intersecting the lane in which the first vehicle is located if the time at which the second longitudinal position appears is earlier than the time at which the first longitudinal position appears on the target predicted driving trajectory; or 6. The vehicle motion state recognition method of claim 5, further comprising a step of determining that the motion state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located if the time at which the first longitudinal position appears is earlier than the time at which the second longitudinal position appears on the target predicted driving trajectory.

7. The vehicle motion state recognition method includes: obtaining a longitudinal distance between the first longitudinal position and a first end of the preset longitudinal length, the longitudinal distance being a distance in a direction parallel to the central axis of the lane in which the first vehicle is located, between the first longitudinal position and the first end of the preset longitudinal length, the first end of the preset longitudinal length being an end closer to the first vehicle; and if the longitudinal distance is less than a fourth threshold, determining whether the motion state of the second vehicle relative to the first vehicle is cutting into the lane in which the first vehicle is located in a first cutting-in state or cutting out from the lane in which the first vehicle is located in a first exit state, the first cutting-in state being a state in which the second vehicle suddenly cuts in toward the first vehicle and cuts into the lane in which the first vehicle is located, and the first exit state being a state in which the second vehicle suddenly turns the steering wheel toward the first vehicle and exits from the lane in which the first vehicle is located; or 7. The vehicle movement state recognition method of claim 6, further comprising the step of: when the longitudinal distance is greater than the fourth threshold, determining whether the movement state of the second vehicle relative to the first vehicle is either cutting in to the lane in which the first vehicle is located in a second cutting-in state or exiting from the lane in which the first vehicle is located in a second exiting state, wherein the second cutting-in state is a state in which the second vehicle cuts in to the lane in which the first vehicle is located while maintaining a certain vehicle distance from the first vehicle, and the second exiting state is a state in which the second vehicle exits from the lane in which the first vehicle is located while maintaining a certain vehicle distance from the first vehicle.

8. The motion information of the second vehicle includes a horizontal speed of the second vehicle, and prior to the step of determining at least two predicted driving trajectories of the second vehicle based on the second lane information and the position information and the motion information of the second vehicle, the vehicle motion state recognition method includes: The method for recognizing a vehicle motion state according to claim 1 , further comprising the step of modifying the horizontal speed included in the motion information of the second vehicle based on an average historical horizontal speed of the second vehicle.

9. A vehicle motion state recognition device, the vehicle motion state recognition device comprising: an acquisition module configured to acquire first lane information, second lane information, and position information and movement information of a second vehicle relative to a first vehicle, wherein the first lane information is trajectory information of a center axis of a lane in which the first vehicle is located, and the second lane information includes at least two types of trajectory information of a center axis of a lane in which the second vehicle is located, trajectory information of a center axis of a first adjacent lane adjacent to the lane in which the second vehicle is located, and trajectory information of a center axis of a second adjacent lane (i) adjacent to the lane in which the second vehicle is located and (ii) opposite to the first adjacent lane, and the lane in which the first vehicle is located is either the lane in which the second vehicle is located, the first adjacent lane, or the second adjacent lane; a prediction module configured to determine at least two predicted driving trajectories of the second vehicle based on the second lane information, the position information of the second vehicle, and the movement information of the second vehicle relative to the lane in which the second vehicle is located, the first adjacent lane, and the second adjacent lane, each predicted driving trajectory corresponding to a respective type of lane information included in the second lane information; a determination module configured to determine a motion state of the second vehicle relative to the first vehicle based on the at least two predicted driving trajectories and the first lane information; the determination module determines a target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and a similarity between each predicted driving trajectory of the second vehicle and a historical driving trajectory of the second vehicle in a first preset period in the past, the target predicted driving trajectory being a predicted driving trajectory of the at least two predicted driving trajectories that shows a highest similarity to the historical driving trajectory of the second vehicle; and determining the motion state of the second vehicle relative to the first vehicle based on the target predicted driving trajectory and the first lane information; The similarity is [0045] and ρ i t is expressed as follows: [0050] where i=0 indicates that the second vehicle maintains driving within the lane, i=1 indicates that the second vehicle changes lanes to the left lane, and i=2 indicates that the second vehicle changes lanes to the right lane, Yt,h(j) indicates the jth component of Yt,h, Yit,p(j) indicates the jth component of Yit,p, and aj(j=0,...,M) respectively indicate weights of the difference between the predicted driving trajectory and the historical driving trajectory in the jth period from the current time to the past, [006] Fulfill the conditions of Vehicle motion status recognition equipment.

10. The decision module: obtaining a first horizontal coordinate vector of the historical driving trajectory of the second vehicle during a first preset time period, the first horizontal coordinate vector being used to indicate a distance vector between the historical driving trajectory and a center axis of the lane in which the second vehicle is located; and 10. The vehicle motion state recognition device of claim 9, further configured to: obtain a second horizontal coordinate vector of each predicted driving trajectory during a second preset period; and determine a similarity between each predicted driving trajectory and the historical driving trajectory based on the second horizontal coordinate vector and the first horizontal coordinate vector, wherein the second horizontal coordinate vector is used to indicate a distance vector between each predicted driving trajectory and the central axis of the lane in which the second vehicle is located.

11. The decision module: predicting a similarity between each predicted travel trajectory and an actual travel trajectory of the second vehicle based on a similarity between each predicted travel trajectory and the historical travel trajectory of the second vehicle; and 11. The vehicle motion state recognition equipment of claim 9 or 10, configured to determine the target predicted driving trajectory of the second vehicle based on the at least two predicted driving trajectories and the similarity between each predicted driving trajectory of the second vehicle and the actual driving trajectory.

12. The decision module: determining a minimum horizontal distance between the target predicted driving trajectory and a center axis of the lane in which the first vehicle is located, the minimum horizontal distance being within a preset longitudinal length, based on the target predicted driving trajectory and the first lane information; and 12. The vehicle motion state recognition device according to claim 9, configured to determine that the motion state of the second vehicle relative to the first vehicle is maintaining traveling in a different lane from the first vehicle when the minimum horizontal distance is greater than a first threshold, the first threshold being greater than half the width of a body of the first vehicle.

13. The decision module: determining a maximum horizontal distance between the target predicted driving trajectory and the central axis of the lane in which the first vehicle is located within the preset longitudinal length based on the target predicted driving trajectory and the first lane information; and determining that the movement state of the second vehicle relative to the first vehicle is crossing the lane in which the first vehicle is located if the minimum horizontal distance is less than the first threshold and the maximum horizontal distance is greater than a second threshold, the second threshold being greater than the first threshold; or determining that the motion state of the second vehicle relative to the first vehicle is maintaining travel in the same lane as the first vehicle if the maximum horizontal distance is less than a third threshold, the third threshold being less than the first threshold; or 13. The vehicle motion state recognition equipment of claim 12, further configured to: determine, when the minimum horizontal distance is smaller than the first threshold and the maximum horizontal distance is greater than the third threshold and smaller than the second threshold, that the motion state of the second vehicle relative to the first vehicle is entering the lane in which the first vehicle is located or exiting the lane in which the first vehicle is located.

14. The decision module: obtaining a first vertical position corresponding to the minimum horizontal distance and a second vertical position corresponding to the maximum horizontal distance; and determining that the motion state of the second vehicle relative to the first vehicle is intersecting the lane in which the first vehicle is located when the minimum horizontal distance is smaller than the first threshold, the maximum horizontal distance is greater than the third threshold and smaller than the second threshold, and the time at which the second longitudinal position appears is earlier than the time at which the first longitudinal position appears on the target predicted driving trajectory; or 14. The vehicle motion state recognition device of claim 13, further configured to: determine that the motion state of the second vehicle relative to the first vehicle is exiting the lane in which the first vehicle is located if the time at which the first longitudinal position appears is earlier than the time at which the second longitudinal position appears on the target predicted driving trajectory.

15. The decision module: obtaining a longitudinal distance between the first longitudinal position and a first end of the preset longitudinal length, the longitudinal distance being a distance between the first longitudinal position and the first end of the preset longitudinal length in a direction parallel to the central axis of the lane in which the first vehicle is located, the first end of the preset longitudinal length being an end closer to the first vehicle; and determining, when the longitudinal distance is less than a fourth threshold, whether the motion state of the second vehicle relative to the first vehicle is cutting into the lane in which the first vehicle is located in a first cutting-in state or cutting out from the lane in which the first vehicle is located in a first exit state, the first cutting-in state being a state in which the second vehicle suddenly cuts into the lane in which the first vehicle is located relative to the first vehicle, and the first exit state being a state in which the second vehicle suddenly turns the steering wheel relative to the first vehicle to exit from the lane in which the first vehicle is located; or 15. The vehicle motion state recognition device of claim 14, further configured to: determine, when the longitudinal distance is greater than the fourth threshold, whether the motion state of the second vehicle relative to the first vehicle is either cutting in to the lane in which the first vehicle is located in a second cutting in state or exiting from the lane in which the first vehicle is located in a second exiting state, wherein the second cutting in state is a state in which the second vehicle cuts in to the lane in which the first vehicle is located while maintaining a certain distance from the first vehicle, and the second exiting state is a state in which the second vehicle exits from the lane in which the first vehicle is located while maintaining a certain distance from the first vehicle.

16. the motion information of the second vehicle includes a horizontal velocity of the second vehicle; 16. The vehicle motion state recognition device of claim 9, wherein the prediction module is further configured to modify the horizontal speed included in the motion information of the second vehicle based on an average historical horizontal speed of the second vehicle.

17. A vehicle motion state recognition device, the vehicle motion state recognition device comprising: an interface circuit configured to receive data transmitted by another device; a processor coupled to the interface circuit; A memory storing a program in which a code for the vehicle motion state recognition method according to any one of claims 1 to 8 is written, The processor calls the program stored in the memory and executes the vehicle motion state recognition method according to any one of claims 1 to 8. Vehicle motion status recognition equipment.

18. A vehicle, the vehicle comprising: A memory storing a program in which a code for the vehicle motion state recognition method according to any one of claims 1 to 8 is written; a processor coupled to the memory, The processor calls up the program stored in the memory and executes the vehicle motion state recognition method according to any one of claims 1 to 8.

19. A server, the server comprising: A memory storing a program in which a code for the vehicle motion state recognition method according to any one of claims 1 to 8 is written; a processor coupled to the memory, The processor calls up a program stored in the memory and executes the vehicle motion state recognition method according to any one of claims 1 to 8.

20. A vehicle driving system, comprising: A memory storing a program in which a code for the vehicle motion state recognition method according to any one of claims 1 to 8 is written; a processor coupled to the memory, The vehicle driving system, wherein the processor calls up a program stored in the memory and executes the vehicle motion state recognition method according to any one of claims 1 to 8.

21. A computer-readable storage medium containing computer software instructions describing the code of a vehicle motion state recognition method as claimed in any one of claims 1 to 8, wherein when the computer software instructions are executed in a vehicle motion state recognition device or a chip incorporated in the vehicle motion state recognition device, the vehicle motion state recognition device executes the vehicle motion state recognition method as claimed in any one of claims 1 to 8.

Images