Cut-in intent prediction method and apparatus, and probabilistic intent inference model training method and apparatus

Abstract

A cut-in intent prediction method and apparatus, and a probabilistic intent inference model training method and apparatus. The cut-in intent prediction method comprises: acquiring a preset number of consecutive frames of historical detection information of a target vehicle before the current moment, wherein the historical detection information comprises transverse distances and transverse speeds of the target vehicle relative to the present vehicle; inputting the preset number of consecutive frames of historical detection information into a probabilistic intent inference model, and the probabilistic intent inference model calculating, on the basis of discrete probability distribution, a node cut-in probability at each transverse distance and each transverse speed in the preset number of consecutive frames of historical detection information, and using the node cut-in probabilities and node weights to obtain a predicted cut-in probability; and if the predicted cut-in probability is greater than a first preset threshold value, determining that the target vehicle has an intent to cut in.

Description

Cut-in intention prediction method, probabilistic intention reasoning model training method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on December 4, 2023, with application number 2023116511773 and application name “Cut-in intention prediction method, probabilistic intention reasoning model training method and device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present disclosure relates to the field of intelligent driving, and is related to, but not limited to, a method for predicting entry intentions, a method for training a probabilistic intention reasoning model, and a device. Background Art

[0004] With the continuous development of autonomous and assisted driving technologies, vehicle safety on the road has been further guaranteed. However, the current complex roads in cities, with vehicles overtaking each other, constantly performing complex maneuvers such as merging and changing lanes, easily lead to traffic accidents.

[0005] Currently, the target vehicle's intention to cut into the ego vehicle's lane is typically determined by whether it continues to drive along the boundary line of the ego vehicle's lane. However, this method requires the target vehicle to have been driving along the boundary line for a certain period of time before triggering a warning. Furthermore, this method can lead to misjudgments if a vehicle cuts out of the ego vehicle's lane, resulting in low warning accuracy. Therefore, how to more accurately determine whether a vehicle intends to cut into the ego vehicle's lane and issue a warning at the appropriate time has become an urgent problem to be solved. Summary of the Invention

[0006] In order to solve the above technical problems, the present disclosure provides a method for predicting cutting-in intention, a method for training a probabilistic intention reasoning model and a device to more accurately determine whether a vehicle has the intention to cut into its own lane.

[0007] In a first aspect, an embodiment of the present disclosure provides a method for predicting a cut-in intention, comprising:

[0008] Acquire a preset number of consecutive frames of historical detection information of the target vehicle before the current moment, the historical detection information including the lateral distance and lateral speed of the target vehicle relative to the own vehicle;

[0009] Inputting the historical detection information of the continuous preset number of frames into the probabilistic intention reasoning model, the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and using the node cut-in probability and the node weight to obtain the predicted cut-in probability;

[0010] If the predicted cut-in probability is greater than a first preset threshold, it is determined that the target vehicle has a cut-in intention.

[0011] In some embodiments, the probabilistic intention inference model calculates the node penetration probability of each lateral distance and lateral speed in the historical detection information of a preset number of consecutive frames through discrete probability distribution, and uses the node penetration probability and the node weight to obtain the predicted penetration probability, including:

[0012] The node probability layer of the model is calculated through discrete probability distribution to obtain the corresponding node entry probability for each lateral distance and lateral speed in a continuous preset number of frames;

[0013] The weight distribution layer of the model determines the node weight corresponding to each lateral distance and lateral speed according to the sequential position of each lateral distance and lateral speed in a continuous preset number of frames;

[0014] The predicted cut-in probability is calculated by the probability layer of the model based on the node cut-in probability and node weight corresponding to each lateral distance and lateral speed.

[0015] In some embodiments, before obtaining historical detection information of the target vehicle for a preset number of consecutive frames before the current moment, the method further includes:

[0016] Determine the adjacent lanes of the lane where the vehicle is located;

[0017] A vehicle located in the adjacent lane and having a distance to the vehicle less than a preset distance is regarded as a target vehicle.

[0018] In some embodiments, determining an adjacent lane of the lane in which the vehicle is located includes:

[0019] If the adjacent lane does not exist, a virtual lane adjacent to the lane where the vehicle is located is created as the adjacent lane, and the width of the virtual lane is the same as the width of the lane where the vehicle is located.

[0020] In some embodiments, if the predicted cut-in probability is greater than a first preset threshold, determining that the target vehicle has a cut-in intention includes:

[0021] If the predicted cut-in probability is greater than a first preset threshold and the driving state information of the target vehicle meets a preset condition, it is determined that the target vehicle has a cut-in intention.

[0022] In some embodiments, the driving state information of the target vehicle satisfies a preset condition, including:

[0023] The target vehicle is traveling on the boundary line of the lane where the own vehicle is located, the target vehicle is the vehicle closest to the own vehicle, the collision time between the target vehicle and the own vehicle is less than a preset time, and the ratio of the distance between the target vehicle and the own vehicle and / or the speed of the own vehicle is less than a second preset threshold.

[0024] In a second aspect, an embodiment of the present disclosure provides a probabilistic intent inference model training method, including:

[0025] Acquiring training data, the training data comprising a preset number of groups of historical data, the historical data comprising a preset number of consecutive frames of historical detection information of a historical vehicle, and actual results of whether a cut-in behavior occurred corresponding to the preset number of consecutive frames of historical detection information, wherein the preset number of consecutive frames of historical detection information comprises a lateral distance and a lateral speed of the historical vehicle relative to the historical data collection vehicle for the preset number of consecutive frames;

[0026] Inputting the historical detection information of the continuous preset number of frames into the probabilistic intention reasoning model, the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and using the node cut-in probability and the node weight to obtain the predicted cut-in probability;

[0027] By comparing the predicted cut-in probability of historical vehicles with the actual results of whether the cut-in behavior occurred, and adjusting the model parameters according to the comparison results, the probabilistic intention reasoning model to be trained is trained to obtain a trained probabilistic intention reasoning model.

[0028] In a third aspect, an embodiment of the present disclosure provides a device for predicting a cut-in intention, comprising:

[0029] A first acquisition module is configured to acquire a preset number of consecutive frames of historical detection information of the target vehicle before a current moment, wherein the historical detection information includes a lateral distance and a lateral speed of the target vehicle relative to the ego vehicle;

[0030] a prediction module configured to input the historical detection information of the consecutive preset number of frames into a probabilistic intention reasoning model, calculate the node penetration probability of each lateral distance and lateral speed in the historical detection information of the consecutive preset number of frames by the probabilistic intention reasoning model through discrete probability distribution, and obtain a predicted penetration probability using the node penetration probability and the node weight;

[0031] The first determination module is configured to determine that the target vehicle has a cut-in intention if the predicted cut-in probability is greater than a first preset threshold.

[0032] In a fourth aspect, an embodiment of the present disclosure provides a probabilistic intention inference model training device, comprising:

[0033] a second acquisition module configured to acquire training data, the training data comprising a preset number of groups of historical data, the historical data comprising a preset number of consecutive frames of historical detection information of a historical vehicle, and actual results of whether a cut-in behavior occurred corresponding to the preset number of consecutive frames of historical detection information, wherein the preset number of consecutive frames of historical detection information comprises a lateral distance and a lateral speed of the historical vehicle relative to the historical data collection vehicle for the preset number of consecutive frames;

[0034] a training module configured to input the historical detection information of the consecutive preset number of frames into a probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node penetration probability of each lateral distance and lateral speed in the historical detection information of the consecutive preset number of frames through discrete probability distribution, and obtains a predicted penetration probability using the node penetration probability and the node weight;

[0035] The adjustment module is configured to compare the predicted cut-in probability of historical vehicles with the actual results of whether the cut-in behavior occurred, and adjust the model parameters according to the comparison results, thereby completing the training of the probabilistic intention reasoning model to be trained and obtaining a trained probabilistic intention reasoning model.

[0036] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0037] Memory;

[0038] processor; and

[0039] computer programs;

[0040] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect or the second aspect.

[0041] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method described in the first aspect or the second aspect.

[0042] In a seventh aspect, an embodiment of the present disclosure provides a vehicle comprising the device, electronic device or computer-readable storage medium as described above.

[0043] The cutting-in intention prediction method, probabilistic intention reasoning model training method and device provided by the embodiments of the present disclosure utilize historical detection information of a preset number of consecutive frames of the target vehicle to be predicted before the current moment and the probabilistic intention reasoning model to predict the probability of the target vehicle cutting into the own vehicle lane at a future moment, so that the obtained predicted cutting-in probability can be supported by strong data and theory, thereby improving the accuracy of the cutting-in intention prediction method.

[0044] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0046] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] FIG1 is a flow chart of a method for predicting a cut-in intention according to an embodiment of the present disclosure;

[0048] FIG2 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0049] FIG3 is a flow chart of a method for predicting a cut-in intention according to another embodiment of the present disclosure;

[0050] FIG4 is a schematic structural diagram of a device for predicting cutting intention according to an embodiment of the present disclosure;

[0051] FIG5 is a schematic diagram of the structure of a probabilistic intention reasoning model training device provided by an embodiment of the present disclosure;

[0052] FIG6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] In order to be able to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure. All other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of the present disclosure. It should be noted that, in the absence of conflict, the embodiments of the present disclosure and the features therein can be combined with each other.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0055] The embodiments of the present disclosure provide a method for predicting cut-in intention, which is introduced below in conjunction with specific embodiments.

[0056] Figure 1 is a flow chart of the method for predicting a cut-in intention provided by an embodiment of the present disclosure. This method can be applied to the application scenario shown in Figure 2, which includes a vehicle 21 and a target vehicle 22. Vehicle 21 includes an onboard device, specifically a vehicle computer, a smartphone, a PDA, a tablet computer, a laptop, an all-in-one computer, an intelligent driving device, etc. It is understood that the method for predicting a cut-in intention provided by an embodiment of the present disclosure can also be applied in other scenarios.

[0057] The following describes the cut-in intention prediction method shown in FIG1 in conjunction with the application scenario shown in FIG2 . The method includes the following specific steps:

[0058] S101. Acquire historical detection information of a target vehicle for a preset number of consecutive frames before a current moment, wherein the historical detection information includes a lateral distance and a lateral speed of the target vehicle relative to the vehicle.

[0059] A target vehicle refers to any vehicle other than the ego vehicle, particularly one that may be engaging in dangerous driving behavior. Dangerous driving behavior includes the target vehicle cutting into the ego vehicle's lane at close range. Specifically, a target vehicle cutting into the ego vehicle's lane may include the target vehicle overtaking the ego vehicle and then cutting in from the front, or the target vehicle cutting in from behind.

[0060] Historical detection information is information about the target vehicle's driving status acquired by the vehicle's onboard sensors. These sensors include, but are not limited to, laser radar, cameras, and millimeter-wave radar. The specific sensor can be determined based on actual circumstances and is not limited in this disclosure.

[0061] The lateral distance of the target vehicle relative to the own vehicle can be the distance between the target vehicle and the own vehicle in the direction perpendicular to the lane, and the lateral speed of the target vehicle relative to the own vehicle can be the speed of the target vehicle in the direction perpendicular to the lane. Both the lateral distance and the lateral speed of the target vehicle relative to the own vehicle are used to determine whether the target vehicle has the intention to cut in.

[0062] The target vehicle's historical detection information for a preset number of frames prior to the current moment may be a continuous preset number of frames of historical detection information prior to the current moment, or a preset number of frames of historical detection information sampled from multiple frames of historical detection information prior to the current moment. For example, the lateral distance and lateral speed corresponding to each of 40 frames of historical detection information of the target vehicle may be obtained.

[0063] S102: Inputting the historical detection information of the preset consecutive frames into a probabilistic intention inference model to obtain a predicted cut-in probability.

[0064] Optionally, the historical detection information of the continuous preset number of frames is input into the probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node entry probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and uses the node entry probability and node weight to obtain the predicted entry probability.

[0065] Among them, the probabilistic intention reasoning model includes: node probability layer, weight distribution layer and probability layer;

[0066] The node probability layer of the model is calculated through discrete probability distribution to obtain the corresponding node entry probability for each lateral distance and lateral speed in a continuous preset number of frames;

[0067] The weight distribution layer of the model determines the node weight corresponding to each lateral distance and lateral speed according to the sequential position of each lateral distance and lateral speed in a continuous preset number of frames;

[0068] The model's probability layer calculates the predicted cut-in probability based on the node cut-in probability and node weight corresponding to each lateral distance and lateral velocity. It should be noted that before using the probabilistic intent inference model, the probabilistic intent inference model used to obtain the predicted cut-in probability must be pre-trained. The following details the training method for the probabilistic intent inference model.

[0069] First, training data is obtained. The training data includes a preset number of groups of historical data. The historical data includes historical detection information for a preset number of consecutive frames of historical vehicles, and actual results of whether a cut-in behavior occurred corresponding to the preset number of consecutive frames of historical detection information. The preset number of consecutive frames of historical detection information includes the lateral distance and lateral speed of the historical vehicle relative to the historical data collection vehicle for a preset number of consecutive frames. The historical data collection vehicle is the vehicle that collected the historical vehicle's driving status data. The actual results in the training data correspond to whether the historical vehicle cut into the lane of the historical data collection vehicle. In addition, the preset number of frames should remain consistent during the training of the probabilistic intention inference model and the use of the probabilistic intention inference model. Furthermore, the preset number of consecutive frames of historical detection information of the historical vehicle is used as input data for the probabilistic intention inference model, and the predicted cut-in probability of the historical vehicle is used as output data of the probabilistic intention inference model. The predicted cut-in probability of the historical vehicle is compared with the actual results of whether a cut-in behavior occurred, and the model parameters are adjusted based on the comparison results (i.e., the node weights corresponding to each lateral distance and lateral speed are adjusted). This completes the training of the probabilistic intention inference model to be trained, thereby obtaining a trained probabilistic intention inference model.

[0070] Optionally, through discrete probability distribution calculation, the corresponding node cut-in probability is obtained for each lateral distance and lateral speed in the continuous preset frame number, wherein, through discrete probability distribution calculation, the actual cut-in probability corresponding to each lateral distance in all historical data can be counted, and the actual cut-in probability corresponding to each lateral speed in all historical data can also be counted, and then the actual cut-in probability corresponding to each lateral distance and each lateral speed in the continuous preset frame number can be obtained. In addition, each lateral distance and each lateral speed in the continuous preset frame number can be regarded as a node, and the actual cut-in probability obtained is used as the node cut-in probability, so that the node cut-in probability corresponding to each lateral distance and lateral speed in the continuous preset frame number is obtained.

[0071] Optionally, the node weight corresponding to each lateral distance and lateral speed is determined according to the sequential position of each lateral distance and lateral speed in the continuous preset number of frames, wherein, since each frame in the continuous preset number of frames has a corresponding sequential position, the position order can be used to determine the node weight corresponding to the lateral distance and lateral speed, and then the node weight corresponding to each lateral distance and lateral speed in the continuous preset number of frames can be obtained; it should be noted that the node weight is obtained after the probabilistic intention inference model training is completed, and the weight value of the node weight needs to be continuously adjusted during the model training.

[0072] Optionally, the predicted cut-in probability is calculated based on the node cut-in probability and node weight corresponding to each lateral distance and lateral speed, wherein each lateral distance and each lateral speed in a continuous preset number of frames can be regarded as a node, and the sum of the node cut-in probability and the node weight product of all nodes is calculated to obtain the predicted cut-in probability.

[0073] Afterwards, the predicted cut-in probability of the historical detection information can be compared with the actual result of whether the cut-in behavior occurs (the actual cut-in can be recorded as a probability of 1, and the actual cut-in failure can be recorded as a probability of 0). By adjusting the node weight of each node, the average gap between the predicted cut-in probability of each historical detection information and the actual result of whether the cut-in behavior occurs can be narrowed. When the average gap is lower than the end threshold, the training can be ended.

[0074] Taking the historical detection information of 5 consecutive preset frames as an example, which includes 5 lateral distances y0, y1, y2, y3, y4 and 5 lateral velocities v0, v1, v2, v3, v4, the predicted cut-in probability calculation formula is shown in formula (1):

[0075] Where I represents whether the vehicle cuts in, I = 1 if it does, and I = 0 if it does not. V represents the five lateral velocities, namely V0 = v0, V1 = v1, V2 = v2, V3 = v3, and V4 = v4, and Y represents the five lateral distances, namely Y0 = y0, Y1 = y1, Y2 = y2, Y3 = y3, and Y4 = y4. P(I = 1 | V, Y) is the conditional probability of a cut-in when the vehicle's lateral distances are y0, y1, y2, y3, and y4, and its lateral velocities are v0, v1, v2, v3, and v4.

[0076] Among them, P(I=1, V, Y) can be That is, the sum of the product of the node entry probability and the node weight of each node, P(I=1, V, Y)+P(I=0, V, Y) can be the sum of the node entry probability and the node non-entry probability, P(I=0, V, Y) can be That is, in the sum of the product of the node non-cut-in probability and the node weight of each node, the node non-cut-in probability = 1 - the node cut-in probability.

[0077] After obtaining the trained probabilistic intention inference model, the historical detection information of a preset number of consecutive frames before the current moment obtained in the above steps is input into the probabilistic intention inference model to obtain the cut-in probability of the target vehicle. The cut-in probability of the target vehicle represents the probability that the target vehicle will perform a cut-in behavior within a preset time after the corresponding moment of the last frame in the historical detection information.

[0078] It can be understood that the number of frames in the historical detection information is the same as the number of frames during model training, and the continuous relationship between the frames in the historical detection information is also the same as during model training.

[0079] S103: If the predicted cut-in probability is greater than a first preset threshold, it is determined that the target vehicle has a cut-in intention.

[0080] When the predicted cutting-in probability of the target vehicle is greater than the first preset threshold, it is considered that the target vehicle has a greater probability of cutting-in to the lane where the ego vehicle is located, that is, it is determined that the target vehicle has a cutting-in intention.

[0081] Furthermore, when the predicted probability of the target vehicle cutting in is greater than a first preset threshold, whether the target vehicle's cutting-in behavior will affect the safe driving of the own vehicle is judged by whether the target vehicle's driving status information meets the preset conditions. For example, when the distance between the target vehicle and the own vehicle is too close, it is considered that the target vehicle's cutting-in behavior may affect the safe driving of the own vehicle, and the vehicle cutting-in warning is triggered at this time.

[0082] The disclosed embodiment obtains historical detection information of the target vehicle for a preset number of frames before the current moment, wherein the historical detection information includes the lateral distance and lateral speed of the target vehicle relative to the own vehicle; the historical detection information of the preset number of frames is input into a probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information for the preset number of frames through discrete probability distribution, and obtains the predicted cut-in probability using the node cut-in probability and the node weight; if the predicted cut-in probability is greater than a first preset threshold, it is determined that the target vehicle has the intention to cut in, and the historical detection information of the target vehicle to be predicted for a preset number of frames before the current moment and the probabilistic intention reasoning model are used to predict the probability of the target vehicle cutting into the own vehicle lane at a future moment, so that the obtained predicted cut-in probability can be supported by strong data and theory, thereby improving the accuracy of the cut-in intention prediction method.

[0083] In addition, since the embodiment of the present disclosure uses a probabilistic intent reasoning model, it is more interpretable and has a faster calculation speed than a neural network.

[0084] FIG3 is a flow chart of a method for predicting a cut-in intention according to another embodiment of the present disclosure. As shown in FIG3 , the method includes the following steps:

[0085] S301: Determine adjacent lanes to the lane where the vehicle is located.

[0086] Specifically, if the adjacent lane does not exist, a virtual lane adjacent to the lane where the vehicle is located is created, and the width of the virtual lane is the same as that of the lane where the vehicle is located.

[0087] The lane your vehicle is currently traveling in is the lane in which it is currently traveling. Adjacent lanes to your lane include the lane to the left and the lane to the right. Vehicles in adjacent lanes are most likely to cut into your lane.

[0088] In some embodiments, lane lines can be identified through visual recognition to determine the adjacent lanes of the lane where the vehicle is located; alternatively, the adjacent lanes of the lane where the vehicle is located can be determined through high-precision map data. The specific method of determining the adjacent lanes of the lane where the vehicle is located can be determined based on actual conditions, and the embodiments of the present disclosure are not limited to this.

[0089] In some embodiments, the adjacent lane of the ego vehicle's lane may not be identified due to lane line wear or missing map data, in which case a virtual lane is created as the adjacent lane of the ego vehicle's lane based on the width of the ego vehicle's lane.

[0090] S302: A vehicle located in the adjacent lane and having a distance from the vehicle less than a preset distance is taken as a target vehicle.

[0091] Initially screen vehicles in adjacent lanes. If a vehicle in an adjacent lane is far from the ego vehicle, even if it cuts into the ego vehicle's lane, it will not affect the ego vehicle's safe driving. Therefore, there is no need to calculate the predicted cutting-in probability for these vehicles. Only target vehicles that are closer to the ego vehicle are considered.

[0092] Specifically, vehicles located in the adjacent lanes and within a preset distance from the vehicle are considered target vehicles. This includes target vehicles located in the adjacent lanes in front of and behind the vehicle. In some embodiments, different preset distances can be set for the vehicle in front of and behind the vehicle, or the same preset distance can be set, which is not limited in the present embodiment.

[0093] For example, a vehicle located in the adjacent lane and within a range of 50m in front and 15m in rear from the vehicle is regarded as a target vehicle.

[0094] In some embodiments, the position information of the vehicle in the odom coordinate system (ego coordinate system) can be obtained, and the position information in the odom coordinate system can be further converted to the ego coordinate system to determine the distance between the vehicle and the ego vehicle.

[0095] S303 , obtaining the distance between the target vehicle and the center line of the lane where the target vehicle is located in the historical detection information of each frame, and obtaining the lateral distance of the target vehicle in each frame.

[0096] The lateral distance is the distance between the target vehicle and the ego vehicle perpendicular to the lane. For each frame of historical detection information, the distance between the target vehicle and the ego vehicle perpendicular to the lane in that frame of historical detection information is determined as the lateral distance of the target vehicle in that frame of historical detection information. This process continues until the lateral distance of the target vehicle is obtained for each frame of historical detection information.

[0097] S304: Perform differential calculation on the horizontal distances between two adjacent frames to obtain a calculation result.

[0098] S305 : Filter the calculation results to obtain the lateral velocity of the target vehicle in each frame.

[0099] The lateral distance between two adjacent frames is differentially calculated. This difference, along with the frame rate of the historical detection information, is used to calculate the average speed of the target vehicle during the two frames of historical detection information collection. Because the time interval between the collection of two adjacent frames of historical detection information is extremely short, this average speed can also be considered the target vehicle's instantaneous speed in each frame.

[0100] The results obtained from the differential calculation are then subjected to a Butterworth filter to make the results more stable. The characteristic of a Butterworth filter is that the frequency response curve is extremely flat within the passband, with no fluctuations, while it gradually decreases to zero in the stopband. On a Bode plot of the logarithm of the amplitude versus the diagonal frequency, starting from a certain boundary angular frequency, the amplitude gradually decreases as the angular frequency increases, tending towards negative infinity.

[0101] S306 : Input the historical detection information into a probabilistic intention reasoning model to obtain a predicted cut-in probability of the target vehicle.

[0102] In some embodiments, after the predicted cut-in probability of the target vehicle is obtained, Butterworth filtering is performed on the predicted cut-in probability of the target vehicle.

[0103] S307: If the predicted cut-in probability of the target vehicle is greater than a first preset threshold, and the driving state information of the target vehicle meets a preset condition, triggering a vehicle cut-in warning.

[0104] Specifically, the driving status information of the target vehicle meets preset conditions, including: the target vehicle is driving on the boundary line of the lane where the own vehicle is located, the target vehicle is the vehicle closest to the own vehicle, the collision time between the target vehicle and the own vehicle is less than a preset time, and the ratio of the distance between the target vehicle and the own vehicle and / or the speed of the own vehicle is less than a second preset threshold.

[0105] If a target vehicle is driving on the boundary of the lane in which the ego vehicle is located, the target vehicle is considered to have already caused a certain impact on the normal driving of the ego vehicle. If the target vehicle is the closest to the ego vehicle, the target vehicle is considered to be the vehicle most likely to affect the safe driving of the ego vehicle. If the collision time between the target vehicle and the ego vehicle is less than a preset time, and the ratio of the distance between the target vehicle and the ego vehicle to the ego vehicle's speed is less than a second preset threshold, the target vehicle is considered to be likely to collide with the ego vehicle in the very near future. If the target vehicle has a cut-in probability greater than the first preset threshold and meets the above preset conditions, the target vehicle is considered to be highly likely to affect the safe and normal driving of the ego vehicle when cutting into the ego vehicle's lane, and a vehicle cut-in warning is required.

[0106] Specifically, the implementation process and principle of S306 to S307 are the same as those of S102 to S103 and will not be described in detail here.

[0107] The disclosed embodiment determines an adjacent lane of a lane where the own vehicle is located; takes a vehicle located in the adjacent lane and at a distance less than a preset distance from the own vehicle as a target vehicle; obtains the distance between the target vehicle and the center line of the lane where the target vehicle is located in the historical detection information of each frame to obtain the lateral distance of the target vehicle in each frame; performs differential calculation on the lateral distances of two adjacent frames to obtain a calculation result; performs Butterworth filtering on the calculation result to obtain the lateral speed of the target vehicle in each frame; inputs the historical detection information into a probabilistic intention inference model to obtain a predicted cut-in probability of the target vehicle; if the predicted cut-in probability of the target vehicle is greater than a first preset threshold and the driving status information of the target vehicle meets the preset conditions, a vehicle cut-in warning is triggered, and by further judging the degree of danger of the target vehicle to the safe and normal driving of the own vehicle based on the target vehicle's driving status information on the basis that the cut-in probability of the target vehicle is greater than the first preset threshold, the accuracy and flexibility of the cut-in intention prediction method are further improved.

[0108] At the same time, the embodiment of the present disclosure uses lateral distance and lateral speed to predict the predicted cut-in probability of the target vehicle, and performs Butterworth filtering on the differentially calculated lateral speed and the inferred predicted cut-in probability, thereby increasing the stability of the cut-in intention prediction method.

[0109] FIG4 is a schematic diagram of the structure of a cutting-in intention prediction device provided by an embodiment of the present disclosure. The cutting-in intention prediction device can be the vehicle-mounted device described in the above embodiment, or the cutting-in intention prediction device can be a component or assembly of the vehicle-mounted device. The cutting-in intention prediction device provided by an embodiment of the present disclosure can execute the processing flow provided by the cutting-in intention prediction method embodiment. As shown in FIG4 , the cutting-in intention prediction device 40 includes: a first acquisition module 41, a prediction module 42, and a first determination module 43. The first acquisition module 41 is configured to acquire a preset number of consecutive frames of historical detection information of the target vehicle before the current moment, wherein the historical detection information includes the lateral distance and lateral speed of the target vehicle relative to the vehicle. The prediction module 42 is configured to input the preset number of consecutive frames of historical detection information into a probabilistic intention inference model. The probabilistic intention inference model calculates the node cutting-in probability for each lateral distance and lateral speed in the preset number of consecutive frames of historical detection information through a discrete probability distribution, and uses the node cutting-in probability and the node weight to obtain a predicted cutting-in probability. The first determination module 43 is configured to determine that the target vehicle has a cutting-in intention if the predicted cutting-in probability is greater than a first preset threshold.

[0110] Optionally, the prediction module 42 includes a first determination unit 421, a second determination unit 422, and a first calculation unit 423; the first determination unit 421 is configured to calculate by the node probability layer of the model through discrete probability distribution, and obtain the corresponding node entry probability for each lateral distance and lateral speed in the continuous preset number of frames; the second determination unit 422 is configured to determine the node weight corresponding to each lateral distance and lateral speed according to the sequential position of each lateral distance and lateral speed in the continuous preset number of frames by the weight distribution layer of the model; the calculation unit 423 is configured to calculate the predicted entry probability based on the node entry probability and node weight corresponding to each lateral distance and lateral speed by the probability layer of the model.

[0111] Optionally, the cutting-in intention prediction device 40 also includes a second determination module 44, including a third determination unit 441 and a fourth determination unit 442; the third determination unit 441 is configured to determine the adjacent lane of the lane where the vehicle is located; the fourth determination unit 442 is configured to take a vehicle located in the adjacent lane and at a distance less than a preset distance from the vehicle as a target vehicle.

[0112] Optionally, the third determining unit 441 is further configured to create a virtual lane adjacent to the lane where the vehicle is located as the adjacent lane if the adjacent lane does not exist, and the width of the virtual lane is the same as the width of the lane where the vehicle is located.

[0113] Optionally, the first determination module 43 is specifically configured to determine that the target vehicle has a cut-in intention if the predicted cut-in probability is greater than a first preset threshold and the driving state information of the target vehicle meets a preset condition.

[0114] Optionally, the driving status information of the target vehicle meets preset conditions, including: the target vehicle is driving on the boundary line of the lane where the own vehicle is located, the target vehicle is the vehicle closest to the own vehicle, the collision time between the target vehicle and the own vehicle is less than a preset time, and the ratio of the distance between the target vehicle and the own vehicle and / or the speed of the own vehicle is less than a second preset threshold.

[0115] The cutting intention prediction device of the embodiment shown in FIG4 can be used to implement the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0116] FIG5 is a schematic diagram of the structure of a probabilistic intention reasoning model training device provided by an embodiment of the present disclosure. As shown in FIG5 , the probabilistic intention reasoning model training device includes a second acquisition module 51, a training module 52, and an adjustment module 53; the second acquisition module 51 is configured to acquire training data, wherein the training data includes a preset number of historical data groups, wherein the historical data includes historical detection information of a preset number of consecutive frames of historical vehicles, and the actual results of whether a cut-in behavior occurred corresponding to the preset number of consecutive frames of historical detection information, wherein the preset number of consecutive frames of historical detection information includes the lateral distance and lateral speed of the historical vehicle relative to the historical data collection vehicle for a preset number of consecutive frames; the training module 52 is configured to input the preset number of consecutive frames of historical detection information into the probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the preset number of consecutive frames of historical detection information through discrete probability distribution, and uses the node cut-in probability and node weight to obtain the predicted cut-in probability. The adjustment module 53 is configured to compare the predicted cut-in probability of historical vehicles with the actual results of whether the cut-in behavior occurred, and adjust the model parameters according to the comparison results, thereby completing the training of the probabilistic intention reasoning model to be trained and obtaining a trained probabilistic intention reasoning model.

[0117] In addition, an embodiment of the present disclosure also provides a vehicle, which includes the cutting-in intention prediction device or the probabilistic intention reasoning model training device as described in the above embodiment.

[0118] FIG6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. The electronic device may be a vehicle-mounted device as described in the above embodiment. The electronic device provided in an embodiment of the present disclosure can execute the processing flow provided in the embodiment of the method for predicting the cutting-in intention or the method for training a probabilistic intention reasoning model. As shown in FIG6 , the electronic device 60 includes: a memory 61, a processor 62, a computer program, and a communication interface 63; wherein the computer program is stored in the memory 61 and is configured so that the processor 62 executes the method for predicting the cutting-in intention or the method for training a probabilistic intention reasoning model as described above.

[0119] In addition, an embodiment of the present disclosure also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the entry intention prediction method or the probabilistic intention reasoning model training method described in the above embodiments.

[0120] In addition, an embodiment of the present disclosure also provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, implements the above-mentioned entry intention prediction method or probabilistic intention reasoning model training method.

[0121] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0123] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0124] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein. Industrial Applicability

[0125] The embodiment of the present application provides a method for predicting a cutting-in intention, a method for training a probabilistic intention reasoning model, and an apparatus. The method for predicting a cutting-in intention includes: obtaining historical detection information of a target vehicle for a preset number of consecutive frames before the current moment, the historical detection information including the lateral distance and lateral speed of the target vehicle relative to the own vehicle; inputting the historical detection information of the preset number of consecutive frames into the probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node cutting-in probability of each lateral distance and lateral speed in the historical detection information of the preset number of consecutive frames through discrete probability distribution, and uses the node cutting-in probability and the node weight to obtain the predicted cutting-in probability; if the predicted cutting-in probability is greater than a first preset threshold, it is determined that the target vehicle has a cutting-in intention. The above method is used to implement the solution, and the historical detection information of the target vehicle to be predicted for a preset number of consecutive frames before the current moment and the probabilistic intention reasoning model are used to predict the probability of the target vehicle cutting into the own vehicle lane at a future moment, so that the obtained predicted cutting-in probability can be supported by strong data and theory, thereby improving the accuracy of the cutting-in intention prediction method.

Claims

1. A method for predicting a cut-in intention, the method comprising: Acquire historical detection information of a preset number of consecutive frames of the target vehicle before the current moment, wherein the historical detection information includes a lateral distance and a lateral speed of the target vehicle relative to the own vehicle; Inputting the historical detection information of the continuous preset number of frames into the probabilistic intention reasoning model, the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and using the node cut-in probability and the node weight to obtain the predicted cut-in probability; If the predicted cut-in probability is greater than a first preset threshold, it is determined that the target vehicle has a cut-in intention.

2. The method according to claim 1, wherein: The probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the preset number of consecutive frames through discrete probability distribution, and uses the node cut-in probability and node weight to obtain the predicted cut-in probability, including: The node probability layer of the model is used to calculate the discrete probability distribution, and the corresponding node entry probability is obtained for each lateral distance and lateral speed in the continuous preset number of frames; The weight distribution layer of the model determines the node weight corresponding to each lateral distance and lateral speed according to the sequential position of each lateral distance and lateral speed in the continuous preset number of frames; The predicted cut-in probability is calculated by the probability layer of the model based on the node cut-in probability and node weight corresponding to each lateral distance and lateral velocity.

3. The method according to claim 1, wherein: Before obtaining the historical detection information of the target vehicle for a preset number of consecutive frames before the current moment, the method further includes: Determine the adjacent lanes of the lane where the vehicle is located; A vehicle located in the adjacent lane and whose distance to the own vehicle is less than a preset distance is taken as a target vehicle.

4. The method according to claim 3, wherein: The determining of the adjacent lane of the lane where the vehicle is located includes: If the adjacent lane does not exist, a virtual lane adjacent to the lane where the vehicle is located is created as the adjacent lane, and the width of the virtual lane is the same as the width of the lane where the vehicle is located.

5. The method according to claim 1, wherein: If the predicted cut-in probability is greater than a first preset threshold, determining that the target vehicle has a cut-in intention includes: If the predicted cut-in probability is greater than a first preset threshold value and the driving state information of the target vehicle meets a preset condition, it is determined that the target vehicle has a cut-in intention.

6. The method according to claim 5, wherein: The driving state information of the target vehicle meets the preset conditions, including: The target vehicle is driving on the boundary line of the lane where the own vehicle is located, the target vehicle is the vehicle closest to the own vehicle, the collision time between the target vehicle and the own vehicle is less than a preset time, and the ratio of the distance between the target vehicle and the own vehicle and / or the speed of the own vehicle is less than a second preset threshold.

7. A method for training a probabilistic intention reasoning model, wherein the probabilistic intention reasoning model is applied to the method according to any one of claims 1 to 6, the method comprising: Acquire training data, the training data including a preset number of groups of historical data, the historical data including a preset number of consecutive frames of historical detection information of a historical vehicle, and actual results of whether a cut-in behavior occurs corresponding to the preset number of consecutive frames of historical detection information, wherein the preset number of consecutive frames of historical detection information includes a lateral distance and a lateral speed of the historical vehicle relative to the historical data collection vehicle for a preset number of consecutive frames; Inputting the historical detection information of the continuous preset number of frames into the probabilistic intention reasoning model, the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and using the node cut-in probability and the node weight to obtain the predicted cut-in probability; By comparing the predicted cut-in probability of historical vehicles with the actual results of whether the cut-in behavior occurred, and adjusting the model parameters according to the comparison results, the probabilistic intention reasoning model to be trained is trained to obtain a trained probabilistic intention reasoning model.

8. A device for predicting a cut-in intention, the device comprising: A first acquisition module is configured to acquire a preset number of consecutive frames of historical detection information of the target vehicle before a current moment, wherein the historical detection information includes a lateral distance and a lateral speed of the target vehicle relative to the vehicle; A prediction module is configured to input the historical detection information of the continuous preset number of frames into a probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and obtains the predicted cut-in probability using the node cut-in probability and the node weight; The first determination module is configured to determine that the target vehicle has a cut-in intention if the predicted cut-in probability is greater than a first preset threshold.

9. A probabilistic intention inference model training device, the device comprising: A second acquisition module is configured to acquire training data, wherein the training data includes a preset number of groups of historical data, wherein the historical data includes historical detection information of a preset number of consecutive frames of historical vehicles, and actual results of whether a cut-in behavior occurs corresponding to the historical detection information of the preset number of consecutive frames, wherein the historical detection information of the preset number of consecutive frames includes a lateral distance and a lateral speed of the historical vehicle relative to the historical data collection vehicle for the preset number of consecutive frames; A training module is configured to input the historical detection information of the continuous preset number of frames into the probabilistic intention reasoning model, and the probabilistic intention reasoning model calculates the node cut-in probability of each lateral distance and lateral speed in the historical detection information of the continuous preset number of frames through discrete probability distribution, and obtains the predicted cut-in probability using the node cut-in probability and the node weight; The adjustment module is configured to compare the predicted cut-in probability of historical vehicles with the actual results of whether the cut-in behavior occurred, and adjust the model parameters according to the comparison results, thereby completing the training of the probabilistic intention reasoning model to be trained and obtaining a trained probabilistic intention reasoning model.

10. An electronic device, comprising: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 7.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 7.

12. A vehicle comprising: The cutting intention prediction device as claimed in claim 8; or the probabilistic intention reasoning model training device as claimed in claim 9; Or the electronic device as claimed in claim 10; or, the computer-readable storage medium as claimed in claim 11.

Images