Traffic obstacle avoidance method, device and system based on trajectory prediction

Abstract

The invention is suitable for the technical field of automatic driving, and provides a driving obstacle avoidance method, device and system based on trajectory prediction, and the method comprises the steps: obtaining a road traffic model, obtaining a first type of prediction trajectory of each other vehicle, and obtaining a first type of forbidden zone; based on the abnormal motion vector of the problem vehicle, obtaining a second type of prediction trajectory of the problem vehicle to obtain a second type of forbidden zone; other vehicles interfered by the second type of prediction trajectory are set as associated vehicles, and motion vectors of the associated vehicles are acquired; based on the motion vector of the associated vehicle, obtaining a third type of prediction trajectory of the associated vehicle; obtaining a third type of forbidden zone; and after removing the forbidden zone from the area in the road boundary coordinate, re-planning the driving track of the own vehicle. The method is not limited to the prediction of the obstacle, and also considers the risk avoiding action possibly generated by other vehicles affected by the association of the obstacle, thereby improving the safety and reliability of the route planning.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving, and in particular relates to a driving obstacle avoidance method, device and system based on trajectory prediction. Background Art

[0002] Automatic obstacle avoidance technology is a core part of the vehicle's autonomous driving system, which enables the vehicle to autonomously identify and avoid obstacles in complex road environments. The implementation of this technology relies on the integrated operation of multiple sensors, algorithms, and a large number of decision-making systems, and is highly complex.

[0003] The reliability of the automatic obstacle avoidance function not only depends on the perception system, but also requires a powerful path planning and decision-making system. Through real-time calculation, the system will select the best obstacle avoidance path to ensure driving safety. There are many existing obstacle avoidance algorithms, such as the fast random tree algorithm, the probabilistic roadmap method, the model predictive control method, etc. The principle of this type of algorithm is that when the system detects that an obstacle suddenly appears in front of the vehicle, the system will always pay attention to and obtain the real-time dynamic position of the obstacle, predict the path of the obstacle, and then re-plan the vehicle's own driving trajectory according to the predicted path of the obstacle, so that the vehicle can choose strategies such as braking, accelerating, detouring or changing lanes to achieve obstacle avoidance.

[0004] However, existing solutions often only focus on avoiding obstacles that affect traffic, but ignore the fact that other vehicles may also be affected by obstacles and perform abnormal driving behaviors such as sudden turns and lane changes. These associated abnormal driving behaviors may also endanger their own driving safety. Therefore, it is necessary to further improve the existing path prediction planning methods. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a driving obstacle avoidance method based on trajectory prediction, which aims to solve the problem that existing obstacle avoidance solutions often only focus on avoiding obstacles that affect traffic, but ignore the associated dangerous behaviors of other vehicles that may also be affected by obstacles and make sudden turns, lane changes and other abnormal driving behaviors, and these associated abnormal driving behaviors may also endanger the driving safety of the vehicle itself.

[0006] The embodiment of the present application is implemented by providing a vehicle obstacle avoidance method based on trajectory prediction, the method comprising: Acquire a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road; Obtaining respective motion vectors of each other vehicle in the road traffic model, and obtaining first-class predicted trajectories of each other vehicle based on the motion vectors; and obtaining first-class restricted areas based on the first-class predicted trajectories; Monitoring whether there is an abnormally deviated vehicle among a number of other vehicles, and setting the vehicle with abnormal deviation as a problem vehicle; the abnormal deviation is an abnormal driving behavior in which the deviation between the actual trajectory and the historical trajectory of the vehicle is higher than an abnormal threshold; Based on the abnormal motion vector of the problem vehicle, a second type of predicted trajectory of the problem vehicle is obtained, and based on the second type of predicted trajectory, a second type of restricted area is obtained; Set other vehicles interfered by the second type of predicted trajectory as associated vehicles, and obtain the motion vector of the associated vehicle; obtain the third type of predicted trajectory of the associated vehicle based on the motion vector of the associated vehicle; and obtain the third type of restricted area based on the third type of predicted trajectory; After removing the first-category restricted area, the second-category restricted area, and the third-category restricted area from the area within the road boundary coordinates, the driving trajectory of the vehicle is replanned.

[0007] Preferably, a method for obtaining a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road is: Define the vehicle coordinates as the coordinate origin, take the road extension direction as the y-axis, take the vehicle travel direction as the positive direction of the y-axis, and establish a plane rectangular coordinate system; Get the coordinate set M of other vehicles: ; Among them, m is the vehicle number of other vehicles, Represents the position coordinates of the mth vehicle; The road boundary is divided into several differential segments, and the road boundary B is defined based on the differential segments: ; in, Represents the bth segment boundary, and the number of boundaries is n in total.

[0008] Preferably, the method of obtaining the motion vectors of each other vehicle in the road traffic model and obtaining the first type predicted trajectory of each other vehicle based on the motion vectors is: Get the historical coordinates of the vehicle to be predicted compared to the vehicle itself And the collection I of the timestamp t corresponding to the coordinate: in, Indicates that the vehicle to be predicted is location in time; The collection I is input into the path prediction network, which is built based on the long short-term memory network and includes three parts: an input gate, a forget gate, and an output gate. The path prediction network is used to predict and output the vehicle to be predicted at a future time based on the data dependency relationship in the collection I. Position coordinates at the moment .

[0009] Preferably, the loss function of the path prediction network is set to: Among them, i means there are i historical data in total, k means the kth one, and represents the x-axis and y-axis coordinates of the k-th fitting coordinate, and Represents the x-axis and y-axis coordinates of k historical coordinates.

[0010] Preferably, a method for monitoring whether there is a vehicle with abnormal deviation among a number of other vehicles and setting the vehicle with abnormal deviation as a problem vehicle is as follows: Based on the real-time driving trajectory of the vehicle, obtain the absolute value of the displacement change per unit time of the vehicle at the current moment and the absolute value of the change in direction angle per unit time ; Based on the historical driving trajectory of the vehicle, obtain the absolute value of the vehicle's displacement change per unit time and the absolute value of the change in direction angle per unit time ; Vehicles that meet the following conditions are considered to have abnormal deviation: and / or in, is the displacement anomaly threshold coefficient, is the direction angle anomaly threshold coefficient.

[0011] Preferably, the method for obtaining the associated vehicle is: Obtaining the forward directions of other vehicles to be judged except the problem vehicle, and setting them as the forward interference area; Determine whether the second-type predicted trajectory and the forward interference area of ​​the vehicle to be determined have mutual interference, overlap or intersection, and obtain a first determination result; Determine whether the second-type predicted trajectory and the first-type predicted trajectory of the vehicle to be determined have mutual interference, overlap or intersection, and obtain a second determination result; When one of the first judgment result and the second judgment result is satisfied or both are satisfied, the to-be-judged vehicle satisfying the judgment condition is set as an associated vehicle.

[0012] Preferably, the trajectory prediction method of the associated vehicle is: Constructing a risk avoidance path dataset under the emergency risk avoidance state of the vehicle, wherein the risk avoidance path dataset includes several typical risk avoidance paths that occur when the vehicle is disturbed, and each of the typical risk avoidance paths is annotated with its corresponding typical path features; The typical path feature is used to characterize the data feature of the moving path of the typical risk avoidance path in the initial stage of the path; Based on the motion vector of the associated vehicle, a real path of the associated vehicle in an emergency avoidance state is obtained, and real data features of the real path are acquired; Comparing the real data features with all the typical path features in the risk avoidance path dataset to obtain several similarity comparison results; The typical risk avoidance paths corresponding to all the typical path features whose similarity comparison results are higher than the similarity threshold are set as the third type of predicted trajectory.

[0013] Another object of an embodiment of the present application is to provide a vehicle obstacle avoidance device based on trajectory prediction, the device comprising: A road traffic model acquisition module is used to acquire a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road; A first-category restricted zone acquisition module, configured to acquire the motion vectors of each other vehicle in the road traffic model, and obtain the first-category predicted trajectory of each other vehicle based on the motion vectors; and obtain the first-category restricted zone based on the first-category predicted trajectory; A problem vehicle acquisition module is used to monitor whether there are vehicles with abnormal deviations among a number of other vehicles, and set vehicles with abnormal deviations as problem vehicles; the abnormal deviation is an abnormal driving behavior in which the deviation between the actual trajectory of the vehicle and the historical trajectory exceeds an abnormal threshold; A second-category restricted zone acquisition module, configured to acquire a second-category predicted trajectory of the problem vehicle based on the abnormal motion vector of the problem vehicle, and obtain a second-category restricted zone based on the second-category predicted trajectory; A third-category restricted zone acquisition module is used to set other vehicles interfered by the second-category predicted trajectory as associated vehicles, and acquire the motion vector of the associated vehicle; based on the motion vector of the associated vehicle, obtain the third-category predicted trajectory of the associated vehicle; and based on the third-category predicted trajectory, obtain the third-category restricted zone; The path planning module is used to re-plan the driving trajectory of the vehicle after removing the first-category restricted area, the second-category restricted area and the third-category restricted area from the area within the road boundary coordinates.

[0014] Another purpose of an embodiment of the present application is to provide a vehicle obstacle avoidance system based on trajectory prediction, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of a vehicle obstacle avoidance method based on trajectory prediction as described above.

[0015] The embodiment of the present application provides a driving obstacle avoidance method based on trajectory prediction. Its outstanding advantage is that the present application predicts the driving trajectory in real time according to the motion state of the vehicle and other vehicles, and is not limited to predicting the obstacle itself. It also takes into account the possible avoidance actions of other vehicles affected by its association, so that the obstacle avoidance planning can be adjusted to the above potential dangers according to the real-time traffic status, rather than just based on static maps or pre-set trajectories, thereby improving the safety and reliability of route planning. By monitoring the abnormal deviation of the vehicle, potential dangerous driving behaviors or emergencies can be discovered in time, improving road safety. By acquiring and judging different types of dangerous restricted areas, the method has higher accuracy and predictive foresight when dealing with complex traffic environments, and improves the comprehensive safety level of the planned path. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 An application environment diagram of a vehicle obstacle avoidance method based on trajectory prediction provided in an embodiment of the present application; Figure 2 A flowchart of a vehicle obstacle avoidance method based on trajectory prediction provided in an embodiment of the present application; Figure 3 A road state simulation diagram provided in an embodiment of the present application; Figure 4 Another road state simulation diagram provided in an embodiment of the present application; Figure 5 A structural block diagram of a vehicle obstacle avoidance device based on trajectory prediction provided in an embodiment of the present application; Figure 6 FIG. 4 is a block diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script without departing from the scope of this application.

[0019] Figure 1 The application environment diagram of the vehicle obstacle avoidance method based on trajectory prediction provided in the embodiment of the present application is as follows: Figure 1 As shown, in the application environment, a sensor 110 and a computer device 120 are included.

[0020] The computer device 120 can be an independent physical server or terminal, or a server cluster composed of multiple physical servers. It can be a cloud server that provides basic cloud computing services such as a cloud server, or a local vehicle-mounted computer, etc., but is not limited to these.

[0021] The sensor 110 may be a laser radar, a millimeter wave radar, a visual camera device, etc., and can be used to detect the surrounding conditions of the vehicle. The sensor 110 and the computer device 120 may be connected via a wired or wireless network, and this application does not limit this.

[0022] like Figure 2 As shown, in one embodiment, a vehicle obstacle avoidance method based on trajectory prediction is proposed. This embodiment mainly applies this method to the above Figure 1 A method for avoiding obstacles based on trajectory prediction may include the following steps: Step S10, obtaining a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road; In this embodiment, the system first constructs or obtains a road traffic model with the vehicle as the coordinate origin, including the road boundary and the positions of other vehicles. The road traffic model constructed with the vehicle as the coordinate origin allows the model to only consider the relative motion relationship between vehicles, simplifying the data calculation amount of the motion prediction algorithm.

[0023] Step S20, obtaining the motion vectors of each other vehicle in the road traffic model, and obtaining the first type of predicted trajectory of each other vehicle based on the motion vector; and obtaining the first type of restricted area based on the first type of predicted trajectory; In this embodiment, there are multiple methods for predicting the trajectory of the vehicle based on the motion vector. For example, the relative speed, acceleration and azimuth of the vehicle to be predicted compared to the vehicle itself and the historical driving data or relative position data of the vehicle can be first obtained, and then the trajectory can be fitted using polynomial regression, and then the historical trajectory data can be fitted using the least squares method to estimate the future relative speed, acceleration and azimuth coefficients, thereby obtaining the predicted future position. Based on the area occupied by the vehicle and the first type of predicted trajectory of the vehicle, the first type of restricted area can be obtained.

[0024] In one embodiment, Figure 3 As shown, coordinate O is the position coordinate of the ego vehicle, and vehicles A, B, and C are other vehicles. Vehicle C is accelerating compared to the ego vehicle. Figure 3 The dotted area on top of the middle C car is the first type of restricted area.

[0025] Step S30, monitoring whether there is any vehicle with abnormal deviation among a number of other vehicles, and setting the vehicle with abnormal deviation as a problem vehicle; the abnormal deviation is an abnormal driving behavior in which the deviation between the actual trajectory and the historical trajectory of the vehicle is higher than the abnormal threshold.

[0026] In this embodiment, an abnormal vehicle may refer to a vehicle that experiences sudden acceleration, deceleration, or lane change, for example Figure 3 For vehicle A, the system sensor detects that it has not given a lane change turn signal and predicts that it is driving in a straight line. However, the vehicle suddenly changes lanes to the left lane at this time, so it can be set as an abnormal vehicle.

[0027] Step S40: acquiring a second type of predicted trajectory of the problem vehicle based on the abnormal motion vector of the problem vehicle, and obtaining a second type of restricted area based on the second type of predicted trajectory.

[0028] In this embodiment, for abnormal behaviors of vehicles marked as problematic, their future trajectories can be predicted through their abnormal motion vectors, and a second type of restricted area can be formed. Figure 3 As shown in FIG. 1 , the dotted area on the left side of vehicle A is the second restricted area. The second type of trajectory prediction method for abnormal problem vehicles can be predicted based on the existing trajectory prediction method, which will not be described in detail here.

[0029] Step S50, setting other vehicles interfered by the second type of predicted trajectory as associated vehicles, obtaining the motion vector of the associated vehicle; obtaining the third type of predicted trajectory of the associated vehicle based on the motion vector of the associated vehicle; and obtaining the third type of restricted area based on the third type of predicted trajectory.

[0030] In this embodiment, if the second restricted area affects the driving trajectory of other vehicles, the other vehicles will be marked as related vehicles, and based on the movement information of these related vehicles, their trajectories are further predicted to form a third restricted area. Figure 3 As shown in the figure, vehicle A suddenly changes lanes when vehicle B is driving in a normal straight line. At this time, vehicle B may be affected by the abnormality and may have multiple relative movements relative to vehicle O. The third restricted area is Figure 3 The dotted area on the right side or rear side of vehicle B.

[0031] Step S60, after removing the first-category restricted area, the second-category restricted area and the third-category restricted area from the area within the road boundary coordinates, replanning the driving trajectory of the vehicle.

[0032] In an embodiment of the present application, the vehicle will re-plan its route, and after determining all the above-mentioned restricted areas, it will remove these restricted areas and re-plan its driving trajectory to avoid entering these dangerous areas.

[0033] In the embodiments of the present application, the present application predicts the driving trajectory in real time according to the motion state of the vehicle and other vehicles, and is not limited to predicting the obstacle itself, but also takes into account the possible risk avoidance actions of other vehicles affected by its association, so that the obstacle avoidance planning can be adjusted to the above potential dangers according to the real-time traffic status, rather than just based on static maps or pre-set trajectories, thereby improving the safety and reliability of route planning. By monitoring the abnormal deviation of the vehicle, potential dangerous driving behaviors or emergencies can be discovered in time, thereby improving road safety. By acquiring and judging different types of dangerous restricted areas, the method has higher accuracy and predictive foresight when dealing with complex traffic environments, and improves the comprehensive safety level of the planned path.

[0034] In a preferred embodiment, a method for obtaining a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road is: Define the vehicle coordinates as the coordinate origin, take the road extension direction as the y-axis, take the vehicle travel direction as the positive direction of the y-axis, and establish a plane rectangular coordinate system; Get the coordinate set M of other vehicles: ; Among them, m is the vehicle number of other vehicles, Represents the position coordinates of the mth vehicle; The road boundary is divided into several differential segments, and the road boundary B is defined based on the differential segments: ; in, Represents the bth segment boundary, and the number of boundaries is n in total.

[0035] In the embodiment of the present application, the road model can be acquired and established based on the above method, and the various boundary coefficients and the coordinate positions of the vehicles can be obtained. In this coordinate system, only the coefficients of the relative position change, speed change, acceleration change, etc. between the vehicles need to be obtained, which can reduce the amount of calculation of the system.

[0036] In a preferred embodiment, the method of obtaining the motion vectors of each other vehicle in the road traffic model and obtaining the first type predicted trajectory of each other vehicle based on the motion vectors is: Get the historical coordinates of the vehicle to be predicted compared to the vehicle itself And the collection I of the timestamp t corresponding to the coordinate: in, Indicates that the vehicle to be predicted is location in time; The collection I is input into the path prediction network, which is built based on the long short-term memory network and includes three parts: an input gate, a forget gate, and an output gate. The path prediction network is used to predict and output the vehicle to be predicted at a future time based on the data dependency relationship in the collection I. Position coordinates at the moment .

[0037] In the embodiment of the present application, although polynomial regression combined with least squares method can achieve path prediction, the above method is not good at dealing with complex path problems such as nonlinearity. Therefore, in order to further improve the prediction accuracy of the path, this solution uses a deep learning model to build a path prediction network. Therefore, as a preferred embodiment, the present application uses a long short-term memory network (Long Short-Term Memory) model to process path prediction. The basic framework of the model consists of an input gate, a forget gate, and an output gate. It captures the dependency of data in the input time series through a recurrent neural network, so that the system can better handle long-term dependency problems in time series data and improve the prediction accuracy of the path.

[0038] In a preferred embodiment, the loss function of the path prediction network is set to: Among them, i means there are i historical data in total, k means the kth one, and represents the x-axis and y-axis coordinates of the k-th fitting coordinate, and Represents the x-axis and y-axis coordinates of k historical coordinates.

[0039] In the embodiment of the present application, the loss function of the model is the key to controlling the deviation between the prediction and the actual trajectory. Compared with other control methods, since the present application needs to perform path prediction for multiple vehicles at the same time, through comprehensive comparison, the following loss function is used to improve the prediction accuracy, and its comprehensive measurement accuracy is relatively high: In a preferred embodiment, a method for monitoring whether there is an abnormally deviated vehicle among a number of other vehicles and setting the abnormally deviated vehicle as a problem vehicle is as follows: Based on the real-time driving trajectory of the vehicle, obtain the absolute value of the displacement change per unit time of the vehicle at the current moment and the absolute value of the change in direction angle per unit time ; Based on the historical driving trajectory of the vehicle, obtain the absolute value of the vehicle's displacement change per unit time and the absolute value of the change in direction angle per unit time ; Vehicles that meet the following conditions are considered to have abnormal deviation: and / or in, is the displacement anomaly threshold coefficient, is the direction angle anomaly threshold coefficient.

[0040] In the embodiment of the present application, it is considered that the problem vehicle is often caused by an abnormal sudden increase or decrease in the throttle, resulting in an instantaneous speed change, which is manifested in the sensor detecting that the displacement change of the vehicle per unit time is a sudden change compared with the historical value, or a sudden change in the vehicle's driving angle per unit time caused by a sudden turn of the vehicle's direction, wherein Displacement anomaly threshold coefficient, The direction angle anomaly threshold coefficient may refer to a sudden change rate threshold, and the specific coefficient may be set based on actual conditions.

[0041] In a preferred embodiment, the method for obtaining the associated vehicle is: Obtaining the forward directions of other vehicles to be judged except the problem vehicle, and setting them as the forward interference area; Determine whether the second-type predicted trajectory and the forward interference area of ​​the vehicle to be determined have mutual interference, overlap or intersection, and obtain a first determination result; Determine whether the second-type predicted trajectory and the first-type predicted trajectory of the vehicle to be determined have mutual interference, overlap or intersection, and obtain a second determination result; When one of the first judgment result and the second judgment result is satisfied or both are satisfied, the to-be-judged vehicle satisfying the judgment condition is set as an associated vehicle.

[0042] In the embodiment of the present application, since all vehicles are moving forward, during the driving process, even if the trajectory of the abnormal vehicle does not intersect with some vehicles, some vehicles may still be frightened by the abnormal vehicle passing in front of them, thereby generating related anomalies, causing the driver to exhibit abnormal driving behavior, such as emergency lane changes, etc.

[0043] Therefore, this embodiment further expands the scope of vehicles that may exhibit abnormal driving behavior, allowing the path planning prediction system to predict abnormal path changes that may occur to such vehicles at the same time, without having to predict the trajectories of normal vehicles that are not affected by them, thereby reducing the computational requirements and being able to further improve the safety factor of path planning.

[0044] In a preferred embodiment, the trajectory prediction method of the associated vehicle is: Constructing a risk avoidance path dataset under the emergency risk avoidance state of the vehicle, wherein the risk avoidance path dataset includes several typical risk avoidance paths that occur when the vehicle is disturbed, and each of the typical risk avoidance paths is annotated with its corresponding typical path features; The typical path feature is used to characterize the data feature of the moving path of the typical risk avoidance path in the initial stage of the path; Based on the motion vector of the associated vehicle, a real path of the associated vehicle in an emergency avoidance state is obtained, and real data features of the real path are acquired; Comparing the real data features with all the typical path features in the risk avoidance path dataset to obtain several similarity comparison results; The typical risk avoidance paths corresponding to all the typical path features whose similarity comparison results are higher than the similarity threshold are set as the third type of predicted trajectory.

[0045] In the embodiments of the present application, Figure 4As shown, in this schematic diagram, vehicle B is a normally traveling vehicle, and its preset direction is forward. At this time, vehicle A is a vehicle that suddenly changes lanes, and vehicle B may be affected by it and appear in a relative motion path composed of solid direction arrows and dotted direction arrows in the figure. These paths are called typical risk avoidance paths. Among them, the solid direction arrow is recorded as the moving path of the typical risk avoidance path in the initial stage of the path, and the characteristic performance of the route in the data is obtained and recorded as the typical path feature. Different paths have different typical path features. By determining the characteristics of the initial stage, the complete predicted path can be approximated. Compare the data features shown in the initial stage of the vehicle's real driving data with all the typical path features in the risk avoidance path data set, and set all the paths with high similarity comparison results as the third type of predicted trajectory, which can further improve the safety of the prediction.

[0046] like Figure 5 As shown, in one embodiment, a vehicle obstacle avoidance device based on trajectory prediction is provided. The vehicle obstacle avoidance device based on trajectory prediction can be integrated into the above-mentioned computer device 120, and specifically can include a road traffic model acquisition module 510, a first type of restricted area acquisition module 520, a problem vehicle acquisition module 530, a second type of restricted area acquisition module 540, a third type of restricted area acquisition module 550 and a path planning module 560.

[0047] The road traffic model acquisition module 510 is used to acquire a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road; The first-category restricted zone acquisition module 520 is used to acquire the motion vectors of each other vehicle in the road traffic model, and obtain the first-category predicted trajectory of each other vehicle based on the motion vector; and obtain the first-category restricted zone based on the first-category predicted trajectory; The problem vehicle acquisition module 530 is used to monitor whether there is a vehicle with abnormal deviation among a number of other vehicles, and set the vehicle with abnormal deviation as a problem vehicle; the abnormal deviation is an abnormal driving behavior in which the deviation between the actual trajectory and the historical trajectory of the vehicle is higher than the abnormal threshold; A second-category restricted zone acquisition module 540 is configured to acquire a second-category predicted trajectory of the problem vehicle based on the abnormal motion vector of the problem vehicle, and obtain a second-category restricted zone based on the second-category predicted trajectory; The third-type restricted area acquisition module 550 is used to set other vehicles interfered by the second-type predicted trajectory as associated vehicles, and acquire the motion vector of the associated vehicle; based on the motion vector of the associated vehicle, obtain the third-type predicted trajectory of the associated vehicle; and based on the third-type predicted trajectory, obtain the third-type restricted area; The path planning module 560 is used to re-plan the driving trajectory of the vehicle after removing the first-category restricted area, the second-category restricted area and the third-category restricted area from the area within the road boundary coordinates.

[0048] In the embodiment of the present application, the explanation and description of the above-mentioned driving obstacle avoidance device based on trajectory prediction can refer to the explanation and description of the above-mentioned corresponding method. For the description of the above-mentioned driving obstacle avoidance method based on trajectory prediction, please refer to the above, which will not be repeated here.

[0049] In the embodiments of the present application, the present application predicts the driving trajectory in real time according to the motion state of the vehicle and other vehicles, and is not limited to predicting the obstacle itself, but also takes into account the possible risk avoidance actions of other vehicles affected by its association, so that the obstacle avoidance planning can be adjusted to the above potential dangers according to the real-time traffic status, rather than just based on static maps or pre-set trajectories, thereby improving the safety and reliability of route planning. By monitoring the abnormal deviation of the vehicle, potential dangerous driving behaviors or emergencies can be discovered in time, thereby improving road safety. By acquiring and judging different types of dangerous restricted areas, the method has higher accuracy and predictive foresight when dealing with complex traffic environments, and improves the comprehensive safety level of the planned path.

[0050] Figure 6 The internal structure diagram of a computer device in one embodiment is shown. The computer device may specifically be Figure 1 The computer device 120 in FIG. Figure 6 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement a driving obstacle avoidance method based on trajectory prediction. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute a driving obstacle avoidance method based on trajectory prediction. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0051] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0052] In one embodiment, the vehicle obstacle avoidance device based on trajectory prediction provided by the present application can be implemented in the form of a computer program. The computer program can be used in Figure 6 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules constituting the vehicle obstacle avoidance device based on trajectory prediction, for example, Figure 5 The road traffic model acquisition module 510, the first restricted area acquisition module 520, the problem vehicle acquisition module 530, the second restricted area acquisition module 540, the third restricted area acquisition module 550 and the path planning module 560 are shown. The computer program composed of each program module enables the processor to execute the steps of the vehicle obstacle avoidance method based on trajectory prediction in each embodiment of the present application described in this specification.

[0053] For example, Figure 6 The computer device shown can be Figure 5 The road traffic model acquisition module 510 in the vehicle obstacle avoidance device based on trajectory prediction performs step S10. The computer device can perform step S20 through the first type restricted area acquisition module 520. And so on.

[0054] In one embodiment, a vehicle obstacle avoidance system based on trajectory prediction is proposed, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of a vehicle obstacle avoidance method based on trajectory prediction as described above.

[0055] In the embodiment of the present application, please refer to the above for the description of the above-mentioned vehicle obstacle avoidance method based on trajectory prediction, which will not be repeated here.

[0056] In the embodiments of the present application, the present application predicts the driving trajectory in real time according to the motion state of the vehicle and other vehicles, and is not limited to predicting the obstacle itself, but also takes into account the possible risk avoidance actions of other vehicles affected by its association, so that the obstacle avoidance planning can be adjusted to the above potential dangers according to the real-time traffic status, rather than just based on static maps or pre-set trajectories, thereby improving the safety and reliability of route planning. By monitoring the abnormal deviation of the vehicle, potential dangerous driving behaviors or emergencies can be discovered in time, thereby improving road safety. By acquiring and judging different types of dangerous restricted areas, the method has higher accuracy and predictive foresight when dealing with complex traffic environments, and improves the comprehensive safety level of the planned path.

[0057] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the vehicle obstacle avoidance method based on trajectory prediction as described above.

[0058] In the embodiment of the present application, please refer to the above for the description of the above-mentioned vehicle obstacle avoidance method based on trajectory prediction, which will not be repeated here.

[0059] In the embodiment of the present application, the program run by the method stored in the storage medium of the embodiment of the present application enables the present application to predict the driving trajectory in real time according to the motion state of the vehicle and other vehicles, and is not limited to predicting the obstacle itself, but also takes into account the possible risk avoidance actions of other vehicles affected by its association, so that the obstacle avoidance planning can be adjusted according to the real-time traffic status for the above potential dangers, rather than just based on static maps or pre-set trajectories, thereby improving the safety and reliability of route planning. By monitoring the abnormal deviation of the vehicle, potential dangerous driving behaviors or emergencies can be discovered in time, improving road safety. By acquiring and judging different types of dangerous restricted areas, the method has higher accuracy and predictive foresight when dealing with complex traffic environments, and improves the comprehensive safety level of the planned path.

[0060] It should be understood that, although each step in the flow chart of each embodiment of the present application is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0061] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0062] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0063] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle obstacle avoidance method based on trajectory prediction, characterized in that: The method comprises: Acquire a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road; Obtaining respective motion vectors of each other vehicle in the road traffic model, and obtaining first-class predicted trajectories of each other vehicle based on the motion vectors; and obtaining first-class restricted areas based on the first-class predicted trajectories; Monitoring whether there is an abnormally deviated vehicle among a number of other vehicles, and setting the vehicle with abnormal deviation as a problem vehicle; the abnormal deviation is an abnormal driving behavior in which the deviation between the actual trajectory and the historical trajectory of the vehicle is higher than an abnormal threshold; Based on the abnormal motion vector of the problem vehicle, a second type of predicted trajectory of the problem vehicle is obtained, and based on the second type of predicted trajectory, a second type of restricted area is obtained; Set other vehicles interfered by the second type of predicted trajectory as associated vehicles, and obtain the motion vector of the associated vehicle; obtain the third type of predicted trajectory of the associated vehicle based on the motion vector of the associated vehicle; and obtain the third type of restricted area based on the third type of predicted trajectory; After removing the first-category restricted area, the second-category restricted area, and the third-category restricted area from the area within the road boundary coordinates, the driving trajectory of the vehicle is replanned.

2. The method for avoiding obstacles while driving based on trajectory prediction according to claim 1, characterized in that: A method for obtaining a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road is: Define the vehicle coordinates as the coordinate origin, take the road extension direction as the y-axis, take the vehicle travel direction as the positive direction of the y-axis, and establish a plane rectangular coordinate system; Get the coordinate set M of other vehicles: ； Among them, m is the vehicle number of other vehicles, Represents the position coordinates of the mth vehicle; The road boundary is divided into several differential segments, and the road boundary B is defined based on the differential segments: ； in, Represents the bth segment boundary, and the number of boundaries is n in total.

3. The method for avoiding obstacles while driving based on trajectory prediction according to claim 1, characterized in that: The method of obtaining the motion vectors of each other vehicle in the road traffic model and obtaining the first type predicted trajectory of each other vehicle based on the motion vectors is as follows: Get the historical coordinates of the vehicle to be predicted compared to the vehicle itself And the collection I of the timestamp t corresponding to the coordinate: in, Indicates that the vehicle to be predicted is location in time; The collection I is input into the path prediction network, which is built based on the long short-term memory network and includes three parts: an input gate, a forget gate, and an output gate. The path prediction network is used to predict and output the vehicle to be predicted at a future time based on the data dependency relationship in the collection I. Position coordinates at the moment .

4. The method for avoiding obstacles while driving based on trajectory prediction according to claim 3, characterized in that: The loss function of the path prediction network is set as: Among them, i means there are i historical data in total, k means the kth one, and represents the x-axis and y-axis coordinates of the k-th fitting coordinate, and Represents the x-axis and y-axis coordinates of k historical coordinates.

5. The method for avoiding obstacles while driving based on trajectory prediction according to claim 1, characterized in that: The method of monitoring whether there is an abnormally deviated vehicle among a number of other vehicles and setting the abnormally deviated vehicle as a problem vehicle is as follows: Based on the real-time driving trajectory of the vehicle, obtain the absolute value of the displacement change per unit time of the vehicle at the current moment and the absolute value of the change in direction angle per unit time ; Based on the historical driving trajectory of the vehicle, obtain the absolute value of the vehicle's displacement change per unit time and the absolute value of the change in direction angle per unit time ; Vehicles that meet the following conditions are considered to have abnormal deviation: and / or in, is the displacement anomaly threshold coefficient, is the direction angle anomaly threshold coefficient.

6. The method for avoiding obstacles while driving based on trajectory prediction according to claim 1, characterized in that: The method for obtaining the associated vehicle is: Obtaining the forward directions of other vehicles to be judged except the problem vehicle, and setting them as the forward interference area; Determine whether the second-type predicted trajectory and the forward interference area of ​​the vehicle to be determined have mutual interference, overlap or intersection, and obtain a first determination result; Determine whether the second-type predicted trajectory and the first-type predicted trajectory of the vehicle to be determined have mutual interference, overlap or intersection, and obtain a second determination result; When one of the first judgment result and the second judgment result is satisfied or both are satisfied, the to-be-judged vehicle satisfying the judgment condition is set as an associated vehicle.

7. The method for avoiding obstacles while driving based on trajectory prediction according to claim 1, characterized in that: The trajectory prediction method of the associated vehicle is: Constructing a risk avoidance path dataset under the emergency risk avoidance state of the vehicle, wherein the risk avoidance path dataset includes several typical risk avoidance paths that occur when the vehicle is disturbed, and each of the typical risk avoidance paths is annotated with its corresponding typical path features; The typical path feature is used to characterize the data feature of the moving path of the typical risk avoidance path in the initial stage of the path; Based on the motion vector of the associated vehicle, a real path of the associated vehicle in an emergency avoidance state is obtained, and real data features of the real path are acquired; Comparing the real data features with all the typical path features in the risk avoidance path dataset to obtain several similarity comparison results; The typical risk avoidance paths corresponding to all the typical path features whose similarity comparison results are higher than the similarity threshold are set as the third type of predicted trajectory.

8. A vehicle obstacle avoidance device based on trajectory prediction, characterized in that: The device comprises: A road traffic model acquisition module is used to acquire a road traffic model constructed with the vehicle as the coordinate origin, wherein the road traffic model includes the road boundary coordinates of the road and the vehicle coordinates of several other vehicles on the road; A first-category restricted zone acquisition module, configured to acquire the motion vectors of each other vehicle in the road traffic model, and obtain the first-category predicted trajectory of each other vehicle based on the motion vectors; and obtain the first-category restricted zone based on the first-category predicted trajectory; A problem vehicle acquisition module is used to monitor whether there are vehicles with abnormal deviations among a number of other vehicles, and set vehicles with abnormal deviations as problem vehicles; the abnormal deviation is an abnormal driving behavior in which the deviation between the actual trajectory of the vehicle and the historical trajectory exceeds an abnormal threshold; A second-category restricted zone acquisition module, configured to acquire a second-category predicted trajectory of the problem vehicle based on the abnormal motion vector of the problem vehicle, and obtain a second-category restricted zone based on the second-category predicted trajectory; A third-category restricted zone acquisition module is used to set other vehicles interfered by the second-category predicted trajectory as associated vehicles, and acquire the motion vector of the associated vehicle; based on the motion vector of the associated vehicle, obtain the third-category predicted trajectory of the associated vehicle; and based on the third-category predicted trajectory, obtain the third-category restricted zone; The path planning module is used to re-plan the driving trajectory of the vehicle after removing the first-category restricted area, the second-category restricted area and the third-category restricted area from the area within the road boundary coordinates.

9. A vehicle obstacle avoidance system based on trajectory prediction, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of a vehicle obstacle avoidance method based on trajectory prediction as described in any one of claims 1 to 7.

Images