Vehicle control method, computer program product and electronic device

Abstract

The invention provides a vehicle control method, a computer program product and electronic equipment, according to the vehicle control method provided by the invention, after a lane changing auxiliary function of a vehicle is activated, candidate target objects located in a lane where the vehicle is located and in a lane adjacent to the vehicle can be screened out from initial target objects existing around the vehicle; then, according to the lane change progress information of the vehicle, a collision risk object which can influence the safety of the vehicle can be accurately screened out from the candidate target objects, so that the lane change process of the vehicle is controlled according to a collision risk prediction result between the vehicle and the collision risk object.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular, to a vehicle control method, a computer program product, and an electronic device. Background Art

[0002] With the continuous development of technology, automobiles are gradually equipped with some lane change assistance functions to automatically control the vehicle to change lanes by combining the surrounding environment information of the vehicle and the operating condition information of the vehicle itself, thereby improving the operation convenience and safety of the driver during driving. However, when the lane change assistance function of the current vehicle is running, it not only controls the lane change process of the vehicle by combining the target objects that have a greater impact on the lane change process of the vehicle in the area such as the lane where the vehicle is located and the adjacent lanes of the vehicle, but also controls the lane change process of the vehicle by combining the target objects that have a smaller impact on the lane change process of the vehicle in other areas. As a result, the lane change assistance function of the vehicle is prone to being unable to control the vehicle to complete the lane change due to the interference of the target objects in the above-mentioned other areas, affecting the operation stability and reliability of the lane change assistance function of the vehicle. Summary of the Invention

[0003] Based on this, the present invention provides a vehicle control method, a computer program product, and an electronic device. By using this vehicle control method, the operation stability and reliability of the lane change assistance function of the vehicle can be improved on the basis of effectively ensuring the safety of the lane change process of the vehicle.

[0004] On the one hand, the present invention provides a vehicle control method, and the method includes:

[0005] After the lane change assistance function of the vehicle is activated, obtain the initial target objects existing around the vehicle;

[0006] Determine the candidate target objects located in the preset lanes from the initial target objects; wherein, the preset lanes include the lane where the vehicle is located and the adjacent lanes of the vehicle;

[0007] Generate a collision risk prediction result between the collision risk objects among the candidate target objects and the vehicle according to the lane change progress information of the vehicle;

[0008] Generate a lane change process control instruction for the vehicle based on the collision risk prediction result.

[0009] Further, in some embodiments, the obtaining the initial target objects existing around the vehicle includes:

[0010] Obtain the position information of the initial target objects obtained by processing the surrounding environment image of the vehicle collected by the image acquisition device; or,

[0011] Obtain the position information of the initial target object obtained by processing the perception data of the surrounding environment of the vehicle collected by the radar device; or,

[0012] Obtain the position information of the initial target object obtained by processing the perception data of the surrounding environment of the vehicle collected by the radar device and the surrounding environment image of the vehicle collected by the image acquisition device.

[0013] Further, in some embodiments, determining the candidate target object located in the preset lane from the initial target object includes:

[0014] Analyze and process at least one of the surrounding environment image of the vehicle, the historical driving trajectory data of the vehicle, and the target driving trajectory data of the vehicle to obtain at least one of the position information of the preset lane within a preset distance in front of the vehicle and the position information of the preset lane within a specified distance behind the vehicle;

[0015] If it is determined that the initial target object is located in the preset lane according to the position information of the preset lane and the position information of the initial target object, then the initial target object is determined as the candidate target object.

[0016] Further, in some embodiments, generating a collision risk prediction result between the collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle includes:

[0017] If the lane change progress information reflects that the vehicle has changed from the initial lane to a specific adjacent lane, then determine the candidate target object located in the preset lane to which the specific adjacent lane belongs to obtain the collision risk object of the vehicle;

[0018] If the lane change progress information reflects that the vehicle has not changed from the initial lane to a specific adjacent lane, then determine the candidate target object located in the preset lane to which the initial lane belongs, and the candidate target object located in the preset lane to which the specific adjacent lane belongs to obtain the collision risk object of the vehicle;

[0019] Perform a prediction process on the collision risk between the vehicle and the collision risk object to obtain a collision risk prediction result between the vehicle and the collision risk object.

[0020] Further, in some embodiments, before generating a collision risk prediction result between the collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle, it further includes:

[0021] Generate the lane change progress information of the vehicle according to whether the preset position of the vehicle body moves from the initial lane to the specific adjacent lane, and / or whether the area ratio or area difference between the area where the vehicle body is located in the initial lane and the area where the vehicle body is located in the specific adjacent lane is within a preset value range.

[0022] Further, in some embodiments, generating a lane change process control instruction for the vehicle based on the collision risk prediction result includes:

[0023] If it is determined based on the collision risk prediction result that there is a collision risk object having a collision risk with the vehicle, then generate a shutdown control instruction for the lane change assist function, or generate a driving control instruction for reducing the collision risk, or generate a display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver.

[0024] Further, in some embodiments, after generating a display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver, it further includes:

[0025] Send a display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver to the information display device of the vehicle; wherein, the information display device is used to display at least one of the risk prompt information and the takeover vehicle prompt information.

[0026] Further, in some embodiments, before generating a lane change process control instruction for the vehicle based on the collision risk prediction result, it further includes:

[0027] Determine the initial target object located outside the preset lane as a safe object having no collision risk with the vehicle.

[0028] On the other hand, the present invention also provides a computer program product, which includes a computer program, and when the computer program is executed, the steps of the above method are implemented.

[0029] On the other hand, the present invention also provides an electronic device, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the steps of the above method.

[0030] Further, in some embodiments, the electronic device includes at least one of an image acquisition device, a radar device, and a domain controller.

[0031] According to the vehicle control method provided by the present invention, after the lane change assist function of the vehicle is activated, candidate target objects located in the lane where the vehicle is located and the adjacent lanes of the vehicle can be first screened out from the initial target objects existing around the vehicle; then, according to the information on the progress of the vehicle's lane change, collision risk objects that have a relatively high impact on the safety of the vehicle can be accurately screened out from the candidate target objects, so as to control the vehicle's lane change process according to the collision risk prediction result between the vehicle and the above-mentioned collision risk objects, thereby being able to effectively ensure the safety of the vehicle's lane change process and reduce the interference caused to the operation process of the vehicle's lane change assist function by target objects with relatively small influence on the vehicle's lane change process, which is beneficial to improving the operation stability and reliability of the vehicle's lane change assist function.

[0032] It should be understood that the content described in the Summary of the Invention section is not intended to limit the key or important features of the embodiments of the present invention, nor to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Brief Description of the Drawings

[0033] Figure 1 A schematic diagram of a vehicle driving scenario provided by an embodiment of the present invention;

[0034] Figure 2 A flowchart of a vehicle control method provided by an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed Description of the Embodiments

[0036] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0037] In the description of one or more embodiments of the present invention, the terms "including" and its like shall be understood as open inclusion, that is, "including but not limited to". The term "based on" shall be understood as "at least partially based on". The term "one embodiment" or "the embodiment" shall be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. There may also be other explicit and implicit definitions below.

[0038] At present, automobiles are gradually equipped with some lane-changing assist functions to automatically control the vehicle to change lanes, thereby improving the operation convenience and safety of the driver during driving. However, when the current lane-changing assist function of an automobile is running, it can usually accurately identify the probability of the existence of a target object in the lane where the vehicle is located or in the adjacent lane of the vehicle, but it cannot accurately identify the probability of the existence of the target object in other lanes. At this time, in order to ensure the comprehensiveness of the identification of the collision risk that the vehicle may face, these target objects outside the scope of the lane where the vehicle is located and the adjacent lane of the vehicle will be directly regarded as the collision risk objects of the vehicle, and the longitudinal collision risk between these collision risk objects and the vehicle will be combined to control the lane-changing process of the vehicle.

[0039] However, since the lateral distance between these target objects outside the scope of the lane where the vehicle is located and the adjacent lane of the vehicle and the vehicle is relatively far, the risk that these target objects can bring to the lane-changing process of the vehicle is actually small. As a result, the vehicle is easily interfered by the longitudinal collision risk between these target objects and the vehicle, and wrongly aborts the execution of the lane-changing assist function, making the vehicle unable to successfully complete the lane change, and affecting the operation stability and reliability of the lane-changing assist function of the vehicle.

[0040] Figure 1 A schematic diagram of a vehicle driving scenario provided by an embodiment of the present invention; for the convenience of understanding, the current vehicle lane-changing control scheme is illustrated by way of example in combination with Figure 1 the content therein. As Figure 1 shown, it is assumed that the road where vehicle 101 is located includes five lanes such as lane 11-15 arranged from left to right, and the lane-changing assist function of vehicle 101 needs to control vehicle 101 to change from the initial lane 13 to the specific adjacent lane 12. Then, the lane-changing assist function can regard the target objects (for example, object 102 and object 103) with a probability of existence greater than the threshold value included in the initial lane 13 and the specific adjacent lane 12 as collision risk objects. In addition, the target objects (for example, object 105, object 106 and object 107) included in lanes 11 and 15 outside the lane 13 where vehicle 101 is located and the adjacent lanes on both sides (for example, lane 12 and lane 14) will also be regarded as collision risk objects. If the longitudinal collision probability between any collision risk object and vehicle 101 reaches the preset probability, the operation of the lane-changing assist function can be aborted.

[0041] However, since the lateral distance between the target objects in lane 11 and lane 15 and vehicle 101 is relatively large, even if they are driving side by side, it often does not pose a great risk to the lane-changing process of vehicle 101. However, at this time, because the longitudinal collision probability between the two reaches the preset probability, the operation of the lane-changing assistance function at vehicle 101 is wrongly aborted, making it impossible for vehicle 101 to successfully complete the lane change, thus easily affecting the operation stability and reliability of the lane-changing assistance function.

[0042] Based on this, the present invention proposes a vehicle control method. After the lane-changing assistance function of the vehicle is activated, this method can first screen out candidate target objects located in the lane where the vehicle is located and the adjacent lanes of the vehicle from the initial target objects existing around the vehicle. Then, according to the lane change progress information of the vehicle, it can accurately screen out the collision risk objects that will have a high impact on the safety of the vehicle from the candidate target objects, so as to control the lane change process of the vehicle according to the collision risk prediction result between the vehicle and the above-mentioned collision risk objects, thereby being able to effectively ensure the safety of the vehicle's lane change process and reduce the interference caused by the target objects with less impact on the vehicle's lane change process to the operation process of the vehicle's lane-changing assistance function, which is beneficial to improving the operation stability and reliability of the vehicle's lane-changing assistance function.

[0043] Please refer to Figure 2 , which is a schematic flowchart of a vehicle control method provided by an embodiment of the present invention. From a program perspective, the execution subject of this process can be an application program installed on a vehicle, a vehicle control device, a device for target detection at the vehicle, etc. Or, the execution subject of this process can also be a vehicle, a vehicle control device, a device for target detection at the vehicle, or other devices that can communicate with a vehicle, a vehicle control device, a device for target detection at the vehicle, etc., and no specific limitation is made thereto.

[0044] Next, for Figure 2 the process shown below, the vehicle control method can specifically include the following steps:

[0045] Step S202, after the lane-changing assistance function of the vehicle is activated, obtain the initial target objects existing around the vehicle.

[0046] In the embodiment of the present invention, the lane-changing assistance function can refer to a function that can automatically analyze the driving environment around the vehicle and can safely control the vehicle to change lanes to an adjacent lane. In practical applications, there can be various types of lane-changing assistance functions. For example, it can include an automatic lane change assistance function (Auto Lane Change, abbreviated as ALC function). Of course, it can also include other driving assistance functions that can achieve automatic control of the vehicle to change lanes, and no specific limitation is made thereto.

[0047] In practical applications, the lane change assist function of this vehicle can be activated when the preset function activation conditions are met. Among them, the preset function activation conditions can be set according to actual situations. For example, the vehicle's turn signal is in the lit state, the steering wheel angle of the vehicle reaches a preset angle, the change rate of the steering wheel angle of the vehicle reaches a preset rate, the lateral speed or lateral acceleration of the vehicle reaches a threshold value, etc. Specific limitations are not made in this regard.

[0048] In the embodiments of the present invention, in order to ensure the safety of the vehicle during the lane change process, it is usually necessary to sense the initial target objects existing around the vehicle, and combine the positions, running conditions, etc. of the vehicle itself and at least some of the initial target objects to evaluate the risks existing in the lane change process of the vehicle, and then control the lane change process of the vehicle.

[0049] Step S204: Determine candidate target objects located in the preset lane from the initial target objects; wherein, the preset lane includes the lane where the vehicle is located and the adjacent lanes of the vehicle.

[0050] In the embodiments of the present invention, since the initial target objects located in other lanes outside the lane where the vehicle is located and the adjacent lanes of the vehicle have a relatively large lateral distance from the vehicle, the risks brought by these initial target objects to the current lane change process of the vehicle are relatively small, so that it is often not necessary to evaluate the collision risks between these initial target objects and the vehicle. Based on this, these initial target objects located outside the lane where the vehicle is located and the adjacent lanes of the vehicle can be filtered out from the initial target objects existing around the vehicle, and the initial target objects located in the lane where the vehicle is located and the adjacent lanes of the vehicle are retained as candidate target objects, so as to further accurately screen out the collision risk objects that may bring relatively large risks to the vehicle's lane change process from the candidate target objects, and then evaluate the collision risks existing between the vehicle and the collision risk objects.

[0051] In the embodiments of the present invention, the lane where the vehicle is located and the adjacent lanes of the vehicle can be collectively referred to as the preset lane. Among them, the lane where the vehicle is located can refer to the lane where the vehicle is currently located. In practical applications, the lane where the centroid of the vehicle is located or the lane where the center point of the rear axle of the vehicle is located can be used as the lane where the vehicle is located. Of course, other strategies can also be used to determine the lane where the vehicle is located. Specific limitations are not made in this regard.

[0052] The adjacent lanes of the vehicle may include the directly adjacent lane on the left and the directly adjacent lane on the right of the lane where the vehicle is located. Of course, since when the lane change assist function controls the vehicle to change lanes to the left, the initial target objects in the directly adjacent lane on the right of the lane where the vehicle is located usually do not pose a great risk to the vehicle during the lane change process. Therefore, only the initial target objects in the directly adjacent lane on the left of the lane where the vehicle is located can be used as candidate target objects, and the initial target objects in the directly adjacent lane on the right of the lane where the vehicle is located are not used as candidate target objects, so that the adjacent lanes of the vehicle in the preset lanes can also include the directly adjacent lane on the left of the lane where the vehicle is located, and do not include the directly adjacent lane on the right of the lane where the vehicle is located. Similarly, when the lane change assist function controls the vehicle to change lanes to the right, the adjacent lanes of the vehicle in the preset lanes can also only include the directly adjacent lane on the right of the lane where the vehicle is located, and do not include the directly adjacent lane on the left of the lane where the vehicle is located, and no specific limitation is made on this.

[0053] Step S206: Generate a collision risk prediction result between the collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle.

[0054] In the embodiment of the present invention, the process of the lane change assist function of the vehicle controlling the vehicle to change lanes from the initial lane to a specific adjacent lane often includes multiple stages. For example, the stage where no part of the vehicle body enters the specific adjacent lane, the stage where part of the vehicle body enters the specific adjacent lane, the stage where all parts of the vehicle body enter the specific adjacent lane, etc. Since when a small part of the vehicle body enters the specific adjacent lane, the objects existing in the initial lane and the specific adjacent lane where the vehicle is located may pose a high risk to the safety of the vehicle, so the candidate target objects existing in the above lanes can be used as the collision risk objects of the vehicle; and when all parts of the vehicle body enter the specific adjacent lane, usually only the objects located in the specific adjacent lane will pose a high risk to the safety of the vehicle, so the candidate target objects currently existing in the specific adjacent lane can be used as the collision risk objects of the vehicle. It can be seen that when the vehicle is in different lane change progress situations, the target objects that can pose a collision risk to the vehicle may be different.

[0055] Based on this, according to the information on the progress of the lane change of the vehicle, after accurately screening out the collision risk objects that have a greater impact on the safety of the vehicle from the candidate target objects, the collision risk between the collision risk object and the vehicle can be predicted to obtain the collision risk prediction result between the two. There is no need to predict the collision risk prediction result between the vehicle and other target objects with lower risk in the candidate target objects. This is not only beneficial to saving computing resources, but also can avoid controlling the lane change process of the vehicle based on these target objects with lower risk, which is beneficial to ensuring the operation stability and reliability of the lane change assistance function of the vehicle.

[0056] Among them, the information on the progress of the lane change can be the information reflecting the completion of the lane change of the vehicle, which can be determined in combination with the position information of the vehicle relative to the initial lane and the specific adjacent lane. Of course, it can also be determined in combination with other operation data of the vehicle, and no specific limitation is made thereto.

[0057] It can be understood that the above initial lane can be the lane where the vehicle is located when the lane change assistance function is activated; and the specific adjacent lane can be the directly adjacent lane on the left or the directly adjacent lane on the right of the initial lane; and the specific adjacent lane can be determined in combination with the turn signal lit on the vehicle, the steering wheel angle of the vehicle, the lateral speed and lateral acceleration of the vehicle, etc., and no specific limitation is made thereto.

[0058] Step S208, generate a lane change process control instruction for the vehicle based on the collision risk prediction result.

[0059] In the embodiment of the present invention, the collision risk prediction result can usually reflect whether there is a collision risk between the vehicle and the collision risk object; of course, it can also more specifically reflect the type of collision risk and the severity of the collision risk between the two, which can be set according to the actual situation, and no specific limitation is made thereto.

[0060] In the embodiment of the present invention, since the lane change assistance function needs to avoid the vehicle from colliding with other target objects during the process of controlling the vehicle to automatically change lanes to ensure the safety of the vehicle and other traffic participants, based on this, a lane change process control instruction for controlling the lane change process of the vehicle and the collision risk faced by the vehicle can be generated according to the collision risk prediction result to ensure the safety of the lane change process of the vehicle.

[0061] Figure 2In the method, by accurately screening out the collision risk objects that have a high impact on the safety of the vehicle from the initial target objects around the vehicle, the lane change process of the vehicle is controlled according to the collision risk prediction result between the vehicle and the above-mentioned collision risk objects, so that on the basis of effectively ensuring the safety of the vehicle's lane change process, the interference caused by the target objects with less impact on the vehicle's lane change process to the operation process of the lane change assistance function of the vehicle can be reduced, which is beneficial to improving the operation stability and reliability of the lane change assistance function of the vehicle.

[0062] In a feasible implementation manner, the obtaining of the initial target objects existing around the vehicle may include:

[0063] Obtaining the position information of the initial target objects obtained by processing the image of the vehicle's surrounding environment collected by the image acquisition device. Or,

[0064] Obtaining the position information of the initial target objects obtained by processing the perception data of the vehicle's surrounding environment collected by the radar device. Or,

[0065] Obtaining the position information of the initial target objects obtained by processing the perception data of the vehicle's surrounding environment collected by the radar device and the image of the vehicle's surrounding environment collected by the image acquisition device.

[0066] In the embodiment of the present invention, if the vehicle is equipped with an image acquisition device capable of collecting the image of the vehicle's surrounding environment, the image of the vehicle's surrounding environment collected by the image acquisition device can be subjected to target detection processing to obtain the position information of the initial target objects existing around the vehicle. Or, if the vehicle is equipped with a radar device capable of environmental perception, the radar device can be used to collect data for the surrounding area of the vehicle, and by performing radar target detection on the perception data of the vehicle's surrounding environment collected by it, the position information of the initial target objects existing around the vehicle can also be obtained.

[0067] Of course, it is also possible to perform collaborative analysis and processing on the data collected by the radar device and the image acquisition device installed on the vehicle, etc., to obtain the position information of the initial target objects existing around the vehicle. In practical applications, the data collected by the radar device and the image acquisition device can be first subjected to target detection processing respectively to obtain two groups of target objects to be fused; then, the multiple target objects to be fused belonging to the same target in these two groups of target objects to be fused are subjected to fusion processing, so as to obtain reliable initial target objects existing in the surrounding area of the vehicle; or, the data collected by the radar device and the image acquisition device can also be input into a pre-trained artificial intelligence model, so that the artificial intelligence model can generate reliable initial target objects existing around the vehicle in combination with the above data, which is efficient and convenient; no specific limitation is made on this.

[0068] In a feasible implementation manner, determining a candidate target object located within a preset lane from the initial target objects may include:

[0069] Analyze and process at least one of the surrounding environment image of the vehicle, the historical driving trajectory data of the vehicle, and the target driving trajectory data of the vehicle to obtain at least one of the position information of the preset lane within a preset distance in front of the vehicle and the position information of the preset lane within a specified distance behind the vehicle.

[0070] If it is determined that the initial target object is located within the preset lane according to the position information of the preset lane and the position information of the initial target object, then the initial target object is determined as the candidate target object.

[0071] In the embodiments of the present invention, since a vehicle usually travels in a lane, and the width of each lane is usually within a certain range, the historical driving trajectory data of the vehicle can, to a certain extent, reflect the location of the lane where the vehicle has driven through; while the target driving trajectory data of the vehicle can, to a certain extent, reflect the location of the lane where the vehicle is about to drive through. Based on this, the position information of the preset lane within a specified distance behind the vehicle can be generated by combining the historical driving trajectory data of the vehicle, and the position information of the preset lane within a preset distance in front of the vehicle can be generated by combining the target driving trajectory data of the vehicle.

[0072] In addition, since target detection and affine transformation processing are performed on the surrounding environment image of the vehicle collected by the in-vehicle image acquisition device, the data of the lane lines existing around the vehicle can be accurately determined, so that the position information of the preset lane within a preset distance in front of the vehicle can be determined according to the surrounding environment image of the vehicle, and the position information of the preset lane within a specified distance behind the vehicle can be obtained by extending the lane lines of the preset lane in front of the vehicle in a parallel manner towards the rear of the vehicle.

[0073] Specifically, when the surrounding environment image of the vehicle obtained is an image of the front area of the vehicle, the position data of the lane lines existing in front of the vehicle can be determined through image processing technology. Subsequently, according to the position data of the lane line closest to the vehicle (for example, a lane line in the form of a straight line N meters forward from the center point of the rear axle of the vehicle, where N is usually a relatively small value), the straight-line lane line can be extended in a parallel manner towards the rear of the vehicle to a specified distance to serve as the lane line existing within a specified distance behind the vehicle, and then the position information of the preset lane existing within a specified distance behind the vehicle can be determined, which is convenient and fast.

[0074] Of course, it is also possible to comprehensively analyze and determine the position information of a preset lane within a preset distance in front of or a specified distance behind the vehicle by combining the surrounding environment image of the vehicle, the historical driving trajectory data of the vehicle, and the target driving trajectory data of the vehicle, etc. No specific limitation is imposed thereon. Among them, the preset distance and the specified distance can be set according to actual needs, but generally, the numerical value should not be too large. For example, it can be several meters or a dozen meters, and no specific limitation is imposed thereon.

[0075] In an embodiment of the present invention, the position information of the preset lane obtained and the position information of the initial target object can be data in the same coordinate system. Therefore, by combining the above data, it is possible to accurately and conveniently determine whether each initial target object is located in the preset lane. If so, the initial target object can be determined as the candidate target object. In practical applications, it is often also possible to determine the existence probability of each initial target object in each preset lane. Thus, when the existence probability of an initial target object in a certain preset lane reaches a threshold value, it can be considered that the initial target object is located in that preset lane. No specific limitation is imposed thereon.

[0076] In a feasible implementation manner, before generating a lane change process control instruction for the vehicle based on the collision risk prediction result, it may further include:

[0077] Determine the initial target object located outside the preset lane as a safe object that does not have a collision risk with the vehicle.

[0078] In an embodiment of the present invention, since the current lane change assist function usually cannot accurately calculate the existence probability of a target object located outside the preset lane (i.e., the lane where the vehicle is located and the adjacent lane of the vehicle) at each lane, such target objects are often directly regarded as collision risk objects of the vehicle to avoid missing the collision risk of the vehicle. However, since the lateral distance between the target object located outside the preset lane and the vehicle is relatively far, the risk it brings to the lane change process of the vehicle is usually small. Therefore, it should not be regarded as a collision risk object of the vehicle. Based on this, in the solution provided in the present invention, after identifying the initial target object located outside the preset lane, it can be determined as a safe object that does not have a collision risk with the vehicle, so that it will not interfere with the lane change process of the vehicle, which is beneficial to ensuring the operation stability and reliability of the lane change assist function of the vehicle.

[0079] In practical applications, a preset identifier or preset attribute can be added to an initial target object located outside the preset lane to indicate that it is a safe object that does not pose a collision risk to the vehicle itself. Of course, other methods can also be used to enable the lane change assistance function of the vehicle not to perform lane change control based on the collision risk between the initial target object located outside the preset lane and the vehicle itself, so as to achieve the effect of regarding it as a safe object that does not pose a collision risk to the vehicle itself. No specific limitation is made in this regard.

[0080] In a feasible implementation manner, the generating a collision risk prediction result between the collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle may include:

[0081] If the lane change progress information reflects that the vehicle has changed from the initial lane to a specific adjacent lane, then determine the candidate target objects located within the preset lane that belongs to the same lane as the specific adjacent lane, to obtain the collision risk objects of the vehicle.

[0082] If the lane change progress information reflects that the vehicle has not changed from the initial lane to a specific adjacent lane, then determine the candidate target objects located within the preset lane that belongs to the same lane as the initial lane, and, the candidate target objects located within the preset lane that belongs to the same lane as the specific adjacent lane, to obtain the collision risk objects of the vehicle.

[0083] Perform a prediction process on the collision risk between the vehicle and the collision risk objects to obtain a collision risk prediction result between the vehicle and the collision risk objects.

[0084] In the embodiment of the present invention, since when the lane change progress information reflects that the vehicle has changed from the initial lane to a specific adjacent lane, the vehicle usually keeps driving within the specific adjacent lane, so that the objects currently located within the specific adjacent lane will bring greater risks to the driving process of the vehicle. Therefore, the candidate target objects currently located within the preset lane that belongs to the same lane as the specific adjacent lane can be used as the collision risk objects of the vehicle, without using the candidate target objects within other preset lanes as the collision risk objects of the vehicle, which is beneficial to improving the accuracy of the selected collision risk objects.

[0085] When the information on the progress of the lane change indicates that the vehicle has not yet changed from the initial lane to the specific adjacent lane, the vehicle usually continues to change lanes into the specific adjacent lane. As a result, objects currently in the specific adjacent lane and the vehicle's initial lane will both pose a significant risk to the vehicle's driving process. Therefore, candidate target objects currently in a preset lane that belongs to the same lane as the specific adjacent lane and the initial lane respectively can be regarded as the vehicle's collision risk objects, without considering candidate target objects in other preset lanes. This is beneficial to improving the accuracy of the selected collision risk objects.

[0086] For ease of understanding, an example of the vehicle's collision risk objects will be given here in combination with Figure 1 the content in Figure 1 As shown in the figure, assume that vehicle 101 changes lanes from lane 13 to lane 12. If vehicle 101 has changed from the initial lane (i.e., lane 13) to the specific adjacent lane (i.e., lane 12), then the candidate target object in lane 12 (e.g., object 103) can be regarded as the vehicle's collision risk object. If vehicle 101 has not changed from the initial lane (i.e., lane 13) to the specific adjacent lane (i.e., lane 12), then the candidate target object in lane 12 (e.g., object 103) and the candidate target object in lane 13 (e.g., object 102) can be jointly regarded as the vehicle's collision risk objects.

[0087] Of course, if the candidate target objects initially selected from the initial target objects around the vehicle are only the target objects within a specified distance behind the vehicle, then when vehicle 101 has not changed from the initial lane (i.e., lane 13) to the specific adjacent lane (i.e., lane 12), since the object 102 in front of vehicle 101 in lane 13 does not belong to the candidate target objects, and the object 103 behind vehicle 101 in lane 12 belongs to the candidate target objects, at this time, only the object 103 that belongs to the candidate target objects can also be regarded as the vehicle's collision risk object.

[0088] Similarly, if the candidate target objects initially selected from the initial target objects around the vehicle are only the target objects within a preset distance in front of the vehicle, then when vehicle 101 has not changed from the initial lane (i.e., lane 13) to the specific adjacent lane (i.e., lane 12), since the object 102 in front of vehicle 101 in lane 13 belongs to the candidate target objects, and the object 103 behind vehicle 101 in lane 12 does not belong to the candidate target objects, at this time, only the object 102 that belongs to the candidate target objects can also be regarded as the vehicle's collision risk object.

[0089] In practical applications, when the lane change assist function at the vehicle uses a three-lane model (including the lane where the vehicle is located and the adjacent lanes to the vehicle mentioned in step S204) to control the vehicle to change lanes, as the vehicle moves left or right, the actual lanes corresponding to the lane where the vehicle is located and the adjacent lanes to the vehicle included in the three-lane model may change. For example, when the vehicle changes lanes from the initial lane to the adjacent lane on the left, as the vehicle continuously moves left, the lane where the vehicle is located included in the three-lane model may change from the initial lane to the adjacent lane on the left; and the right lane of the vehicle in the three-lane model may change from the right lane of the initial lane to the initial lane. Based on this, it is necessary to determine the corresponding relationship between each preset lane mentioned in step S204, the initial lane of the vehicle, and the specific adjacent lane to which the vehicle needs to change lanes, so as to accurately screen out the collision risk objects of the vehicle from the candidate target objects currently included in each preset lane, which will not be elaborated here.

[0090] In an embodiment of the present invention, usually, the position information of the vehicle and the collision risk object respectively and their respective operation data (for example, moving speed, moving acceleration, and running direction) can be combined to estimate the longitudinal collision probability and / or lateral collision probability between the two, and when the longitudinal collision probability and / or lateral collision probability between the two reach a preset probability, a collision risk prediction result indicating that there is a collision risk between the two can be generated. Otherwise, a collision risk prediction result indicating that there is no collision risk between the two can be generated, which is convenient and fast. Of course, other strategies can also be used to preset the collision risk between the vehicle and the collision risk object, and then obtain the collision risk prediction result between the collision risk object and the vehicle, which is not specifically limited here.

[0091] In a feasible implementation manner, before generating the collision risk prediction result between the collision risk object in the candidate target objects and the vehicle according to the lane change progress information of the vehicle, it may further include:

[0092] Generate the lane change progress information of the vehicle according to whether the preset position of the vehicle body moves from the initial lane to the specific adjacent lane, and / or whether the area ratio or area difference between the area where the vehicle body is located in the initial lane and the area where the vehicle body is located in the specific adjacent lane is within a preset value range.

[0093] In the embodiment of the present invention, after moving from the initial lane to the specific adjacent lane at a preset position on the vehicle body of the vehicle, information on the progress of the lane change indicating that the vehicle has changed from the initial lane to the specific adjacent lane can be generated; alternatively, when the ratio or difference in area between the area of the vehicle body in the initial lane and the area of the vehicle body in the specific adjacent lane is within a preset numerical range, information on the progress of the lane change indicating that the vehicle has changed from the initial lane to the specific adjacent lane can be generated, which has good flexibility.

[0094] Among them, the preset position on the vehicle body of the vehicle can be set according to actual needs. For example, it can be the center point of the rear axle of the vehicle, the center of mass of the vehicle, the left / right end points of the rear bumper of the vehicle, etc., and no specific limitation is made thereto. The preset numerical range can also be set according to actual needs. For example, the preset numerical range corresponding to the above-mentioned area ratio can be [0, X], where X is generally a decimal with a relatively small value less than 1, and the preset numerical range corresponding to the above-mentioned area difference can be [Y, Z], where Y is generally a negative number, and Z can be 1 / M of the area of the vehicle body of the vehicle, and no specific limitation is made thereto.

[0095] In a feasible implementation manner, generating a lane change process control instruction for the vehicle based on the collision risk prediction result may include:

[0096] If it is determined based on the collision risk prediction result that there is a collision risk object having a collision risk with the vehicle, then a shutdown control instruction for the lane change assist function is generated, or a driving control instruction for reducing the collision risk is generated, or a display instruction for at least one of a risk prompt message for the collision risk and a takeover vehicle prompt message for the driver is generated.

[0097] In the embodiment of the present invention, when the lane change process control instruction is a shutdown control instruction for the lane change assist function, the vehicle can respond to the shutdown control instruction to exit the lane change assist function, and subsequently, the driver of the vehicle can drive the vehicle by himself / herself, which is beneficial to ensuring the driving intention of the driver.

[0098] When the lane change process control instruction is a driving control instruction for reducing the collision risk, the driving control instruction can be an instruction for controlling the vehicle to accelerate, decelerate, turn left or right, etc., so as to control the vehicle to move away from the collision risk object having a collision risk with it, which is beneficial to ensuring the safety of the passengers in the vehicle.

[0099] When the lane change process control instruction is a display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver, the vehicle can respond to the display instruction to display the above-mentioned risk prompt information and takeover vehicle prompt information, so that the driver of the vehicle can perceive that the vehicle is facing a collision risk or know that they need to drive the vehicle by themselves currently, so that the driver can perform operations to avoid the collision risk, with good flexibility.

[0100] It can be understood that the lane change process control instruction can also be other forms of instructions for managing the lane change process of the vehicle or the collision risk faced by the vehicle, and specific limitations are not made here.

[0101] In a feasible implementation manner, after generating the display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver, it may further include:

[0102] Sending the display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver to the information display device of the vehicle; wherein, the information display device is used to display at least one of the risk prompt information and the takeover vehicle prompt information.

[0103] In the embodiments of the present invention, the information display device may include the human machine interface (HMI), headlight device, audio device, vibration device, etc. of the vehicle, so as to display the risk prompt information and the takeover vehicle prompt information in the form of text, light, audio or vibration, with good flexibility and beneficial to improving the user experience.

[0104] The present invention also provides a computer program product, which includes a computer program. When the computer program is executed, it realizes the steps of the vehicle control method in the above-mentioned embodiments. The specific execution process can refer to the specific descriptions in the above-mentioned embodiments and will not be elaborated here.

[0105] In one embodiment, the present invention also provides Figure 3 The structural schematic diagram of the electronic device shown. As Figure 3 shown, at the hardware level, the electronic device may include a processor 31 and a memory 35. Of course, it may also include an internal bus 32, a network interface 33, a memory 34, and other hardware required for other services. The processor 31 can read the corresponding computer program from the memory 35 into the memory and then run it to implement the above-mentioned vehicle control method. The specific execution process can refer to the specific descriptions in the above-mentioned embodiments and will not be elaborated here.

[0106] In a feasible implementation, the electronic device may include at least one of an image acquisition device, a radar device, and a domain controller. Of course, the electronic device may also include other in-vehicle devices or remote devices capable of communicating with the vehicle, and no specific limitations are imposed thereon.

[0107] Finally, the embodiments of the present invention are all described in a progressive manner. For the same or similar parts among the embodiments, reference may be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for embodiments such as computer program products and electronic devices, since they are basically similar to the method embodiments, the description is relatively simple, and reference may be made to the partial description of the method embodiments for the relevant parts.

[0108] The above description is only for the embodiments of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and changes can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A vehicle control method, comprising: After the lane change assist function of the vehicle is activated, obtaining initial target objects existing around the vehicle; Determining candidate target objects located within a preset lane from the initial target objects; wherein the preset lane includes the lane where the vehicle is located and the adjacent lanes of the vehicle; Generating a collision risk prediction result between a collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle; Generating a lane change process control instruction for the vehicle based on the collision risk prediction result.

2. The method according to claim 1, wherein the obtaining of the initial target objects existing around the vehicle comprises: Obtaining the position information of the initial target objects obtained by processing the surrounding environment image of the vehicle collected by an image acquisition device; Or, Obtaining the position information of the initial target objects obtained by processing the surrounding environment perception data of the vehicle collected by a radar device; Or, Obtaining the position information of the initial target objects obtained by processing the surrounding environment perception data of the vehicle collected by a radar device and the surrounding environment image of the vehicle collected by an image acquisition device.

3. The method according to claim 2, wherein the determining of the candidate target objects located within the preset lane from the initial target objects comprises: Analyzing and processing at least one of the surrounding environment image of the vehicle, the historical driving trajectory data of the vehicle, and the target driving trajectory data of the vehicle to obtain at least one of the position information of the preset lane within a preset distance in front of the vehicle and the position information of the preset lane within a specified distance behind the vehicle; If it is determined that the initial target object is located within the preset lane according to the position information of the preset lane and the position information of the initial target object, then determining the initial target object as the candidate target object.

4. The method according to claim 1, wherein the generating of the collision risk prediction result between the collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle comprises: If the lane change progress information indicates that the vehicle has changed from the initial lane to a specific adjacent lane, then determining the candidate target objects located within the preset lane that belongs to the same lane as the specific adjacent lane to obtain the collision risk objects of the vehicle; If the lane change progress information indicates that the vehicle has not changed from the initial lane to a specific adjacent lane, then determining the candidate target objects located within the preset lane that belongs to the same lane as the initial lane and the candidate target objects located within the preset lane that belongs to the same lane as the specific adjacent lane to obtain the collision risk objects of the vehicle; Performing a prediction process on the collision risk between the vehicle and the collision risk objects to obtain a collision risk prediction result between the vehicle and the collision risk objects.

5. The method according to claim 4, before the generating of the collision risk prediction result between the collision risk object among the candidate target objects and the vehicle according to the lane change progress information of the vehicle, further comprising: Generate the lane change progress information of the vehicle according to whether the preset position of the vehicle body of the vehicle moves from the initial lane to the specific adjacent lane, and / or whether the area ratio or area difference between the area where the vehicle body is located in the initial lane and the area where the vehicle body is located in the specific adjacent lane is within a preset value range.

6. The method according to claim 1, wherein generating the lane change process control instruction for the vehicle based on the collision risk prediction result includes: If it is determined based on the collision risk prediction result that there is a collision risk object having a collision risk with the vehicle, then generate a shutdown control instruction for the lane change assist function, or generate a driving control instruction for reducing the collision risk, or generate a display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver.

7. The method according to claim 6, after generating the display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver, further includes: Send the display instruction for at least one of the risk prompt information for the collision risk and the takeover vehicle prompt information for the driver to the information display device of the vehicle; wherein, the information display device is used to display at least one of the risk prompt information and the takeover vehicle prompt information.

8. The method according to any one of claims 1-7, before generating the lane change process control instruction for the vehicle based on the collision risk prediction result, further includes: Determine the initial target object located outside the preset lane as a safe object having no collision risk with the vehicle.

9. A computer program product, which includes a computer program, and when the computer program is executed, it implements the steps of the method according to any one of claims 1-8.

10. An electronic device, comprising: A processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the steps of the method according to any one of claims 1-8.

11. The electronic device according to claim 10, wherein the electronic device includes at least one of an image acquisition device, a radar device, and a domain controller.

Images