Target screening method, vehicle motion control method, domain controller and computer program product

Abstract

The invention provides a target screening method, a vehicle motion control method, a domain controller and a computer program product, according to the target screening method provided by the invention, when motion control is carried out on a vehicle based on environmental perception data, a target object obtained based on environmental perception data detection is obtained, and the target object is screened. The environment sensing data comprises point cloud data acquired based on a radar, determining a reflection point set corresponding to the target object in the point cloud data, determining a lowest height value corresponding to a lowest height reflection point in the reflection point set, and when the lowest height value is higher than a preset height threshold value, sending the target object to the target object. And determining the target object as the false target object, so that the false target object sensed by the environment can be distinguished, vehicle motion control based on the false target object is avoided, and the accuracy and safety of vehicle motion control are improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a target selection method, a vehicle motion control method, a domain controller, and a computer program product. Background Technology

[0002] With the advancement and development of technology, more and more vehicles are equipped with driver assistance systems. These systems use sensors installed in the vehicle to perceive the surrounding environment, identify traffic conditions, and automatically control the vehicle's movement based on the perception results, such as braking control, steering control, and acceleration / deceleration control.

[0003] In related technologies, radar sensors and vision sensors are typically used to perceive and identify the vehicle's surrounding environment. However, vision sensors are highly dependent on changes in ambient light and shadow. When the ambient light changes significantly, vision sensors are prone to identifying non-existent false targets. If the driver assistance system uses these false targets to control the vehicle's motion, it will lead to incorrect control results, affecting the driver's driving experience and vehicle usage experience, and in severe cases, even causing safety accidents. Summary of the Invention

[0004] Based on this, the present invention provides a target screening method, a vehicle motion control method, a domain controller, and a computer program product. By using this target screening method and vehicle motion control method, when performing vehicle motion control based on environmental perception data, false target objects detected by environmental perception data can be screened out, thereby avoiding vehicle motion control based on false target objects and improving the accuracy and safety of vehicle motion control.

[0005] On one hand, the present invention provides a target screening method, comprising:

[0006] Acquire target objects detected based on environmental perception data, wherein the environmental perception data includes point cloud data collected by radar;

[0007] In the point cloud data, determine the set of reflection points corresponding to the target object, and in the set of reflection points, determine the minimum height value corresponding to the lowest height reflection point;

[0008] When the minimum height value is higher than a preset height threshold, the target object is determined to be a false target object.

[0009] Furthermore, in some embodiments, the method further includes:

[0010] Obtain the radar cross section corresponding to the target object;

[0011] The step of determining the target object as a false target object when the minimum height value is higher than a preset height threshold includes:

[0012] When the minimum height value is higher than a preset height threshold and the radar cross section is less than a preset radar cross section threshold, the target object is determined to be a false target object.

[0013] Furthermore, in some embodiments, determining the target object as a false target object when the minimum height value is higher than a preset height threshold and the radar cross-section is less than a preset radar cross-section threshold includes:

[0014] When the minimum altitude value is higher than a preset altitude threshold, the radar cross section is less than a preset radar cross section threshold, and the target object is a stationary target, the target object is determined to be a false target object.

[0015] Furthermore, in some embodiments, the environmental perception data also includes image data acquired by a camera, and the target object is detected by fusing the point cloud data and the image data.

[0016] Furthermore, in some embodiments, determining the set of reflection points corresponding to the target object in the point cloud data includes:

[0017] Obtain the visual detection result corresponding to the target object based on the image data;

[0018] In the point cloud data, determine the set of reflection points associated with the visual detection results.

[0019] Furthermore, in some embodiments, the set of reflection points includes attribute information of each reflection point, including the pitch angle and radial distance corresponding to the reflection point;

[0020] Determining the minimum height value corresponding to the lowest height reflection point in the set of reflection points includes:

[0021] The height value corresponding to each reflection point in the set of reflection points is determined based on the pitch angle and the radial distance.

[0022] Determine the lowest height value corresponding to the lowest height reflection point from the height values ​​corresponding to each of the reflection points.

[0023] On the other hand, the present invention also provides a vehicle motion control method, comprising:

[0024] Acquire target objects detected based on environmental perception data;

[0025] The target filtering method described above is used to determine whether the target object is a false target object;

[0026] If the target object is determined to be a false target object, the target object is discarded.

[0027] When it is determined that the target object is not a false target object, the vehicle's motion control is performed based on the target object.

[0028] Furthermore, in some embodiments, the motion control includes, but is not limited to, one or more of cruise control, emergency braking control, and automatic driving control.

[0029] On the other hand, the present invention also provides a domain controller, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the steps of the method described above.

[0030] On the other hand, the present invention also provides a computer program product having at least one instruction stored thereon, wherein the at least one instruction, when executed by a controller, implements the steps of the above-described acceleration compensation method and vehicle control method.

[0031] According to the target screening method and vehicle motion control method provided by the present invention, when performing motion control of a vehicle based on environmental perception data, a target object detected based on the environmental perception data is acquired. The environmental perception data includes point cloud data collected by radar. Then, a set of reflection points corresponding to the target object is determined in the point cloud data, and a minimum height value corresponding to the lowest height reflection point is determined in the set of reflection points. When the minimum height value is higher than a preset height threshold, the target object is determined to be a false target object. This can distinguish false target objects perceived by the environment, thereby avoiding vehicle motion control based on false target objects and improving the accuracy and safety of vehicle motion control.

[0032] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of the present invention, nor is it intended to restrict the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0033] Figure 1 A flowchart illustrating a target screening method provided in an embodiment of the present invention;

[0034] Figure 2 This is a flowchart illustrating a vehicle motion control method provided in an embodiment of the present invention.

[0035] Figure 3 This is a schematic diagram of the structure of a domain controller provided in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0037] In the description of one or more embodiments of the present invention, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0038] In driving scenarios, vehicles frequently encounter situations such as crossing bridges, tunnels, and traversing gantries. When a vehicle enters a bridge or tunnel, there are often dramatic changes in light and shadow. At this time, the vehicle's visual sensors may identify some non-existent false targets due to changes in light. If the driver assistance system makes motion control decisions based on these false targets, it will lead to incorrect control results, affecting the driver's driving experience and vehicle usage experience, and in severe cases, even causing safety accidents.

[0039] Based on this, the present invention proposes a target selection method and a vehicle motion control method. According to the target selection method and vehicle motion control method provided by the present invention, when performing vehicle motion control based on environmental perception data, the target object detected by the environmental perception data is obtained. The environmental perception data includes point cloud data collected by radar. Then, a set of reflection points corresponding to the target object is determined in the point cloud data, and the lowest height value corresponding to the lowest height reflection point is determined in the set of reflection points. When the lowest height value is higher than a preset height threshold, the target object is determined to be a false target object. This can distinguish false target objects perceived by the environment, thereby avoiding vehicle motion control based on false target objects and improving the accuracy and safety of vehicle motion control.

[0040] Please see Figure 1 This is a schematic flowchart of a target screening method provided in an embodiment of the present invention. The following section focuses on... Figure 1 The process shown will be described in detail. The target screening method may specifically include the following steps:

[0041] Step S102: Obtain the target object detected based on environmental perception data, including point cloud data collected by radar.

[0042] Environmental perception is the foundation of vehicle-assisted driving or autonomous driving technology. By using sensors such as radar and cameras to perceive the environmental information around the vehicle, the driving assistance system can automatically control the vehicle based on the environmental information.

[0043] Specifically, during vehicle operation, environmental perception sensors installed on the vehicle perceive the surrounding environment, obtaining real-time environmental perception data. Based on this sensor-collected data, target objects in the environment are detected. These target objects are those that affect the vehicle's movement, such as obstacles along the vehicle's path. The environmental perception data includes at least point cloud data collected by radar, which comprises multiple radar reflection points and their corresponding reflection point attributes.

[0044] In one feasible implementation, the radar can be a millimeter-wave radar. During vehicle operation, the millimeter-wave radar transmits millimeter-wave radio waves and receives the reflected echoes, obtaining point cloud data including information about each reflection point. By analyzing changes in the frequency of reflected waves at each reflection point in the point cloud data, it can detect whether there is a target object ahead, as well as information such as the distance and relative speed between the detected vehicle and the target object.

[0045] Optionally, the environmental perception data may also include image data acquired by cameras, thereby fusing image data acquired by cameras and point cloud data acquired by radar when detecting the environment around the vehicle.

[0046] Step S104: Determine the set of reflection points corresponding to the target object in the point cloud data, and determine the minimum height value corresponding to the lowest height reflection point in the set of reflection points;

[0047] Specifically, after obtaining the target object detected based on environmental perception data, the set of reflection points corresponding to the target object is determined based on the point cloud data collected by the radar. It can be understood that the radar emits several transmitted wave signals in one detection cycle. These transmitted wave signals are reflected upon contact with an object, and the radar receives the echo signals reflected from the object. Each echo signal can be used to determine a reflection point and its corresponding attribute information. These reflection points and their corresponding attribute information constitute the point cloud data. The point cloud data includes both the reflection point corresponding to the target object and other reflection points. In this embodiment, the authenticity of the detected target object is determined based on the reflection points corresponding to the target object in the point cloud data.

[0048] Furthermore, the lowest height value corresponding to the lowest height reflection point is determined in the set of reflection points. The lowest height reflection point is the reflection point with the lowest height in the set of reflection points, and the lowest height value can be the height of the reflection point from the ground.

[0049] Step S106: When the minimum height value is higher than the preset height threshold, the target object is determined to be a false target object.

[0050] Specifically, if the minimum height value exceeds a preset height threshold, the target object is determined to be a false target object. This is easy to understand: in driving scenarios such as bridges and tunnels, the point clouds corresponding to the bridge cross-section and the outer surface of the tunnel entrance, collected by radar, have reflection points above the ground at a certain height. When the height value of the lowest reflection point of the detected target object exceeds the preset height threshold, the detected target object is determined to be a false target object misidentified due to the bridge or tunnel.

[0051] The preset height threshold can be set according to actual needs, and one or more embodiments of the present invention do not limit the specific value of the preset height threshold.

[0052] Preferably, the preset height threshold can be 6.5 meters. That is, when the height of the lowest reflection point of the target object detected by the radar is higher than 6.5 meters, the detected target object is determined to be a false target object misidentified due to a bridge or tunnel.

[0053] In this embodiment of the invention, based on the height of the lowest height reflection point corresponding to the target object in the point cloud data, it is determined whether the target object is detected in driving scenarios such as entering the bottom of a bridge or inside a tunnel. If so, it can be determined as a false target object that is misidentified when the vehicle enters the bottom of a bridge or inside a tunnel, thereby avoiding vehicle motion control based on false target objects and improving the accuracy and safety of vehicle motion control.

[0054] In one embodiment, after acquiring the target object detected based on environmental perception data, the method further includes acquiring the radar cross-section corresponding to the target object.

[0055] Radar cross section (RCS) is a physical quantity that characterizes the intensity of the echo generated by a target under radar wave illumination. It refers to the ratio of the reflected power per unit solid angle in the radar incident direction to the power density of the target cross section. It is related to the electrical properties and geometry of the target object.

[0056] Furthermore, in this embodiment, a radar cross section threshold corresponding to the bridge and tunnel is predefined. When determining whether the detected target object is a false target object, step S106 can specifically be: when the minimum height value is higher than the preset height threshold and the radar cross section is less than the preset radar cross section threshold, the target object is determined to be a false target object.

[0057] It's easy to understand that the radar cross-section (RCS) of a bridge or tunnel differs from that of a real target. By setting a preset RCS threshold, when the minimum height is higher than a preset height threshold and the RCS is lower than the preset RCS threshold, the current scene is determined to be a bridge or tunnel scene. This identifies the target as a false target mistakenly identified when a vehicle enters the underside of a bridge or into a tunnel. RCS can improve the accuracy of identifying false targets.

[0058] Preferably, the preset radar cross-section threshold can be -2dB.

[0059] In one embodiment, step S106 may specifically be: when the minimum height value is higher than a preset height threshold, the radar cross section is less than a preset radar cross section threshold, and the target object is a stationary target, the target object is determined to be a false target object.

[0060] It's easy to understand that when the minimum height value is higher than a preset height threshold, the radar cross-section is lower than a preset radar cross-section threshold, and the target object is a stationary target, the current scene is determined to be a bridge or tunnel scene. This identifies the target object as a false target object mistakenly identified when a vehicle enters the bridge or tunnel. Having a stationary target further improves the accuracy of identifying false targets.

[0061] Whether a target is stationary can be determined based on the target's motion state detected by radar and / or cameras. When the target's velocity detected by radar and / or cameras is zero, the target is determined to be stationary.

[0062] In one embodiment, the environmental perception data also includes image data acquired by a camera, and the target object is detected by fusing point cloud data and image data.

[0063] The target selection method proposed in one or more embodiments of the present invention can be applied to vehicle systems that use a combination of radar and cameras for environmental perception. It performs fusion detection based on point cloud data acquired by radar and image data acquired by cameras to determine the corresponding target object. This target object is an object that affects the vehicle's movement, such as an obstacle in the vehicle's path.

[0064] In one embodiment, in step S104, determining the set of reflection points corresponding to the target object in the point cloud data can specifically be: obtaining the visual detection result corresponding to the target object obtained based on image data detection, and determining the set of reflection points associated with the visual detection result in the point cloud data.

[0065] In this context, visual detection results refer to the detection of target objects based on image data. Specifically, in schemes that fuse point cloud data acquired by radar and image data acquired by cameras to detect corresponding target objects, associated reflection points are typically determined in the point cloud data based on the relevant attributes of the target object detected in the image data. Multiple associated reflection points form the reflection point set. These relevant attributes include, but are not limited to, the target object's velocity, position, and distance.

[0066] Each reflection point in the reflection point set is a radar reflection point corresponding to the target object, thus the authenticity of the detected target object can be judged based on the reflection point corresponding to the target object.

[0067] In one embodiment, the set of reflection points includes attribute information of each reflection point, including the pitch angle and radial distance corresponding to the reflection point. Then, in step S104, the lowest height value corresponding to the lowest height reflection point is determined in the set of reflection points. Specifically, this can be done by: determining the height value corresponding to each reflection point in the set of reflection points based on the pitch angle and radial distance, and determining the lowest height value corresponding to the lowest height reflection point from the height values ​​corresponding to each reflection point.

[0068] It should be noted that the radar emits several transmitted wave signals in one detection cycle. These transmitted wave signals are reflected upon contact with an object, and the radar receives the echo signals reflected from the object. From each echo signal, a reflection point and its corresponding attribute information can be determined. These reflection points and their corresponding attribute information constitute point cloud data. The reflection point attributes include the elevation angle and radial distance corresponding to the reflection point.

[0069] In this embodiment, the height value corresponding to the reflection point can be determined based on the pitch angle and radial distance corresponding to the launch point, thereby determining the lowest height value among the height values ​​corresponding to each reflection point corresponding to the target object.

[0070] Please see Figure 2 This is a flowchart illustrating a vehicle motion control method provided in an embodiment of the present invention. The following section focuses on... Figure 2 The process shown will be described in detail. The vehicle motion control method may specifically include the following steps:

[0071] Step S202: Obtain the target object detected based on environmental perception data;

[0072] It should be noted that the vehicle motion control mentioned in the embodiments of the present invention refers to the automatic motion control of the vehicle implemented by the vehicle driving assistance system based on environmental perception data, such as braking control, steering control, acceleration and deceleration control, etc. In some embodiments, the driving assistance system may be an emergency braking system (AEB), an adaptive cruise control system (ACC), an automated driving assistance system, etc.

[0073] Specifically, when a vehicle automatically implements motion control based on environmental perception data through a driver assistance system, the system first acquires the target object detected based on the collected environmental perception data. This target object is an object that affects the vehicle's motion. Typically, when this target object is detected, the corresponding driver assistance system needs to make corresponding motion control decisions for the vehicle based on the target object. For example, the target object can be an obstacle located on the vehicle's driving path.

[0074] It should be further noted that the entity executing the vehicle motion control method proposed in one or more embodiments of the present invention can be a vehicle controller or domain controller equipped with the above-mentioned driving assistance system.

[0075] Step S204: Use the target screening method described above to determine whether the target object is a false target object;

[0076] Step S206: If the target object is determined to be a false target object, discard the target object;

[0077] Step S208: When it is determined that the target object is not a false target object, the motion control of the vehicle is performed based on the target object.

[0078] Specifically, after obtaining the target object, the target screening method proposed in the above embodiments is used to identify whether the target object is a false target object. If the target object is determined to be a false target object, the target object is discarded, that is, the vehicle is not subject to corresponding motion control based on the target object; if the target object is determined not to be a false target object, the vehicle's motion control is performed based on the target object.

[0079] Optionally, motion control includes, but is not limited to, cruise control, emergency braking control, and automatic driving control.

[0080] In this embodiment of the invention, when the vehicle automatically implements motion control based on environmental perception data through the driving assistance system, a target object detected based on the environmental perception data is acquired, and the target screening method proposed in the above embodiments is used to identify whether the target object is a false target object. If the target object is determined to be a false target object, the target object is discarded, that is, the vehicle is not subject to corresponding motion control based on the target object; if the target object is determined not to be a false target object, the vehicle's motion control is performed based on the target object. This can avoid vehicle motion control based on false target objects, thereby improving the accuracy and safety of vehicle motion control.

[0081] Furthermore, for vehicles equipped with AEB functionality, this embodiment of the invention identifies and discards false target objects by verifying whether the target object is a fake target object, thereby preventing the AEB function from being falsely triggered by false target objects, ensuring driving safety, and improving user experience.

[0082] The present invention also provides a storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described in the above embodiments of the target selection method and vehicle motion control method. For the specific execution process, please refer to the detailed description in the above embodiments, which will not be repeated here.

[0083] The present invention also provides a computer program product, which stores at least one instruction, the at least one instruction being loaded by the processor and executed as the target selection method and vehicle motion control method of the above embodiments. For the specific execution process, please refer to the specific descriptions in the above embodiments, which will not be repeated here.

[0084] In one embodiment, the present invention also provides Figure 3 The diagram shows the structure of a domain controller. Figure 3 At the hardware level, the domain controller includes a processor 21, an internal bus 22, a network interface 23, memory 24, and non-volatile memory 25, and may also include other hardware required for business operations. This domain controller can be installed in a vehicle, where the processor 21 reads the corresponding computer program from the non-volatile memory 25 into memory and then runs it to implement the aforementioned target selection method and vehicle motion control method.

[0085] Finally, the various embodiments in this invention are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0086] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for target screening, comprising: obtaining a target object detected based on environment perception data, the environment perception data comprising point cloud data collected based on radar; determining a set of reflection points corresponding to the target object in the point cloud data, and determining a lowest height value corresponding to a lowest height reflection point in the set of reflection points; when the lowest height value is higher than a preset height threshold, determining that the target object is a false target object. 2.The method of claim 1, further comprising: obtaining a radar cross section area corresponding to the target object; when the lowest height value is higher than the preset height threshold, determining that the target object is a false target object, comprising: when the lowest height value is higher than the preset height threshold and the radar cross section area is smaller than a preset radar cross section area threshold, determining that the target object is a false target object. 3.The method of claim 2, when the lowest height value is higher than the preset height threshold and the radar cross section area is smaller than the preset radar cross section area threshold, determining that the target object is a false target object, comprising: when the lowest height value is higher than the preset height threshold, the radar cross section area is smaller than the preset radar cross section area threshold, and the target object is a stationary target, determining that the target object is a false target object. 4.The method of claim 1, wherein the environment perception data further comprises image data collected based on a camera, and the target object is detected based on fusion of the point cloud data and the image data. 5.The method of claim 4, wherein determining a set of reflection points corresponding to the target object in the point cloud data, comprising: obtaining a visual detection result corresponding to the target object detected based on the image data; determining a set of reflection points associated with the visual detection result in the point cloud data. 6.The method of claim 1, wherein the set of reflection points comprises attribute information of each reflection point, the attribute information comprising a pitch angle and a radial distance corresponding to the reflection point; determining a lowest height value corresponding to a lowest height reflection point in the set of reflection points, comprising: determining a height value corresponding to each reflection point in the set of reflection points based on the pitch angle and the radial distance; determining a lowest height value corresponding to a lowest height reflection point in the height values corresponding to each reflection point. 7.A method for vehicle motion control, comprising: obtaining a target object detected based on environment perception data; determining whether the target object is a false target object by using the target screening method of any one of claims 1-6; when the target object is determined to be a false target object, discarding the target object; when the target object is determined not to be a false target object, performing motion control of a host vehicle based on the target object. 8.The method of claim 7, wherein the motion control comprises one or more of cruise control, emergency braking control, and automatic driving control.

9. A domain controller comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded and executed by the processor to perform the steps of the method according to any one of claims 1 to 8.

10. A computer program product having at least one instruction stored thereon, which, when executed by a controller, performs the steps of the method according to any one of claims 1 to 8.

Images