Method and device for determining target for determining lane occupancy within radar field of view in front of vehicle

Abstract

The invention provides a method for determining a target used for determining lane occupancy in a radar field of view in front of a vehicle. The method comprises the following steps: acquiring point cloud data of the target in the radar field of view in front of the vehicle; based on the point cloud data, determining a target micro-Doppler feature difference between at least two targets split from the target; and determining a target for determining lane occupancy from the at least two targets based on the target micro-Doppler feature difference. Through the method disclosed by the invention, the target for determining the lane occupancy can be quickly and accurately determined, the ACC system is promoted to make a correct vehicle control decision, and the user experience of the adaptive cruise control system is improved.

Description

Technical Field

[0001] This disclosure relates to the field of driver assistance technology, and more specifically, to a method and apparatus for determining lane occupancy targets within the radar field of view ahead of a vehicle. Background Technology

[0002] Adaptive cruise control (ACC) uses information detected by distance sensors (such as millimeter-wave radar or distance radar) and information about the vehicle's driving route determined by the vehicle's speed and yaw rate sensors to determine whether there are vehicles traveling ahead in the same lane. When there are no vehicles ahead, it maintains the set speed as with normal cruise control; when a vehicle appears ahead, it travels at a speed lower than the set speed to maintain a safe distance from the vehicle in front. Summary of the Invention

[0003] This disclosure provides a scheme for determining a target within the radar field of view in front of a vehicle to determine lane occupancy. Using this scheme, based on point cloud data of at least two targets split from a single target, one of the at least two targets is identified as the target for determining lane occupancy. Subsequently, based on the vehicle's lane occupancy status of the target used to determine lane occupancy, the adaptive cruise control system is controlled to make lane occupancy response decisions, thereby improving the user experience of the adaptive cruise control system.

[0004] According to one aspect of this disclosure, a method is provided for determining a target within a radar field of view in front of a vehicle for determining lane occupancy, comprising: acquiring point cloud data of the target within the radar field of view in front of the vehicle; determining, based on the point cloud data, the target micro-Doppler feature difference between at least two targets split from the target; and determining, based on the target micro-Doppler feature difference, the target for determining lane occupancy from the at least two targets.

[0005] According to another aspect of this disclosure, an apparatus is provided for determining a target for lane occupancy within a radar field of view ahead of a vehicle, comprising: a point cloud data acquisition module configured to acquire point cloud data of a target within the radar field of view ahead of the vehicle; a target micro-Doppler feature difference determination module configured to determine, based on the point cloud data, a target micro-Doppler feature difference between at least two targets split from the target; and a lane occupancy target determination module configured to determine, based on the target micro-Doppler feature difference, a target for determining lane occupancy from at least two targets.

[0006] According to another aspect of this disclosure, a control method for an adaptive cruise system is provided, comprising: determining, according to the aforementioned method, a target for determining lane occupancy from at least two targets, wherein the at least two targets are derived from targets within the radar field of view in front of the vehicle; determining the vehicle's lane occupancy of the target for determining lane occupancy; and, in response to the vehicle's lane being occupied, controlling the adaptive cruise system to make a lane occupancy response decision.

[0007] According to another aspect of this disclosure, a control device for an adaptive cruise control system is provided, comprising: a lane occupancy target determination module configured to determine a target for determining lane occupancy from at least two targets according to the aforementioned method, wherein the at least two targets are split from targets within the radar field of view in front of the vehicle; a lane occupancy determination module configured to determine the vehicle's lane occupancy of the target for determining lane occupancy; and an occupancy response decision module configured to control the adaptive cruise control system to make a lane occupancy response decision in response to the vehicle's lane being occupied.

[0008] According to another aspect of this disclosure, an apparatus for determining lane occupancy targets within a radar field of view ahead of a vehicle includes: a memory storing a computer program thereon; and at least one processor coupled to the memory, the at least one processor being configured to execute the computer program to implement the aforementioned method.

[0009] According to another aspect of this disclosure, a computer program product includes a computer program / instructions that, when executed by a processor, implement the aforementioned method. Attached Figure Description

[0010] Various embodiments of the claimed subject matter will now be described by way of example with reference to the accompanying drawings. In the different drawings, the same reference numerals are used to denote the same or similar parts.

[0011] Figure 1 A schematic diagram of a vehicle and road according to one embodiment of the present disclosure is shown.

[0012] Figure 2 A schematic diagram is shown in a practical radar system according to an embodiment of the present disclosure, illustrating a single forward vehicle splitting into two targets.

[0013] Figure 3 A flowchart is shown of a method for determining lane occupancy targets within the radar field of view ahead of a vehicle, according to an embodiment of the present disclosure.

[0014] Figure 4 A schematic diagram representing the differences in target microDoppler features according to an embodiment of the present disclosure is shown.

[0015] Figure 5 A schematic diagram representing the differences in target microDoppler features according to an embodiment of the present disclosure is shown.

[0016] Figure 6 A flowchart is shown of a method for determining lane occupancy targets within the radar field of view ahead of a vehicle, according to an embodiment of the present disclosure.

[0017] Figure 7 A flowchart is shown of a method for determining lane occupancy targets within the radar field of view ahead of a vehicle, according to an embodiment of the present disclosure.

[0018] Figure 8 A flowchart is shown of a method for determining lane occupancy targets within the radar field of view ahead of a vehicle, according to an embodiment of the present disclosure.

[0019] Figure 9 A schematic diagram illustrating the effect of determining a target for determining lane occupancy according to an embodiment of the present disclosure is shown.

[0020] Figure 10 A flowchart of a control method for an adaptive cruise system according to an embodiment of the present disclosure is shown.

[0021] Figure 11 An example block diagram of an apparatus for determining lane occupancy targets within a radar field of view ahead of a vehicle, according to an embodiment of the present disclosure, is shown.

[0022] Figure 12 An example block diagram of the control device for an adaptive cruise system according to an embodiment of the present disclosure is shown.

[0023] Figure 13 An example schematic diagram of a device for determining lane occupancy targets within a radar field of view ahead of a vehicle, implemented according to an embodiment of the present disclosure, is shown.

[0024] Figure 14 An example schematic diagram of a control device for an adaptive cruise system implemented using a computer system according to an embodiment of the present disclosure is shown. Detailed Implementation

[0025] In the following description, numerous specific details are set forth to provide a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that this disclosure may be practiced without one or more of these specific details, or that alternative methods, components, etc., may be used. In some instances, well-known structures and operations have not been shown or described in detail so as not to unnecessarily obscure this disclosure.

[0026] It is important to note that applying the methods described in this disclosure may involve using user-related information, such as road images collected by various vehicle sensors. It is crucial to remember that the use of information involving user privacy requires user authorization, and the use of such information must not exceed the scope of the user's authorization.

[0027] The systems and methods described herein can be applied to vehicles equipped with driver assistance technologies, including but not limited to non-autonomous vehicles, semi-autonomous vehicles, robots, warehouse vehicles, off-road vehicles, ships, emergency vehicles, motorcycles, electric or motorized bicycles, aircraft, construction vehicles, underwater vehicles, drones and / or other vehicle types.

[0028] Figure 1 A schematic diagram 100 of a vehicle and road according to an embodiment of the present disclosure is shown.

[0029] like Figure 1 As shown, vehicle 102 is traveling in lane 104. Vehicle 102 may be equipped with one or more sensors 106. Sensors 106 may be installed at any location inside and / or outside vehicle 102 to sense information about the external environment of vehicle 102, such as the type, shape, location data, speed, acceleration, etc. of vehicles, pedestrians, or other traffic participants around vehicle 102. Examples of sensors 106 may include, but are not limited to, GPS sensors, speed sensors, steering angle sensors, and acceleration sensors. In some embodiments, sensors 106 may be implemented as image sensors, laser sensors, radar sensors, ultrasonic sensors, and infrared sensors, etc.

[0030] The vehicle 102 may also be equipped with a driving assistance device 108. After the sensor 106 senses external environmental information, the driving assistance device 108 can make driving assistance decisions based on the sensed external environmental information, such as controlling the vehicle to perform emergency braking or deceleration. The driving assistance device 108 can implement one or more driving assistance functions. Various driving assistance functions can be implemented as one or more individual modules, controllers, processors, or electronic control units, or implemented as a single driving assistance platform.

[0031] Vehicle 102 may also be provided with an output device 110. The output device 110 is configured to notify the driver of driving assistance decisions made by the driving assistance device 108. For example, the output device 110 may notify the driver of driving assistance decisions in a tactile, auditory, and / or visual manner. Examples of the output device 110 may include, but are not limited to, a speaker, a monitor, a display screen, etc. In some embodiments, vehicle 102 may also be provided with a vehicle navigation system 112 for providing navigation services to the vehicle.

[0032] In some embodiments, the driving assistance device 108 can determine lane occupancy based on point cloud data of a target acquired by the sensor 106. In some embodiments, the point cloud data of the target can be sensed in real time by a millimeter-wave radar installed on a vehicle traveling in lane 104. In some embodiments, a camera 114 for monitoring road conditions may also be present beside lane 104. The camera 114 is used to capture point cloud data of targets on the road in real time, and then the camera 114 transmits the data to the vehicle 102.

[0033] Figure 2 A schematic diagram is shown in a practical radar system according to an embodiment of the present disclosure, illustrating a single forward vehicle splitting into two targets.

[0034] In the diagram, the black SUV indicated by arrow 201 is located at the edge of the radar's field of view and is crawling at low speed. Because vehicles at the edge of the radar's field of view and crawling at low speed are prone to target splitting, even though there is only one black SUV in front of this vehicle on the actual road, the vehicle's millimeter-wave radar identifies it as two targets: a first target with ID 25 and a second target with ID 2. When the vehicle in front splits into two targets, one of the targets with lateral speed (usually the second target with ID 2) will be judged by the ACC system as having entered the vehicle's lane. The ACC system then considers the vehicle corresponding to that target to have entered the vehicle's lane and applies the brakes. However, in actual road conditions, the black SUV in front of the vehicle has not entered the vehicle's lane. Therefore, the ACC system applies the brakes incorrectly when it should not, resulting in a degraded user experience.

[0035] The solution to this problem is that when a target splits in an adjacent lane, the system can promptly and accurately identify the lane occupancy of the first and second targets. When it is determined that the second target occupies the vehicle's lane, it should promptly and effectively merge the second target with the first target, thus preventing the ACC system from using the second target as the ACC function target and making incorrect vehicle control decisions (such as maintaining speed, braking, or steering), thereby improving the user experience. However, existing methods only consider the target's speed and distance from the vehicle when determining lane occupancy, therefore they cannot promptly and accurately merge the second target with the first target. Consequently, existing methods cannot prevent erroneous braking by the ACC system.

[0036] Figure 3 A flowchart 300 illustrates a method for determining lane occupancy targets within a radar field of view ahead of a vehicle, according to an embodiment of the present disclosure.

[0037] At point 302, acquire point cloud data of targets within the radar field of view in front of the vehicle;

[0038] At point 304, based on point cloud data, the target micro-Doppler feature difference between at least two targets split from the target is determined; in one embodiment, the target micro-Doppler feature difference is characterized as a target micro-Doppler cycle value. In one embodiment, the target micro-Doppler cycle value is determined based on the target's maximum radial velocity and average radial velocity, and the maximum radial velocity and average radial velocity are determined based on the target's point cloud data.

[0039] In one specific embodiment, the target microDoppler cycle value can be determined by the following method:

[0040]

[0041]

[0042] Where microDopplerCycles is the target microDoppler cycle value, m microDopplerRaw Here, Vr is the target's micro-Doppler value, maxVr is the target's maximum radial velocity, and meanVr is the target's average radial velocity. In one embodiment, the vehicle's radar emits radar waves in one cycle, and then the vehicle in front reflects the radar waves. Based on the radar echoes, the radar identifies dozens to hundreds of point cloud data points. Subsequently, based on these point cloud data points, the radar can obtain the radial velocities of multiple vehicles in front. The maximum value among these radial velocities is maxVr, and the average value among these radial velocities is meanVr.

[0043] Figure 4 A schematic diagram 400 representing the differences in microDoppler features of a target is shown according to an embodiment of the present disclosure. The following is in conjunction with... Figure 4 This disclosure describes how to determine the differences in target microDoppler characteristics. Figure 4In the diagram, vehicle 402 is located in vehicle lane 404. This vehicle has, for example, a radar located at the front of the vehicle. The right lane 406 of vehicle lane 404 has a vehicle 408 on one side ahead. The radar field of view of this vehicle is represented by an arc 410 in the figure, wherein the edge of the radar field of view of this vehicle is represented by a region 412 between parallel straight lines. As can be seen from the figure, the vehicle 408 on the side ahead has just entered the edge of the radar field of view of this vehicle. For example, because the vehicle 408 on the side ahead has entered the edge of the radar field of view of this vehicle, and the speed of the vehicle 408 on the side ahead is relatively slow, target splitting occurs. In the radar, the vehicle 408 on the side ahead splits into two targets, wherein the first target is represented by the vehicle 408 on the side ahead itself, and the second target is represented by the split target 414. In a specific embodiment, when the vehicle 408 on the side ahead has just entered the edge of the radar field of view of this vehicle, the micro-Doppler cycle value of the first target calculated by formula (1) is 3, and the micro-Doppler cycle value of the second target calculated by formula (1) is 1.

[0044] Figure 5 A schematic diagram 500 representing the differences in microDoppler features of a target according to an embodiment of the present disclosure is shown. Figure 5 In the indicated state, the vehicle 408 on the side continues to move forward, gradually penetrating the edge region 412 of the radar's field of view. At this time, the second target 414, which splits off from the vehicle 408 on the side, has been identified by the radar as an intrusion into the vehicle's lane 404, while the first target represented by the vehicle 408 itself remains in the right lane 406. In one specific embodiment, in Figure 5 Under the condition, the micro-Doppler cycle value of the first target calculated by formula (1) is 5, and the micro-Doppler cycle value of the second target calculated by formula (1) is 2.

[0045] At position 306, based on the differences in target micro-Doppler characteristics, a target for determining lane occupancy is identified from at least two targets. This is then further combined with... Figure 4 and Figure 5To illustrate step 306, consider the example of the vehicle 408 entering the radar's field of view. The micro-Doppler cycle value of the first target, split from the vehicle 408, changes from 3 to 5, while the micro-Doppler cycle value of the second target changes from 1 to 2. Since the vehicle 408 remains in the right lane 406, the first target accurately reflects the vehicle 408's occupancy of the vehicle's lane 404, while the second target does not. In other words, a target with a consistently higher micro-Doppler cycle value accurately reflects the vehicle 408's occupancy of the vehicle's lane 404, while a target with a consistently lower micro-Doppler cycle value does not. Therefore, in one embodiment, a target with a large micro-Doppler cycle value can be identified as the target for determining lane occupancy. The ACC system can then determine the vehicle's lane occupancy relative to this target and make a vehicle control decision based on this determined lane occupancy. Since the method of this disclosure can determine the target for lane occupancy in a timely and accurate manner, and the vehicle's lane occupancy relative to the target correctly reflects the vehicle's lane occupancy relative to vehicles to the side and ahead on the actual road, the ACC system will not erroneously apply active braking before the vehicle to the side and ahead has entered its lane. Therefore, the method of this disclosure can improve the user experience.

[0046] Figure 6 A flowchart 600 illustrates a method for determining lane occupancy targets within a radar field of view ahead of a vehicle according to an embodiment of the present disclosure. As shown, the method of the present disclosure further includes:

[0047] At position 602: Point cloud data obtained from the vehicle;

[0048] At 604: Based on point cloud data of the vehicle and at least two targets, determine the lateral distance of each target relative to the rear axle center of the vehicle; it should be understood that steps 602 and 604 may be performed before steps 302 and 304, between steps 302 and 304, in parallel with steps 302 and 304, or after steps 302 and 304.

[0049] Step 306 further includes: determining a target for determining lane occupancy from at least two targets based on the target micro-Doppler feature differences and lateral distance. In one embodiment, still using Figure 4 and Figure 5 Taking the embodiment as an example, the first lateral distance of the first target relative to the center of the rear axle of the vehicle is d. y1The second lateral distance of the second target relative to the center of the rear axle of the vehicle is d. y2 ;from Figure 4 and Figure 5 It can be seen that the first horizontal distance is d y1 Always greater than the second lateral distance d y2 Therefore, in one embodiment, since the first target can accurately reflect the occupancy of the lane 404 of the vehicle from the side front vehicle 408, the criterion for determining the target for determining lane occupancy from at least two targets based on the differences in target micro-Doppler characteristics and lateral distance can be: the target with the larger micro-Doppler cycle value and the larger lateral distance of the target relative to the center of the rear axle of the vehicle is determined as the target for determining lane occupancy.

[0050] Figure 7 A flowchart 700 illustrates a method for determining lane occupancy targets within a radar field of view ahead of a vehicle according to an embodiment of the present disclosure. As shown, the method of the present disclosure further includes:

[0051] At position 702: Determine the target similarity between at least two targets;

[0052] At 704: Based on target similarity, group at least two targets; it should be understood that steps 702 and 704 may be executed before steps 302 and 304, between steps 302 and 304, in parallel with steps 302 and 304, or after steps 302 and 304.

[0053] Step 306 further includes: for each group of targets, determining the target used to determine lane occupancy from the group of targets based on the differences in the micro-Doppler characteristics of the targets.

[0054] In one embodiment, target similarity is determined based on the Doppler features of the target, the intersection of point cloud data between the target and other targets, and the sensitivity of the target's presence region. In a specific embodiment, target similarity can be determined by the following method:

[0055]

[0056] Among them, D M It is target similarity. in, Where, x n This represents the microDoppler cycle value of the nth target out of at least two targets;

[0057] y nThis represents the intersection of point cloud data between the nth target and the other targets in a set of at least two targets. In one embodiment, if the point cloud data of the nth target intersects with the point cloud data of the other targets, then y n The value is 1. If the point cloud data of the nth target has no intersection with the point cloud data of other targets, then y... n The value is 0;

[0058] Among them, z n This represents the sensitivity of the area where the nth target out of at least two targets is located. In one embodiment, if the nth target is located at the edge of the radar field of view, then z... n The value is 1; if the nth target is not located at the edge of the radar's field of view, then z... n The value is 0;

[0059] in, Where, μ N The mean μ is the element calculated from the elements in vector B. C The mean μ is the element calculated from the elements in vector C. D The mean value calculated for the elements in vector D;

[0060] in, Where, σ 11 Let σ be the variance of all elements that make up vector B. 22 Let σ be the variance of all elements that make up vector C. 33 Let σ be the variance of all elements that make up vector D. 12 With σ 21 Let σ be the covariance between vectors B and C. 13 and σ 31 Let σ be the covariance between vectors B and D. 23 and σ 32 Let be the covariance between vectors C and D.

[0061] In one embodiment, if the target similarity D M If the similarity is less than or equal to the threshold, at least two targets are grouped together, and then the target with the larger micro-Doppler cycle value in each target group is identified as the target used to determine lane occupancy. If the target similarity D M If the number of targets exceeds the threshold, at least two targets will not be grouped together. The radar will then retain these targets, and the ACC system will make vehicle control decisions based on these retained targets.

[0062] Figure 8 A flowchart 800 illustrates a method for determining lane occupancy targets within a radar field of view ahead of a vehicle according to an embodiment of the present disclosure. As shown, the method of the present disclosure further includes:

[0063] At point 802: Group at least two targets based on one or more of the following: target merging between targets, point cloud data intersection between targets, and target correlation between targets.

[0064] It should be understood that step 802 can be executed before, between, or in parallel with steps 302 and 304, or after steps 302 and 304.

[0065] Step 306 further includes: for each group of targets, determining the target used to determine lane occupancy from the group of targets based on the differences in the micro-Doppler characteristics of the targets.

[0066] In one embodiment, the target merging property between targets can be determined by: determining a first radial distance d from the center of the vehicle's rear axle to the first target. x1 The first lateral distance d from the center of the rear axle of the vehicle y1 First radial velocity v x1 and the first lateral velocity v y1 Determine the second target distance as the second radial distance d from the center of the vehicle's rear axle. x2 The second lateral distance d from the center of the rear axle of the vehicle y2 Second radial velocity v x2 and the second lateral velocity v y2 ;

[0067] The first objective and the second objective are determined to have objective merging when the following conditions are met:

[0068] (1) d x1 With d x2 The difference is less than the first threshold; and

[0069] (2) d y1 With d y2 The difference is less than the second threshold; and

[0070] (3) v x1 With v x2 The difference is less than the third threshold; and

[0071] (4) v y1 With v y2 The difference is less than the fourth threshold.

[0072] In one specific embodiment, the aforementioned first threshold can be 10m, the second threshold can be the merging coefficient multiplied by 5m, wherein the merging coefficient can be dynamically determined, the third threshold can be 3m / s, and the fourth threshold can be 50m / s.

[0073] In one embodiment, if at least two targets exhibit target merging, the at least two targets are grouped, and the target with the larger micro-Doppler cyclic value in each target group is identified as the target used to determine lane occupancy. If at least two targets do not exhibit target merging, the at least two targets are not grouped, and the radar retains these targets. The ACC system then makes vehicle control decisions based on these retained targets.

[0074] In one embodiment, the intersection of point cloud data between targets can be determined by judging whether there is an intersection between the point cloud data of the target and other targets. In one embodiment, if the point cloud data of the target intersects with that of other targets, at least two targets are grouped, and then the target with the larger micro-Doppler cycle value in each target group is identified as the target used to determine lane occupancy. If the point cloud data of the target does not intersect with that of other targets, at least two targets are not grouped, and the radar retains these targets. The ACC system then makes vehicle control decisions based on these retained targets.

[0075] In one embodiment, the target correlation between targets can be characterized by the Mahalanobis distance between them, which can be calculated based on point cloud data of the targets. In one embodiment, if the Mahalanobis distance between at least two targets is less than or equal to a threshold, the at least two targets can be grouped, and then the target with the larger micro-Doppler cyclic value in each target group is identified as the target used to determine lane occupancy. If the Mahalanobis distance between at least two targets is greater than the threshold, the at least two targets are not grouped, and the radar will retain these targets, which the ACC system will use to make vehicle control decisions.

[0076] Figure 9 A schematic diagram illustrating the effect of determining a target for determining lane occupancy according to an embodiment of the present disclosure is shown.

[0077] The black SUV indicated by arrow 901 in the picture is at the edge of the radar field of view and is crawling at low speed. Figure 9 The position and driving status of the black SUV in the picture are similar to those of the black SUV in the picture. Figure 2 The position and driving status of the black SUV in the picture are similar. If the method presented in this disclosure is not used, then... Figure 2 As shown, the black SUV will split into two targets: the first target with ID 25 and the second target with ID 2. Figure 2 The vehicle's radar system might incorrectly make a braking decision based on the assumption that a second target is occupying its lane. However, if... Figure 9As shown, after adopting the method proposed in this disclosure, the radar will identify only one target, namely the target with ID 4 used to determine lane occupancy. This target with ID 4 is located in the right lane of the vehicle's lane, therefore it accurately reflects the lane occupancy of the black SUV to the right. Thus, the method of this disclosure can prevent the ACC system from making erroneous braking actions based on the lane occupancy of a target not used to determine lane occupancy, thereby improving the user experience.

[0078] Figure 10 A flowchart 1000 of a control method for an adaptive cruise system according to an embodiment of the present disclosure is shown.

[0079] At point 1002, a target for determining lane occupancy is identified from at least two targets, wherein the at least two targets are derived from targets within the radar field of view in front of the vehicle; the method for determining the target for determining lane occupancy is as described above. Figures 3-8 The described process is used to determine the target for lane occupancy.

[0080] At point 1004, the lane occupancy of the vehicle, used to determine the target for determining lane occupancy, is identified; and

[0081] At point 1006, in response to the vehicle's lane being occupied, the adaptive cruise control system is controlled to make lane occupancy response decisions.

[0082] Figure 11 An example block diagram 1100 of an apparatus for determining lane occupancy targets within a radar field of view ahead of a vehicle, according to an embodiment of the present disclosure, is shown. Figure 11 As shown, the device 1102 for determining lane occupancy targets within the radar field of view in front of the vehicle includes a point cloud data acquisition module 1104, a target micro-Doppler feature difference determination module 1106, and a lane occupancy target determination module 1108.

[0083] The point cloud data acquisition module 1104 is configured to acquire point cloud data of targets within the radar's field of view in front of the vehicle. The operation of the point cloud data acquisition module 1104 can be referenced above. Figure 3 The operation described in 302.

[0084] The target micro-Doppler feature difference determination module 1106 is configured to determine the target micro-Doppler feature differences between at least two targets split from the target based on point cloud data. The operation of the target micro-Doppler feature difference determination module 1106 can be referenced above. Figure 3 The 304 error describes the operation.

[0085] The lane occupancy target determination module 1108 is configured to determine the target for determining lane occupancy from at least two targets based on the difference in target micro-Doppler features. The operation of the lane occupancy target determination module 1108 can be referenced above. Figure 3 The operation described in 306.

[0086] Figure 12 An example block diagram 1200 of a control device for an adaptive cruise system according to an embodiment of the present disclosure is shown. Figure 12 As shown, the control device 1202 of the adaptive cruise system includes a lane occupancy target determination module 1204, a lane occupancy determination module 1206, and an occupancy response decision module 1208.

[0087] The lane occupancy target determination module 1204 is configured to determine a target for determining lane occupancy from at least two targets, wherein the at least two targets are derived from targets within the radar's field of view in front of the vehicle. The operation of the lane occupancy target determination module 1204 can be referenced above. Figure 10 The operation described in 1002.

[0088] The lane occupancy determination module 1206 is configured to determine the lane occupancy of the target vehicle used for determining lane occupancy. The operation of the lane occupancy determination module 1206 can be referenced above. Figure 10 The operation described in 1004.

[0089] The lane occupancy response decision module 1208 is configured to control the adaptive cruise control system to make lane occupancy response decisions in response to lane occupancy being detected by the vehicle. The operation of the lane occupancy response decision module 1208 can be referenced above. Figure 10 The operation described in 1006.

[0090] As per the above reference Figures 1 to 12 This document describes a method for determining lane occupancy targets within the radar field of view ahead of a vehicle, an apparatus for determining lane occupancy targets within the radar field of view ahead of a vehicle, a control method for an adaptive cruise control system, and a control apparatus for an adaptive cruise control system, according to embodiments of the present disclosure. The aforementioned apparatus for determining lane occupancy targets within the radar field of view ahead of a vehicle and the control apparatus for an adaptive cruise control system can be implemented in hardware, software, or a combination of hardware and software.

[0091] Figure 13 A schematic diagram 1300 illustrates an example of a computer-based device 1302 for determining lane occupancy targets within a radar field of view ahead of a vehicle, according to an embodiment of the present disclosure. (See diagram 1300.) Figure 13As shown, the device 1302 for determining lane occupancy targets within the radar field of view ahead of the vehicle may include at least one processor 1304, a memory (e.g., non-volatile memory) 1306, a RAM 1308, and a communication interface 1310, and the at least one processor 1304, memory 1306, RAM 1308, and communication interface 1310 are connected together via a bus 1312. At least one processor 1304 executes at least one computer-readable instruction (i.e., the elements implemented in software described above) stored or encoded in the memory.

[0092] In one embodiment, computer-executable instructions are stored in memory that, when executed, cause at least one processor 1304 to: acquire point cloud data of targets within the radar field of view in front of the vehicle; determine, based on the point cloud data, the target micro-Doppler feature differences between at least two targets split from the target; and, based on the target micro-Doppler feature differences, determine, from the at least two targets, a target for determining lane occupancy.

[0093] It should be understood that the computer-executable instructions stored in memory, when executed, cause at least one processor 1304 to perform the above-described combinations in the various embodiments of this specification. Figures 3-8 and Figure 11 The description includes various operations and functions.

[0094] Figure 14 A schematic diagram 1400 illustrates a control device 1402 for an adaptive cruise system implemented using a computer system according to an embodiment of the present disclosure. (See diagram 1400.) Figure 14 As shown, the lane occupancy determination device 1402 may include at least one processor 1404, a memory (e.g., non-volatile memory) 1406, a RAM 1408, and a communication interface 1410, and the at least one processor 1404, memory 1406, RAM 1408, and communication interface 1410 are connected together via a bus 1412. At least one processor 1404 executes at least one computer-readable instruction (i.e., the elements implemented in software described above) stored or encoded in the memory.

[0095] In one embodiment, computer-executable instructions are stored in memory that, when executed, cause at least one processor 1404 to: determine from at least two targets a target for determining lane occupancy, wherein the at least two targets are derived from targets within the radar field of view in front of the vehicle; determine the vehicle's lane occupancy of the target for determining lane occupancy; and, in response to the vehicle's lane being occupied, control the adaptive cruise system to make a lane occupancy response decision.

[0096] It should be understood that the computer-executable instructions stored in the memory, when executed, cause at least one processor 1404 to perform the above-described combinations in the various embodiments of this specification. Figures 3-8 as well as Figures 10-12 The description includes various operations and functions.

[0097] According to one embodiment, a program product, such as a machine-readable medium (e.g., a non-transitory machine-readable medium), is provided. The machine-readable medium may have instructions (i.e., the elements implemented in software as described above), which, when executed by a machine, cause the machine to perform the above-described combinations of the various embodiments of this specification. Figures 3-14 The various operations and functions described. Specifically, a system or apparatus equipped with a readable storage medium storing software program code that implements the functions of any of the embodiments described above, and enabling the computer or processor of the system or apparatus to read and execute the instructions stored in the readable storage medium.

[0098] In this case, the program code read from the readable medium itself can perform the functions of any of the above embodiments, and therefore the machine-readable code and the readable storage medium storing the machine-readable code constitute part of this disclosure.

[0099] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer or the cloud via a communication network.

[0100] According to one embodiment, a computer program product is provided, the computer program product including a computer program, which, when executed by a processor, causes the processor to perform the above-described combinations of the various embodiments of this specification. Figures 3-14 The description includes various operations and functions.

[0101] In addition to the content described herein, various modifications may be made to the disclosed embodiments and implementations without departing from the scope of this disclosure. Therefore, the descriptions and examples herein should be interpreted illustratively rather than limitingly. The scope of this disclosure should be measured solely by reference to the claims.

Claims

1. A method for determining lane occupancy targets within the radar field of view ahead of a vehicle, comprising: Acquire point cloud data of targets within the radar field of view in front of the vehicle; Based on the point cloud data, determine the target micro-Doppler feature differences between at least two targets split from the target; as well as Based on the differences in the target microDoppler features, a target for determining lane occupancy is determined from the at least two targets.

2. The method according to claim 1, wherein, The target microDoppler feature differences are characterized as target microDoppler cycle values.

3. The method according to claim 2, wherein, The target microDoppler cycle value is determined based on the target's maximum radial velocity and average radial velocity, and the maximum radial velocity and average radial velocity are determined based on the point cloud data.

4. The method according to claim 1, further comprising: Point cloud data acquired from vehicles; as well as Based on the point cloud data of the vehicle and the at least two targets, determine the lateral distance of each target relative to the rear axle center of the vehicle; Based on the differences in the target micro-Doppler features, the target for determining lane occupancy is determined from the at least two targets, including: Based on the differences in the target micro-Doppler features and the lateral distance, the target used to determine lane occupancy is determined from the at least two targets.

5. The method according to claim 1, further comprising: Determine the target similarity of the at least two targets; as well as Based on the target similarity, the at least two targets are grouped. Based on the differences in the target micro-Doppler features, the target for determining lane occupancy is determined from the at least two targets, including: For each group of targets, the target used to determine lane occupancy is determined from that group of targets based on the differences in the micro-Doppler features of the targets.

6. The method according to claim 5, wherein, The target similarity is determined based on the Doppler features of the target, the intersection of point cloud data between the target and other targets, and the sensitivity of the target's presence area.

7. The method according to claim 1, further comprising: Grouping of the at least two objectives based on one or more of the following: Target merging between targets, point cloud data intersection between targets, and target correlation between targets. Based on the differences in the target micro-Doppler features, the target for determining lane occupancy is determined from the at least two targets, including: For each group of targets, the target used to determine lane occupancy is determined from that group of targets based on the differences in the micro-Doppler features of the targets.

8. A device for determining lane occupancy of targets within a radar field of view ahead of a vehicle, comprising: The point cloud data acquisition module is configured to acquire point cloud data of targets within the radar field of view in front of the vehicle. A target micro-Doppler feature difference determination module is configured to determine, based on the point cloud data, the target micro-Doppler feature difference between at least two targets split from the target; as well as A lane occupancy target determination module is configured to determine a target for determining lane occupancy from at least two targets based on the differences in the target's micro-Doppler features.

9. A control method for an adaptive cruise system, comprising: According to any one of claims 1-7, a target for determining lane occupancy is determined from at least two targets, wherein the at least two targets are split from targets within the radar field of view in front of the vehicle; Determine the vehicle's lane occupancy as the target for determining lane occupancy; and In response to the vehicle's lane being occupied, the adaptive cruise control system is controlled to make lane occupancy response decisions.

10. A control device for an adaptive cruise system, comprising: A lane occupancy target determination module is configured to determine a target for determining lane occupancy from at least two targets according to the method of any one of claims 1-7, wherein the at least two targets are split from targets within the radar field of view in front of the vehicle; A lane occupancy determination module, configured to determine the lane occupancy of the vehicle for the target used to determine lane occupancy; and The lane occupancy response decision module is configured to control the adaptive cruise system to make lane occupancy response decisions in response to the vehicle's lane being occupied.

11. A device for determining lane occupancy of targets within a radar field of view ahead of a vehicle, comprising: A memory on which computer programs are stored; At least one processor coupled to the memory, the at least one processor being configured to execute the computer program to implement the method of any one of claims 1-7.

12. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the method of any one of claims 1-7.

Images