Control Method, Device, Controller, Storage Medium and Vehicle for Brake Function

Abstract

An embodiment of the present application provides a control method, device, controller, storage medium and vehicle for a braking function, which can suppress the mis-triggering of the automatic braking function when the position of the determined target obstacle jumps, thereby improving the user experience. Among them, the control method for the braking function includes: periodically obtaining target obstacle information during the driving of the vehicle, where the target obstacle information includes the target position of the target obstacle and the first relative distance between the vehicle and the target obstacle; if the first relative distance corresponding to the i-th cycle is not greater than the first set threshold and the first relative distance corresponding to the (i-1)-th cycle is greater than the first set threshold, calculate the first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i-1)-th cycle; if the first position deviation is not less than the second set threshold, suppress the triggering of the automatic braking function.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent driving technologies, and in particular, to a control method, device, controller, storage medium, and vehicle for a braking function.

Background Art

[0002] With the popularization of the Autonomous Emergency Braking (AEB) system in automotive safety technologies, when the distance between a target obstacle and a vehicle is detected to be less than a safe distance, the automatic braking function will be triggered to avoid a collision between the vehicle and the target obstacle.

[0003] In the prior art, the position of a target obstacle is usually obtained based on data acquired by a millimeter-wave radar and a binocular camera and then generated after algorithm fusion. However, when the vehicle is driving in a specific scenario, such as a tunnel or a culvert, affected by light or signals, the millimeter-wave radar and the binocular camera may experience position jumps when determining the position of the target obstacle. If both the millimeter-wave radar and the binocular camera have jumped, then the position indicated by the target obstacle contour fused by the algorithm is incorrect. And the AEB will continuously detect the position of the target obstacle and determine the distance between the vehicle and the target obstacle based on the position of the target obstacle, and then judge whether the distance between the target obstacle and the vehicle is within the safe distance range. If it is determined that the distance between the vehicle and the target obstacle is less than the safe distance, the AEB will erroneously trigger the automatic emergency braking function based on the incorrect distance between the vehicle and the target obstacle, causing the vehicle to automatically brake, but the actual relative distance is greater than the safe distance, thus affecting the user experience.

Summary of the Invention

[0004] The embodiments of the present application provide a control method, device, controller, storage medium, and vehicle for a braking function, which can reduce the occurrence of erroneously triggering the automatic braking function due to misdetecting the position of the target obstacle, thereby improving the user experience.

[0005] In a first aspect, the embodiments of the present application provide a control method for a braking function, the method comprising:

[0006] Periodically obtaining target obstacle information during the driving of the vehicle, the target obstacle information including the target position of the target obstacle and a first relative distance between the vehicle and the target obstacle, the target position being generated after the positions of the target obstacle detected by the millimeter-wave radar and the positions of the target obstacle detected by the binocular camera are input into a fusion algorithm, and the first relative distance being generated by the fusion algorithm based on the target position;

[0007] If the first relative distance corresponding to the i-th cycle is not greater than a first set threshold and the first relative distance corresponding to the (i - 1)-th cycle is greater than the first set threshold, calculate a first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle;

[0008] If the first position deviation is not less than a second set threshold, inhibit triggering the automatic braking function.

[0009] In the embodiments of the present application, the target obstacle information includes the target position of the target obstacle periodically obtained by the vehicle during driving and the first relative distance between the target obstacle and the vehicle. Since the time of each cycle is very short, the change in the target position of the target obstacle corresponding to adjacent cycles is very small. If the first relative distance corresponding to the i-th cycle is not greater than the first set threshold and the first relative distance corresponding to the (i - 1)-th cycle is greater than the first set threshold, it indicates that the first relative distance corresponding to the i-th cycle has become less than the minimum safety distance, while the first relative distance corresponding to the (i - 1)-th cycle is still greater than the minimum safety distance. Therefore, the target obstacle information obtained in the i-th cycle may have jumped, and thus the target position and the first relative distance corresponding to the i-th cycle may be inaccurate. To verify the accuracy of the target obstacle obtained in the i-th cycle, calculate the first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle. If the first position deviation is not less than the second set threshold, it indicates that the deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle is relatively large, and the deviation of the target position within two adjacent cycle times will not be too large. At this time, it can be considered that the target position corresponding to the i-th cycle has jumped, that is, it is considered that the actual relative distance between the target obstacle and the vehicle is still within the safety distance, and there is no need to trigger the automatic braking function, thereby reducing the occurrence of false triggering of the automatic braking function due to misdetection of the target obstacle position, and thus improving the user experience.

[0010] Optionally, after periodically obtaining the target obstacle information of the vehicle during driving, the method further includes:

[0011] If the first relative distance corresponding to the (i + 1)-th cycle and the first relative distance corresponding to the (i - 1)-th cycle are greater than the first set threshold and the first relative distance corresponding to the i-th cycle is not greater than the first set threshold, calculate a second position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle and a third position deviation between the target position information corresponding to the (i + 1)-th cycle and the target position information corresponding to the i-th cycle;

[0012] If both the second position deviation and the third position deviation are not less than the second set threshold, the automatic braking function is inhibited from being triggered.

[0013] In the embodiments of the present application, since the time of each cycle is very short, the change amount of the corresponding target positions between adjacent cycles is very small. If the first relative distance corresponding to the (i + 1)-th cycle and the first relative distance corresponding to the (i - 1)-th cycle are greater than the first set threshold, while the first relative distance corresponding to the i-th cycle is not greater than the first set threshold, it indicates that the first relative distance obtained in the i-th cycle has been less than the minimum safety distance, and the first relative distances corresponding to the (i - 1)-th cycle and the (i + 1)-th cycle are still greater than the minimum safety distance. Therefore, the target obstacle information obtained in the i-th cycle may have jumped, and further, the target position and the first relative distance corresponding to the i-th cycle may be inaccurate. To verify the accuracy of the target obstacle obtained in the i-th cycle, calculate the second position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle, and the third position deviation between the target position information corresponding to the (i + 1)-th cycle and the target position information corresponding to the i-th cycle. If both the second position deviation and the third position deviation are not greater than the second set threshold, it indicates that the deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle, and the deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i + 1)-th cycle are both large, while the deviation of the target position within the time of adjacent cycles will not be too large. At this time, it can be considered that the target position corresponding to the i-th cycle has jumped, that is, it is considered that the target position corresponding to the (i + 1)-th cycle has jumped back to the correct position, and the actual relative distance between the target obstacle and the vehicle should still be within the safety distance, and there is no need to trigger the automatic braking function, thereby reducing the occurrence of accidentally triggering the automatic braking function due to mis-detecting the position of the target obstacle, and thus improving the user experience.

[0014] Optionally, periodically obtaining target obstacle information during the driving of the vehicle includes:

[0015] Periodically obtaining the first position of the target obstacle collected by the millimeter-wave radar and the second position of the target obstacle collected by the binocular camera;

[0016] Calculating a fourth position deviation between the first position corresponding to the i-th cycle and the second position corresponding to the i-th cycle;

[0017] Determining whether the fourth position deviation is greater than a third set threshold;

[0018] If the fourth position deviation is greater than the third set threshold, calculate a fifth position deviation between the first position corresponding to the i-th cycle and the first position corresponding to the (i - 1)-th cycle, and a sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i - 1)-th cycle;

[0019] If the fifth position deviation is greater than the fourth set threshold and the sixth position deviation is not greater than the fifth set threshold, assign a first confidence weight to the first position corresponding to the i-th cycle to generate a first weighted position, and assign a second confidence weight to the second position corresponding to the i-th cycle to generate a second weighted position, where the first confidence weight is less than the second confidence weight;

[0020] Input the first weighted position and the second weighted position into the fusion algorithm to generate the target position.

[0021] In the embodiments of the present application, after obtaining the first position of the target obstacle collected by the millimeter-wave radar and the second position of the target obstacle collected by the binocular camera, it is determined whether the fourth position deviation between the first position and the second position is greater than the third set threshold. If the fourth position deviation is greater than the third set threshold, it can be considered that the position deviation between the target obstacle collected by the millimeter-wave radar and the target obstacle collected by the binocular camera is large, and the first position and the second position may have a jump. After calculating the fifth deviation value between the first position corresponding to the i-th cycle and the first position corresponding to the (i - 1)-th cycle, and the sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i - 1)-th cycle, if the fifth position deviation is greater than the fourth set threshold and the sixth position deviation is not greater than the fifth set threshold, it indicates that in the i-th cycle, the first position obtained by the millimeter-wave radar has a jump while the second position obtained by the binocular camera has no jump. Therefore, the second position that has not jumped is more accurate than the first position that has jumped. At this time, a first confidence weight can be assigned to the first position corresponding to the i-th cycle to generate a first weighted position, and a second confidence weight can be assigned to the second position corresponding to the i-th cycle to generate a second weighted position, where the first confidence weight is less than the second confidence weight. Then, the first weighted position and the second weighted position are input into the fusion algorithm to generate the target position. It can be considered that when calculating the target position, the influence of the first position with a jump is small, and the influence of the second position without a jump is large, so that the influence of the jump of the first position on the accuracy of determining the target position is smaller, thereby improving the accuracy of determining the target position.

[0022] Optionally, after calculating a fifth position deviation between the first position corresponding to the i-th cycle and the first position corresponding to the (i-1)-th cycle, and a sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i-1)-th cycle, the method further includes:

[0023] If the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, assign a third confidence weight to the first position corresponding to the i-th cycle to generate a third weighted position, and assign a fourth confidence weight to the second position corresponding to the i-th cycle to generate a fourth weighted position, where the third confidence weight is greater than the fourth confidence weight;

[0024] Input the third weighted position and the fourth weighted position into the fusion algorithm to generate the target position.

[0025] In the embodiments of the present application, after calculating a fifth deviation value between the first position corresponding to the i-th cycle and the first position corresponding to the (i-1)-th cycle, and a sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i-1)-th cycle, if the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, it indicates that in the i-th cycle, the second position obtained by the binocular camera has a jump while the first position obtained by the millimeter-wave radar has no jump. Therefore, the first position without jump is more accurate than the second position with jump. At this time, a third confidence weight can be assigned to the first position corresponding to the i-th cycle to generate a third weighted position, and a fourth confidence weight can be assigned to the second position corresponding to the i-th cycle to generate a fourth weighted position, where the third confidence weight is greater than the fourth confidence weight. Then, input the third weighted position and the fourth weighted position into the fusion algorithm to generate the target position. It can be considered that when calculating the target position, the influence of the inaccurate second position is smaller, and the influence of the accurate first position is larger, so that the influence on the accuracy of determining the target position is smaller when the second position has a jump, thereby improving the accuracy of determining the target position.

[0026] Optionally, periodically obtaining the first position of the target obstacle collected by the millimeter-wave radar and the second position of the target obstacle collected by the binocular camera includes:

[0027] Periodically obtaining a first target obstacle feature collected by the millimeter-wave radar and a second target obstacle feature collected by the binocular camera;

[0028] Determine whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle;

[0029] If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, determine the first position based on the first target obstacle feature and determine the second position based on the second target obstacle feature.

[0030] In the embodiments of the present application, after obtaining the first target obstacle feature collected by the millimeter-wave radar and the second target obstacle feature collected by the binocular camera, by comparing the first obstacle feature and the second obstacle feature, it can be determined whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle. If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, determine the first position based on the first target obstacle feature and determine the second position based on the second target obstacle feature. It can be considered that both the first position and the second position represent the position of the same obstacle. And based on different acquisition subjects to respectively acquire the position information of the same obstacle, it can provide more reference data for the fusion algorithm to calculate the target position, making the determined target position more accurate, thereby avoiding the determined target position being affected by the positions of other obstacles.

[0031] Optionally, suppressing the triggering of the automatic braking function includes:

[0032] Sending a disabling instruction to the automatic braking system within a set time, where the disabling instruction is used to disable the automatic braking function.

[0033] In the embodiments of the present application, if it is detected that the target position corresponding to a certain period jumps, resulting in the imminent mis-triggering of the automatic braking function, sending a disabling instruction to the automatic braking system within a set time can be considered to suppress the automatic braking function in a short time, thereby effectively reducing the probability of mis-triggering of the automatic braking function.

[0034] In a second aspect, the embodiments of the present application provide a control device for a braking function, and the device includes:

[0035] An acquisition unit, configured to periodically acquire target obstacle information during the driving of the vehicle, where the target obstacle information includes the target position of the target obstacle and the first relative distance between the vehicle and the target obstacle. The target position is generated after the position of the target obstacle detected by the millimeter-wave radar and the position of the target obstacle detected by the binocular camera are input into a fusion algorithm, and the first relative distance is generated by the fusion algorithm based on the target position;

[0036] A calculation unit, configured to calculate a first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle if the first relative distance corresponding to the i-th cycle is not greater than a first set threshold and the first relative distance corresponding to the (i - 1)-th cycle is greater than the first set threshold;

[0037] A control unit, configured to inhibit the triggering of the automatic braking function if the first position deviation is not less than a second set threshold.

[0038] Optionally, the calculation unit is further configured to calculate a second position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle, and a third position deviation between the target position information corresponding to the (i + 1)-th cycle and the target position information corresponding to the i-th cycle if the first relative distance corresponding to the (i + 1)-th cycle and the first relative distance corresponding to the (i - 1)-th cycle are greater than the first set threshold and the first relative distance corresponding to the i-th cycle is not greater than the first set threshold;

[0039] The control unit is further configured to inhibit the triggering of the automatic braking function if both the second position deviation and the third position deviation are not less than the second set threshold.

[0040] Optionally, the acquisition unit includes:

[0041] An acquisition subunit, configured to periodically acquire a first position of the target obstacle collected by the millimeter-wave radar and a second position of the target obstacle collected by the binocular camera;

[0042] A first calculation subunit, configured to calculate a fourth position deviation between the first position corresponding to the i-th cycle and the second position corresponding to the i-th cycle;

[0043] A judgment subunit, configured to judge whether the fourth position deviation is greater than a third set threshold;

[0044] A second calculation subunit, configured to calculate a fifth position deviation between the first position corresponding to the i-th cycle and the first position corresponding to the (i - 1)-th cycle, and a sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i - 1)-th cycle if the fourth position deviation is greater than the third set threshold;

[0045] The first generating subunit is configured to, if the fifth position deviation is greater than the fourth set threshold and the sixth position deviation is not greater than the fifth set threshold, assign a first confidence weight to the first position corresponding to the i-th cycle, generate a first weighted position, and assign a second confidence weight to the second position corresponding to the i-th cycle, generate a second weighted position, where the first confidence weight is less than the second confidence weight;

[0046] The second generating subunit is configured to input the first weighted position and the second weighted position into the fusion algorithm to generate the target position.

[0047] Optionally, the first generating subunit is further configured to, if the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, assign a third confidence weight to the first position corresponding to the i-th cycle, generate a third weighted position, and assign a fourth confidence weight to the second position corresponding to the i-th cycle, generate a fourth weighted position, where the third confidence weight is greater than the fourth confidence weight;

[0048] The second generating subunit is further configured to input the third weighted position and the fourth weighted position into the fusion algorithm to generate the target position.

[0049] Optionally, the obtaining subunit is specifically configured to:

[0050] Determine whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle;

[0051] If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, determine the first position based on the first target obstacle feature and determine the second position based on the second target obstacle feature.

[0052] Optionally, the control unit is specifically configured to:

[0053] Send a disabling instruction to the automatic braking system within a set time, where the disabling instruction is used to disable the automatic braking function.

[0054] In a third aspect, an embodiment of the present invention provides a vehicle controller, where the vehicle controller includes a processor and a memory, and the processor is configured to implement the steps of the method according to any one of the embodiments in the first aspect or the second aspect when executing a computer program stored in the memory.

[0055] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method according to any one of the embodiments in the first aspect or the second aspect.

[0056] In a fifth aspect, an embodiment of the present invention provides a vehicle, including: a vehicle controller provided by the embodiment of the third aspect of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1 It is a schematic flowchart of a control method for a braking function provided by an embodiment of the present application;

[0059] Figure 2 It is a schematic flowchart of a control method for a braking function provided by an embodiment of the present application;

[0060] Figure 3 It is a schematic flowchart of a method for obtaining target obstacle information provided by an embodiment of the present application;

[0061] Figure 4 It is a schematic flowchart of a method for obtaining a first position and a second position provided by an embodiment of the present application;

[0062] Figure 5 It is a schematic flowchart of a method for obtaining target obstacle information provided by an embodiment of the present application;

[0063] Figure 6 It is a schematic flowchart of a control method for a braking function provided by an embodiment of the present application;

[0064] Figure 7 It is a schematic structural diagram of a control device for a braking function provided by an embodiment of the present application;

[0065] Figure 8 It is a schematic structural diagram of a vehicle controller provided by an embodiment of the present application;

[0066] Figure 9 It is a schematic structural diagram of a vehicle provided by an embodiment of the present application.

DETAILED DESCRIPTION

[0067] In order to better understand the technical solutions of this specification, the embodiments of the present application will be described in detail below in conjunction with the drawings.

[0068] It should be clear that the described embodiments are only some embodiments of this specification, not all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this specification without creative efforts belong to the scope protected by this specification.

[0069] The terms used in the embodiments of this application are only for the purpose of describing specific embodiments and are not intended to limit this specification. The singular forms "a", "the", and "said" used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0070] Through research by the inventors of this application, it is found that if the millimeter-wave radar and the binocular camera are affected by the driving environment, the determined position undergoes a jump. Therefore, the determined position may be an incorrect position, and the relative distance between the incorrect position and the vehicle may be less than the safety distance. As a result, the automatic braking function will be triggered erroneously. However, at this time, the actual relative distance between the target obstacle and the vehicle is still greater than the safety distance, and the erroneous triggering of the automatic braking function will greatly affect the user experience.

[0071] In view of this, the embodiments of this application provide a control method for the braking function. In this method, by judging the size of the distance between the vehicle and the target obstacle obtained in each period, if the distance between the vehicle and the target obstacle corresponding to a certain period is less than the safety distance, the automatic braking function will be triggered. However, to avoid the erroneous triggering of the automatic braking function due to the jump of the determined target position, it is possible to detect whether the target position of the determined target obstacle has jumped by judging the size of the deviation between the target positions of the target obstacle obtained in adjacent periods. If it is detected that the deviation between the target positions of the target obstacle obtained in adjacent periods is too large, it can be determined that the determined target position has jumped, and when the jump of the target position causes the vehicle to trigger the automatic braking function, the erroneous triggering of the automatic braking function can be suppressed in a timely manner, thereby improving the user experience.

[0072] The following introduces the technical solutions provided by the embodiments of this application in conjunction with the accompanying drawings. Please refer to Figure 1 , the embodiments of this application provide a control method for the braking function. This method is applied to a controller, and the method flow is described as follows:

[0073] Step 101: Periodically obtain the target obstacle information during the driving of the vehicle. The target obstacle information includes the target position of the target obstacle and the first relative distance between the vehicle and the target obstacle. The target position is generated after inputting the position of the target obstacle detected by the millimeter-wave radar and the position of the target obstacle detected by the binocular camera into the fusion algorithm, and the first relative distance is generated by the fusion algorithm based on the target position.

[0074] In the embodiments of the present application, the automatic braking system generally uses a millimeter-wave radar and a binocular camera to detect the positions of target obstacles respectively, and inputs the positions of the target obstacles collected by the millimeter-wave radar and the information of the target obstacles collected by the binocular camera into a fusion algorithm. The fusion algorithm can be various types of algorithms such as a Kalman filtering algorithm and a weighted average algorithm, which are not limited herein, to generate the target position of the target obstacle, and determine the first relative distance between the target obstacle and the vehicle based on the target position in the fusion algorithm.

[0075] Step 102: If the first relative distance corresponding to the i-th cycle is not greater than the first set threshold and the first relative distance corresponding to the (i - 1)-th cycle is greater than the first set threshold, calculate the first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle.

[0076] In the embodiments of the present application, if it is detected that the first relative distance corresponding to the i-th cycle is not greater than the first set threshold while the first relative distance corresponding to the (i - 1)-th cycle is greater than the first set threshold (the first set threshold ensures the minimum value of the safe distance required to be maintained between the vehicle and the obstacle, and the specific value of the first set threshold can be adjusted according to actual needs, which is not specifically limited in the present application), it indicates that the first relative distance corresponding to the i-th cycle has become less than the safe distance, while the first relative distance corresponding to the (i - 1)-th cycle is still within the safe distance range. Generally, when the first relative distance is less than the safe distance, the automatic braking system will immediately trigger the automatic braking function. If the positions of the target obstacles determined by the millimeter-wave radar in the i-th cycle and the positions of the target obstacles determined by the binocular camera in the i-th cycle are affected by the driving environment and both undergo jumps, then the target position calculated by the fusion algorithm in the i-th cycle is also inaccurate. To detect whether the target position corresponding to the i-th cycle has jumped, it is necessary to calculate the first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle.

[0077] Step 103: If the first position deviation is not less than the second set threshold, inhibit the triggering of the automatic braking function.

[0078] In the embodiments of the present application, if the first position deviation is not less than the second set threshold (since the time of each period is short, the change amount of the target position between adjacent periods cannot be greater than the second set threshold, and the second set threshold is the maximum allowable error of the deviation value between the target positions of adjacent periods. The second set threshold can be adjusted according to actual requirements, and the present application does not make specific limitations), it indicates that the target position corresponding to the i-th period has jumped, the target position corresponding to the i-th period is inaccurate, and further the first relative distance corresponding to the i-th period is also incorrect. Therefore, before the automatic braking function is accidentally triggered, it is necessary to suppress the triggering of the automatic braking function, so as to reduce the accidental triggering of the automatic braking function due to the misdetection of the position of the target obstacle, thereby improving the user experience.

[0079] Figure 2 A control method for a braking function provided in the embodiments of the present application. As a possible embodiment, after step 101 is executed, the control process of the braking function can also be implemented through steps 201-202:

[0080] Step 201: If the first relative distance corresponding to the (i + 1)-th period and the first relative distance corresponding to the (i - 1)-th period are greater than the first set threshold and the first relative distance corresponding to the i-th period is not greater than the first set threshold, calculate the second position deviation between the target position corresponding to the i-th period and the target position corresponding to the (i - 1)-th period and the third position deviation between the target position information corresponding to the (i + 1)-th period and the target position information corresponding to the i-th period.

[0081] Step 202: If both the second position deviation and the third position deviation are not less than the second set threshold, suppress the triggering of the automatic braking function.

[0082] In the embodiments of the present application, the time of each period is very short. Therefore, the change amount of the target position corresponding to adjacent periods is very small. If the first relative distance corresponding to the (i + 1)-th period and the first relative distance corresponding to the (i - 1)-th period are greater than the first set threshold, while the first relative distance corresponding to the i-th period is not greater than the first set threshold, it indicates that the first relative distance obtained in the i-th period has been less than the minimum safety distance, and the first relative distances corresponding to the (i - 1)-th period and the (i + 1)-th period are still within the safety distance range. It can be considered that there is a possibility of a jump in the target position corresponding to the i-th period. To detect whether there is a jump in the target position corresponding to the i-th period, it is necessary to calculate the second position deviation between the target position corresponding to the i-th period and the target position corresponding to the (i - 1)-th period, and the third position deviation between the target position information corresponding to the (i + 1)-th period and the target position information corresponding to the i-th period. If both the calculated second position deviation and third position deviation are not greater than the second set threshold, it can be considered that the deviation between the target position corresponding to the i-th period and the target position corresponding to the (i - 1)-th period, and the deviation between the target position corresponding to the i-th period and the target position corresponding to the (i + 1)-th period are both large. Generally speaking, the deviation of the target position within the time of adjacent periods will not be too large. Therefore, it can be determined that the target position corresponding to the i-th period has jumped, and it has jumped back to the correct position in the (i + 1)-th period. Therefore, the actual relative distance between the target obstacle and the vehicle is within the safety distance. Therefore, before the automatic braking function is accidentally triggered, it is necessary to suppress the triggering of the automatic braking function, so as to reduce the accidental triggering of the automatic braking function due to the misdetection of the target obstacle position, thereby improving the user experience.

[0083] Figure 3 A method for obtaining target obstacle information provided in the embodiments of the present application. As a possible implementation manner, when performing step 101, the specific method for obtaining target obstacle information can be implemented through steps 301 - 306:

[0084] Step 301: Periodically obtain the first position of the target obstacle collected by the millimeter-wave radar and the second position of the target obstacle collected by the binocular camera.

[0085] Step 302: Calculate the fourth position deviation between the first position corresponding to the i-th period and the second position corresponding to the i-th period.

[0086] Step 303: Determine whether the fourth position deviation is greater than the third set threshold.

[0087] Step 304: If the fourth position deviation is greater than the third set threshold, calculate the fifth position deviation between the first position corresponding to the i-th cycle and the first position corresponding to the (i - 1)-th cycle, and the sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i - 1)-th cycle.

[0088] Step 305: If the fifth position deviation is greater than the fourth set threshold and the sixth position deviation is not greater than the fifth set threshold, assign a first confidence weight to the first position corresponding to the i-th cycle to generate a first weighted position, and assign a second confidence weight to the second position corresponding to the i-th cycle to generate a second weighted position, where the first confidence weight is less than the second confidence weight.

[0089] Step 306: Input the first weighted position and the second weighted position into a fusion algorithm to generate a target position.

[0090] In an embodiment of the present application, after the millimeter-wave radar acquires the first position of the target obstacle and the binocular camera acquires the second position of the target obstacle, in order to check whether there is an error in the positions of the target obstacle obtained by the millimeter-wave radar and the binocular camera, it can be checked by calculating the fourth position deviation between the first position and the second position and judging the relationship between the fourth position deviation and the third set threshold. If the fourth position deviation is greater than the third set threshold (the third set threshold is the maximum allowable error between the first position and the second position, which can be adjusted according to requirements and is not limited herein), it indicates that there is a large deviation between the position obtained by the millimeter-wave in the i-th cycle and the position obtained by the binocular camera. It should be understood that the first position or the second position may jump. In order to check whether the first position and the second position jump, calculate the fifth deviation value between the first position corresponding to the i-th cycle and the first position corresponding to the i-1-th cycle, and calculate the sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the i-1-th cycle, and judge the relationship between the fifth position deviation and the fourth set threshold (since the time of each cycle is short, the change amount of the first position between adjacent cycles cannot be greater than the fourth set threshold. The fourth set threshold is the maximum allowable error of the deviation value between the first positions of adjacent cycles. The fourth set threshold can be adjusted according to actual requirements and is not specifically limited in this application) and the relationship between the fifth position deviation and the fifth set threshold (since the time of each cycle is short, the change amount of the second position between adjacent cycles cannot be greater than the fifth set threshold. The fifth set threshold is the maximum allowable error of the deviation value between the second positions of adjacent cycles. The fifth set threshold can be adjusted according to actual requirements and is not specifically limited in this application) to check. If the fifth position deviation is greater than the fourth set threshold and the sixth position deviation is not greater than the fifth set threshold, it indicates that in the i-th cycle, the first position obtained by the millimeter-wave radar jumps while the second position obtained by the binocular camera does not jump. It can be considered that the non-jumping second position is more accurate than the jumping first position. At this time, assign the first confidence weight to the first position corresponding to the i-th cycle to generate the first weighted position, assign the second confidence weight to the second position corresponding to the i-th cycle to generate the second weighted position, and then input the first weighted position and the second weighted position into the fusion algorithm to generate the target position. The first confidence weight is less than the second confidence weight. It can be considered that the confidence level of the jumping first position is lower and the confidence level of the non-jumping second position is higher when calculating the target position. Among them, the confidence level is also called the reliability. The higher the confidence level, the higher the accuracy of the data, so that the influence of the jump of the first position on the accuracy of determining the target position is smaller, thereby improving the accuracy of determining the target position.

[0091] Figure 4A method for obtaining target obstacle information provided in an embodiment of the present application. As a possible implementation manner, after step 304 is executed, the method for specifically obtaining target obstacle information can also be implemented through steps 307-308:

[0092] Step 307: If the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, assign a third confidence weight to the first position corresponding to the i-th cycle to generate a third weighted position, and assign a fourth confidence weight to the second position corresponding to the i-th cycle to generate a fourth weighted position, where the third confidence weight is greater than the fourth confidence weight.

[0093] Step 308: Input the third weighted position and the fourth weighted position into a fusion algorithm to generate a target position.

[0094] In an embodiment of the present application, after calculating the fifth position deviation and the sixth position deviation, if the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, it indicates that in the i-th cycle, the second position obtained by the binocular camera has jumped while the first position obtained by the millimeter-wave radar has not jumped. It can be considered that the first position that has not jumped is more accurate than the second position that has jumped. At this time, assign a third confidence weight to the first position corresponding to the i-th cycle to generate a third weighted position, assign a fourth confidence weight to the second position corresponding to the i-th cycle to generate a fourth weighted position, and then input the third weighted position and the fourth weighted position into the fusion algorithm to generate a target position. The third confidence weight is greater than the fourth confidence weight. It can be considered that the confidence level of the second position that has jumped is lower and the confidence level of the first position that has not jumped is higher when calculating the target position. Among them, the confidence level is also called the reliability. The higher the confidence level, the higher the accuracy of the data, so that the impact of the jump of the second position on the accuracy of determining the target position is smaller, thereby improving the accuracy of determining the target position.

[0095] Figure 5 A method for obtaining the first position and the second position provided in an embodiment of the present application. As a possible implementation manner, when step 301 is executed, the specific process of obtaining the first position and the second position can be implemented through steps 401-403:

[0096] Step 401: Periodically obtain the first target obstacle feature collected by the millimeter-wave radar and the second target obstacle feature collected by the binocular camera.

[0097] Step 402: Determine whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle.

[0098] Step 403: If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, determine a first position based on the first target obstacle feature and determine a second position based on the second target obstacle feature.

[0099] In the embodiment of the present application, after the millimeter-wave radar collects the first target obstacle feature and the binocular camera collects the second target obstacle feature, in order to detect whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, it can be detected by comparing the first obstacle feature and the second obstacle feature. If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, a first position is determined based on the first target obstacle and a second position is determined based on the second target obstacle feature. It can be considered that both the first position and the second position represent the position of the same obstacle. And collecting the position information of the same obstacle based on different acquisition subjects respectively can provide more reference data for the fusion algorithm to calculate the target position, making the determined target position more accurate, thereby avoiding the determined target position being affected by the positions of other obstacles.

[0100] Figure 6 For a control method of a braking function provided in the embodiment of the present application, please refer to Figure 6 When performing step 101, it can be specifically implemented by step 501:

[0101] Step 501: Send a disabling instruction to the automatic braking system within a set time, and the disabling instruction is used to disable the automatic braking function.

[0102] In the embodiment of the present application, if it is detected that the target position corresponding to a certain period jumps, resulting in an imminent mis-triggering of the automatic braking function, a disabling instruction is sent to the automatic braking system within a set time. Among them, within the set time (the set time is very short, and the specific value of the set time can be adjusted according to actual needs, and the present application does not make a specific limitation), the automatic braking function cannot be triggered yet. It can be considered that the automatic braking function can be suppressed in a short time, thereby effectively reducing the probability of mis-triggering of the automatic braking function.

[0103] Please refer to Figure 7 Based on the same inventive concept, the embodiment of the present application further provides a control device for a braking function. The device includes: an acquisition unit 601, a calculation unit 602, and a control unit 603.

[0104] An acquisition unit 601 is configured to periodically acquire target obstacle information during the driving of a vehicle. The target obstacle information includes the target position of a target obstacle and a first relative distance between the vehicle and the target obstacle. The target position is generated after the positions of the target obstacle detected by a millimeter-wave radar and the positions of the target obstacle detected by a binocular camera are input into a fusion algorithm. The first relative distance is generated by the fusion algorithm based on the target position;

[0105] A calculation unit 602 is configured to calculate a first position deviation between the target position corresponding to the i-th period and the target position corresponding to the (i - 1)-th period if the first relative distance corresponding to the i-th period is not greater than a first set threshold and the first relative distance corresponding to the (i - 1)-th period is greater than the first set threshold;

[0106] A control unit 603 is configured to inhibit the triggering of the automatic braking function if the first position deviation is not less than a second set threshold.

[0107] Optionally, the calculation unit 602 is further configured to calculate a second position deviation between the target position corresponding to the i-th period and the target position corresponding to the (i - 1)-th period and a third position deviation between the target position information corresponding to the (i + 1)-th period and the target position information corresponding to the i-th period if the first relative distances corresponding to the (i + 1)-th period and the (i - 1)-th period are greater than the first set threshold and the first relative distance corresponding to the i-th period is not greater than the first set threshold;

[0108] The control unit 603 is further configured to inhibit the triggering of the automatic braking function if both the second position deviation and the third position deviation are not less than the second set threshold.

[0109] Optionally, the acquisition unit 601 includes:

[0110] An acquisition subunit is configured to periodically acquire a first position of a target obstacle collected by a millimeter-wave radar and a second position of the target obstacle collected by a binocular camera;

[0111] A first calculation subunit is configured to calculate a fourth position deviation between the first position corresponding to the i-th period and the second position corresponding to the i-th period;

[0112] A judgment subunit is configured to judge whether the fourth position deviation is greater than a third set threshold;

[0113] A second calculation subunit is configured to calculate a fifth position deviation between the first position corresponding to the i-th period and the first position corresponding to the (i - 1)-th period and a sixth position deviation between the second position corresponding to the i-th period and the second position corresponding to the (i - 1)-th period if the fourth position deviation is greater than the third set threshold;

[0114] The first generation subunit is configured to, if the fifth position deviation is greater than the fourth set threshold and the sixth position deviation is not greater than the fifth set threshold, assign a first confidence weight to the first position corresponding to the i-th cycle, generate a first weighted position, and assign a second confidence weight to the second position corresponding to the i-th cycle, generate a second weighted position, where the first confidence weight is less than the second confidence weight;

[0115] The second generation subunit is configured to input the first weighted position and the second weighted position into a fusion algorithm to generate a target position.

[0116] Optionally, the first generation subunit is further configured to, if the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, assign a third confidence weight to the first position corresponding to the i-th cycle, generate a third weighted position, and assign a fourth confidence weight to the second position corresponding to the i-th cycle, generate a fourth weighted position, where the third confidence weight is greater than the fourth confidence weight;

[0117] The second generation subunit is further configured to input the third weighted position and the fourth weighted position into a fusion algorithm to generate a target position.

[0118] Optionally, the acquisition subunit is specifically configured to:

[0119] Determine whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle;

[0120] If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, determine a first position based on the first target obstacle feature and determine a second position based on the second target obstacle feature.

[0121] Optionally, the control unit 603 is specifically configured to:

[0122] Send a disable instruction to the automatic braking system within a set time, where the disable instruction is used to disable the automatic braking function.

[0123] Please refer to Figure 8 , based on the same inventive concept, an embodiment of the present application provides a vehicle controller 100, where the vehicle controller 100 includes at least one processor 701, and the processor 701 is configured to execute a computer program stored in a memory to implement the steps of the control method for the braking function provided in the embodiment of the present application as Figures 1-6 shown.

[0124] Optionally, the vehicle controller 100 may further include a memory 702 connected to at least one processor 701. The memory 702 may include ROM, RAM, and disk storage. The memory 702 is used to store data required for the operation of the processor 701, that is, instructions executable by at least one processor 701 are stored. The at least one processor 701 executes the instructions stored in the memory 702 to perform as Figure 1 shown in the method. Among them, the number of memories 702 is one or more. Among them, the memory 702 is shown together in the figure, but it should be noted that the memory 702 is not an essential functional module, so in Figure 8 it is shown by a dashed line.

[0125] Among them, the entity devices corresponding to the acquisition unit 601, the calculation unit 602, and the control unit 603 may all be the aforementioned processor 701. The vehicle controller 100 can be used to execute Figures 1-6 the method provided by the embodiment shown. Therefore, for the functions that can be realized by each functional module in the controller, reference can be made to the corresponding description in the embodiment shown in Figures 1-6 and will not be elaborated here.

[0126] The embodiment of the present application also provides a computer storage medium. Among them, the computer storage medium stores computer instructions. When the computer instructions run on a computer, the computer is caused to execute as executed Figures 1-6 in the method described.

[0127] Please refer to Figure 9 , the embodiment of the present application also provides a vehicle 200. The vehicle 200 includes a vehicle controller 100 as Figure 8 shown.

[0128] The above are only the preferred embodiments of this specification and are not intended to limit this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification shall be included within the scope of protection of this specification.

Claims

1. A control method for a braking function, characterized in that, The method includes: Periodically obtaining target obstacle information during the driving of the vehicle, where the target obstacle information includes the target position of the target obstacle and a first relative distance between the vehicle and the target obstacle, the target position is generated after the positions of the target obstacle detected by a millimeter-wave radar and the positions of the target obstacle detected by a binocular camera are input into a fusion algorithm, and the first relative distance is generated by the fusion algorithm based on the target position; If the first relative distance corresponding to the i-th period is not greater than a first set threshold and the first relative distance corresponding to the (i - 1)-th period is greater than the first set threshold, calculate a first position deviation between the target position corresponding to the i-th period and the target position corresponding to the (i - 1)-th period; If the first position deviation is not less than a second set threshold, inhibit the triggering of the automatic braking function; Wherein, periodically obtaining target obstacle information during the driving of the vehicle includes: Periodically obtaining a first position of the target obstacle collected by the millimeter-wave radar and a second position of the target obstacle collected by the binocular camera; Calculate a fourth position deviation between the first position corresponding to the i-th period and the second position corresponding to the i-th period; Determine whether the fourth position deviation is greater than a third set threshold; If the fourth position deviation is greater than the third set threshold, calculate a fifth position deviation between the first position corresponding to the i-th period and the first position corresponding to the (i - 1)-th period and a sixth position deviation between the second position corresponding to the i-th period and the second position corresponding to the (i - 1)-th period; If the fifth position deviation is greater than a fourth set threshold and the sixth position deviation is not greater than a fifth set threshold, assign a first confidence weight to the first position corresponding to the i-th period to generate a first weighted position, and assign a second confidence weight to the second position corresponding to the i-th period to generate a second weighted position, where the first confidence weight is less than the second confidence weight; input the first weighted position and the second weighted position into the fusion algorithm to generate the target position; If the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, assign a third confidence weight to the first position corresponding to the i-th period to generate a third weighted position, and assign a fourth confidence weight to the second position corresponding to the i-th period to generate a fourth weighted position, where the third confidence weight is greater than the fourth confidence weight; input the third weighted position and the fourth weighted position into the fusion algorithm to generate the target position.

2. The method according to claim 1, characterized in that, After periodically obtaining target obstacle information during the driving of the vehicle, the method further includes: If the first relative distance corresponding to the (i + 1)-th cycle and the first relative distance corresponding to the (i - 1)-th cycle are greater than the first set threshold and the first relative distance corresponding to the i-th cycle is not greater than the first set threshold, calculate the second position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle, and the third position deviation between the target position information corresponding to the (i + 1)-th cycle and the target position information corresponding to the i-th cycle; If both the second position deviation and the third position deviation are not less than the second set threshold, inhibit the triggering of the automatic braking function.

3. The method according to claim 1, characterized in that, Periodically obtain the first position of the target obstacle collected by the millimeter-wave radar and the second position of the target obstacle collected by the binocular camera, including: Periodically obtain the first target obstacle feature collected by the millimeter-wave radar and the second target obstacle feature collected by the binocular camera; Judge whether the first target obstacle feature and the second target obstacle feature indicate the same target obstacle; If the first target obstacle feature and the second target obstacle feature indicate the same target obstacle, determine the first position based on the first target obstacle feature and determine the second position based on the second target obstacle feature.

4. The method according to claim 1, wherein Inhibit the triggering of the automatic braking function, including: Send a disabling command to the automatic braking system within a set time, and the disabling command is used to disable the automatic braking function.

5. A control device for a braking function, characterized in that, The device includes: An acquisition unit, configured to periodically acquire target obstacle information during the driving of the vehicle, where the target obstacle information includes the target position of the target obstacle and the first relative distance between the vehicle and the target obstacle, the target position is generated after the positions of the target obstacle detected by the millimeter-wave radar and the positions of the target obstacle detected by the binocular camera are input into a fusion algorithm, and the first relative distance is generated by the fusion algorithm based on the target position; A calculation unit, configured to calculate the first position deviation between the target position corresponding to the i-th cycle and the target position corresponding to the (i - 1)-th cycle if the first relative distance corresponding to the i-th cycle is not greater than the first set threshold and the first relative distance corresponding to the (i - 1)-th cycle is greater than the first set threshold; A control unit, configured to inhibit the triggering of the automatic braking function if the first position deviation is not less than the second set threshold; The acquisition unit includes: An acquisition subunit, configured to periodically acquire the first position of the target obstacle collected by the millimeter-wave radar and the second position of the target obstacle collected by the binocular camera; A first calculation subunit, configured to calculate the fourth position deviation between the first position corresponding to the i-th cycle and the second position corresponding to the i-th cycle; A judgment subunit, configured to judge whether the fourth position deviation is greater than the third set threshold; A second computing subunit, configured to calculate a fifth position deviation between the first position corresponding to the i-th cycle and the first position corresponding to the (i-1)-th cycle and a sixth position deviation between the second position corresponding to the i-th cycle and the second position corresponding to the (i-1)-th cycle if the fourth position deviation is greater than the third set threshold; A first generating subunit, configured to assign a first confidence weight to the first position corresponding to the i-th cycle, generate a first weighted position, and assign a second confidence weight to the second position corresponding to the i-th cycle, generate a second weighted position if the fifth position deviation is greater than a fourth set threshold and the sixth position deviation is not greater than a fifth set threshold, and the first confidence weight is less than the second confidence weight; A second generating subunit, configured to input the first weighted position and the second weighted position into the fusion algorithm to generate the target position; The first generating subunit is further configured to assign a third confidence weight to the first position corresponding to the i-th cycle, generate a third weighted position, and assign a fourth confidence weight to the second position corresponding to the i-th cycle, generate a fourth weighted position if the fifth position deviation is not greater than the fourth set threshold and the sixth position deviation is greater than the fifth set threshold, and the third confidence weight is greater than the fourth confidence weight; The second generating subunit is further configured to input the third weighted position and the fourth weighted position into the fusion algorithm to generate the target position.

6. A vehicle controller, characterized in that, The vehicle controller includes at least one processor and a memory connected to the at least one processor, and the at least one processor is configured to implement the steps of the method according to any one of claims 1-4 when executing a computer program stored in the memory.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, implements the steps of the method according to any one of claims 1-4.

8. A vehicle, characterized in that, Including the vehicle controller according to claim 6.

Images