Braking method, device, electronic equipment and storage medium of vehicle

Abstract

This invention provides a vehicle braking method and apparatus, relating to the field of active safety driving technology. The method includes: calculating a longitudinal collision time based on the longitudinal position of an obstacle relative to the vehicle; determining whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle; if so, determining the detection condition of the collision object using sensors; confirming a target missed detection rate and a target false detection rate from the sensor characteristics, operating conditions, and the distance between the collision object and the vehicle; and determining whether to brake the collision object based on the target missed detection rate and the target false detection rate. This invention, by considering the sensor's false detection rate, missed detection rate, and errors, can effectively reduce false braking and missed braking, thereby achieving more accurate braking and making driving safer.

Description

Technical Field

[0001] This invention relates to the field of active safety driving technology for vehicles, and in particular to a vehicle braking method, a vehicle braking device, an electronic device, and a computer-readable storage medium. Background Technology

[0002] In recent years, with the rapid development of automotive intelligence, more and more sensors have been installed in vehicles, such as inertial navigation, ultrasonic radar, panoramic cameras, millimeter-wave radar, and lidar. Various OEMs have also launched a wide variety of complex intelligent products, and the existing active safety functions have been improved due to the increased use of sensors. Automatic Emergency Braking (AEB) is a widely used automotive active safety technology.

[0003] In existing technologies, AEB calculates the collision time for each target by acquiring the position and motion state of the vehicle and the position and motion state of the target vehicle. This method directly calculates the collision time and triggers the AEB function, which can lead to a series of problems such as false braking and missed braking. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a vehicle braking method, a corresponding vehicle braking device, an electronic device, and a computer-readable storage medium that overcome or at least partially solve the above problems.

[0005] To address the aforementioned problems, embodiments of the present invention disclose a vehicle braking method, the method comprising:

[0006] The longitudinal collision time between the obstacle and the vehicle is calculated based on the longitudinal position of the obstacle relative to the vehicle.

[0007] Based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle, it is determined whether the obstacle is a collision object;

[0008] If so, then the detection condition of the sensor detecting the colliding object is determined;

[0009] Based on the sensor's sensing characteristics, the detection conditions, and the distance of the colliding object relative to the vehicle, a target missed detection rate and a target false detection rate are determined from multiple missed detection rates and multiple false detection rates in the sensing characteristics, and a decision is made on whether to brake the vehicle based on the target missed detection rate and the target false detection rate.

[0010] In one or more embodiments, the sensing characteristics are obtained in the following manner:

[0011] Acquire first target information and second target information of a test vehicle. The test vehicle includes sensors and a truth system. The sensors are used to collect the first target information, and the truth system is used to collect the second target information. The target information includes the target's category, as well as the target's lateral and longitudinal positions, velocity, and acceleration.

[0012] The first target information is associated with the second target information to obtain the sensing characteristics of the sensor; the sensing characteristics include multiple statistical errors, multiple false detection rates and multiple false detection rates of the sensor, and the statistical errors include multiple horizontal and vertical position errors, multiple horizontal and vertical velocity errors and multiple horizontal and vertical acceleration errors of the sensor.

[0013] In one or more embodiments, calculating the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle includes:

[0014] The longitudinal position, longitudinal velocity, and longitudinal acceleration of the obstacle relative to the vehicle are obtained from the sensors.

[0015] The longitudinal collision time between the obstacle and the vehicle is calculated based on the obstacle's longitudinal position, longitudinal velocity, and longitudinal acceleration relative to the vehicle.

[0016] In one or more embodiments, determining whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle includes:

[0017] The lateral position, lateral velocity, and lateral acceleration of the obstacle relative to the vehicle are obtained from the sensors.

[0018] The lateral position of the obstacle relative to the vehicle after the longitudinal collision time is calculated based on the longitudinal collision time, the lateral position, the lateral velocity, and the lateral acceleration.

[0019] Determine whether the lateral position is within a preset range;

[0020] If so, then the obstacle is determined to be the collision object.

[0021] In one or more embodiments, determining the detection condition of the sensor detecting the colliding object includes:

[0022] If the forward-facing camera in the sensor detects the colliding object, but the millimeter-wave radar in the sensor does not detect the colliding object, then the detection condition is condition one.

[0023] If the forward-facing camera does not detect the colliding object, but the millimeter-wave radar does detect the colliding object, then the detection condition is condition two.

[0024] If the forward-facing camera detects the colliding object, and the millimeter-wave radar detects the colliding object, then the detection condition is condition three.

[0025] In one or more embodiments, determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes:

[0026] When the detection condition is condition one, the first distance between the colliding object and the vehicle is calculated, and the first false detection rate of the forward-facing camera and the first false detection rate of the millimeter-wave radar in the sensor are determined based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0027] If the first false detection rate is greater than the first false detection rate threshold and the first false detection rate is less than the first false detection rate threshold, then the vehicle will not be braked.

[0028] In one or more embodiments, determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes:

[0029] When the detection condition is condition two, the second distance between the colliding object and the vehicle is calculated. Based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics, the second false detection rate of the forward-facing camera in the sensor and the second false detection rate of the millimeter-wave radar in the sensor are determined.

[0030] If the second false negative rate is less than the second false negative rate threshold and the second false positive rate is greater than the second false positive rate threshold, then the vehicle will not be braked.

[0031] In one or more embodiments, determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes:

[0032] When the detection condition is condition three, the third distance between the colliding object and the vehicle is calculated. Based on the false detection rate of the distance segment corresponding to the distance in the perception characteristics, the third false detection rate of the forward-facing camera in the sensor and the fourth false detection rate of the millimeter-wave radar in the sensor are determined.

[0033] If the third false detection rate is greater than the third false detection rate threshold, and the fourth false detection rate is greater than the fourth false detection rate threshold, then the vehicle will not be braked;

[0034] If the third false detection rate is less than the third false detection rate threshold and the fourth false detection rate is less than the fourth false detection rate threshold, then the statistical error of the millimeter-wave radar in the sensor is obtained from the perception characteristics, and the final collision time of the colliding object is calculated based on the statistical error, and the vehicle is braked according to the final collision time.

[0035] Accordingly, embodiments of the present invention disclose an order processing apparatus, the apparatus comprising:

[0036] A calculation module is used to calculate the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle.

[0037] The judgment module is used to determine whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle;

[0038] The determination module is used to determine the detection status of the sensor when the obstacle is a collision object;

[0039] The braking module is used to determine a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and to determine whether to brake the vehicle based on the target missed detection rate and the target false detection rate.

[0040] In one or more embodiments, the braking module further includes:

[0041] The target information acquisition sub-template is used to acquire first target information and second target information of the test vehicle. The test vehicle includes sensors and a truth system. The sensors are used to collect first target information, and the truth system is used to collect second target information. The target information includes the target category, as well as the target's lateral and longitudinal position, velocity, and acceleration.

[0042] The sensing characteristics submodule is used to associate the first target information with the second target information to obtain the sensing characteristics of the sensor; the sensing characteristics include multiple statistical errors, multiple false detection rates and multiple false detection rates of the sensor, and the statistical errors include multiple horizontal and vertical position errors, multiple horizontal and vertical velocity errors and multiple horizontal and vertical acceleration errors of the sensor.

[0043] In one or more embodiments, the computing module includes:

[0044] The longitudinal data acquisition submodule is used to acquire the longitudinal position, longitudinal velocity, and longitudinal acceleration of the obstacle relative to the vehicle as detected by the sensor.

[0045] The longitudinal collision time calculation submodule is used to calculate the longitudinal collision time between the obstacle and the vehicle based on the obstacle's longitudinal position, longitudinal velocity, and longitudinal acceleration relative to the vehicle.

[0046] In one or more embodiments, the determining module includes:

[0047] The lateral data acquisition submodule is used to acquire the lateral position, lateral velocity, and lateral acceleration of the obstacle relative to the vehicle as detected by the sensor.

[0048] The lateral position calculation submodule is used to calculate the lateral position of the obstacle relative to the vehicle after the longitudinal collision time based on the longitudinal collision time, the lateral position, the lateral velocity, and the lateral acceleration.

[0049] The judgment submodule is used to determine whether the horizontal position is within a preset range;

[0050] The determination submodule is used to determine the obstacle as the collision object when the lateral position is within a preset range.

[0051] In one or more embodiments, the determining module includes:

[0052] The Condition 1 determination submodule is used to determine the detection condition as Condition 1 if the forward-facing camera in the sensor detects the colliding object but the millimeter-wave radar in the sensor does not detect the colliding object.

[0053] The second working condition determination submodule states that if the forward-facing camera does not detect the colliding object, but the millimeter-wave radar does detect the colliding object, then the detection working condition is working condition two.

[0054] The third working condition determination submodule determines the working condition as follows: if the forward-facing camera detects the colliding object and the millimeter-wave radar detects the colliding object, then the detection working condition is the third working condition.

[0055] In one or more embodiments, the braking module further includes:

[0056] The working condition one data confirmation submodule is used to calculate the first distance between the collision object and the vehicle when the detection working condition is working condition one, and determine the first false detection rate of the forward-facing camera in the sensor and the first false detection rate of the millimeter-wave radar in the sensor based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0057] The first braking submodule is configured to not brake the vehicle if the first false detection rate is greater than the first false detection rate threshold and the first missed detection rate is less than the first missed detection rate threshold.

[0058] In one or more embodiments, the braking module further includes:

[0059] The Condition 2 Data Confirmation Submodule is used to calculate the second distance between the colliding object and the vehicle when the detection condition is Condition 2, and determine the second false detection rate of the forward-facing camera and the second false detection rate of the millimeter-wave radar in the sensor based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0060] The second braking submodule is used to prevent braking of the vehicle if the second missed detection rate is less than the second missed detection rate threshold and the second false detection rate is greater than the second false detection rate threshold.

[0061] In one or more embodiments, the braking module further includes:

[0062] The Condition 3 Data Confirmation Submodule is used to calculate the third distance between the colliding object and the vehicle when the detection condition is Condition 3, and determine the third false detection rate of the forward-facing camera in the sensor and the fourth false detection rate of the millimeter-wave radar in the sensor based on the false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0063] The first working condition three-braking submodule is used to prevent braking of the vehicle if the third false detection rate is greater than the third false detection rate threshold and the fourth false detection rate is greater than the fourth false detection rate threshold.

[0064] The second working condition three-braking submodule is used to obtain the statistical error of the millimeter-wave radar in the sensor from the perception characteristics if the third false detection rate is less than the third false detection rate threshold and the fourth false detection rate is less than the fourth false detection rate threshold, and calculate the final collision time of the colliding object based on the statistical error, and brake the vehicle according to the final collision time.

[0065] Accordingly, embodiments of the present invention disclose an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the various steps of the above-described vehicle braking method embodiments.

[0066] Accordingly, embodiments of the present invention disclose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the various steps of the above-described vehicle braking method embodiments.

[0067] The embodiments of the present invention have the following advantages:

[0068] In this embodiment of the invention, the longitudinal collision time of the obstacle is calculated based on its longitudinal position. Then, based on the longitudinal collision time and the lateral position of the obstacle, it is determined whether the obstacle is a collision object. If so, the obstacle's condition type is determined according to the sensor's detection conditions. Based on the condition type and the sensor's sensing characteristics, namely the missed detection rate, false detection rate, statistical error of each sensor, and preset missed detection rate and false detection rate thresholds, the obstacle is either not braked or the final collision time is calculated before braking. By considering the sensor's missed detection rate and false detection rate and comparing them with the thresholds, the obstacle is not braked, which can reduce AEB false braking. Considering the sensor's statistical error and recalculating the collision time can make the collision time smaller and more likely to trigger AEB braking, thereby reducing AEB missed braking. Because AEB false braking and missed braking are reduced, braking is performed more accurately, making driving safer. Attached Figure Description

[0069] Figure 1 This is a flowchart illustrating the steps of an embodiment of a vehicle braking method according to the present invention;

[0070] Figure 2 This is a schematic diagram of a vehicle position coordinate system according to the present invention;

[0071] Figure 3 This is a schematic diagram of a sensor sensing characteristic table template according to the present invention;

[0072] Figure 4 This is a structural block diagram of an embodiment of a vehicle braking device according to the present invention. Detailed Implementation

[0073] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0074] One of the core concepts of this invention is that, in this embodiment, the longitudinal collision time of the obstacle is calculated based on its longitudinal position. Then, based on the longitudinal collision time and the lateral position of the obstacle, it is determined whether the obstacle is a collision object. If so, the obstacle's condition type is determined according to the sensor's detection conditions. Based on the condition type and the sensor's sensing characteristics, namely, the missed detection rate, false detection rate, statistical error of each sensor, and preset missed detection rate and false detection rate thresholds, the obstacle is either not braked or the final collision time is calculated before braking. By considering the sensor's missed detection rate and false detection rate and comparing them with the thresholds, the obstacle is not braked, which can reduce AEB false braking. Considering the sensor's statistical error and recalculating the collision time can make collision events smaller and more likely to trigger AEB braking, thereby reducing AEB missed braking, false braking and missed braking, and thus braking more accurately, making driving safer.

[0075] Reference Figure 1 The diagram illustrates a step flowchart of a vehicle braking method according to a first embodiment of the present invention, which may specifically include the following steps:

[0076] Step 101: Calculate the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle.

[0077] During actual vehicle operation, with the AEB function activated by the user, the automatic emergency braking system uses radar, ultrasonic waves, cameras, and other devices to detect the road ahead. Once a collision risk is detected, the onboard computer will automatically apply emergency braking, thus ensuring safe travel.

[0078] Specifically, based on the longitudinal position of the obstacle relative to the vehicle detected by the vehicle's sensors, the longitudinal collision time between the obstacle and the vehicle is calculated, such as... Figure 2 The coordinate system of the vehicle is shown, with the center point of the vehicle's front width as the origin, the X-axis as the longitudinal position of the obstacle relative to the vehicle, and the Y-axis as the lateral position of the obstacle relative to the vehicle.

[0079] In this embodiment of the invention, calculating the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle includes:

[0080] The longitudinal position, longitudinal velocity, and longitudinal acceleration of the obstacle relative to the vehicle are obtained from the sensors.

[0081] The longitudinal collision time between the obstacle and the vehicle is calculated based on the obstacle's longitudinal position, longitudinal velocity, and longitudinal acceleration relative to the vehicle.

[0082] Specifically, vehicle sensors detect obstacles and obtain relevant data, acquiring the obstacle's longitudinal position, longitudinal velocity, and longitudinal acceleration relative to the vehicle. The longitudinal collision time between the obstacle and the vehicle is then calculated using the following formula:

[0083]

[0084] Where X is the longitudinal position of the obstacle relative to the vehicle, v x Let a be the longitudinal velocity of the obstacle relative to the vehicle. x Let t0 be the longitudinal acceleration of the obstacle relative to the vehicle, and t0 be the longitudinal collision time between the obstacle and the vehicle.

[0085] Step 102: Based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle, determine whether the obstacle is a collision object.

[0086] Specifically, the system obtains the lateral position of the obstacle relative to the vehicle detected by the vehicle's sensors. Based on the lateral position of the obstacle and the longitudinal collision time of the obstacle, it determines whether the obstacle poses a risk of collision with the vehicle, that is, whether the obstacle is a collision object.

[0087] In this embodiment of the invention, determining whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle includes:

[0088] The lateral position, lateral velocity, and lateral acceleration of the obstacle relative to the vehicle are obtained from the sensors.

[0089] The lateral position of the obstacle relative to the vehicle after the longitudinal collision time is calculated based on the longitudinal collision time, the lateral position, the lateral velocity, and the lateral acceleration.

[0090] Determine whether the lateral position is within a preset range;

[0091] If so, then the obstacle is determined to be the collision object.

[0092] Specifically, vehicle sensors detect obstacles and obtain relevant data, acquiring the obstacle's lateral position, lateral velocity, and lateral acceleration relative to the vehicle. The lateral position y of the obstacle relative to the vehicle after the longitudinal collision time t0 is then calculated using the following formula:

[0093]

[0094] Where Y is the lateral position of the obstacle relative to the vehicle, v y Let a be the longitudinal velocity of the obstacle relative to the vehicle.y The longitudinal acceleration of the obstacle relative to the vehicle is given. The lateral position y of the obstacle is determined to be within a preset range, which is [-0.5*W, 0.5*W], where W is the width of the vehicle. When the lateral position y of the obstacle falls within this range, the obstacle is considered to have a collision risk with the vehicle, and the obstacle is confirmed as a collision object.

[0095] Step 103: If yes, then determine the detection condition of the sensor detecting the colliding object.

[0096] When the lateral position y of the obstacle falls within the preset range, the obstacle is confirmed as a collision object, and the vehicle's sensors are confirmed to be detecting the collision object.

[0097] In this embodiment of the invention, determining the detection condition of the sensor detecting the colliding object includes:

[0098] If the forward-facing camera in the sensor detects the colliding object, but the millimeter-wave radar in the sensor does not detect the colliding object, then the detection condition is condition one.

[0099] If the forward-facing camera does not detect the colliding object, but the millimeter-wave radar does detect the colliding object, then the detection condition is condition two.

[0100] If the forward-facing camera detects the colliding object, and the millimeter-wave radar detects the colliding object, then the detection condition is condition three.

[0101] Specifically, the detection condition is determined based on the detection status of the collision object by the sensors. If the collision object is detected by the forward-facing camera but not by the millimeter-wave radar, the detection condition is determined to be condition one; if the collision object is not detected by the forward-facing camera but is detected by the millimeter-wave radar, the detection condition is determined to be condition two; if the collision object is detected by both the forward-facing camera and the millimeter-wave radar, the detection condition is determined to be condition three. In this embodiment, the sensors include a forward-facing camera and a millimeter-wave radar. There are three possibilities, or three detection conditions, depending on whether the forward-facing camera and the millimeter-wave radar detect the collision object.

[0102] It should be noted that, in addition to forward-facing cameras and millimeter-wave radar, sensors may also include other types of sensors. When other types of sensors, such as sensor A, are included, there are seven possibilities, or seven detection conditions, depending on whether the forward-facing camera, millimeter-wave radar, and sensor A detect a collision object. The actual types and number of sensors included can be set according to actual needs in practical applications, and this embodiment of the invention does not limit this.

[0103] Step 104: Based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, determine the target missed detection rate and the target false detection rate from multiple missed detection rates and multiple false detection rates of the sensing characteristics, and determine whether to brake the vehicle based on the target missed detection rate and the target false detection rate.

[0104] Specifically, based on the sensor perception characteristics stored in the vehicle system, the determined detection conditions, and the calculated distance of the colliding object relative to the vehicle, the target missed detection rate and target false detection rate are identified from multiple missed detection rates and multiple false detection rates of the sensor perception characteristics. Then, based on the target missed detection rate and target false detection rate, it is determined whether to brake the vehicle.

[0105] In this embodiment of the invention, the sensing characteristics are obtained in the following manner:

[0106] Acquire first target information and second target information of a test vehicle. The test vehicle includes sensors and a truth system. The sensors are used to collect the first target information, and the truth system is used to collect the second target information. The target information includes the target's category, as well as the target's lateral and longitudinal positions, velocity, and acceleration.

[0107] The first target information is associated with the second target information to obtain the sensing characteristics of the sensor; the sensing characteristics include multiple statistical errors, multiple false detection rates and multiple false detection rates of the sensor, and the statistical errors include multiple horizontal and vertical position errors, multiple horizontal and vertical velocity errors and multiple horizontal and vertical acceleration errors of the sensor.

[0108] Specifically, the test vehicle includes sensors for testing performance and a truth system. The truth system collects and tests data in a real road environment, processes the data to generate data (truth values) with higher reliability than the sensors under test, and achieves rapid data return and verification through remote transmission, dedicated line transmission, and data logistics. It also connects the storage computing platform and the visualization platform, enabling the data to be quickly and efficiently applied to subsequent business, such as evaluating the performance of the sensors under test.

[0109] The system acquires first target information collected by various sensors on the test vehicle and second target information collected by the ground truth system. Target information includes the target category and the target's lateral and longitudinal positions relative to the vehicle at various distance segments, as well as its lateral and longitudinal velocities and accelerations. The acquired first and second target information is parsed, transformed according to a pre-defined unified data structure, and then stored.

[0110] The stored first target information and second target information are correlated offline. Statistical analysis is then performed on the correlated targets to obtain the sensing characteristics of each sensor. These characteristics include the statistical error, false detection rate, and false negative rate of each sensor sensing targets at different short distances (Euclidean distances). The statistical errors include lateral and longitudinal position errors, lateral and longitudinal velocity errors, and lateral and longitudinal acceleration errors. For example... Figure 3 It shows a template of sensor sensing characteristics, including sensor error, false negative rate and false positive rate at different distances (Euclidean distance).

[0111] In this embodiment of the invention, determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes:

[0112] When the detection condition is condition one, the first distance between the colliding object and the vehicle is calculated, and the first false detection rate of the forward-facing camera and the first false detection rate of the millimeter-wave radar in the sensor are determined based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0113] If the first false detection rate is greater than the first false detection rate threshold and the first false detection rate is less than the first false detection rate threshold, then the vehicle will not be braked.

[0114] Specifically, when the determined detection condition is Condition 1, i.e., the colliding object is detected by the forward-facing camera but not by the millimeter-wave radar, the Euclidean distance between the colliding object and the vehicle is first calculated based on the lateral and longitudinal positions of the detected colliding object relative to the vehicle. Then, based on the calculated Euclidean distance, the false detection rate in the distance segment corresponding to the perception characteristics of the forward-facing camera is obtained and determined as the first false detection rate of the forward-facing camera. Based on the calculated Euclidean distance, the false detection rate in the distance segment corresponding to the perception characteristics of the millimeter-wave radar is obtained and determined as the first false detection rate of the millimeter-wave radar. If the first false detection rate is greater than the first false detection rate threshold and the first false detection rate is less than the first false detection rate threshold, the colliding object is ignored and the vehicle is not braked, thereby reducing the false braking of AEB. The threshold is set based on practical experience and can be set according to actual needs in practical applications; this embodiment of the invention does not impose any restrictions on this. In this embodiment of the invention, the false detection rate of the sensor that detects the collision object and the false detection rate of the sensor that does not detect the collision object are determined according to the sensor's sensing characteristics. Then, the false detection rate and the false detection rate are compared with the corresponding thresholds to determine whether to brake the vehicle. By taking into account the false detection rate and the false detection rate of the sensor, the collision object can be braked more accurately.

[0115] In this embodiment of the invention, determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes:

[0116] When the detection condition is condition two, the second distance between the colliding object and the vehicle is calculated. Based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics, the second false detection rate of the forward-facing camera in the sensor and the second false detection rate of the millimeter-wave radar in the sensor are determined.

[0117] If the second false negative rate is less than the second false negative rate threshold and the second false positive rate is greater than the second false positive rate threshold, then the vehicle will not be braked.

[0118] Specifically, when the detection condition is determined to be Condition Two, meaning the colliding object is not detected by the forward-facing camera but is detected by the millimeter-wave radar, the Euclidean distance between the colliding object and the vehicle is first calculated based on the lateral and longitudinal positions of the detected colliding object relative to the vehicle. Then, based on the calculated Euclidean distance, the false detection rate in the distance segment corresponding to the perception characteristics of the forward-facing camera is obtained and determined as the second false detection rate of the forward-facing camera. Based on the calculated Euclidean distance, the false detection rate in the distance segment corresponding to the perception characteristics of the millimeter-wave radar is obtained and determined as the second false detection rate of the millimeter-wave radar. If the second false detection rate is less than the second false detection rate threshold and the second false detection rate is greater than the second false detection rate threshold, the colliding object is ignored and the vehicle is not braked, thereby reducing the false braking of AEB.

[0119] In this embodiment of the invention, determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes:

[0120] When the detection condition is condition three, the third distance between the colliding object and the vehicle is calculated. Based on the false detection rate of the distance segment corresponding to the distance in the perception characteristics, the third false detection rate of the forward-facing camera in the sensor and the fourth false detection rate of the millimeter-wave radar in the sensor are determined.

[0121] If the third false detection rate is greater than the third false detection rate threshold and the fourth false detection rate is greater than the fourth false detection rate threshold, then the vehicle will not be braked, thereby reducing the false braking of AEB.

[0122] If the third false detection rate is less than the third false detection rate threshold and the fourth false detection rate is less than the fourth false detection rate threshold, then the statistical error of the millimeter-wave radar in the sensor is obtained from the perception characteristics, and the final collision time of the colliding object is calculated based on the statistical error, and the vehicle is braked according to the final collision time.

[0123] Specifically, when the detection condition is determined to be condition three, meaning the object being detected by both the forward-facing camera and the millimeter-wave radar, the Euclidean distance between the object and the vehicle is first calculated based on the object's lateral and longitudinal positions relative to the vehicle. Then, based on the calculated Euclidean distance, the false detection rate within the corresponding distance range for the forward-facing camera's perception characteristics is determined as the third false detection rate. Finally, based on the calculated Euclidean distance, the false detection rate within the corresponding distance range for the millimeter-wave radar's perception characteristics is determined as the fourth false detection rate. The third and fourth false detection rates are then compared to their corresponding false detection rate thresholds.

[0124] If the third false detection rate is greater than the third false detection rate threshold and the fourth false detection rate is greater than the fourth false detection rate threshold, then the collision object is ignored and the vehicle is not braked.

[0125] If the third false detection rate is less than the third false detection rate threshold, and the fourth false detection rate is less than the fourth false detection rate threshold, then statistical errors in the sensor's perception characteristics are introduced, and the final collision time of the colliding object is recalculated. Based on the calculated Euclidean distance, the longitudinal position statistical error, longitudinal velocity statistical error, and longitudinal acceleration statistical error in the range segment corresponding to the millimeter-wave radar's perception characteristics are obtained. The final collision time of the colliding object is then calculated based on the following formula:

[0126]

[0127] Among them, ERR X The longitudinal position statistical error of the colliding object. The longitudinal velocity statistical error of the colliding object. Let t be the longitudinal acceleration statistical error of the colliding object, and t be the final collision time of the colliding object. Solving the above formula yields the final collision time of the colliding object. The longitudinal collision time t0 is updated using the final collision time t, and the colliding object is braked based on the final collision time. In this embodiment of the invention, when the false detection rate of the sensors is less than a threshold, the statistical error of the sensors is introduced, and the final collision time of the colliding object is recalculated. By taking the statistical error factor of the sensors into account, the collision time converges, resulting in a smaller final collision time, which makes it easier to trigger AEB braking, thereby reducing AEB missed braking.

[0128] In this embodiment of the invention, the longitudinal collision time of the obstacle is calculated based on its longitudinal position. Then, based on the longitudinal collision time and the lateral position of the obstacle, it is determined whether the obstacle is a collision object. If so, the obstacle's condition type is determined according to the sensor's detection conditions. Based on the condition type and the sensor's sensing characteristics, namely the missed detection rate, false detection rate, statistical error of each sensor, and preset missed detection rate and false detection rate thresholds, the obstacle is either not braked or the final collision time is calculated before braking. By considering the sensor's missed detection rate and false detection rate and comparing them with the thresholds, the obstacle is not braked, which can reduce AEB false braking. Considering the sensor's statistical error and recalculating the collision time can make collision events smaller and more likely to trigger AEB braking, thereby reducing AEB missed braking, false braking and missed braking, and thus braking more accurately, making driving safer.

[0129] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0130] Reference Figure 4 The diagram shows a structural block diagram of an embodiment of a vehicle braking device according to the present invention, which may specifically include the following modules:

[0131] The calculation module 401 is used to calculate the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle.

[0132] The judgment module 402 is used to determine whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle;

[0133] The determination module 403 is used to determine the detection condition of the sensor when the obstacle is a collision object;

[0134] The braking module 404 is used to determine a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions and the distance of the collision object relative to the vehicle, and to determine whether to brake the vehicle based on the target missed detection rate and the target false detection rate.

[0135] In this embodiment of the invention, the braking module further includes:

[0136] The target information acquisition sub-template is used to acquire first target information and second target information of the test vehicle. The test vehicle includes sensors and a truth system. The sensors are used to collect first target information, and the truth system is used to collect second target information. The target information includes the target category, as well as the target's lateral and longitudinal position, velocity, and acceleration.

[0137] The sensing characteristics submodule is used to associate the first target information with the second target information to obtain the sensing characteristics of the sensor; the sensing characteristics include multiple statistical errors, multiple false detection rates and multiple false detection rates of the sensor, and the statistical errors include multiple horizontal and vertical position errors, multiple horizontal and vertical velocity errors and multiple horizontal and vertical acceleration errors of the sensor.

[0138] In this embodiment of the invention, the computing module includes:

[0139] The longitudinal data acquisition submodule is used to acquire the longitudinal position, longitudinal velocity, and longitudinal acceleration of the obstacle relative to the vehicle as detected by the sensor.

[0140] The longitudinal collision time calculation submodule is used to calculate the longitudinal collision time between the obstacle and the vehicle based on the obstacle's longitudinal position, longitudinal velocity, and longitudinal acceleration relative to the vehicle.

[0141] In this embodiment of the invention, the determining module includes:

[0142] The lateral data acquisition submodule is used to acquire the lateral position, lateral velocity, and lateral acceleration of the obstacle relative to the vehicle as detected by the sensor.

[0143] The lateral position calculation submodule is used to calculate the lateral position of the obstacle relative to the vehicle after the longitudinal collision time based on the longitudinal collision time, the lateral position, the lateral velocity, and the lateral acceleration.

[0144] The judgment submodule is used to determine whether the horizontal position is within a preset range;

[0145] The determination submodule is used to determine the obstacle as the collision object when the lateral position is within a preset range.

[0146] In this embodiment of the invention, the determining module includes:

[0147] The Condition 1 determination submodule is used to determine the detection condition as Condition 1 if the forward-facing camera in the sensor detects the colliding object but the millimeter-wave radar in the sensor does not detect the colliding object.

[0148] The second working condition determination submodule states that if the forward-facing camera does not detect the colliding object, but the millimeter-wave radar does detect the colliding object, then the detection working condition is working condition two.

[0149] The third working condition determination submodule determines the working condition as follows: if the forward-facing camera detects the colliding object and the millimeter-wave radar detects the colliding object, then the detection working condition is the third working condition.

[0150] In this embodiment of the invention, the braking module further includes:

[0151] The working condition one data confirmation submodule is used to calculate the first distance between the collision object and the vehicle when the detection working condition is working condition one, and determine the first false detection rate of the forward-facing camera in the sensor and the first false detection rate of the millimeter-wave radar in the sensor based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0152] The first braking submodule is configured to not brake the vehicle if the first false detection rate is greater than the first false detection rate threshold and the first missed detection rate is less than the first missed detection rate threshold.

[0153] In this embodiment of the invention, the braking module further includes:

[0154] The Condition 2 Data Confirmation Submodule is used to calculate the second distance between the colliding object and the vehicle when the detection condition is Condition 2, and determine the second false detection rate of the forward-facing camera and the second false detection rate of the millimeter-wave radar in the sensor based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0155] The second braking submodule is used to prevent braking of the vehicle if the second missed detection rate is less than the second missed detection rate threshold and the second false detection rate is greater than the second false detection rate threshold.

[0156] In this embodiment of the invention, the braking module further includes:

[0157] The Condition 3 Data Confirmation Submodule is used to calculate the third distance between the colliding object and the vehicle when the detection condition is Condition 3, and determine the third false detection rate of the forward-facing camera in the sensor and the fourth false detection rate of the millimeter-wave radar in the sensor based on the false detection rate of the distance segment corresponding to the distance in the perception characteristics.

[0158] The first working condition three-braking submodule is used to prevent braking of the vehicle if the third false detection rate is greater than the third false detection rate threshold and the fourth false detection rate is greater than the fourth false detection rate threshold.

[0159] The second working condition three-braking submodule is used to obtain the statistical error of the millimeter-wave radar in the sensor from the perception characteristics if the third false detection rate is less than the third false detection rate threshold and the fourth false detection rate is less than the fourth false detection rate threshold, and calculate the final collision time of the colliding object based on the statistical error, and brake the vehicle according to the final collision time.

[0160] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0161] This invention also provides an electronic device, comprising:

[0162] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described vehicle braking method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0163] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described vehicle braking method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0164] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0165] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0167] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0169] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0170] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0171] The above provides a detailed description of a vehicle braking method and a vehicle braking device provided by the present invention. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A braking method for a vehicle, characterized in that, The vehicle includes sensors; the method includes: The longitudinal collision time between the obstacle and the vehicle is calculated based on the longitudinal position of the obstacle relative to the vehicle. Based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle, it is determined whether the obstacle is a collision object; If so, then the detection condition of the sensor detecting the colliding object is determined; Based on the sensor's sensing characteristics, the detection conditions, and the distance of the colliding object relative to the vehicle, a target missed detection rate and a target false detection rate are determined from multiple missed detection rates and multiple false detection rates in the sensing characteristics, and a decision is made on whether to brake the vehicle based on the target missed detection rate and the target false detection rate.

2. The method according to claim 1, characterized in that, The sensing characteristics are obtained in the following manner: Acquire first target information and second target information of a test vehicle. The test vehicle includes sensors and a truth system. The sensors are used to collect the first target information, and the truth system is used to collect the second target information. The target information includes the target's category, as well as the target's lateral and longitudinal positions, velocity, and acceleration. The first target information is associated with the second target information to obtain the sensing characteristics of the sensor; the sensing characteristics include multiple statistical errors, multiple false detection rates and multiple false detection rates of the sensor, and the statistical errors include multiple horizontal and vertical position errors, multiple horizontal and vertical velocity errors and multiple horizontal and vertical acceleration errors of the sensor.

3. The method according to claim 1, characterized in that, The calculation of the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle includes: The longitudinal position, longitudinal velocity, and longitudinal acceleration of the obstacle relative to the vehicle are obtained from the sensors. The longitudinal collision time between the obstacle and the vehicle is calculated based on the obstacle's longitudinal position, longitudinal velocity, and longitudinal acceleration relative to the vehicle.

4. The method according to claim 1, characterized in that, The step of determining whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle includes: The lateral position, lateral velocity, and lateral acceleration of the obstacle relative to the vehicle are obtained from the sensors. The lateral position of the obstacle relative to the vehicle after the longitudinal collision time is calculated based on the longitudinal collision time, the lateral position, the lateral velocity, and the lateral acceleration. Determine whether the lateral position is within a preset range; If so, then the obstacle is determined to be the collision object.

5. The method according to claim 1, characterized in that, The determination of the detection conditions by which the sensor detects the colliding object includes: If the forward-facing camera in the sensor detects the colliding object, but the millimeter-wave radar in the sensor does not detect the colliding object, then the detection condition is condition one. If the forward-facing camera does not detect the colliding object, but the millimeter-wave radar does detect the colliding object, then the detection condition is condition two. If the forward-facing camera detects the colliding object, and the millimeter-wave radar detects the colliding object, then the detection condition is condition three.

6. The method according to claim 5, characterized in that, The step of determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes: When the detection condition is condition one, the first distance between the colliding object and the vehicle is calculated, and the first false detection rate of the forward-facing camera and the first false detection rate of the millimeter-wave radar in the sensor are determined based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics. If the first false detection rate is greater than the first false detection rate threshold and the first false detection rate is less than the first false detection rate threshold, then the vehicle will not be braked.

7. The method according to claim 5, characterized in that, The step of determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes: When the detection condition is condition two, the second distance between the colliding object and the vehicle is calculated. Based on the false detection rate and false detection rate of the distance segment corresponding to the distance in the perception characteristics, the second false detection rate of the forward-facing camera in the sensor and the second false detection rate of the millimeter-wave radar in the sensor are determined. If the second false negative rate is less than the second false negative rate threshold and the second false positive rate is greater than the second false positive rate threshold, then the vehicle will not be braked.

8. The method according to claim 5, characterized in that, The step of determining a target missed detection rate and a target false detection rate from a plurality of missed detection rates and a plurality of false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and determining whether to brake the vehicle based on the target missed detection rate and the target false detection rate, includes: When the detection condition is condition three, the third distance between the colliding object and the vehicle is calculated. Based on the false detection rate of the distance segment corresponding to the distance in the perception characteristics, the third false detection rate of the forward-facing camera in the sensor and the fourth false detection rate of the millimeter-wave radar in the sensor are determined. If the third false detection rate is greater than the third false detection rate threshold, and the fourth false detection rate is greater than the fourth false detection rate threshold, then the vehicle will not be braked; If the third false detection rate is less than the third false detection rate threshold and the fourth false detection rate is less than the fourth false detection rate threshold, then the statistical error of the millimeter-wave radar is obtained from the perception characteristics, and the final collision time of the colliding object is calculated based on the statistical error, and the vehicle is braked according to the final collision time.

9. A braking method device for a vehicle, characterized in that, The device includes: A calculation module is used to calculate the longitudinal collision time between the obstacle and the vehicle based on the longitudinal position of the obstacle relative to the vehicle. The judgment module is used to determine whether the obstacle is a collision object based on the longitudinal collision time and the lateral position of the obstacle relative to the vehicle; The determination module is used to determine the detection status of the sensor when the obstacle is a collision object; The braking module is used to determine a target missed detection rate and a target false detection rate from multiple missed detection rates and multiple false detection rates based on the sensing characteristics of the sensor, the detection conditions, and the distance of the colliding object relative to the vehicle, and to determine whether to brake the vehicle based on the target missed detection rate and the target false detection rate.

10. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the braking method for the vehicle as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the braking method for the vehicle as described in any one of claims 1-8.

Images