Safety detection method, device and computer equipment based on automatic driving

Abstract

The application relates to a safety detection method and device based on automatic driving, a computer device, a storage medium and a computer program product. The method comprises the following steps: acquiring driving control data of a vehicle in an automatic driving test state and physiological data of a member in the vehicle; brake braking data in the driving control data is extracted; if the brake braking is automatically triggered by an automatic driving system, brake braking speed is extracted from the brake braking data; if the maximum value of the brake braking speed is less than a preset braking speed, vehicle body vibration data corresponding to brake braking is extracted from the brake braking data; if the vehicle body vibration data represents that the vehicle is in a preset vehicle body vibration change interval, a safety detection result of automatic driving of the vehicle is generated according to a comparison result of the physiological data and a preset physiological tension index. The method continuously refines parameter indexes to judge the safety detection result of the automatic driving, overcomes the problem that the safety detection result is relatively one-sided, and improves the accuracy of the safety detection result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of autonomous driving, in particular to a safety detection method and device based on autonomous driving, a computer device, a storage medium and a computer program product. BACKGROUND

[0002] With the development of modern science and technology, intelligent vehicles have become a strategic development direction of the automotive industry, and the autonomous driving technology has become a research hotspot and technical frontier in recent years and has been widely developed.

[0003] The autonomous driving technology is usually realized based on an autonomous driving algorithm. The autonomous driving algorithm includes a number of safety performance test processes from functional requirement acquisition, functional development, software development, software integration testing, vehicle integration testing to final mass production. Until the vehicle with the autonomous driving system completely passes the safety performance test, the vehicle can be mass-produced and delivered.

[0004] However, in the traditional technical solution, the safety detection of the autonomous driving algorithm or the autonomous driving system mainly focuses on the single-function safety performance detection of autonomous driving, the coverage of safety detection is small, the safety detection result obtained is one-sided, and the accuracy is relatively low. SUMMARY

[0005] Therefore, it is necessary to provide a safety detection method, device, computer device, computer readable storage medium and computer program product based on autonomous driving with higher accuracy to solve the above technical problems.

[0006] In a first aspect, the present application provides a safety detection method based on autonomous driving. The method comprises:

[0007] obtaining driving control data of a vehicle in an autonomous driving test state and physiological data of a vehicle occupant;

[0008] extracting brake braking data from the driving control data;

[0009] if the brake braking is automatically triggered by the autonomous driving system, extracting brake braking speed from the brake braking data;

[0010] if the maximum value of the brake braking speed is less than a preset braking speed, extracting vehicle body vibration data corresponding to the brake braking from the brake braking data;

[0011] if the vehicle body vibration data represents that the vehicle is in a preset vehicle body vibration change interval, generating a safety detection result of autonomous driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index.

[0012] In one of the embodiments, the obtaining the driving control data of the vehicle in the automatic driving test state comprises:

[0013] collecting lane marks of a lane where the vehicle is located in the automatic driving test state or distance information between the vehicle tires and the lane lines, and generating lane information of the vehicle driving;

[0014] generating a driving state of the vehicle in the automatic driving test state according to the lane information, the driving state comprising a straight driving state and a lane changing driving state;

[0015] collecting straight driving control data in the straight driving state and lane changing driving control data in the lane changing driving state, and collecting the driving control data of the vehicle in the automatic driving test state.

[0016] In one of the embodiments, the collecting the straight driving control data in the straight driving state comprises:

[0017] collecting first control data generated when the vehicle drives straight in the current lane;

[0018] collecting second control data generated when a non-motor vehicle or a pedestrian enters the current lane;

[0019] collecting third control data generated when a vehicle in an adjacent lane enters the current lane;

[0020] collecting the first control data, the second control data, and the third control data to obtain the straight driving control data.

[0021] In one of the embodiments, the collecting the lane changing driving control data in the lane changing driving state comprises:

[0022] collecting fourth control data generated when the vehicle repeatedly changes lanes;

[0023] collecting fifth control data generated when the vehicle is in road congestion;

[0024] collecting sixth control data generated when the vehicle is in turning driving;

[0025] collecting the fourth control data, the fifth control data, and the sixth control data to obtain the lane changing driving control data.

[0026] In one of the embodiments, the extracting the brake braking speed from the brake braking data comprises:

[0027] extracting action duration of deceleration braking behavior from the brake braking data;

[0028] collecting a vehicle driving speed at which the deceleration braking behavior occurs;

[0029] calculating a braking deceleration speed corresponding to the deceleration braking behavior data according to the action duration and the vehicle driving speed.

[0030] In one embodiment, the extracting the vehicle body vibration data corresponding to the braking from the braking data comprises:

[0031] obtaining a vehicle body vibration natural frequency, a vehicle body vibration acceleration, a vertical direction vibration frequency and a horizontal direction vibration frequency generated by the vehicle when the deceleration braking behavior occurs.

[0032] In one embodiment, the obtaining the physiological data of the in-vehicle member comprises:

[0033] collecting, by an in-vehicle sensor, electrodermal response data, heart rate data, blood pressure data, breathing depth data and eye movement data of the in-vehicle member.

[0034] In a second aspect, the present application further provides a safety detection device based on automatic driving. The device comprises:

[0035] a driving data obtaining module, configured to obtain driving control data of a vehicle in an automatic driving test state and physiological data of an in-vehicle member;

[0036] a braking data extracting module, configured to extract braking data from the driving control data;

[0037] a braking data obtaining module, configured to extract a braking deceleration speed from the braking data when the braking is automatically triggered by an automatic driving system;

[0038] a vehicle body vibration extracting module, configured to extract vehicle body vibration data corresponding to the braking from the braking data when a maximum value of the braking deceleration speed is less than a preset braking speed;

[0039] a detection module, configured to generate a safety detection result of the automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index when the vehicle body vibration data indicates that the vehicle is in a preset vehicle body vibration change interval.

[0040] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0041] obtaining driving control data of a vehicle in an automatic driving test state and physiological data of an in-vehicle member;

[0042] extracting brake braking data in the driving control data;

[0043] extracting brake braking speed from the brake braking data if the brake braking is automatically triggered by the automatic driving system;

[0044] extracting vehicle body vibration data corresponding to the brake braking from the brake braking data if a maximum value of the brake braking speed is less than a preset braking speed;

[0045] generating a safety detection result of the automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index if the vehicle body vibration data indicates that the vehicle is in a preset vehicle body vibration change interval.

[0046] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the following steps:

[0047] obtaining driving control data of a vehicle in an automatic driving test state and physiological data of a member in the vehicle;

[0048] extracting brake braking data in the driving control data;

[0049] extracting brake braking speed from the brake braking data if the brake braking is automatically triggered by the automatic driving system;

[0050] extracting vehicle body vibration data corresponding to the brake braking from the brake braking data if a maximum value of the brake braking speed is less than a preset braking speed;

[0051] generating a safety detection result of the automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index if the vehicle body vibration data indicates that the vehicle is in a preset vehicle body vibration change interval.

[0052] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program, when executed by a processor, implements the following steps:

[0053] obtaining driving control data of a vehicle in an automatic driving test state and physiological data of a member in the vehicle;

[0054] extracting brake braking data in the driving control data;

[0055] extracting brake braking speed from the brake braking data if the brake braking is automatically triggered by the automatic driving system;

[0056] if the maximum value of the brake braking speed is less than the preset braking speed, extracting vehicle body vibration data corresponding to the brake braking from the brake braking data;

[0057] if the vehicle body vibration data represents that the vehicle is in a preset vehicle body vibration change interval, generating a safety detection result of automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index.

[0058] The present application provides a safety detection method and device based on automatic driving, a computer device, a storage medium and a computer program product. The whole scheme is based on driving control data in the automatic driving test state. First, it is judged whether the brake braking data in the driving control data is automatically triggered by the automatic driving system, and the safety of the automatic driving system is detected whether it has the ability to respond to road conditions. Then, it is judged whether the maximum value of the brake braking speed is less than the preset braking speed, and the strength of the automatic driving system in responding to road conditions is detected. Further, the scheme judges whether the vehicle body vibration data when braking is in a preset vehicle body vibration change interval, and whether the physiological data of the vehicle occupants meets the physiological tension index and is in a tense emotional state. From the perspective of the riding experience, the automatic driving in responding to the sudden road conditions is detected. The scheme successively judges different dimensional parameter indexes such as the source of the brake braking data, the brake braking speed, the vehicle body vibration data, and the physiological data, and finally obtains the safety detection result of the automatic driving, which covers more data elements and contents, effectively overcomes the problem of relatively one-sided safety detection result, and improves the accuracy of the safety detection result. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 It is an application environment diagram of the safety detection method based on automatic driving in one embodiment;

[0060] Figure 2 It is a flowchart of the safety detection method based on automatic driving in one embodiment;

[0061] Figure 3 It is a flowchart of the sub-step of obtaining vehicle driving control data in one embodiment;

[0062] Figure 4 It is a flowchart of the safety detection method based on automatic driving in another embodiment;

[0063] Figure 5 It is a structure block diagram of the safety detection device based on automatic driving in one embodiment;

[0064] Figure 6 It is an internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0065] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0066] The safety detection method based on automatic driving provided by the embodiments of the present application can be applied to, for example Figure 1The application environment shown. Among them, the vehicle terminal 102 communicates with the server 104 through the mobile network. The server 104 is provided with a data storage system, which can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. It should be noted that the application environment is an environment for testing the safety of the automatic driving function of the vehicle or the automatic driving system carried by the vehicle. In this environment, the vehicle driving data obtained includes but is not limited to real vehicle test data and simulation test data. In this environment, first, the control instruction of automatic driving is issued to the vehicle terminal 102. In response to this control instruction, the vehicle will be automatically driven, and in the process of automatic driving, the driving control data of the vehicle will be obtained through various sensors of the vehicle, including but not limited to laser radar, high-definition camera and ultrasonic sensor. In addition, the vehicle can also be provided with corresponding sensors inside the vehicle to collect the physiological data of the people inside the vehicle. The driving control data and physiological data collected by various sensors will be temporarily stored in the vehicle terminal 102, and then uploaded to the server 104 through the network communication protocol between the vehicle terminal 102 and the server 104. After obtaining the driving control data of the vehicle in the automatic driving state, the server 104 will first screen the driving control data to determine whether there is a collision behavior or record due to the lack of deceleration and braking operation in the process of automatic driving; if so, it is determined that the safety detection is unqualified. After that, the server 104 will judge the operation source of the braking data in the driving control data to determine whether this operation is the operation performed by the automatic driving system; if not, it is determined that the safety detection of the braking driving system is unqualified. If yes, the next step is to determine whether the maximum value of the braking speed in the automatic driving process is less than the preset braking speed; if not, it is determined that the safety detection is unqualified. If yes, it is further determined whether the vibration of the vehicle body in the braking process is within the vibration frequency range of comfortable feeling; if not, it is determined that the safety detection is unqualified. If yes, the emotional state of the people inside the vehicle is detected based on the physiological data obtained in the foregoing, and it is determined whether they are in a nervous emotional state; if so, it is also determined that the safety detection is unqualified. If not, it is determined that the measured automatic driving system or automatic driving function passes the safety performance detection. It should be further pointed out that in this application environment, the server 104 can be realized by an independent server or a server cluster composed of multiple servers. It should be noted that the safety detection method based on automatic driving of the present application can also be directly applied to the vehicle terminal, and the specific implementation process is similar to the above-mentioned application in the server 104, which will not be described here.

[0067] In one embodiment, as Figure 2As shown, a safety detection method based on automatic driving is provided, and the method is applied to Figure 1 The server 104 in the method is taken as an example for illustration, and the method comprises the following steps:

[0068] In step 202, driving control data of the vehicle in the automatic driving test state and physiological data of the members in the vehicle are acquired.

[0069] The driving control data comprises driving data of the vehicle and control instructions issued by the automatic driving system to the vehicle, and the driving data comprises but is not limited to driving speed, driving mileage, current position information, current lane information, and distance between the vehicle and the preceding and following vehicles, etc., and the control instructions comprise but are not limited to maintaining straight driving, acceleration, deceleration, lane changing, and light control, etc.

[0070] Exemplarily, the vehicle in the embodiment is provided with a Lidar, which uses a laser beam to scan the surrounding environment and measure the distance and shape of the object. In addition, the vehicle can obtain high-precision three-dimensional point cloud data through the Lidar, which is used to obtain real-time obstacle information, map positioning, etc. The vehicle can obtain the current driving speed of the vehicle through the input shaft speed sensor and the output shaft speed sensor of the gearbox. In addition, the vehicle terminal in the embodiment can record and save the vehicle control instructions generated by the automatic driving system in real time. Then, the vehicle terminal transmits the surrounding environment information of the vehicle, the real-time vehicle speed, and the control instruction content generated by the automatic driving system to the server through the network communication protocol between the vehicle terminal and the server.

[0071] In step 204, brake data in the driving control data is extracted.

[0072] The brake data refers to the data record generated after the vehicle completes deceleration braking, which comprises but is not limited to the vehicle speed when the brake action is performed, the action duration until the vehicle is stopped by braking, the brake pad temperature, and the brake distance, etc. In addition, the source of the instruction for performing the brake operation, i.e., whether the control instruction for deceleration braking is from the automatic driving system or the driver, can also be recorded in the brake data in the embodiment, and the source information of the control instruction is associated with the specific brake data record.

[0073] Exemplarily, in the embodiment, after obtaining the driving control data of the vehicle in the automatic driving test state through network communication, the server parses the driving control data, and extracts the brake data from the parsed data content by keyword indexing of the control instruction. It should be noted that after obtaining and parsing the driving control data, the first step of safety detection is entered, and it is first detected whether the collision scratch record of the vehicle is recorded in the driving control data; if not, the brake data in the driving control data is directly extracted, and the next step of safety detection is entered; if so, the collision is caused by the automatic driving system not making a deceleration brake action, or the collision is caused by the automatic driving system making a deceleration brake action, and it is determined that the current automatic driving system fails to pass the safety detection and needs to be further developed and debugged.

[0074] In step 206, if the brake is automatically triggered by the automatic driving system, the brake speed is extracted from the brake data.

[0075] The brake data includes but is not limited to the longitudinal deceleration of the vehicle. Further, the longitudinal direction refers to the front and rear direction of the vehicle, and the longitudinal deceleration refers to the deceleration generated during the forward or backward movement of the vehicle.

[0076] Exemplarily, in the embodiment, after detecting the basic ability of the automatic driving system for safety control in step 204, it is further detected whether the automatic driving system can actively respond to complex road conditions and control the vehicle safely. In the embodiment, after screening whether there is a collision record in the vehicle driving control data and extracting the brake data, it is further judged whether the brake action is completed by the automatic driving system in the brake process. Specifically, after parsing and obtaining the brake data, the server judges whether the automatic driving function cannot handle the current road condition and is taken over by the driver during the deceleration brake process according to the control instruction source of the deceleration brake action in the brake data. If so, it is determined that the automatic driving system fails to pass the safety performance detection; if not, the brake speed needs to be further extracted from the brake speed to perform the next step of safety performance detection. In the process of extracting the brake speed, the identification and extraction of the key field can also be used to obtain the brake speed, i.e., the longitudinal deceleration of the vehicle.

[0077] In step 208, if the maximum value of the brake speed is less than the preset brake speed, the corresponding body vibration data during braking is extracted from the brake data.

[0078] The preset braking speed is a longitudinal deceleration threshold set before the safety performance detection. The vehicle body vibration data in the embodiments include, but are not limited to, the natural frequency of the vehicle body vibration, the acceleration of the vehicle body vibration, the vertical vibration frequency, the horizontal vibration frequency, and the like.

[0079] Exemplarily, in the case where it is determined that the automatic driving system can control the vehicle to complete the deceleration braking behavior without the driver's access, the control capability of the automatic driving system in the process of the deceleration braking behavior is further judged in a more detailed manner to improve the comfort of the automatic driving function in vehicle control. Specifically, after the server analyzes the braking speed and obtains the same deceleration braking behavior in the vehicle driving control data, the server further obtains the vehicle body vibration data generated due to the execution of the deceleration braking behavior. The analysis and acquisition of the vehicle body vibration data can be obtained by indexing the key fields in the braking data corresponding to the braking speed. As for the collection of the vehicle body vibration data, in the embodiments, the vehicle body vibration data generated when the vehicle performs the deceleration braking action can be collected by the built-in acceleration sensor, inertial measurement unit, pressure sensor, and the like in the vehicle. After the server analyzes and obtains the vehicle body vibration data generated due to the deceleration braking action, it is determined whether the vehicle body vibration data falls within the preset comfort experience interval of the vehicle body vibration. If not, the server determines that the automatic driving system fails the safety performance test; if yes, after the server determines that the automatic driving can accurately control the vehicle body, the next round of safety performance detection is performed.

[0080] In step 210, if the vehicle body vibration data indicates that the vehicle is in the preset vehicle body vibration change interval, a safety detection result of the vehicle automatic driving is generated according to the comparison result of the physiological data and the preset physiological stress index.

[0081] The physiological data include, but are not limited to, skin electrical response data, pulse rate data, heart rate data, blood pressure data, relative respiratory depth, eye movement data, and the like. The physiological stress index is a comprehensive index of physiological states such as heart rate, skin temperature, body temperature, and sweating, and is an index for evaluating the body reaction.

[0082] Exemplarily, in the embodiment, the vehicle body vibration data is subjected to safety performance detection through step 208, and after detection, the server will judge the emotional state of the passengers in the vehicle, including the driver and the passengers, based on the physiological data of the passengers, including the driver and the passengers, to determine whether the driver and the passengers are in a tense emotional state during the control process of the automatic driving system controlling the vehicle to respond to the road conditions and take deceleration braking. Specifically, in the embodiment, when the physiological data of the passengers in the vehicle is collected through various sensors in the vehicle, a time mark will be formed according to the physiological data. At the same time, the driving control data, especially the brake data, is collected and formed through the sensors outside the vehicle, and is also given a corresponding time mark. In the embodiment, the association between the driving control data and the physiological data of the passengers in the vehicle can be formed by judging whether the time marks coincide. In the presence of this association, after the server analyzes the driving control data to obtain the brake data, the server performs correlation search according to the time mark of the brake data to obtain the corresponding physiological data of the passengers in the vehicle. Further, according to the physiological tension index preset before the complete program of safety detection is constructed, the physiological data of the passengers in the vehicle is compared. When the galvanic skin response data, pulse rate data, heart rate data, blood pressure data, relative respiratory depth, and eye movement data in the physiological data all reach the corresponding index in the physiological tension index, it is determined that the passengers in the vehicle are in a tense physiological state during the control process of the automatic driving system for vehicle deceleration braking, i.e., the automatic driving system brings an uncomfortable driving or riding experience to the passengers in the vehicle. Based on this comparison result, the server will determine that the automatic driving system fails to pass the safety performance detection. On the contrary, if the physiological data fails to reach the physiological tension index, it is determined that the automatic driving system of the vehicle successfully passes the safety performance detection and can bring a safe and comfortable driving or riding experience to the passengers in the vehicle.

[0083] The above-mentioned safety detection method based on automatic driving first judges whether the brake data in the driving control data is automatically triggered by the automatic driving system under the automatic driving test state, and detects the road condition response capability of the automatic driving system. Then, it is judged whether the maximum value of the brake deceleration speed is less than the preset brake speed, and the strength of the road condition response capability of the automatic driving system is detected. Further, the method judges whether the vehicle body vibration data during braking is in the preset vehicle body vibration change interval, and whether the physiological data of the passengers in the vehicle meets the physiological tension index and is in a tense emotional state, and detects the automatic driving in response to the sudden road conditions from the perspective of the riding experience. The method finally obtains the safety detection result of the automatic driving by continuously refining the parameter indexes, covers more data elements and contents, effectively overcomes the problem of the relative one-sidedness of the safety detection result, and improves the accuracy of the safety detection result.

[0084] To be able to cope with more complex road scene scenarios, in one embodiment, as shown in Figure 3 obtaining the driving control data of the vehicle in the automatic driving test state includes:

[0085] In step 302, the lane marking of the lane in which the vehicle is located in the automatic driving test state, or the distance information between the vehicle tires and the lane lines, is collected to generate lane information of the vehicle driving.

[0086] The lane information is used to describe the lane in which the vehicle is currently driving.

[0087] Exemplarily, since in a specific implementation scenario, the road conditions faced by the vehicle during driving can include lane changing driving or other more complex driving states, therefore, when the server detects the safety of the automatic driving system of the vehicle, more complex vehicle driving operation scenarios should be covered. Therefore, for the driving control data, control data in different driving operation scenarios needs to be collected. For example, in different driving operation scenarios of the vehicle, including straight driving and lane changing driving, during the collection and integration of driving control data, the lane information of the vehicle driving needs to be collected first. In the embodiment, the specific lane marking or the distance between the left and right wheels of the vehicle and the left and right lane lines can be collected by the collection device outside the vehicle, such as a camera or a laser radar, as the lane information of the vehicle driving.

[0088] In step 304, the driving state of the vehicle in the automatic driving test state is generated according to the lane information, wherein the driving state includes a straight driving state and a lane changing driving state.

[0089] Exemplarily, in the embodiment, the lane information collected based on step 302, i.e., the lane marking or the distance between the left and right wheels of the vehicle and the left and right lane lines, is further used to determine the driving state of the current vehicle. For example, if the lane ID (lane_id) collected in a preset time period does not change, it can be determined that the vehicle maintains a straight driving state in the time period. Conversely, if the lane ID changes in a preset time period, it can be determined that the vehicle is in a lane changing driving state in the time period. For another example, whether the distance between the left and right wheels of the vehicle and the left and right lane lines exceeds half of the lane width in a preset time period is used to determine whether the current driving lane changes, so as to determine whether the vehicle is in a straight driving state or a lane changing driving state.

[0090] In step 306, straight driving operation data in a straight driving state and lane changing driving operation data in a lane changing driving state are collected to collect the driving control data of the vehicle in the automatic driving test state.

[0091] Specifically, the embodiments can collect various vehicle control instructions generated by the automatic driving system in a straight driving state or a lane changing driving state. For example, the collected straight driving control data in the straight driving state includes, but is not limited to, control data generated when keeping straight driving, and control data generated when a non-motor vehicle suddenly enters the current lane. In the embodiments, the control operation data executed by the vehicle automatic driving system in different driving states is collected, and different control operation data can be directly labeled with corresponding state labels based on the difference in driving state, and then integrated to form the driving control data of the vehicle in the automatic driving test state. When performing each round of safety performance detection, the state label can be called in time to improve the efficiency of safety detection. Since the driving control data of the vehicle is collected, the driving control data in different states is covered, which provides more comprehensive and reliable data support for safety performance detection, and the accuracy of the safety detection result is higher.

[0092] In one embodiment, the process of collecting straight driving control data in a straight driving state in the method can include the following steps:

[0093] Step one, collecting first control data generated when the vehicle is driving straight in the current lane.

[0094] Step two, collecting second control data generated when a non-motor vehicle or a pedestrian enters the current lane.

[0095] Step three, collecting third control data generated when a vehicle in an adjacent lane enters the current lane.

[0096] Step four, collecting the first control data, the second control data, and the third control data to obtain the straight driving control data.

[0097] Exemplarily, when the vehicle is determined to be in the straight-line driving state in the automatic driving test state, different road condition information is acquired by the camera and the laser radar and other acquisition devices arranged outside the vehicle, and the control data generated by the automatic driving system of the vehicle under different road condition information is synchronously acquired. For example, when the automatic driving system controls the vehicle to keep straight-line driving in the current lane, the control data generated by the automatic driving system is the first control data. For another example, when the vehicle keeps straight-line driving in the current lane, the control data generated by the automatic driving system when the preceding vehicle decelerates or brakes is the first control data. For another example, when the vehicle keeps straight-line driving in the current lane, the control data generated by the automatic driving system when a non-motor vehicle or a pedestrian suddenly enters the front of the lane is the second control data. For another example, when the vehicle keeps straight-line driving in the current lane, the control data generated by the automatic driving system when a vehicle in the adjacent lane suddenly inserts into the current lane is the third control data. The straight-line driving control data formed by the three kinds of different control data is used for safety performance detection of the automatic driving system, so that the safety performance detection can be performed on different road condition information, and more detailed safety detection results can be obtained.

[0098] In one embodiment, the process of collecting the lane-changing driving control data of the vehicle in the lane-changing driving state in the method can include the following steps:

[0099] Step one, collecting the fourth control data generated by the vehicle when repeatedly changing lanes.

[0100] Step two, collecting the fifth control data generated by the vehicle when the road is congested.

[0101] Step three, collecting the sixth control data generated by the vehicle when turning.

[0102] Step four, collecting the fourth control data, the fifth control data, and the sixth control data to obtain the lane-changing driving control data.

[0103] Similarly, in the automatic driving test state, the driving state of the vehicle is judged to be in lane changing operation data. Through the camera and laser radar and other collection devices arranged outside the vehicle, different road condition information is obtained, and the control data generated by the automatic driving system of the vehicle under different road condition information is obtained synchronously. For example, when the vehicle is overtaking by continuously changing lanes, the control data generated by the automatic driving system, or when the vehicle enters or exits the ramp, the control data generated by the automatic driving system when the vehicle completes the parallel driving or lane changing driving, is recorded as the fourth control data. For example, when congestion appears in front and lane changing is needed, the control data generated by the automatic driving system is recorded as the fifth control data. For example, when the vehicle needs to turn, the control data generated by the automatic driving system is recorded as the sixth control data. The lane changing operation data formed by collecting and integrating three kinds of different operation data can be used to detect the safety performance of the automatic driving system under different road condition information, so as to obtain more detailed safety detection results.

[0104] In one embodiment, the method for extracting the brake braking speed from the brake braking data can include the following steps:

[0105] Step one, extract the action duration of deceleration braking behavior from the brake braking data.

[0106] Step two, collect the vehicle speed when the deceleration braking behavior occurs.

[0107] Step three, calculate the brake braking speed corresponding to the deceleration braking behavior data according to the action duration and the vehicle speed.

[0108] Exemplarily, in the embodiment, the server can also identify and index based on the key fields of the data content in the process of analyzing the brake braking data to obtain the action duration of the deceleration braking behavior of the vehicle controlled by the automatic driving system. According to the data record of the deceleration braking behavior, the vehicle speed when the vehicle performs the deceleration braking behavior is extracted from the driving control data of the vehicle, and then the brake braking speed of the vehicle during deceleration braking, i.e. the longitudinal deceleration, is calculated according to the acceleration calculation formula. For example, in the embodiment, the maximum value of the longitudinal deceleration during the deceleration braking of the vehicle is calculated according to the acceleration calculation formula, which is 5.88 m / s 2 , which is about 0.6 times the gravitational acceleration, i.e. 0.6g. g = 9.78030 m / s 2And in the embodiment, the preset braking speed in the safety performance detection is 0.9g, and through comparison, it can be determined that the maximum value of the vehicle braking speed is less than the preset braking speed, and the server determines that the automatic driving system passes the safety performance detection of the current round and enters the safety performance detection of the next round.

[0109] In one embodiment, the process of extracting the corresponding vehicle body vibration data from the brake braking data in the method can be specifically as follows:

[0110] The inherent frequency of vehicle body vibration, vehicle body vibration acceleration, vertical direction vibration frequency, and horizontal direction vibration frequency generated when the vehicle decelerates and brakes are obtained.

[0111] Exemplarily, the preset vehicle body vibration change interval in the embodiment includes the following indexes: inherent frequency of vehicle body vibration 60-80 times / min (1-1.6 Hz); vehicle body vibration acceleration 0.2g-0.3g; vertical direction vibration frequency 4-12.5 Hz; and horizontal direction vibration frequency 0.5-2 Hz. The vehicle body vibration data generated when the automatic driving system controls the vehicle to decelerate and brake is obtained by the acceleration sensor, the inertial measurement unit, and the pressure sensor arranged in the vehicle, and includes the following contents: inherent frequency of vehicle body vibration 65 times / min; vehicle body vibration acceleration 0.18g; vertical direction vibration frequency 5.6 Hz; and horizontal direction vibration frequency 0.43 Hz. The server compares the above vehicle body vibration data with the preset vehicle body vibration change interval, and can directly confirm that the vehicle body vibration acceleration does not fall into the preset vehicle body vibration acceleration interval, and the horizontal direction vibration frequency does not reach the parameter index of the horizontal direction vibration frequency. According to the comparison result, since the preset condition in the embodiment is that each value of the vehicle body vibration data reaches the preset vehicle body vibration change interval or index, it is determined that the automatic driving system does not pass the safety performance detection. Therefore, the server can determine based on the foregoing comparison result that the automatic driving system can pass the safety performance detection.

[0112] In one embodiment, the process of obtaining the physiological data of the vehicle occupant in the method can be specifically as follows:

[0113] The galvanic skin response data, heart rate data, blood pressure data, breathing depth data, and eye movement data of the vehicle occupant are collected by the in-vehicle sensor.

[0114] Exemplarily, the physiological tension index includes the following: the galvanic skin response (GSR) is GSR1248 on average when under tension, GSR846 on average when under terror, surprise, and fear; the normal heart rate is 60 to 100 times per minute; the normal blood pressure parameters are that the systolic pressure is 90 to 140 mmHg, and the diastolic pressure is 60 to 90 mmHg; the breathing rate is 16 to 20 times per minute in a calm state, and the number of blinks per minute is about 15 to 20 times under normal circumstances, and the interval time of blinks is 3 to 5 seconds. The embodiment collects physiological data of the person in the vehicle through the sensors arranged in the vehicle; taking the driver as an example, the collected galvanic skin response is GSR1248; the heart rate is 105 times per minute; the systolic pressure reaches 180 mmHg; the breathing rate is 30 times per minute; and the eye movement frequency is about 25 times. After the server obtains the physiological data of the driver, the server compares the physiological data with the physiological tension index. According to the comparison result, although the values of other physiological data are only slightly higher than the physiological tension index, it can be determined that the driver is obviously in a state of tension through the comparison of the systolic pressure in the blood parameters in the corresponding time. Therefore, the server can determine that the driver is in a state of tension according to the comparison result, and it is determined that the automatic driving system fails to pass the safety performance test.

[0115] The complete implementation process of the safety detection method based on automatic driving provided in the present application is described in detail below in combination with the accompanying drawings. Figure 4 The complete implementation process of the safety detection method based on automatic driving provided in the present application is described in detail below in combination with the accompanying drawings.

[0116] When the preceding vehicle decelerates or brakes, the reaction time of the automatic driving function vehicle to decelerate and brake is defined as safe or not from the following steps:

[0117] Step one, if the automatic driving function does not decelerate and brake to cause a collision or has not decelerated and braked to still cause a collision, it is determined to be unsafe, and if not, it enters step two for determination.

[0118] Step two, if the automatic driving function cannot handle this situation and prompts the driver to take over, it is determined to be unsafe, and if not, it enters step three for determination.

[0119] Step three, if the reaction time of the automatic driving function vehicle to decelerate and brake is short, and the maximum value of the longitudinal deceleration in the entire deceleration and braking process is greater than or equal to 0.9g, it is determined to be unsafe, and if not, it enters step four for determination.

[0120] Step four, if the vehicle body measurement index exceeds the following numerical index in the entire process of the automatic driving function vehicle decelerating and braking, it is determined to be unsafe, and if not, it enters step five for determination:

[0121] A, natural frequency of body vibration 60-80 times / min (1-1.6 Hz);

[0122] B, acceleration of body vibration 0.2g-0.3g;

[0123] C, vertical vibration frequency 4-12.5 Hz;

[0124] D, horizontal vibration frequency 0.5-2 Hz.

[0125] Step five, in the process of deceleration and braking of the automatic driving function vehicle, the physiological indicators of the driver and the passenger exceed the following numerical indicators, if yes, it is determined to be unsafe, if no, the determination is ended, and it is confirmed that the automatic driving function is safe:

[0126] A, galvanic skin response (GSR): average GSR 1248 when nervous, average GSR 846 when frightened, surprised, and scared;

[0127] B, pulse rate / heart rate: normal heart rate 60-100 times / min;

[0128] C, blood pressure: systolic pressure 90-140 mmHg, diastolic pressure 60-90 mmHg;

[0129] D, relative respiratory depth: respiratory rate, 16-20 times / min in a calm state;

[0130] E, eye movement: under normal circumstances, the number of blinks per minute is about 15-20 times, and the interval time of blinking is 3-5 seconds.

[0131] In addition, in this embodiment, weak traffic participants, such as pedestrians, bicycles, electric bicycles, etc., suddenly appear in front of the automatic driving function vehicle; the determination process of steps one to six when the preceding vehicle decelerates or brakes can be repeated.

[0132] Alternatively, when the number of vehicles in the adjacent lane of the automatic driving function vehicle is inserted into the current lane, the determination criteria of steps one to six when the preceding vehicle decelerates or brakes can be repeated.

[0133] Further, in the scenario of lane changing of the automatic driving vehicle, safety determination can also be made according to steps one to six.

[0134] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0135] Based on the same inventive concept, the embodiments of the present application also provide an automatic driving based safety detection device for implementing the above-mentioned automatic driving based safety detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more automatic driving based safety detection device embodiments provided below can refer to the limitations of the automatic driving based safety detection method in the above text, which will not be repeated here.

[0136] In one embodiment, as shown in Figure 5 An automatic driving based safety detection device 500 is provided, comprising: a driving data acquisition module 501, a brake data extraction module 502, a braking data acquisition module 503, a vehicle body vibration extraction module 504 and a detection module 505, wherein:

[0137] The driving data acquisition module 501 is configured to acquire driving control data of a vehicle in an automatic driving test state and physiological data of a vehicle occupant.

[0138] The brake data extraction module 502 is configured to extract brake braking data from the driving control data.

[0139] The braking data acquisition module 503 is configured to extract a brake braking speed from the brake braking data when the brake braking is automatically triggered by the automatic driving system.

[0140] The vehicle body vibration extraction module 504 is configured to extract vehicle body vibration data corresponding to the brake braking from the brake braking data when the maximum value of the brake braking speed is less than a preset braking speed.

[0141] The detection module 505 is configured to generate a safety detection result of the automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index when the vehicle body vibration data indicates that the vehicle is in a preset vehicle body vibration change interval.

[0142] In an embodiment, the driving data acquisition module 501 is further configured to collect lane marks of a lane in which the vehicle is located in the automatic driving test state or distance information between the vehicle tires and the lane marks, and generate lane information of the vehicle driving; generate driving states of the vehicle in the automatic driving test state according to the lane information, the driving states including a straight driving state and a lane changing driving state; collect straight driving control data in the straight driving state and lane changing driving control data in the lane changing driving state, and collect the driving control data of the vehicle in the automatic driving test state.

[0143] In an embodiment, the driving data acquisition module 501 is further configured to collect first control data generated when the vehicle drives straight in a current lane, collect second control data generated when a non-motor vehicle or a pedestrian enters the current lane, collect third control data generated when a vehicle in an adjacent lane enters the current lane, and collect the straight driving control data by collecting the first control data, the second control data and the third control data.

[0144] In an embodiment, the driving data acquisition module 501 is further configured to collect fourth control data generated when the vehicle repeatedly changes lanes, collect fifth control data generated when the vehicle is in a road congestion, collect sixth control data generated when the vehicle turns, and collect the lane changing driving control data by collecting the fourth control data, the fifth control data and the sixth control data.

[0145] In an embodiment, the braking data acquisition module 503 is further configured to extract an action duration of deceleration braking behavior from the brake braking data, collect a vehicle driving speed when the deceleration braking behavior occurs, and calculate a brake braking speed corresponding to the deceleration braking behavior data according to the action duration and the vehicle driving speed.

[0146] In an embodiment, the vehicle body vibration extraction module 504 is further configured to acquire a vehicle body vibration natural frequency, a vehicle body vibration acceleration, a vertical direction vibration frequency and a horizontal direction vibration frequency generated when the vehicle occurs the deceleration braking behavior.

[0147] In an embodiment, the detection module 505 is further configured to collect galvanic skin response data, heart rate data, blood pressure data, breathing depth data and eye movement data of a member in the vehicle through an in-vehicle sensor.

[0148] The above various modules in the safety detection device based on automatic driving can be realized by software, hardware and combinations thereof, in whole or in part. The above various modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the above various modules.

[0149] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 1. Figure 6 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store driving data of an autonomous vehicle. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with terminals outside through network connection. The computer program is executed by the processor to implement a safety detection method based on autonomous driving.

[0150] Those skilled in the art can understand that Figure 6 The structure shown in FIG. 1 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] In one embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0152] In one embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0153] In one embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. The non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0155] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0156] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A safety detection method based on automatic driving, characterized in that, The method comprises: acquiring driving control data of a vehicle in an automatic driving test state and physiological data of a vehicle occupant; extracting brake braking data from the driving control data; if the brake braking is automatically triggered by an automatic driving system, extracting brake braking speed from the brake braking data; if a maximum value of the brake braking speed is less than a preset braking speed, extracting vehicle body vibration data corresponding to brake braking from the brake braking data; if the vehicle body vibration data indicates that the vehicle is in a preset vehicle body vibration change interval, generating a safety detection result of automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index; wherein the acquiring of the driving control data of the vehicle in the automatic driving test state comprises: collecting lane marks of a lane in which the vehicle is located in the automatic driving test state or distance information between vehicle tires and lane lines to generate lane information of vehicle driving; generating a driving state of the vehicle in the automatic driving test state according to the lane information, the driving state comprising a straight-line driving state and a lane-changing driving state; collecting straight-line driving control data in the straight-line driving state and lane-changing driving control data in the lane-changing driving state to collect the driving control data of the vehicle in the automatic driving test state.

2. The method of claim 1, wherein, The collecting of the straight-line driving control data in the straight-line driving state comprises: collecting first control data generated when the vehicle drives straight in a current lane; collecting second control data generated when a non-motor vehicle or a pedestrian enters the current lane; collecting third control data generated when a vehicle in an adjacent lane enters the current lane; collecting the first control data, the second control data and the third control data to obtain the straight-line driving control data.

3. The method of claim 1, wherein, The collecting of the lane-changing driving control data in the lane-changing driving state comprises: collecting fourth control data generated when the vehicle repeatedly changes lanes; collecting fifth control data generated when the vehicle is in road congestion; collecting sixth control data generated when the vehicle turns; collecting the fourth control data, the fifth control data and the sixth control data to obtain the lane-changing driving control data.

4. The method of claim 1, wherein, The extracting of the brake braking speed from the brake braking data comprises: extracting action duration of deceleration braking behavior from the brake braking data; collecting vehicle driving speed when the deceleration braking behavior occurs; calculating brake braking speed corresponding to the deceleration braking behavior data according to the action duration and the vehicle driving speed.

5. The method of claim 1, wherein, The extracting of vehicle body vibration data corresponding to brake braking from the brake braking data comprises: acquiring vehicle body vibration natural frequency, vehicle body vibration acceleration, vertical direction vibration frequency and horizontal direction vibration frequency generated when the deceleration braking behavior occurs.

6. The method according to any one of claims 1 to 5, characterized in that, The acquiring of the physiological data of the vehicle occupant comprises: collecting galvanic skin response data, heart rate data, blood pressure data, breathing depth data and eye movement data of the vehicle occupant through an in-vehicle sensor.

7. An automatic driving-based safety detection device characterized by comprising: The device comprises: a driving data acquisition module configured to acquire driving control data of a vehicle in an automatic driving test state and physiological data of a vehicle occupant; a brake data extraction module configured to extract brake data from the driving control data; a braking data acquisition module configured to extract a brake braking speed from the brake data when the brake braking is automatically triggered by the automatic driving system; a vehicle body vibration extraction module configured to extract vehicle body vibration data corresponding to the brake braking from the brake data when a maximum value of the brake braking speed is less than a preset braking speed; a detection module configured to generate a safety detection result of the automatic driving of the vehicle according to a comparison result of the physiological data and a preset physiological tension index when the vehicle body vibration data indicates that the vehicle is in a preset vehicle body vibration change interval. The driving data acquisition module is further configured to: collect lane marks of a lane in which the vehicle is located in the automatic driving test state or distance information between a tire of the vehicle and a lane line, and generate lane information of driving of the vehicle; generate a driving state of the vehicle in the automatic driving test state according to the lane information, the driving state including a straight-line driving state and a lane-changing driving state; collect straight-line driving control data in the straight-line driving state and lane-changing driving control data in the lane-changing driving state, and collect driving control data of the vehicle in the automatic driving test state.

8. The apparatus of claim 7, wherein, The driving data acquisition module is further configured to: collect first control data generated when the vehicle drives straight in a current lane; collect second control data generated when a non-motor vehicle or a pedestrian enters the current lane; collect third control data generated when a vehicle in an adjacent lane enters the current lane; collect the first control data, the second control data, and the third control data to obtain straight-line driving control data. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images