Safety control method and equipment for pilotless automobile and medium

Abstract

The invention discloses a safety control method and device for a driverless car and a medium, relates to the field of driverless driving, and solves the problem that the violation condition of the driverless car cannot be accurately recognized. The method comprises the following steps: collecting the detection self-car data and the detection environment data of the driverless car; judging the violation condition of the driverless car at the static moment by combining the detected self-car data and the detected environment data; judging the violation condition of the driverless car at the moving moment by combining the detected self-car data and the detected environment data; illegal driving and normal driving of the unmanned vehicle within the measurement time are imported into a Seq2Seq model for training, and an illegal detection model corresponding to the unmanned vehicle is obtained; the real-time driving data of the unmanned vehicle are imported into the violation detection model, if the unmanned vehicle is recognized to be in violation driving, the limiting operation is executed, the violation condition of the unmanned vehicle is accurately recognized, and then safety control over the unmanned vehicle is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of driverless technology, and specifically relates to a safety control method, device and medium for a driverless vehicle. Background Technique

[0002] A driverless vehicle, also known as an autonomous vehicle, intelligent vehicle, etc., is a vehicle that integrates advanced technologies such as sensors, computers, and artificial intelligence and can autonomously complete driving tasks; it is an innovative means of transportation that can, without direct operation by a human driver, rely on its various sensors, cameras, radars and other devices, as well as advanced computer systems and algorithms, to perceive the surrounding environment, identify road conditions, make driving decisions, and control the vehicle to travel;

[0003] However, at the current stage, there are still relatively large potential hazards in the control of driverless vehicles. Driverless vehicles cannot accurately judge their own violations, which may lead to traffic accidents and affect human safety;

[0004] Therefore, the present invention proposes a safety control method, device and medium for a driverless vehicle. Summary of the Invention

[0005] The purpose of the present invention is to propose a safety control method, device and medium for a driverless vehicle to solve the problems raised in the above background technique.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] A safety control method for a driverless vehicle, the method includes:

[0008] Step S1, collecting the self-vehicle detection data and environmental detection data of the driverless vehicle within the measurement time;

[0009] Step S2, combining the self-vehicle detection data and environmental detection data to judge the violation situation of the driverless vehicle at the stationary moment;

[0010] Step S3, combining the self-vehicle detection data and environmental detection data to judge the violation situation of the driverless vehicle at the moving moment;

[0011] Step S4, importing the illegal driving and normal driving of the driverless vehicle within the measurement time into the Seq2Seq model for training to obtain the corresponding illegal detection model of the driverless vehicle;

[0012] Step S5, importing the real-time driving data of the driverless vehicle into the illegal detection model. If it is recognized that the driverless vehicle is driving normally, no operation is performed; if it is recognized that the driverless vehicle is driving illegally, a restriction operation is executed.

[0013] Further, the detected vehicle data is the lateral speed, longitudinal speed, longitudinal acceleration, real-time position, and driving direction of the driverless vehicle. The detected environmental data is divided into dynamic environmental data and static environmental data. The dynamic environmental data includes the pedestrian position and pedestrian speed of pedestrians in the traffic road, and the vehicle position and vehicle speed of road vehicles in the traffic road. The static environmental data includes the position of traffic lights and the position of road obstacles.

[0014] Further, the step S2 includes the following sub-steps:

[0015] Step S21, obtain the detected vehicle data of the driverless vehicle to obtain the lateral speed, lateral acceleration, longitudinal speed, longitudinal acceleration, and driving direction of the driverless vehicle within the measurement time;

[0016] Step S22, record the moment when the longitudinal speed is zero as the stationary moment, and record the moment when the longitudinal speed is greater than zero as the moving moment;

[0017] Step S23, for the moving moment, if the lateral speed is zero, record the corresponding moving moment as the straight-line movement moment; if the lateral speed is greater than zero, record the corresponding moving moment as the lane-changing movement moment;

[0018] Step S24, determine the violation situation of the driverless vehicle at the stationary moment.

[0019] Further, the process of determining the violation situation of the driverless vehicle at the stationary moment is specifically as follows:

[0020] Step S241, obtain the detected environmental data of the driverless vehicle to obtain the position of the traffic lights;

[0021] Step S242, obtain the real-time position of the driverless vehicle at the stationary moment; obtain the range area where vehicles are allowed to park on the traffic road;

[0022] Step S243, if the real-time position of the driverless vehicle at the stationary moment is within the range area where vehicles are allowed to park on the traffic road, it is determined that the driverless vehicle is driving normally at the corresponding stationary moment; if the real-time position of the driverless vehicle is outside the range area where vehicles are allowed to park on the traffic road, the subsequent steps are carried out.

[0023] Further, the process of determining the violation situation of the driverless vehicle at the stationary moment further includes:

[0024] Step S244, obtain the detected environmental data to obtain the vehicle position of the road vehicles on the traffic road, and record the road vehicle closest to the driverless vehicle as the selected road vehicle;

[0025] Step S245: Calculate the distance between the driverless vehicle and the traffic signal as the first distance, and calculate the distance between the driverless vehicle and the selected road vehicle as the second distance;

[0026] Step S246: Compare the first distance and the second distance with the corresponding distance thresholds. If either the first distance or the second distance is less than the corresponding distance threshold, it is determined that the driverless vehicle is driving normally at the corresponding stationary moment; if both the first distance and the second distance are greater than the corresponding distance thresholds, it is determined that the driverless vehicle is driving illegally at the corresponding stationary moment.

[0027] Furthermore, step S3 includes the following sub-steps:

[0028] Step S31: Obtain the self-detection data of the driverless vehicle to get the lateral speed, lateral acceleration, longitudinal speed, longitudinal acceleration, and driving direction of the driverless vehicle within the measurement time;

[0029] Step S32: Judge the illegal situation of the driverless vehicle at the moment of straight-line motion. The judgment process is as follows:

[0030] Step S321: Obtain the longitudinal speed ZSD, longitudinal acceleration ZJS, and real-time position of the driverless vehicle at the moment of straight-line motion; obtain the detection environment data of the driverless vehicle to get the vehicle positions and vehicle speeds of the vehicles on the traffic road, and the pedestrian positions and pedestrian speeds of the pedestrians on the traffic road. Denote the road vehicle closest to the driverless vehicle as the selected straight-line vehicle.

[0031] Furthermore, step S3 also includes the following sub-steps:

[0032] Step S322: Calculate the distance between the driverless vehicle and the pedestrian as the third distance. If the third distance is less than the third distance threshold, judge the relationship between the direction of the longitudinal speed of the driverless vehicle and the direction of the pedestrian speed;

[0033] Step S323: If the direction of the longitudinal speed of the driverless vehicle is perpendicular to the direction of the pedestrian speed, judge the magnitude of the longitudinal acceleration of the driverless vehicle; when the longitudinal acceleration is less than zero, it is determined that the driverless vehicle is driving normally at the corresponding straight-line driving moment; when the longitudinal acceleration is greater than or equal to zero, it is determined that the driverless vehicle is driving illegally at the corresponding straight-line driving moment;

[0034] Step S324: If the direction of the longitudinal speed of the driverless vehicle is parallel to the direction of the pedestrian speed, no operation is performed; if the third distance is greater than or equal to the third distance threshold, proceed to the subsequent steps;

[0035] Step S325, calculate the distance between the driverless vehicle and the selected straight vehicle, denoted as the fourth distance DSJ; calculate the predicted speed YCS when the driverless vehicle travels to the vehicle position corresponding to the selected straight vehicle through the formula, and the specific formula is as follows:

[0036]

[0037] Step S326, if the predicted speed is greater than or equal to the vehicle speed corresponding to the selected straight vehicle, it is determined that the driverless vehicle is illegally driving at the corresponding straight driving moment; if the predicted speed is less than the vehicle speed corresponding to the selected straight vehicle, it is determined that the driverless vehicle is normally driving at the corresponding straight driving moment.

[0038] Furthermore, the step S3 further includes the following sub-steps:

[0039] Step S33, judge the illegal situation of the driverless vehicle at the lane-changing movement moment, and the specific judgment process is as follows:

[0040] Step S331, obtain the direction of the lateral speed of the driverless vehicle, and set the lane-changing range according to the direction of the lateral speed;

[0041] Step S332, obtain the detection environment data, get the vehicle positions in the traffic road vehicles, and select the road vehicle closest to the driverless vehicle in the lane-changing range as the selected lane-changing vehicle; if there is no road vehicle in the lane-changing range, it is determined that the driverless vehicle is normally driving at the corresponding lane-changing moment;

[0042] Step S333, calculate the distance between the driverless vehicle and the selected lane-changing vehicle, denoted as the fifth distance;

[0043] Step S334, compare the fifth distance with the fifth distance threshold. If the fifth distance is greater than or equal to the fifth distance threshold, it is determined that the driverless vehicle is normally driving at the corresponding lane-changing moment; if the fifth distance is less than the fifth distance threshold, it is determined that the driverless vehicle is illegally driving at the corresponding lane-changing moment.

[0044] A computer device, the computer device includes:

[0045] A memory storing a computer program;

[0046] A processor communicatively connected to the memory, and when the computer program is executed by the processor, the above method is implemented.

[0047] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above method is implemented.

[0048] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are:

[0049] The present invention first collects the self-vehicle detection data and environmental detection data of a driverless vehicle within a measurement time; then combines the self-vehicle detection data and environmental detection data to determine the violation situation of the driverless vehicle at the stationary moment; at the same time, combines the self-vehicle detection data and environmental detection data to determine the violation situation of the driverless vehicle at the moving moment; further imports the illegal driving and normal driving of the driverless vehicle within the measurement time into a Seq2Seq model for training to obtain a corresponding violation detection model for the driverless vehicle; finally, imports the real-time driving data of the driverless vehicle into the violation detection model. If it is recognized that the driverless vehicle is driving normally, no operation is performed; if it is recognized that the driverless vehicle is driving illegally, a restriction operation is executed; the present invention realizes accurate identification of the violation situation of the driverless vehicle, and further realizes the safety control of the driverless vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0051] Figure 1 is the method flow chart of the present invention;

[0052] Figure 2 is the schematic diagram of the lane change range in the present invention;

[0053] Figure 3 is the schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0055] Embodiment 1, please refer to Figure 1 and Figure 2 As shown, the technical solution provided by the present invention is: a safety control method for a driverless vehicle, which is used to construct a corresponding determination model in combination with the historical behavior data of the driverless vehicle, and import the real-time behavior data of the driverless vehicle into the determination model during the actual driving of the driverless vehicle, so as to determine whether the driverless vehicle violates the regulations;

[0056] In this embodiment, the safety control method is as follows:

[0057] Step S1, collect the self-vehicle detection data and environmental detection data of the driverless vehicle within the measurement time;

[0058] Among them, the self-vehicle data detected includes the lateral speed, longitudinal speed, longitudinal acceleration, real-time position, and driving direction of the driverless vehicle. The detected environmental data is divided into dynamic environmental data and static environmental data. The dynamic environmental data includes the pedestrian position and pedestrian speed of pedestrians in the traffic road, and the vehicle position and vehicle speed of road vehicles in the traffic road. The static environmental data includes the position where the traffic signal is located and the position where the road obstacle is located;

[0059] In the present invention, the longitudinal direction is the direction of road travel, and the lateral direction is the direction perpendicular to the road travel;

[0060] Specifically, the detected self-vehicle data and the detected environmental data can be obtained by collecting through an actual driverless vehicle or through simulation by a simulator.

[0061] Step S2: Combine the detected self-vehicle data and the detected environmental data to determine the violation situation of the driverless vehicle at the stationary moment;

[0062] In this embodiment, the step S2 includes the following sub-steps:

[0063] Step S21: Obtain the detected self-vehicle data of the driverless vehicle to obtain the lateral speed, lateral acceleration, longitudinal speed, longitudinal acceleration, and driving direction of the driverless vehicle within the measurement time;

[0064] Step S22: Denote the moment when the longitudinal speed is zero as the stationary moment, and denote the moment when the longitudinal speed is greater than zero as the moving moment;

[0065] Step S23: For the moving moment, if the lateral speed is zero, then denote the corresponding moving moment as the straight-line movement moment; if the lateral speed is greater than zero, then denote the corresponding moving moment as the lane-changing movement moment;

[0066] Step S24: Determine the violation situation of the driverless vehicle at the stationary moment. The specific judgment process is as follows:

[0067] Step S241: Obtain the detected environmental data of the driverless vehicle to obtain the position where the traffic signal is located;

[0068] Step S242: Obtain the real-time position of the driverless vehicle at the stationary moment; obtain the range area where vehicles are allowed to park in the traffic road;

[0069] Step S243: If the real-time position of the driverless vehicle at the stationary moment is within the range area where vehicles are allowed to park in the traffic road, then it is determined that the driverless vehicle is driving normally at the corresponding stationary moment; if the real-time position of the driverless vehicle is outside the range area where vehicles are allowed to park in the traffic road, then proceed to the subsequent steps;

[0070] Step S244, obtain the detection environment data, get the vehicle positions of the road vehicles in the traffic road, and record the road vehicle closest to the driverless vehicle as the selected road vehicle;

[0071] Step S245, calculate the distance between the driverless vehicle and the traffic signal and record it as the first distance, and calculate the distance between the driverless vehicle and the selected road vehicle and record it as the second distance;

[0072] Step S246, compare the first distance and the second distance with the corresponding distance thresholds. If either the first distance or the second distance is less than the corresponding distance threshold, it is determined that the driverless vehicle is driving normally at the corresponding stationary moment; if both the first distance and the second distance are greater than the corresponding distance threshold, it is determined that the driverless vehicle is driving illegally at the corresponding stationary moment.

[0073] Step S3, combine the detected vehicle data and the detection environment data to judge the illegal situation of the driverless vehicle at the moving moment;

[0074] In this embodiment, the step S3 includes the following sub-steps:

[0075] Step S31, obtain the detected vehicle data of the driverless vehicle, and get the lateral speed, lateral acceleration, longitudinal speed, longitudinal acceleration and driving direction of the driverless vehicle within the measurement time;

[0076] Step S32, judge the illegal situation of the driverless vehicle at the straight-line motion moment, and the judgment process is as follows:

[0077] Step S321, obtain the longitudinal speed ZSD, longitudinal acceleration ZJS and real-time position of the driverless vehicle at the straight-line motion moment; obtain the detection environment data of the driverless vehicle, get the vehicle positions and vehicle speeds of the vehicles in the traffic road, and the pedestrian positions and pedestrian speeds of the pedestrians in the traffic road, and record the road vehicle closest to the driverless vehicle as the selected straight-line vehicle;

[0078] Step S322, calculate the distance between the driverless vehicle and the pedestrian and record it as the third distance. If the third distance is less than the third distance threshold, judge the relationship between the direction of the longitudinal speed of the driverless vehicle and the direction of the pedestrian speed;

[0079] Step S323, if the direction of the longitudinal speed of the driverless vehicle is perpendicular to the direction of the pedestrian speed, judge the magnitude of the longitudinal acceleration of the driverless vehicle; when the longitudinal acceleration is less than zero, it is determined that the driverless vehicle is driving normally at the corresponding straight-line driving moment; when the longitudinal acceleration is greater than or equal to zero, it is determined that the driverless vehicle is driving illegally at the corresponding straight-line driving moment;

[0080] Step S324, if the direction of the longitudinal speed of the driverless vehicle is parallel to the direction of the pedestrian speed, no operation is performed; if the third distance is greater than or equal to the third distance threshold, the subsequent steps are carried out;

[0081] Step S325, calculate the distance between the driverless vehicle and the selected straight vehicle and record it as the fourth distance DSJ; calculate the predicted speed YCS when the driverless vehicle travels to the vehicle position corresponding to the selected straight vehicle through the formula, and the specific formula is as follows:

[0082]

[0083] Step S326, if the predicted speed is greater than or equal to the vehicle speed corresponding to the selected straight vehicle, it is determined that the driverless vehicle is driving illegally at the corresponding straight driving moment; if the predicted speed is less than the vehicle speed corresponding to the selected straight vehicle, it is determined that the driverless vehicle is driving normally at the corresponding straight driving moment;

[0084] Step S33, judge the illegal situation of the driverless vehicle at the lane-changing moment, and the specific judgment process is as follows:

[0085] Step S331, as Figure 2 shown, obtain the direction of the lateral speed of the driverless vehicle, and set the lane-changing range based on the direction of the lateral speed; specifically, the lane-changing range is the range formed by deflecting 45 degrees above and 45 degrees below on one side of the lane-changing direction of the driverless vehicle;

[0086] Step S332, obtain the detection environment data, get the vehicle positions in the traffic road vehicles, and select the road vehicle closest to the driverless vehicle in the lane-changing range and record it as the selected lane-changing vehicle; if there is no road vehicle in the lane-changing range, it is determined that the driverless vehicle is driving normally at the corresponding lane-changing moment;

[0087] Step S333, calculate the distance between the driverless vehicle and the selected lane-changing vehicle and record it as the fifth distance;

[0088] Step S334, compare the fifth distance with the fifth distance threshold. If the fifth distance is greater than or equal to the fifth distance threshold, it is determined that the driverless vehicle is driving normally at the corresponding lane-changing moment; if the fifth distance is less than the fifth distance threshold, it is determined that the driverless vehicle is driving illegally at the corresponding lane-changing moment.

[0089] Step S4, import the illegal driving and normal driving of the driverless vehicle during the measurement time into the Seq2Seq model for training to obtain the illegal detection model corresponding to the driverless vehicle;

[0090] It should be noted that the Seq2Seq model is a deep learning model for processing sequence data. A key feature of this model is that the lengths of the input sequence and the output sequence can be different, thereby enabling real-time detection of the state of an autonomous vehicle.

[0091] Step S5: Import the real-time driving data of the autonomous vehicle into the violation detection model. If the autonomous vehicle is identified as driving normally, no operation is performed; if the autonomous vehicle is identified as driving in violation, a restriction operation is executed.

[0092] Among them, the real-time driving data is the real-time position and real-time vehicle speed of the autonomous vehicle on the traffic road.

[0093] Specifically, the restriction operations include: longitudinal acceleration restriction, steering angular velocity restriction, and violation records.

[0094] In this application, if there are corresponding calculation formulas, the above calculation formulas are all dimensionless and take their numerical values for calculation. The weight coefficients, proportionality coefficients, and other coefficients in the formulas are set to obtain a result value by quantifying each parameter. Regarding the magnitudes of the weight coefficients and proportionality coefficients, as long as the proportional relationship between the parameters and the result value is not affected.

[0095] Embodiment 2 Figure 3 It is a schematic structural diagram of a computer device, which may include: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The processor can call the logical instructions in the memory to execute a safety control method for an autonomous vehicle, and the method includes: collecting the self-vehicle detection data and environmental detection data of the autonomous vehicle within the measurement time; combining the self-vehicle detection data and environmental detection data to judge the violation situation of the autonomous vehicle at the stationary moment; combining the self-vehicle detection data and environmental detection data to judge the violation situation of the autonomous vehicle at the moving moment; importing the violation driving and normal driving of the autonomous vehicle within the measurement time into the Seq2Seq model for training to obtain a corresponding violation detection model for the autonomous vehicle; importing the real-time driving data of the autonomous vehicle into the violation detection model. If the autonomous vehicle is identified as driving normally, no operation is performed; if the autonomous vehicle is identified as driving in violation, a restriction operation is executed.

[0096] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0097] On the other hand, this application also provides a computer program product. The computer program product includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a safety control method for a driverless vehicle provided by the above-mentioned various methods. The method includes: collecting the self-vehicle data and environmental data detected by the driverless vehicle within the measurement time; combining the detected self-vehicle data and environmental data to judge the violation situation of the driverless vehicle at the stationary moment; combining the detected self-vehicle data and environmental data to judge the violation situation of the driverless vehicle at the moving moment; importing the illegal driving and normal driving of the driverless vehicle within the measurement time into the Seq2Seq model for training to obtain a violation detection model corresponding to the driverless vehicle; importing the real-time driving data of the driverless vehicle into the violation detection model. If it is recognized that the driverless vehicle is driving normally, no operation is performed; if it is recognized that the driverless vehicle is driving illegally, a restriction operation is executed.

[0098] In another aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a safety control method for an autonomous vehicle provided above, and the method includes: collecting the self-vehicle data and environmental data detected by the autonomous vehicle within a measurement time; combining the detected self-vehicle data and environmental data to determine the violation situation of the autonomous vehicle at the stationary moment; combining the detected self-vehicle data and environmental data to determine the violation situation of the autonomous vehicle at the moving moment; importing the illegal driving and normal driving of the autonomous vehicle within the measurement time into a Seq2Seq model for training to obtain a violation detection model corresponding to the autonomous vehicle; importing the real-time driving data of the autonomous vehicle into the violation detection model. If it is recognized that the autonomous vehicle is driving normally, no operation is performed; if it is recognized that the autonomous vehicle is driving illegally, a restriction operation is executed.

[0099] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0100] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A safety control method for an unmanned vehicle, characterized in that: Methods include: Step S1, collecting the self-vehicle detection data and the detection environment data of the unmanned vehicle during the measurement time; Step S2, combining the self-vehicle detection data and the detection environment data to determine the violation of the driverless car when it is stationary; Step S3, combining the self-vehicle detection data and the detection environment data to determine the violation of the driverless car during the movement; Step S4, importing the illegal driving and normal driving of the unmanned vehicle during the measurement time into the Seq2Seq model for training, and obtaining a violation detection model corresponding to the unmanned vehicle; Step S5, importing the real-time driving data of the unmanned vehicle into the violation detection model, if the unmanned vehicle is identified as driving normally, no operation is performed; if the unmanned vehicle is identified as driving illegally, a restriction operation is performed.

2. The safety control method for an unmanned vehicle according to claim 1, characterized in that: The detected vehicle data includes the lateral speed, longitudinal speed, longitudinal acceleration, real-time position and driving direction of the unmanned vehicle. The detected environment data is divided into dynamic environment data and static environment data. The dynamic environment data includes the pedestrian position and pedestrian speed of pedestrians on the traffic road, and the vehicle position and vehicle speed of road vehicles on the traffic road. The static environment data includes the location of traffic lights and the location of road obstacles.

3. The safety control method for an unmanned vehicle according to claim 2, characterized in that: The step S2 includes the following sub-steps: Step S21, acquiring the detection data of the unmanned vehicle, and obtaining the lateral speed, lateral acceleration, longitudinal speed, longitudinal acceleration and driving direction of the unmanned vehicle during the measurement time; Step S22, recording the moment when the longitudinal velocity is zero as the stationary moment, and recording the moment when the longitudinal velocity is greater than zero as the moving moment; Step S23, for the movement moment, if the lateral speed is zero, the corresponding movement moment is recorded as the linear movement moment; if the lateral speed is greater than zero, the corresponding movement moment is recorded as the lane change movement moment; Step S24, determining the violation of the unmanned vehicle when it is stationary.

4. The safety control method for an unmanned vehicle according to claim 3, characterized in that: The specific process of determining the violation of the unmanned vehicle at the stationary moment is as follows: Step S241, acquiring detection environment data of the unmanned vehicle and obtaining the location of the traffic light; Step S242, obtaining the real-time position of the unmanned vehicle at the stationary moment; obtaining the range area where the vehicle is allowed to be parked on the traffic road; Step S243, if the real-time position of the unmanned vehicle at the stationary moment is within the range of the traffic road where parking is allowed, it is determined that the unmanned vehicle at the stationary moment is driving normally; If the real-time position of the driverless vehicle is outside the range area where parking vehicles are allowed on the traffic road, proceed to the next step.

5. The safety control method for an unmanned vehicle according to claim 4, characterized in that: The process of determining the violation of the unmanned vehicle at the stationary moment also includes: Step S244, acquiring detection environment data, obtaining the vehicle positions of road vehicles on the traffic road, and recording the road vehicle closest to the unmanned vehicle as the selected road vehicle; Step S245, calculating the distance between the unmanned vehicle and the traffic light as a first distance, and calculating the distance between the unmanned vehicle and the vehicle on the selected road as a second distance; Step S246, compare the first distance and the second distance with the corresponding distance threshold. If either the first distance or the second distance is less than the corresponding distance threshold, the unmanned vehicle at the corresponding stationary moment is deemed to be driving normally; if both the first distance and the second distance are greater than the corresponding distance threshold, the unmanned vehicle at the corresponding stationary moment is deemed to be driving illegally.

6. The safety control method for an unmanned vehicle according to claim 5, characterized in that: The step S3 includes the following sub-steps: Step S31, acquiring the detection data of the unmanned vehicle, and obtaining the lateral speed, lateral acceleration, longitudinal speed, longitudinal acceleration and driving direction of the unmanned vehicle during the measurement time; Step S32, determining the violation of the unmanned vehicle during the straight-line motion, the determination process is as follows: Step S321, obtain the longitudinal speed ZSD, longitudinal acceleration ZJS and real-time position of the unmanned vehicle during straight-line motion; obtain the detection environment data of the unmanned vehicle, obtain the vehicle position and vehicle speed of vehicles on the traffic road, and the pedestrian position and pedestrian speed of pedestrians on the traffic road, and record the road vehicle closest to the unmanned vehicle as the selected straight-line vehicle.

7. A safety control method for an unmanned vehicle according to claim 6, characterized in that: The step S3 further comprises the following sub-steps: Step S322, calculating the distance between the unmanned vehicle and the pedestrian as a third distance, and if the third distance is less than a third distance threshold, determining the relationship between the direction of the corresponding longitudinal speed of the unmanned vehicle and the direction of the pedestrian's speed; Step S323: if the direction of the corresponding longitudinal speed of the unmanned vehicle is perpendicular to the direction of the pedestrian speed, the magnitude of the longitudinal acceleration of the unmanned vehicle is determined; when the longitudinal acceleration is less than zero, it is determined that the unmanned vehicle is driving normally at the corresponding straight-line driving moment; when the longitudinal acceleration is greater than or equal to zero, it is determined that the unmanned vehicle is driving illegally at the corresponding straight-line driving moment; Step S324: if the direction of the longitudinal speed of the unmanned vehicle is parallel to the direction of the pedestrian speed, no operation is performed; if the third distance is greater than or equal to the third distance threshold, subsequent steps are performed; Step S325, calculate the distance between the unmanned vehicle and the selected straight line vehicle as the fourth distance DSJ; calculate the predicted speed YCS of the unmanned vehicle when it reaches the vehicle position corresponding to the selected straight line vehicle by the formula, the specific formula is as follows: Step S326, if the predicted speed is greater than or equal to the vehicle speed corresponding to the selected straight-line vehicle, the unmanned vehicle at the corresponding straight-line driving moment is deemed to be driving illegally; if the predicted speed is less than the vehicle speed corresponding to the selected straight-line vehicle, the unmanned vehicle at the corresponding straight-line driving moment is deemed to be driving normally.

8. The safety control method for an unmanned vehicle according to claim 6, characterized in that: The step S3 further comprises the following sub-steps: Step S33, determining the violation of the unmanned vehicle during the lane change, the determination process is as follows: Step S331, obtaining the direction of the lateral speed of the unmanned vehicle, and setting the lane change range according to the direction of the lateral speed; Step S332, acquiring detection environment data, obtaining the vehicle position in the traffic road vehicles, selecting the road vehicle closest to the unmanned vehicle within the lane change range as the selected lane change vehicle; if there is no road vehicle within the lane change range, the unmanned vehicle is deemed to be driving normally at the corresponding lane change driving moment; Step S333, calculating the distance between the unmanned vehicle and the vehicle that selects to change lanes and recording it as a fifth distance; Step S334, comparing the fifth distance with the fifth distance threshold, if the fifth distance is greater than or equal to the fifth distance threshold, it is determined that the unmanned vehicle at the corresponding lane-changing driving moment is driving normally; If the fifth distance is less than the fifth distance threshold, the unmanned vehicle is deemed to be driving in violation of regulations at the time of lane change.

9. A computer device, characterized in that: The computer device comprises: A memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images