Real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration

By introducing edge data acquisition and simulation modules into the vehicle-road cloud system, evaluating and predicting traffic flow situations, the problems of high decision-making costs and low evaluation accuracy in the existing technology are solved, and effective control and safety monitoring of network roads are achieved.

CN118736839BActive Publication Date: 2024-11-12NANJING AUSKEY SOFTWARE SERVICE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411208073.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-12
Estimated Expiration
2044-08-30

AI Technical Summary

Technical Problem

The existing vehicle-road cloud system is vehicle-centric in decision-making and computing, increasing the decision-making cost, unable to effectively solve the problem of multi-vehicle operation conflicts in network roads, and reduces the accuracy of vehicle expected functional safety assessment, and fails to effectively control traffic. Operation status.

Method used

Adopt real-time monitoring and protection system for expected functional safety based on vehicle-road cloud collaboration, including edge data acquisition module, edge scene simulation module, expected functional safety evaluation module and traffic flow operation situation prediction module, and evaluate through edge data acquisition and simulation model integration Vehicle safety and predict traffic flow situations to achieve real-time control of network roads.

Benefits of technology

It reduces the cost of system decision-making, improves the accuracy of expected functional safety assessment, solves the problem of multi-vehicle operation conflicts, and realizes effective control and protection of network road traffic operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118736839B_ABST
    Figure CN118736839B_ABST
Patent Text Reader

Abstract

The present invention discloses a real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration, which belongs to the field of safety monitoring technology. The present invention includes an edge data acquisition module, an edge scene simulation module, an expected functional safety assessment module and a traffic flow operation status prediction module; the edge data acquisition module is used to acquire edge data around the target vehicle; the edge scene simulation module is used to simulate the edge scene of the target vehicle; the expected functional safety assessment module is used to assess the expected functional safety of the target vehicle; the traffic flow operation status prediction module is used to control the traffic movement of network roads. The present invention integrates the operating environment conditions of the target vehicle into the edge scene simulation model, which is conducive to improving the assessment accuracy of the expected functional safety of the target vehicle, thereby improving the system's monitoring effect on the expected functional safety of the target vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of safety monitoring technology, and specifically to a real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration. Background Art

[0002] The core of the vehicle-road-cloud integration scenario is the vehicle-road-cloud integration system. The vehicle-road-cloud integration system is an information-physical system that integrates the physical space and information space of people, vehicles, roads, and clouds through the new generation of information and communication technologies, and realizes the safe, energy-saving, comfortable, and efficient operation of the intelligent networked vehicle transportation system based on system collaborative perception, decision-making, and control.

[0003] Since the decision-making and calculation of the existing vehicle-road-cloud system solutions are mostly based on vehicles as the final implementers, the decision-making plan for the vehicle is only formulated after all the simulation results of the edge scenarios are obtained, which increases the decision-making cost and cannot solve the operation conflict problem of multiple vehicles on the network road. At the same time, when evaluating the expected functional safety of the car, the operating environment conditions of the car are not taken into account in the evaluation results, thereby reducing the evaluation accuracy and failing to effectively control the traffic operation conditions on the network road. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration, the system comprising an edge data acquisition module, an edge scenario simulation module, an expected functional safety assessment module and a traffic flow operation situation prediction module;

[0006] The edge data acquisition module processes the image information collected by the roadside information acquisition device installed on the target vehicle through the cloud server, determines the acquisition area of ​​the edge data, and acquires the edge data around the target vehicle based on the determination result;

[0007] The edge scene simulation module simulates the edge scene of the target vehicle according to the edge data acquired by the edge data acquisition module, and the traffic signal information and environmental information in the edge data acquisition area;

[0008] The expected functional safety assessment module controls the operating action of the target vehicle through the cloud server according to the edge scenario simulated by the edge scenario simulation module, obtains the braking degree of the target vehicle when the target vehicle enters the control state, and assesses the expected functional safety of the target vehicle based on the obtained information;

[0009] The traffic flow operation status prediction module obtains the expected functional safety assessment value of the vehicles running in any section of network road through the cloud server, obtains the simulation model of the edge scene of each running vehicle in the network road through the edge data acquisition module and the edge scene simulation module, fuses the obtained simulation models to obtain the simulation model of the network road, and obtains the real-time position information and real-time running speed of each running vehicle in the simulation model of the network road. Based on the obtained information, the traffic flow operation status in the section of network road is predicted, and based on the prediction result, the traffic movement of the section of network road is controlled.

[0010] Further, the edge data acquisition module includes an image acquisition unit, an edge data acquisition area determination unit and an edge data acquisition unit;

[0011] The image acquisition unit acquires images around the target vehicle through a road-side information acquisition device installed on the target vehicle, and the road-side information acquisition device uploads the acquired images to a cloud server;

[0012] The edge data acquisition area determination unit identifies the target object in the received image through the cloud server, and the outer contour of the identified target object is the edge data acquisition area;

[0013] The edge data acquisition unit calculates the azimuth range value of the target object existing in each edge data acquisition area compared to the target vehicle, and the minimum distance value of the target object existing in each edge data acquisition area from the target vehicle. The calculated azimuth range value and the minimum distance value are the edge data around the target vehicle. The edge data around the target vehicle={([a1,aw1],d1),…,([an,awn],dn)}, wherein [an,awn] represents the azimuth range value obtained in the edge data acquisition area numbered n, an represents the minimum azimuth angle obtained in the edge data acquisition area numbered n, awn represents the maximum azimuth angle obtained in the edge data acquisition area numbered n, and dn represents the minimum distance value obtained in the edge data acquisition area numbered n.

[0014] Furthermore, the edge data acquisition unit calculates the minimum distance between the target object and the target vehicle in each edge data acquisition area in the following manner:

[0015] The focal length f of the lens of the road-side information collection device is obtained. Among the target objects, the component object closest to the center of the lens of the road-side information collection device is determined. In the image, the width value d of the component object is obtained. The specification and size of the target object are obtained through big data. The specification and size of the target object refer to the length, width and height of the dangerous object. According to D=(length value of the target object*d) / length value of the target object in the image, the actual width value D of the component object is calculated. According to H=(f*D) / d, the minimum distance value of the target object from the target vehicle is calculated.

[0016] Further, the edge scene simulation module includes an information collection unit, a road weather space model construction unit, a target object screening unit and an edge scene simulation unit;

[0017] The information collection unit acquires traffic signal information and environmental information in each edge data acquisition area through a cloud server, wherein the traffic signal information refers to the display seconds and display colors of the traffic signal lights in the edge data acquisition area, and the environmental information refers to the rainfall, visibility and snowfall in the edge data acquisition area;

[0018] The road weather space model construction unit searches for max{d1, ..., dn} according to the edge data around the target vehicle, and K=max{d1, ..., dn}. The road weather space model construction unit obtains the road space model within K meters of the target vehicle through big data, integrates the obtained environmental information and traffic signal information into the road space model for display, and obtains the road weather space model, wherein max represents the maximum value symbol;

[0019] The target object screening unit puts the target object identified by the edge data acquisition area determination unit into a set D. If the target object is a traffic signal indicator light, when the display color of the target object is green, the target object is screened out from the set D. When the display color of the target object is red or yellow, the target object is retained in the set D.

[0020] The edge scene simulation unit constructs a unit space coordinate system in the road weather space model with the position of the target vehicle as the origin, randomly selects a target object in the set D, and determines the dangerous area corresponding to the selected target object until all the target objects in the set D are selected, and integrates the determined dangerous areas into the road weather space model to obtain a simulation model of the edge scene of the target vehicle.

[0021] Furthermore, the specific method for the edge scene simulation unit to determine the dangerous area corresponding to the selected target object is:

[0022] A circle is drawn in the three-dimensional space coordinate system with the minimum distance between the selected target object and the target vehicle as the radius. Rays A1 and A2 are drawn in the three-dimensional space coordinate system according to the azimuth range between the selected target object and the target vehicle. The rays take the origin as the starting point. The angle between ray A1 and the positive semi-axis of the X-axis is as, the angle between ray A2 and the positive semi-axis of the X-axis is aws, s represents the number corresponding to the edge data acquisition area where the selected target object is located, the coordinates of the intersection of ray A1 and the circle are (x1, y1, z1), the coordinates of the intersection of ray A2 and the circle are (x2, y2, z2), x1-x2 is used as the side length of the dangerous area, the intersection coordinates (x1, y1, z1) are used as the lower right vertex of the dangerous area, the dangerous area is integrated into the road meteorological space model, and a simulation model of the edge scene of the target vehicle is obtained.

[0023] Replacing the target object with the dangerous area reduces the time of the edge scene simulation model to depict the target object in detail, which can improve the simulation efficiency of the edge scene, help reduce the delay time of the monitoring result report, and thus improve the safety monitoring effect of the target vehicle.

[0024] Further, the expected function safety assessment module includes an operation control unit, a braking degree acquisition unit and an expected function safety assessment unit;

[0025] The operation control unit obtains the minimum distance value between each target object and the target vehicle stored in the set D, puts the obtained minimum distance value into the set T, searches for the target danger zone according to the number corresponding to minT, and determines the maximum real-time running speed Vt1 of the target vehicle under the current simulation model based on the search result, Vt1=the running speed of the target danger zone at time t, and predicts the real-time danger coefficient of the target vehicle by Vt1 / V1 in combination with the real-time running speed Vt of the target vehicle, compares Vt1 / V1 with the set threshold, and selects whether to control the operation action of the target vehicle through the cloud server based on the comparison result;

[0026] The braking degree acquisition unit controls the operation action of the target vehicle through the cloud server when Vt1 / V1> the set threshold, and then acquires the control degree r of the target vehicle through the cloud server;

[0027] The expected function safety assessment unit assesses the expected function safety of the target vehicle according to the data information acquired by the braking degree acquisition unit, and when the assessment result is less than 0.6, the expected function safety of the target vehicle is protected.

[0028] Furthermore, the specific method for the expected functional safety assessment unit to assess the expected functional safety of the target vehicle is:

[0029] When the operation of the target vehicle is controlled by the cloud server, the running speed V3 of the target vehicle is obtained, and the actual braking acceleration of the target vehicle is calculated in combination with the environmental information and traffic signal information in the current simulation model. The specific calculation method is:

[0030] According to the three-dimensional coordinate distance formula, the distance value b from the center of the target dangerous area to the origin is calculated;

[0031] If the target object corresponding to the target danger zone is a traffic signal indicator, the actual braking acceleration of the target vehicle G1=(-V3 2 ) / (2*b);

[0032] If the target object corresponding to the target danger zone is not a traffic signal indicator, the actual braking acceleration of the target vehicle G2=(Vt1 2 -V3 2 ) / (2*b);

[0033] According to Qt=(-1) θ *u*p*(e1*w rt1 +e2*w rt2 +e3*w rt3 ) calculates the theoretical braking acceleration of the target vehicle, where u represents the control degree of the cloud server over the target object, p represents the change in the theoretical braking acceleration of the target vehicle when the control degree of the cloud server over the target vehicle changes by 1%, e1+e2+e3=1, rt1 represents the rainfall of the current simulation model at time t, rt2 represents the visibility of the current simulation model at time t, rt3 represents the snowfall of the current simulation model at time t, w is a constant and 0<w<1, θ=1 or θ=2, when θ=1, it means that the cloud server brakes the target vehicle in the reverse direction, when θ=2, it means that the cloud server brakes the target vehicle in the forward direction, and Qt represents the theoretical braking acceleration of the target vehicle at time t;

[0034] According to H=G1 / Q t or H = G2 / Q t The expected functional safety of the target vehicle is evaluated, where H represents the evaluation value of the expected functional safety of the target vehicle.

[0035] The expected functional safety of the target vehicle is evaluated based on the braking acceleration of the target vehicle, and when evaluating, the impact of environmental information on the expected functional safety of the target vehicle is taken into account, thereby improving the accuracy of the evaluation.

[0036] Furthermore, the traffic flow operation situation prediction module includes a traffic flow operation situation prediction unit and a traffic control unit;

[0037] The traffic flow operation situation prediction unit determines the congested sections in the network road in the network road simulation model according to the real-time position information and real-time operation speed of each running vehicle in the network road simulation model, combined with the expected functional safety assessment value of each running vehicle, and predicts the traffic flow operation situation in the section of network road according to the congestion coefficient of each congested section;

[0038] The traffic control unit controls the traffic movement in the divided area when the traffic flow operation status in the divided area is a congested state, and does not need to control the traffic movement in the divided area when the traffic flow operation status in the divided area is a smooth state.

[0039] Furthermore, the specific method for the traffic flow operation situation prediction unit to predict the traffic flow operation situation in the section of network road is:

[0040] Ⅰ. According to the driving direction of the running vehicles, the starting point and the end point of the network road are determined in the network road simulation model, and the real-time position of each running vehicle is used as the starting point, and the starting point is used as the target point. The map software is input, and the displayed distance in the map software is used as the real-time distance value of each running vehicle from the starting point;

[0041] Ⅱ. According to the order of real-time distance value from small to large, the running vehicles are numbered, and the numbering result is: j=1,2,…,m; m represents the total number of running vehicles in the network road simulation model. If |Ctμ*Hμ-Ct1*H1|≤γ, Ctμ and Ct1 are put into set K1. If |Ctμ*Hμ-Ct1*H1|>γ, Ctμ is put into set K2. Ctμ represents the running speed of the running vehicle numbered μ at time t, and Ct1 represents the running vehicle numbered 1. The running speed at time t, Hμ represents the expected functional safety assessment value corresponding to the running vehicle numbered μ, γ represents the allowable error value, and according to the DBSCAN clustering method, the running speeds belonging to the noise points are screened out from the set K1 to obtain the set K1´, and the maximum number value in the set K1´ is determined, and the position of the running vehicle corresponding to the determined maximum number value is taken as the first segmentation node of the road, and the network road between the first segmentation node of the road and the starting point is taken as the first segmentation area, where μ=2,…,m;

[0042] When dividing the network roads, the impact of the expected functional safety assessment value of each running vehicle on the braking condition of the running vehicle is taken into consideration to ensure that the running vehicles in each divided area are in the same frequency state, which is conducive to the unified control of the running vehicles in each divided area;

[0043] III. In the network road between the first segmentation node and the end position of the road, the real-time running speed Ctq corresponding to the running vehicle closest to the first segmentation node of the road is determined. If |Cth*Hh-Ctq*Hq|≤γ, Cth and Ctq are put into set K3. If |Cth-Ctq|>γ, Cth is put into set K4. Cth represents the running speed of the running vehicle numbered h at time t. According to the DBSCAN clustering method, the second segmentation area is determined, where h=q,…,m;

[0044] According to the distribution of the running speed of each vehicle on the network road, the network road is segmented, which is conducive to the accurate analysis of the congested sections in the network road, thereby improving the traffic control effect on the network road;

[0045] IV. Repeat the operation in III until the end position of the network road is used as the road segmentation node. The ratio of the total number of running vehicles in the segmentation area to the maximum number of vehicles that the segmentation area can accommodate is used as the congestion coefficient of the segmentation area. If the congestion coefficient of the segmentation area is greater than 0.7, the traffic flow operation situation in the segmentation area is considered to be congested. If the congestion coefficient of the segmentation area is ≤ 0.7, the traffic flow operation situation in the segmentation area is considered to be unblocked.

[0046] V. Based on operation IV, predict the traffic flow situation of each segmented area in the network road.

[0047] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0048] 1. The present invention replaces the target object with the dangerous area, reduces the time of the edge scene simulation model for detailed description of the target object, reduces the decision-making cost of the system solution, and integrates the operating environment conditions of the target vehicle into the edge scene simulation model, which is conducive to improving the assessment accuracy of the expected functional safety of the target vehicle, thereby improving the system's monitoring effect on the expected functional safety of the target vehicle.

[0049] 2. The present invention segments the network roads according to the distribution of the running speeds of each vehicle in the network roads. During the segmentation process, the influence of the expected functional safety assessment value on the braking condition of each vehicle in operation is taken into consideration to ensure that the running vehicles in each segmented area are in the same frequency state of movement, thereby solving the problem of running conflicts of multiple vehicles in the network roads and facilitating unified control of the running vehicles in each divided area.

[0050] 3. The present invention determines the traffic flow operation status of each divided area according to the congestion coefficient of each divided area, thereby achieving effective control of the traffic operation status in the network road and achieving effective protection of the expected functional safety of the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 It is a structural schematic diagram of the working principle of the expected functional safety real-time monitoring and protection system based on vehicle-road-cloud collaboration of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 , the present invention provides a technical solution: a real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration, the system includes an edge data acquisition module, an edge scene simulation module, an expected functional safety assessment module and a traffic flow operation situation prediction module;

[0055] The edge data acquisition module processes the image information collected by the roadside information acquisition device installed on the target vehicle through the cloud server, determines the acquisition area of ​​the edge data, and acquires the edge data around the target vehicle based on the determination result;

[0056] The edge data acquisition module includes an image acquisition unit, an edge data acquisition area determination unit and an edge data acquisition unit;

[0057] The image acquisition unit collects images around the target vehicle through a road-side information acquisition device installed on the target vehicle, and the road-side information acquisition device uploads the collected images to the cloud server;

[0058] The edge data acquisition area determination unit identifies the target objects in the received image through the cloud server. The target objects include dangerous objects and moving objects. Dangerous objects refer to objects that can change the running state of the target vehicle. Dangerous objects include driving warning signs, traffic signal lights, running vehicles equipped with protruding objects, objects flying or falling above the road, running vehicles with a running speed higher than the prescribed speed of the road, and potholes in the road surface. Moving objects refer to running vehicles with a running speed lower than the prescribed speed of the road and without safety hazards. The outer contour of the identified target object is the acquisition area of ​​the edge data;

[0059] The edge data acquisition unit calculates the azimuth range value of the target object existing in each edge data acquisition area compared to the target vehicle, and the minimum distance value of the target object existing in each edge data acquisition area from the target vehicle. The calculated azimuth range value and the minimum distance value are the edge data around the target vehicle. The edge data around the target vehicle={([a1,aw1],d1),…,([an,awn],dn)}, wherein [a1,aw1] represents the azimuth range value obtained in the edge data acquisition area numbered 1, d1 represents the minimum distance value obtained in the edge data acquisition area numbered 1, [an,awn] represents the azimuth range value obtained in the edge data acquisition area numbered n, an represents the minimum azimuth angle obtained in the edge data acquisition area numbered n, awn represents the maximum azimuth angle obtained in the edge data acquisition area numbered n, dn represents the minimum distance value obtained in the edge data acquisition area numbered n, and the unit of dn is meter.

[0060] The method for determining the azimuth angle is as follows: a plane coordinate system is constructed with the center of the image as the coordinate origin, the X axis of the plane coordinate system is parallel to the upper and lower sides of the image, and the Y axis of the plane coordinate system is parallel to the left and right sides of the image. The connecting line between a point on the target object and the coordinate origin is determined, and the angle between the connecting line and the positive semi-axis of the X axis is the azimuth angle of the target object compared to the target vehicle;

[0061] The edge data acquisition unit calculates the minimum distance between the target object and the target vehicle in each edge data acquisition area as follows:

[0062] The focal length f of the lens of the road-side information collection device is obtained. Among the target objects, the component object closest to the center of the lens of the road-side information collection device is determined. In the image, the width value d of the component object is obtained. The specification and size of the target object are obtained through big data. The specification and size of the target object refer to the length, width and height of the dangerous object. According to D=(length value of the target object*d) / length value of the target object in the image, the actual width value D of the component object is calculated. According to H=(f*D) / d, the minimum distance value between the target object and the target vehicle is calculated, where H represents the minimum distance value between the target object and the target vehicle;

[0063] The edge scene simulation module simulates the edge scene of the target vehicle based on the edge data acquired by the edge data acquisition module and the traffic signal information and environmental information in the edge data acquisition area;

[0064] The edge scene simulation module includes an information collection unit, a road weather space model construction unit, a target object screening unit and an edge scene simulation unit;

[0065] The information collection unit obtains traffic signal information and environmental information in each edge data acquisition area through the cloud server. Traffic signal information refers to the display seconds and display colors of traffic signal lights in the edge data acquisition area. Environmental information refers to rainfall, visibility and snowfall in the edge data acquisition area. Visibility refers to the maximum distance value of an object from the observer's location when the observer can see the object clearly.

[0066] The road meteorological space model construction unit searches for max{d1,…,dn} according to the edge data around the target vehicle, where K=max{d1,…,dn}. The road meteorological space model construction unit obtains the road space model within K meters of the target vehicle through big data. The road space model refers to the road planning model of the driving section where the target vehicle is located. The obtained environmental information and traffic signal information are integrated into the road space model for display to obtain the road meteorological space model, where max represents the maximum value symbol;

[0067] The target object screening unit puts the target object identified by the edge data acquisition area determination unit into a set D. If the target object is a traffic signal indicator light, when the display color of the target object is green, the target object is screened out from the set D. When the display color of the target object is red or yellow, the target object is retained in the set D.

[0068] The edge scene simulation unit constructs a unit space coordinate system in the road weather space model with the location of the target vehicle as the origin, randomly selects a target object in the set D, and determines the danger area corresponding to the selected target object until all the target objects in the set D are selected, and integrates the determined danger areas into the road weather space model to obtain a simulation model of the edge scene of the target vehicle;

[0069] The specific method for the edge scene simulation unit to determine the dangerous area corresponding to the selected target object is:

[0070] A circle is drawn in the three-dimensional space coordinate system with the minimum distance value between the selected target object and the target vehicle as the radius. According to the azimuth range value between the selected target object and the target vehicle, rays A1 and A2 are drawn in the three-dimensional space coordinate system. The rays take the origin as the starting point. The angle value between ray A1 and the positive semi-axis of the X-axis is set to as, and the angle value between ray A2 and the positive semi-axis of the X-axis is set to aws. s represents the number corresponding to the edge data acquisition area where the selected target object is located. As represents the minimum azimuth angle obtained in the edge data acquisition area numbered s, and aws represents the maximum azimuth angle obtained in the edge data acquisition area numbered s. The coordinates of the intersection of ray A1 and the circle are set to (x1, y1, z1), and the coordinates of the intersection of ray A2 and the circle are set to (x2, y2, z2). x1-x2 is used as the side length of the dangerous area, and the intersection coordinates (x1, y1, z1) are used as the lower right vertex of the dangerous area. The dangerous area is integrated into the road meteorological space model to obtain a simulation model of the edge scene of the target vehicle.

[0071] The expected functional safety assessment module controls the operating actions of the target vehicle through the cloud server according to the edge scenario simulated by the edge scenario simulation module. When the target vehicle enters the control state, the braking degree of the target vehicle is obtained, and the expected functional safety of the target vehicle is assessed based on the obtained information.

[0072] The expected function safety assessment module includes an operation control unit, a braking degree acquisition unit and an expected function safety assessment unit;

[0073] The operation control unit obtains the minimum distance value between each target object and the target vehicle stored in the set D, puts the obtained minimum distance value into the set T, searches for the target danger zone according to the number corresponding to minT, and the target danger zone refers to the danger zone determined by the target object represented by the number corresponding to minT. Based on the search result, the maximum real-time running speed Vt1 of the target vehicle under the current simulation model is determined, Vt1=the running speed of the target danger zone at time t, combined with the real-time running speed Vt of the target vehicle, the real-time danger coefficient of the target vehicle is predicted by Vt1 / V1, and Vt1 / V1 is compared with the set threshold value. Based on the comparison result, it is selected whether to control the operation action of the target vehicle through the cloud server, and min represents the minimum value symbol;

[0074] When Vt1 / V1> the set threshold, the braking degree acquisition unit controls the operation of the target vehicle through the cloud server, and then acquires the control degree r of the target vehicle through the cloud server. When the cloud server brakes the target vehicle, r=the distance value of the brake sinking controlled by the cloud server / the corresponding sinking distance when the brake is fully sunk;

[0075] The expected functional safety assessment unit assesses the expected functional safety of the target vehicle based on the data information obtained by the braking degree acquisition unit. The specific method is as follows:

[0076] When the operation of the target vehicle is controlled by the cloud server, the running speed V3 of the target vehicle is obtained, and the actual braking acceleration of the target vehicle is calculated in combination with the environmental information and traffic signal information in the current simulation model. The specific calculation method is:

[0077] According to the three-dimensional coordinate distance formula, the distance value b from the center of the target dangerous area to the origin is calculated;

[0078] If the target object corresponding to the target danger zone is a traffic signal indicator, the actual braking acceleration of the target vehicle G1=(-V3 2 ) / (2*b);

[0079] If the target object corresponding to the target danger zone is not a traffic signal indicator, the actual braking acceleration of the target vehicle G2=(Vt1 2 -V3 2 ) / (2*b);

[0080] The actual braking acceleration refers to the acceleration of the target vehicle obtained based on the actual running speed of the target vehicle;

[0081] According to Qt=(-1) θ *u*p*(e1*w rt1 +e2*w rt2 +e3*w rt3 ) calculates the theoretical braking acceleration of the target vehicle, where u represents the control degree of the cloud server over the target object, p represents the change in the theoretical braking acceleration of the target vehicle when the control degree of the cloud server over the target vehicle changes by 1%, e1+e2+e3=1, rt1 represents the rainfall of the current simulation model at time t, rt2 represents the visibility of the current simulation model at time t, rt3 represents the snowfall of the current simulation model at time t, w is a constant and 0<w<1, θ=1 or θ=2, when θ=1, it means that the cloud server is braking the target vehicle in the reverse direction, and the reverse braking includes the brake braking, when θ=2, it means that the cloud server is braking the target vehicle in the forward direction, and the forward braking includes the accelerator braking, and Qt represents the theoretical braking acceleration of the target vehicle at time t;

[0082] Theoretical braking acceleration refers to the acceleration of the target vehicle calculated based on the expected function of the target vehicle. For example, when the control degree of the cloud server over the target vehicle changes by 1%, according to the expected function of the target vehicle, the corresponding braking acceleration of the target vehicle changes by 3m / s. 2, then when the cloud server controls the target vehicle's braking degree by 5%, the target vehicle's theoretical braking acceleration = -1*5*3*(e1*w rt1 +e2*w rt2 +e3*w rt3 );

[0083] According to H=G1 / Q t or H = G2 / Q t Evaluate the expected functional safety of the target vehicle, where H represents the evaluation value of the expected functional safety of the target vehicle;

[0084] When the evaluation result is less than 0.6, the expected functional safety of the target vehicle is protected;

[0085] The traffic flow operation status prediction module obtains the expected functional safety assessment value of the vehicles running on any section of network road through the cloud server, obtains the simulation model of the edge scene of each running vehicle on the network road through the edge data acquisition module and the edge scene simulation module, fuses the obtained simulation models to obtain the simulation model of the network road, obtains the real-time position information and real-time running speed of each running vehicle in the simulation model of the network road, predicts the traffic flow operation status in the section of network road based on the obtained information, and controls the traffic movement of the section of network road based on the prediction results;

[0086] The traffic flow operation situation prediction module includes a traffic flow operation situation prediction unit and a traffic control unit;

[0087] The traffic flow operation situation prediction unit determines the congested sections in the network road simulation model according to the real-time position information and real-time operation speed of each running vehicle in the network road simulation model, combined with the expected functional safety assessment value of each running vehicle, and predicts the traffic flow operation situation in the network road according to the congestion coefficient of each congested section. The specific method is as follows:

[0088] Ⅰ. According to the driving direction of the running vehicles, the starting point and the end point of the network road are determined in the network road simulation model, and the real-time position of each running vehicle is used as the starting point, and the starting point is used as the target point. The map software is input, and the displayed distance in the map software is used as the real-time distance value of each running vehicle from the starting point;

[0089] Ⅱ. According to the order of real-time distance value from small to large, the running vehicles are numbered, and the numbering result is: j=1,2,…,m; m represents the total number of running vehicles in the network road simulation model. If |Ctμ*Hμ-Ct1*H1|≤γ, Ctμ and Ct1 are put into set K1. If |Ctμ*Hμ-Ct1*H1|>γ, Ctμ is put into set K2. Ctμ represents the running speed of the running vehicle numbered μ at time t, Ct1 represents the running speed of the running vehicle numbered 1 at time t, Hμ represents the expected functional safety assessment value corresponding to the running vehicle numbered μ, and H1 represents the expected functional safety assessment value corresponding to the running vehicle numbered 1. The functional safety assessment value of the period, γ represents the allowable error value, the unit is: m / s. According to the DBSCAN clustering method, the running speed belonging to the noise point is screened out from the set K1 to obtain the set K1´. The maximum number value in the set K1´ is determined, and the position of the running vehicle corresponding to the determined maximum number value is taken as the first segmentation node of the road, and the network road between the first segmentation node of the road and the starting point is taken as the first segmentation area, where μ=2,…,m. The DBSCAN clustering method is a density-based clustering algorithm. The delineation of clusters is completely determined by the degree of clustering of samples. It divides data points into core points, boundary points and noise points. Noise points refer to points that do not belong to any cluster.

[0090] III. In the network road between the first segmentation node and the end position of the road, the real-time running speed Ctq corresponding to the running vehicle closest to the first segmentation node of the road is determined. If |Cth*Hh-Ctq*Hq|≤γ, Cth and Ctq are put into set K3. If |Cth-Ctq|>γ, Cth is put into set K4. Cth represents the running speed of the running vehicle numbered h at time t. According to the DBSCAN clustering method, the running speeds belonging to the noise points are screened out from set K3 to obtain set K3´. The maximum number value in set K3´ is determined, and the position of the running vehicle corresponding to the determined maximum number value is taken as the second segmentation node of the road. The network road between the second segmentation node of the road and the first segmentation node of the road is taken as the second segmentation area, where h=q,…,m;

[0091] IV. Repeat the operation in III until the end position of the network road is used as the road segmentation node. The ratio of the total number of running vehicles in the segmentation area to the maximum number of vehicles that the segmentation area can accommodate is used as the congestion coefficient of the segmentation area. If the congestion coefficient of the segmentation area is greater than 0.7, the traffic flow operation situation in the segmentation area is considered to be congested. If the congestion coefficient of the segmentation area is ≤ 0.7, the traffic flow operation situation in the segmentation area is considered to be unblocked.

[0092] V. Based on operation IV, predict the traffic flow situation of each segmented area in the network road.

[0093] The traffic control unit controls the traffic movement in the divided area when the traffic flow operation status in the divided area is in a congested state. When the traffic flow operation status in the divided area is in a smooth state, there is no need to control the traffic movement in the divided area.

[0094] Example 1: When the operation of the target vehicle is controlled by the cloud server, the running speed of the target vehicle is V3=12.5m / s, the distance value b from the center of the target danger zone to the origin is 10m, and the target object corresponding to the target danger zone is a traffic signal indicator light, then the actual braking acceleration of the target vehicle is:

[0095] G1=(-V32) / (2*b)=(-12.52) / (2*10)=-0.8m / s 2 ;

[0096] Assume that the theoretical braking acceleration of the target vehicle at time t is Qt=-0.9m / s 2 , the expected functional safety assessment value of the target vehicle is:

[0097] H=G1 / Qt=-0.8 / -0.9=0.89;

[0098] The expected functional safety assessment value of the target vehicle is 0.89.

[0099] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0100] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Real-time monitoring and protection system for expected functional safety based on vehicle-road-cloud collaboration, Features: The system includes an edge data acquisition module, an edge scenario simulation module, an expected functional safety assessment module and a traffic flow operation situation prediction module; The edge data acquisition module processes the image information collected by the roadside information acquisition device installed on the target vehicle through the cloud server, determines the acquisition area of ​​the edge data, and acquires the edge data around the target vehicle based on the determination result; The edge data acquisition module includes an image acquisition unit, an edge data acquisition area determination unit and an edge data acquisition unit; The image acquisition unit acquires images around the target vehicle through a road-side information acquisition device installed on the target vehicle, and the road-side information acquisition device uploads the acquired images to a cloud server; The edge data acquisition area determination unit identifies the target object in the received image through the cloud server, and the outer contour of the identified target object is the edge data acquisition area; The edge data acquisition unit calculates the azimuth range value of the target object in each edge data acquisition area compared to the target vehicle, and the minimum distance value of the target object in each edge data acquisition area from the target vehicle. The specific calculation method is: The focal length f of the lens of the road-side information collection device is obtained. Among the target objects, the component object closest to the center of the lens of the road-side information collection device is determined. In the image, the width value d of the component object is obtained. The specification and size of the target object are obtained through big data. The specification and size of the target object refer to the length, width and height of the dangerous object. According to D=(length value of the target object*d) / length value of the target object in the image, the actual width value D of the component object is calculated. According to H=(f*D) / d, the minimum distance value between the target object and the target vehicle is calculated; The calculated set of azimuth range values ​​and minimum distance values ​​is the edge data around the target vehicle, and the edge data around the target vehicle = {([a1, aw1], d1), ..., ([an, awn], dn)}, wherein [an, awn] represents the azimuth range value obtained in the edge data acquisition area numbered n, an represents the minimum azimuth obtained in the edge data acquisition area numbered n, awn represents the maximum azimuth obtained in the edge data acquisition area numbered n, and dn represents the minimum distance value obtained in the edge data acquisition area numbered n; The edge scene simulation module simulates the edge scene of the target vehicle according to the edge data acquired by the edge data acquisition module, and the traffic signal information and environmental information in the edge data acquisition area; The edge scene simulation module includes an information collection unit, a road weather space model construction unit, a target object screening unit and an edge scene simulation unit; The information collection unit acquires traffic signal information and environmental information in each edge data acquisition area through a cloud server, wherein the traffic signal information refers to the display seconds and display colors of the traffic signal lights in the edge data acquisition area, and the environmental information refers to the rainfall, visibility and snowfall in the edge data acquisition area; The road weather space model construction unit searches for max{d1, ..., dn} according to the edge data around the target vehicle, and K=max{d1, ..., dn}. The road weather space model construction unit obtains the road space model within K meters of the target vehicle through big data, integrates the obtained environmental information and traffic signal information into the road space model for display, and obtains the road weather space model, wherein max represents the maximum value symbol; The target object screening unit puts the target object identified by the edge data acquisition area determination unit into a set D. If the target object is a traffic signal indicator light, when the display color of the target object is green, the target object is screened out from the set D. When the display color of the target object is red or yellow, the target object is retained in the set D. The edge scene simulation unit constructs a unit space coordinate system in the road weather space model with the location of the target vehicle as the origin, randomly selects a target object from the set D, and determines the danger zone corresponding to the selected target object. The specific method is as follows: With the minimum distance between the selected target object and the target vehicle as the radius, draw a circle in the three-dimensional space coordinate system. According to the azimuth range of the selected target object compared to the target vehicle, draw rays A1 and A2 in the three-dimensional space coordinate system. The rays take the origin as the starting point. Let the angle between ray A1 and the positive half axis of the X-axis be as, and the angle between ray A2 and the positive half axis of the X-axis be aws. s represents the number corresponding to the edge data acquisition area where the selected target object is located. Let the coordinates of the intersection of ray A1 and the circle be (x1, y1, z1), and the coordinates of the intersection of ray A2 and the circle be (x2, y2, z2). Let x1-x2 be the side length of the dangerous area, and let the coordinates of the intersection (x1, y1, z1) be the lower right vertex of the dangerous area. Until all the target objects in the set D are selected, each determined dangerous area is integrated into the road weather space model to obtain a simulation model of the target vehicle edge scene; The expected functional safety assessment module controls the operating action of the target vehicle through the cloud server according to the edge scenario simulated by the edge scenario simulation module, obtains the braking degree of the target vehicle when the target vehicle enters the control state, and assesses the expected functional safety of the target vehicle based on the obtained information; The expected function safety assessment module includes an operation control unit, a braking degree acquisition unit and an expected function safety assessment unit; The operation control unit obtains the minimum distance value between each target object and the target vehicle stored in the set D, puts the obtained minimum distance value into the set T, searches for the target danger zone according to the number corresponding to minT, and determines the maximum real-time running speed Vt1 of the target vehicle under the current simulation model based on the search result, Vt1=the running speed of the target danger zone at time t, and predicts the real-time danger coefficient of the target vehicle by Vt1 / V1 in combination with the real-time running speed Vt of the target vehicle, compares Vt1 / V1 with the set threshold, and selects whether to control the operation action of the target vehicle through the cloud server based on the comparison result; The braking degree acquisition unit controls the operation action of the target vehicle through the cloud server when Vt1 / V1> the set threshold, and then acquires the control degree r of the target vehicle through the cloud server; The expected functional safety assessment unit assesses the expected functional safety of the target vehicle according to the data information acquired by the braking degree acquisition unit, and the specific method is as follows: When the operation of the target vehicle is controlled by the cloud server, the running speed V3 of the target vehicle is obtained, and the actual braking acceleration of the target vehicle is calculated in combination with the environmental information and traffic signal information in the current simulation model. The specific calculation method is: According to the three-dimensional coordinate distance formula, the distance value b from the center of the target dangerous area to the origin is calculated; If the target object corresponding to the target danger zone is a traffic signal indicator, the actual braking acceleration of the target vehicle G1=(-V3 2 ) / (2*b); If the target object corresponding to the target danger zone is not a traffic signal indicator, the actual braking acceleration of the target vehicle G2=(Vt1 2 -V3 2 ) / (2*b); According to Qt=(-1) θ *u*p*(e1*w rt1 +e2*w rt2 +e3*w rt3 ) calculates the theoretical braking acceleration of the target vehicle, where u represents the control degree of the cloud server over the target object, p represents the change in the theoretical braking acceleration of the target vehicle when the control degree of the cloud server over the target vehicle changes by 1%, e1+e2+e3=1, rt1 represents the rainfall of the current simulation model at time t, rt2 represents the visibility of the current simulation model at time t, rt3 represents the snowfall of the current simulation model at time t, w is a constant and 0<w<1, θ=1 or θ=2, when θ=1, it means that the cloud server brakes the target vehicle in the reverse direction, when θ=2, it means that the cloud server brakes the target vehicle in the forward direction, and Qt represents the theoretical braking acceleration of the target vehicle at time t; According to H=G1 / Q t or H = G2 / Q t Evaluate the expected functional safety of the target vehicle, where H represents the evaluation value of the expected functional safety of the target vehicle; When the evaluation result is less than 0.6, the expected functional safety of the target vehicle is protected; The traffic flow operation status prediction module obtains the expected functional safety assessment value of the vehicles running in any section of network road through the cloud server, obtains the simulation model of the edge scene of each running vehicle in the network road through the edge data acquisition module and the edge scene simulation module, fuses the obtained simulation models to obtain the simulation model of the network road, and obtains the real-time position information and real-time running speed of each running vehicle in the simulation model of the network road. Based on the obtained information, the traffic flow operation status in the section of network road is predicted, and based on the prediction result, the traffic movement of the section of network road is controlled.

2. The expected functional safety real-time monitoring and protection system based on vehicle-road-cloud collaboration according to claim 1, Features: The traffic flow operation situation prediction module includes a traffic flow operation situation prediction unit and a traffic control unit; The traffic flow operation situation prediction unit determines the congested sections in the network road in the network road simulation model according to the real-time position information and real-time operation speed of each running vehicle in the network road simulation model, combined with the expected functional safety assessment value of each running vehicle, and predicts the traffic flow operation situation in the section of network road according to the congestion coefficient of each congested section; The traffic control unit controls the traffic movement in the divided area when the traffic flow operation status in the divided area is a congested state, and does not need to control the traffic movement in the divided area when the traffic flow operation status in the divided area is a smooth state.

3. The expected functional safety real-time monitoring and protection system based on vehicle-road-cloud collaboration according to claim 2, Features: The specific method for the traffic flow operation situation prediction unit to predict the traffic flow operation situation in the section of network road is: Ⅰ. According to the driving direction of the running vehicles, the starting point and the end point of the network road are determined in the network road simulation model, and the real-time position of each running vehicle is used as the starting point, and the starting point is used as the target point. The map software is input, and the displayed distance in the map software is used as the real-time distance value of each running vehicle from the starting point; Ⅱ. According to the order of real-time distance value from small to large, the running vehicles are numbered, and the numbering result is: j=1,2,…,m; m represents the total number of running vehicles in the network road simulation model. If |Ctμ*Hμ-Ct1*H1|≤γ, Ctμ and Ct1 are put into set K1. If |Ctμ*Hμ-Ct1*H1|>γ, Ctμ is put into set K2. Ctμ represents the running speed of the running vehicle numbered μ at time t, and Ct1 represents the running vehicle numbered 1. The running speed at time t, Hμ represents the expected functional safety assessment value corresponding to the running vehicle numbered μ, γ represents the allowable error value, and according to the DBSCAN clustering method, the running speeds belonging to the noise points are screened out from the set K1 to obtain the set K1´, and the maximum number value in the set K1´ is determined, and the position of the running vehicle corresponding to the determined maximum number value is taken as the first segmentation node of the road, and the network road between the first segmentation node of the road and the starting point is taken as the first segmentation area, where μ=2,…,m; III. In the network road between the first segmentation node and the end position of the road, the real-time running speed Ctq corresponding to the running vehicle closest to the first segmentation node of the road is determined. If |Cth*Hh-Ctq*Hq|≤γ, Cth and Ctq are put into set K3. If |Cth-Ctq|>γ, Cth is put into set K4. Cth represents the running speed of the running vehicle numbered h at time t. According to the DBSCAN clustering method, the second segmentation area is determined, where h=q,…,m; IV. Repeat the operation in III until the end position of the network road is used as the road segmentation node. The ratio of the total number of running vehicles in the segmentation area to the maximum number of vehicles that the segmentation area can accommodate is used as the congestion coefficient of the segmentation area. If the congestion coefficient of the segmentation area is greater than 0.7, the traffic flow operation situation in the segmentation area is considered to be congested. If the congestion coefficient of the segmentation area is ≤ 0.7, the traffic flow operation situation in the segmentation area is considered to be unblocked. V. Based on operation IV, predict the traffic flow situation of each segmented area in the network road.