System and method for determining safety status of autonomous driving mixed traffic flow

Through the hybrid traffic flow safety status determination system for autonomous driving, combined with the driving trajectory of autonomous driving and manual driving vehicles, the safety problem of existing systems being unable to be applicable to road traffic coexisting with autonomous driving and manual driving vehicles is solved, achieving more accurate safety Status evaluation and optimization strategies.

CN118038698BActive Publication Date: 2024-11-29ROAD TRAFFIC SAFETY RES CENT THE MINIST OF PUBLIC SECURITY OF THE PEOPLES REPUBLIC OF CHINA
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202311713890.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-13
Publication Date
2024-11-29
Estimated Expiration
2043-12-13

AI Technical Summary

Technical Problem

The existing vehicle safety system cannot be applied to road traffic systems where autonomous vehicles coexist with manual driving vehicles, resulting in the inability to accurately determine the safety of road traffic.

Method used

A hybrid traffic flow safety state determination system for autonomous driving is designed, and the parameter feature acquisition module, road environment construction module and autonomous driving hybrid traffic flow generation module are used to combine the driving trajectory of autonomous driving vehicles and artificial driving vehicles, and based on preset safety Risk indicators determine the safety status of the test scenario.

Benefits of technology

The system can more accurately determine the safety status of the hybrid traffic flow of autonomous driving, avoiding the situation where a single method cannot obtain characteristic parameters or determine the driving trajectory, and provides optimization strategies to improve traffic safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118038698B_ABST
    Figure CN118038698B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and discloses a system and method for determining the safety status of an autonomous driving mixed traffic flow, the system comprising: a parameter feature acquisition module, for acquiring feature parameters; a road environment construction module, which is communicatively connected to the parameter feature acquisition module, for receiving the feature parameters, and determining a test scenario and a vehicle motion model based on the feature parameters; an autonomous driving mixed traffic flow generation module, which is communicatively connected to the parameter feature acquisition module and the road environment construction module, for determining a first driving trajectory of an autonomous driving vehicle and a second driving trajectory of a manually driven vehicle based on the test scenario, the vehicle motion model and the feature parameters; and a safety risk assessment module, which is communicatively connected to the autonomous driving mixed traffic flow generation module, for determining the safety status of the test scenario based on the first driving trajectory, the second driving trajectory and a preset safety risk indicator.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a system and method for determining the safety status of mixed traffic flow in an autonomous driving system, a computer device, and a computer-readable storage medium. Background Art

[0002] In order to reduce safety accidents and improve transportation efficiency, currently, the vehicle safety system of manually driven vehicles on the road is often constructed to determine the vehicle status (such as vehicle speed, vehicle trajectory, vehicle acceleration, etc.), and the safety risk is determined by the vehicle status, so that the vehicle status system is adjusted according to the safety risk.

[0003] However, current vehicle safety systems are often only targeted at manually driven vehicles. If the road traffic system includes both autonomous driving vehicles and manually driven vehicles, the road traffic safety system cannot be applied, making it impossible to accurately determine the safety of the road traffic system. Summary of the invention

[0004] In view of this, the present invention provides a system, method, computer device and computer-readable storage medium for determining the safety status of autonomous driving mixed traffic flow, so as to solve the problem that when the road traffic system includes autonomous driving vehicles and manually driven vehicles, the road traffic safety system cannot be applied, and thus the safety of the road traffic system cannot be accurately determined.

[0005] In a first aspect, the present invention provides a system for determining the safety status of an autonomous driving mixed traffic flow, the system comprising: a parameter feature acquisition module, for acquiring feature parameters; a road environment construction module, which is communicatively connected to the parameter feature acquisition module, for receiving the feature parameters, and determining a test scenario and a vehicle motion model based on the feature parameters; an autonomous driving mixed traffic flow generation module, which is communicatively connected to the parameter feature acquisition module and the road environment construction module, for receiving the test scenario, the vehicle motion model and the feature parameters, and determining a first driving trajectory of an autonomous driving vehicle and a second driving trajectory of a manually driven vehicle based on the test scenario, the vehicle motion model and the feature parameters; a safety risk assessment module, which is communicatively connected to the autonomous driving mixed traffic flow generation module, for determining the safety status of the test scenario based on the first driving trajectory, the second driving trajectory and a preset safety risk indicator.

[0006] The system for determining the safety status of autonomous driving mixed traffic flow provided by the present embodiment determines a test scenario and a vehicle motion model through characteristic parameters, determines a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle through the test scenario, the vehicle motion model and the characteristic parameters, and then determines the safety status of the test scenario through the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle. Compared with the method of only considering manually driven vehicles, the present system combines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle to more accurately determine the safety status of the test scenario.

[0007] In an optional embodiment, the parameter feature acquisition module includes: a configuration unit, which is used to configure the feature parameters in response to the input operation of the target object for the feature parameters based on the input operation; and / or, an acquisition unit, which is used to receive a structured parameter file and acquire the feature parameters based on the structured parameter file; wherein the structured parameter file includes the feature parameters.

[0008] The system for determining the safety status of mixed traffic flow in autonomous driving provided in this embodiment uses two methods of obtaining characteristic parameters to avoid the situation where the characteristic parameters cannot be obtained by using another method when either method cannot be implemented.

[0009] In an optional embodiment, the characteristic parameters include: road environment parameters and road-vehicle fusion parameters: wherein the autonomous driving mixed traffic flow generation module includes: a single vehicle determination unit, used to determine a first fleet sequence of the fleet based on the road environment parameters and the road-vehicle fusion parameters; wherein the fleet includes multiple target vehicles, and the target vehicles include autonomous driving vehicles and / or manually driven vehicles; a single vehicle generation unit, used to determine the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle based on the first fleet sequence and the vehicle motion model; or, an aggregate determination unit, used to determine the second fleet sequence of the fleet according to the area based on the road environment parameters and the road-vehicle fusion parameters; wherein the number of the second fleet sequence is greater than the first fleet sequence; an aggregate generation unit, used to determine the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle based on the second fleet sequence and the vehicle motion model.

[0010] The system for determining the safety status of autonomous driving mixed traffic flow provided in this embodiment can avoid the situation where the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle cannot be determined by using two methods to determine the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle. When either method cannot be implemented, the other method is used to determine the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle, thereby avoiding the situation where the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle cannot be determined.

[0011] In an optional embodiment, the characteristic parameters include: road environment parameters; wherein the road environment construction module includes: a simulation unit, used to determine the test scenario and the vehicle motion model based on the road environment parameters; a display unit, used to receive the safety status and test scenario of the safety risk assessment module, and to visually display the safety status and the test scenario.

[0012] The system for determining the safety status of mixed traffic flow of autonomous driving provided in this embodiment facilitates operators to view by displaying the safety status and test scenarios of the safety risk analysis module.

[0013] In an optional embodiment, the safety risk assessment module includes: a determination unit for determining a safety factor based on a first driving trajectory and a second driving trajectory; wherein the safety factor includes: an acceleration index, a deceleration index, a collision time index, and a post-intrusion time index; a detection unit for detecting whether the safety factor meets a preset threshold; wherein, if the safety factor meets the preset threshold, the safety state is determined to be safe; if the safety factor does not meet the preset threshold, the safety state is determined to be unsafe.

[0014] The system for determining the safety status of autonomous driving mixed traffic flow provided in this embodiment can more accurately determine the safety status by detecting whether four safety factors (acceleration index, deceleration index, collision time index and post-intrusion time index) meet preset thresholds.

[0015] In an optional embodiment, it also includes: a receiving module, which is communicated with the autonomous driving mixed traffic flow generation module and the safety risk assessment module, respectively, for receiving characteristic parameters and safety status; a decision module, which is communicated with the receiving module, for generating an organizational optimization strategy based on the characteristic parameters and safety status.

[0016] The system for determining the safety status of mixed traffic flow in autonomous driving provided in this embodiment can adjust the safety status by organizing optimization strategies, thereby ensuring the safety of the test scenario.

[0017] In an optional embodiment, the decision-making device includes: a first decision unit, which is used to match the corresponding organizational optimization strategy from a preset strategy library based on characteristic parameters and safety status; or, a second decision unit, which is used to generate an organizational optimization strategy in response to the configuration operation of the target object if the first decision unit does not match the corresponding organizational optimization strategy; a parameter feature acquisition module, which is also used to adjust the characteristic parameters based on the organizational optimization strategy to generate target characteristic parameters; a road environment construction module, which is also used to determine the target test scenario based on the target characteristic parameters; an autonomous driving mixed traffic flow generation module, which is also used to determine the first target driving trajectory of the autonomous driving vehicle and the second target driving trajectory of the manually driven vehicle based on the target characteristic parameters and the target test scenario; a safety risk assessment module, which is also used to determine the target safety status of the test scenario based on the first target driving trajectory, the second target driving trajectory and the preset safety risk indicators; the device also includes: a detection module, which is used to detect whether the target safety status meets the preset safety status; an adding module, which is used to write the target characteristic parameters, the organizational optimization strategy corresponding to the second decision unit, and the target safety status into the preset strategy library if the target safety status meets the preset safety status.

[0018] The system for determining the safety status of mixed traffic flow in autonomous driving provided in this embodiment can ensure the accuracy of the organizational optimization strategy by matching the corresponding organizational optimization strategy in a preset strategy library, setting the organizational optimization strategy through a target object, and verifying the way in which the organizational optimization strategy is set by the target object.

[0019] In a second aspect, the present invention provides a method for determining the safety status of autonomous driving mixed traffic flow, the method comprising: obtaining characteristic parameters; determining a test scenario and a vehicle motion model based on the characteristic parameters; determining a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle based on the test scenario, the vehicle motion model and the characteristic parameters; determining the safety status of the test scenario based on the first driving trajectory, the second driving trajectory and a preset safety risk indicator.

[0020] The method for determining the safety status of autonomous driving mixed traffic flow provided in this embodiment determines a test scenario and a vehicle motion model through characteristic parameters, determines a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle through the test scenario, the vehicle motion model and the characteristic parameters, and then determines the safety status of the test scenario through the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle. Compared with the method of only considering manually driven vehicles, this system combines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle to more accurately determine the safety status of the test scenario.

[0021] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for determining the safety status of autonomous driving mixed traffic flow of the above-mentioned second aspect or any corresponding embodiment thereof by executing the computer instructions.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for determining the safety state of autonomous driving mixed traffic flow according to the above-mentioned second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 is a schematic diagram of the structure of a system for determining a safety state of an autonomous driving mixed traffic flow according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of vehicle clustering provided according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of a vehicle arrangement provided according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of the structure of a system for determining a safety state of an autonomous driving mixed traffic flow according to an embodiment of the present invention;

[0028] Figure 5 is a flow chart of a method for determining a safety state of a mixed traffic flow of an autonomous driving system according to an embodiment of the present invention;

[0029] Figure 6 is a structural block diagram of a device for determining a safety state of an autonomous driving mixed traffic flow according to an embodiment of the present invention;

[0030] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] At present, frequent safety accidents and low transportation efficiency have become bottlenecks for the sustainable development of transportation production. With the rapid development of new generation information technologies such as artificial intelligence and 5G, autonomous driving has provided a revolutionary means for the production of freight transportation. The technical routes of autonomous driving are divided into autonomous autonomous driving and vehicle-road cooperative autonomous driving. The two types of autonomous driving vehicles can obtain the driving status of the preceding vehicle in real time through on-board detection equipment and vehicle communication technology. In theory, they have more timely and accurate traffic condition perception capabilities than ordinary drivers, more stable and safer decision-making and judgment capabilities, and more economical and environmentally friendly power output control. However, it will take a long time for the two types of autonomous driving vehicles to fully enter the road system. In the future, the road traffic system will experience a mixed stage of autonomous driving vehicles and manually driven vehicles, forming an autonomous driving mixed traffic flow. Because the driving characteristics of autonomous driving vehicles and manually driven vehicles are significantly different, and autonomous driving vehicles and manually driven vehicles have great differences in obtaining road traffic information, vehicle operation characteristics, and handling road traffic conditions. As a result, when autonomous driving vehicles enter the road traffic system, they will have a greater impact on the existing traffic system composed of manually driven vehicles, and their traffic flow characteristics are significantly different from those of fully manually driven vehicles.

[0033] The current methods, indicators and organizational optimization measures for determining traffic flow safety risks are all aimed at fully manually driven vehicles. If the road traffic system includes autonomous driving vehicles and manually driven vehicles, the road traffic safety system cannot be applied, and thus the safety of the road traffic system cannot be accurately determined.

[0034] Based on this, the system for determining the safety status of autonomous driving mixed traffic flow provided by the present embodiment determines the test scenario and the vehicle motion model through characteristic parameters, determines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle through the test scenario, the vehicle motion model and the characteristic parameters, and then determines the safety status of the test scenario through the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle. Compared with the method of only considering manually driven vehicles, the present system combines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle to more accurately determine the safety status of the test scenario.

[0035] This embodiment provides a system for determining the safety status of mixed traffic flow for autonomous driving. Figure 1 Schematic diagram of the structure of a system for determining the safety status of mixed traffic flow of autonomous driving according to an embodiment of the present invention. Figure 1 As shown, the system includes: a parameter feature acquisition module 101, used to acquire feature parameters; a road environment construction module 102, which is communicated with the parameter feature acquisition module 101, used to receive the feature parameters, and determine the test scenario and the vehicle motion model based on the feature parameters; an autonomous driving mixed traffic flow generation module 103, which is communicated with the parameter feature acquisition module 101 and the road environment construction module 102, used to receive the test scenario, the vehicle motion model and the feature parameters, and determine the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle based on the test scenario, the vehicle motion model and the feature parameters; a safety risk assessment module 104, which is communicated with the autonomous driving mixed traffic flow generation module 103, used to determine the safety status of the test scenario based on the first driving trajectory, the second driving trajectory and a preset safety risk indicator.

[0036] The characteristic parameters may include: road environment parameters, vehicle driving characteristic parameters, road-vehicle fusion parameters, etc., which are not specifically limited here.

[0037] Road environment parameters may include: road geometry parameters, signs and markings, traffic flow, autonomous driving vehicle penetration rate, and autonomous driving vehicle queue strength, etc., which are not specifically limited here. Road geometry parameters include but are not limited to the number of lanes, lane width, vehicle speed, lane length, circular curve radius, and average lane slope, etc., which are not specifically limited here; signs and markings include: prohibition signs, instruction signs, warning signs, road signs, prohibition markings, and warning markings, etc., which are not specifically limited here. Traffic flow refers to the number of vehicles passing through a certain traffic section in a unit time, for example, the number of vehicles in 1 hour is 500, etc., which is not limited here. Autonomous driving vehicle penetration rate refers to the ratio of the number of autonomous driving vehicles passing through a certain traffic section in a unit time to the total number of vehicles. Autonomous driving vehicle queue strength refers to the clustering intensity of autonomous driving vehicles in mixed traffic flow.

[0038] Figure 2 FIG. 1 is a schematic diagram of vehicle clustering according to an embodiment of the present invention. Figure 2As shown in the figure, the value range of clustering strength is [-1,1]. Among them, the value of -1 means that the vehicles with the weakest strength in the autonomous driving vehicle queue form an autonomous driving-active driving isolation mode, and the rest of the vehicles are manually driven vehicles (such as lane (a)), and the value of 1 means that the first half of the group of vehicles are autonomous driving vehicles, and the rest of the vehicles are manually driven vehicles (such as lane (b)). In addition, the situation between these two is that the autonomous driving vehicles and manually driven vehicles are randomly distributed (such as lane (c)).

[0039] Vehicle driving characteristic parameters include vehicle micro-motion model, vehicle geometric parameters, vehicle maneuverability parameters, vehicle following parameters, vehicle lane change parameters, vehicle path, etc., which are not specifically limited here.

[0040] The vehicle micro-motion model includes the vehicle following model and the vehicle lane changing model. The vehicle following model includes but is not limited to safety distance models, psychophysical models, artificial intelligence models, optimal velocity models, IDM models (intelligent driver models) and cellular automata models; the vehicle lane changing model includes but is not limited to rule models, discrete choice models, artificial intelligence models, Markov models, psychophysical models, survival models, etc. Vehicle geometric parameters include but are not limited to vehicle length, vehicle width and vehicle height; vehicle maneuverability parameters include: vehicle maximum speed, vehicle maximum acceleration and vehicle maximum deceleration; vehicle following parameters include but are not limited to: parking distance, headway, vehicle speed vibration, vibration acceleration, parking acceleration and acceleration at 80km / h; vehicle lane change parameters include: lane change distance, maximum deceleration (vehicle overtaking), acceptable deceleration (vehicle overtaking), maximum deceleration (vehicle being overtaken), acceptable deceleration (vehicle being overtaken), minimum headway (front / rear), and maximum deceleration for coordinated braking; vehicle path refers to the spatiotemporal trajectory sequence of a vehicle traveling on the road.

[0041] The road-vehicle fusion parameters are divided into 5 levels, namely, Level E: no collaboration, Level D: static information support, Level C: dynamic information support, Level B: collaborative identification information support, and Level A: collaborative driving information support.

[0042] After the characteristic parameters are obtained, the test scenario and the vehicle motion model can be determined by the characteristic parameters. The test scenario can be used to characterize the environment required for the test. For example: the slope of the vehicle road, the length of the vehicle road, etc., which are not specifically limited here. The vehicle motion model may include a motion model of an autonomous driving vehicle and a motion model of a manually driven vehicle, that is, after determining the distribution of each vehicle on the vehicle road, the motion model of the autonomous driving vehicle and the motion model of the manually driven vehicle can be used to respectively determine the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle, and through the first driving trajectory of the autonomous driving vehicle, the second driving trajectory of the manually driven vehicle and the preset safety risk indicators, the safety state of the test scenario can be determined. Among them, the preset safety risk indicators can be used to characterize that the vehicle can safely pass on the road without causing harm to other traffic participants, and can safely deal with the risks caused by other traffic participants.

[0043] An autonomous driving vehicle can be an unmanned car, a computer-driven car, or a wheeled mobile robot. It is an intelligent car that achieves unmanned driving through a computer system. It can also be a vehicle with a driving automation system of level 3 or above that meets the national standard "Automobile Driving Automation Classification". A manually driven vehicle can be a vehicle that does not have a driving automation system of level 3 or above.

[0044] It should be noted that in the embodiments of the present invention, the form of the vehicle is not limited. The vehicles (autonomous driving vehicles and manually driven vehicles) in the present invention may refer to large cars, small cars, special-purpose vehicles, etc. Exemplarily, according to the vehicle type, the vehicle in the present invention may be a sedan, an off-road vehicle, a fuel vehicle, a new energy vehicle, a hybrid vehicle, etc. The system for determining the safety state of the autonomous driving mixed traffic flow provided in this embodiment determines the test scene and the vehicle motion model through characteristic parameters, determines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle through the test scene, the vehicle motion model and the characteristic parameters, and then determines the safety state of the test scene through the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle. Compared with the method of only considering the manually driven vehicle, the system combines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle to more accurately determine the safety state of the test scene.

[0045] In some optional implementations, the parameter feature acquisition module 101 includes: a configuration unit, configured to configure the feature parameters in response to an input operation of the target object on the feature parameters based on the input operation; or

[0046] The acquisition unit is used to receive the structured parameter file and acquire the characteristic parameters based on the structured parameter file; wherein the structured parameter file includes the characteristic parameters.

[0047] The input operation is an operation generated by a user through a mouse click, a keyboard selection or a touch screen. When the user issues an input operation, the configuration unit of the parameter feature acquisition module 101 can configure the feature parameters in response to the input operation.

[0048] The structured parameter file can be used to characterize a file containing characteristic parameters. Specifically, the characteristic parameters in the structured parameter file can be obtained by reading the structured parameter file by the acquisition unit.

[0049] The system for determining the safety status of mixed traffic flow in autonomous driving provided in this embodiment uses two methods of obtaining characteristic parameters to avoid the situation where the characteristic parameters cannot be obtained by using another method when either method cannot be implemented.

[0050] In some optional implementations, the characteristic parameters include: road environment parameters and road-vehicle fusion parameters; wherein the autonomous driving mixed traffic flow generation module 103 includes:

[0051] The single vehicle determination unit is used to determine a first fleet sequence of the fleet based on the road environment parameters and the road-vehicle fusion parameters; wherein the fleet includes multiple target vehicles, and the target vehicles include autonomous driving vehicles and / or manually driven vehicles; the single vehicle generation unit is used to determine a first driving trajectory of each autonomous driving vehicle and a second driving trajectory of each manually driven vehicle based on the first fleet sequence and the vehicle motion model;

[0052] or,

[0053] The aggregate determination unit is used to determine the second fleet sequence of the fleet according to the area based on the road environment parameters and the road-vehicle fusion parameters; wherein the number of the second fleet sequence is greater than the first fleet sequence; the aggregate generation unit is used to determine the first driving trajectory of each automatic driving vehicle and the second driving trajectory of each manually driven vehicle based on the second fleet sequence and the vehicle motion model.

[0054] A fleet can be used to represent a fleet of multiple autonomous vehicles and / or manually driven vehicles. For example, if there are 3 autonomous vehicles and 3 manually driven vehicles on a vehicle road, then the fleet includes 3 autonomous vehicles and 3 manually driven vehicles. Another example: if there are 3 autonomous vehicles on a vehicle road, then the fleet includes 3 autonomous vehicles on the vehicle road.

[0055] For the single-vehicle determination unit and the single-vehicle generation unit, the first fleet sequence can be used to characterize the position order of the manually driven vehicles and the autonomous driving vehicles in the fleet. For example: the vehicle road includes an autonomous driving vehicle A and a manually driven vehicle B, and the corresponding first fleet sequence can be AB (that is, the autonomous driving vehicle is in front and the manually driven vehicle is in the back), or BA (that is, the autonomous driving vehicle is in the back and the manually driven vehicle is in the front). Then, after obtaining the first fleet sequence, the characteristic parameters of each vehicle are input into the vehicle motion model, and the trajectories corresponding to each vehicle can be obtained, that is, the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle.

[0056] For the aggregate determination unit and the aggregate generation unit, the second fleet sequence can be used to characterize the position sorting of manually driven vehicles and autonomous driving vehicles in different areas of the fleet, and the second fleet sequence can be accurately determined by the mixed traffic flow generation model of the Markov chain, the autonomous driving penetration rate in the road environment parameters, and the autonomous driving fleet formation strength. For example: the autonomous driving penetration rate is 50%, and the corresponding number of autonomous driving vehicles and manually driven vehicles is the same, then the sorting of autonomous driving vehicles and manually driven vehicles can include many kinds, such as: the number of autonomous driving vehicles is 3, the number of manually driven vehicles is 3, the autonomous driving vehicles and manually driven vehicles are interspersed in the area, or the autonomous driving vehicles and manually driven vehicles are randomly set, or the autonomous driving vehicles are in the front area and the manually driven vehicles are in the rear area, etc.

[0057] It should be noted that the mixed traffic flow generation model based on the Markov chain is used to generate a vehicle type sequence (i.e., a second convoy sequence) under a given traffic mode on a single lane. The mixed traffic flow generation model based on the Markov chain is described in detail below.

[0058] The traffic pattern is determined by the penetration rate P of autonomous vehicles and the queue intensity O. The penetration rate P represents the percentage of autonomous vehicles in the total number of vehicles in the mixed traffic flow; the queue intensity O represents the queue intensity of autonomous vehicles, that is, the clustering intensity of autonomous vehicles in the mixed traffic flow. For example, if O is set to the maximum value, it means that the clustering intensity of autonomous vehicles is the largest, so the type of the rear vehicle matches the type of the front vehicle; if O is set to the minimum value, the clustering intensity of autonomous vehicles is the weakest, and the probability of the rear vehicle model overlapping with the front vehicle model is the lowest. In theory, for a certain P value, O determines the probability of the next vehicle model appearing when the previous vehicle model is given between two adjacent vehicles.

[0059] The impact of different AV platoon intensities on overall traffic flow is a matter of concern, because different AV vehicle technologies and road traffic strategies can greatly affect how AVs form platoons and the corresponding traffic flow. For example, if AVs have a weak tendency to form platoons throughout the process, they can be randomly distributed in mixed traffic, in which case the improvement in traffic capacity is limited. If AVs have a strong desire to cluster and are operated by a coordinated and unified fleet of operators, AVs may form fairly long platoons, which will significantly improve the overall traffic flow. In addition, appropriate road traffic strategies, such as setting up dedicated AV lanes, can also be used to encourage AVs to form platoons.

[0060] Figure 3 Schematic diagram of a vehicle arrangement according to an embodiment of the present invention. Figure 3 As shown in Figure 2, different autonomous driving vehicle technologies and vehicle-road collaboration levels affect the headway time of vehicles. In mixed traffic flow, the following vehicle will adjust its headway time according to the type of the preceding vehicle. AA Characterizes the headway time between autonomous vehicles; h AM It represents the headway time between the autonomous driving vehicle behind and the manual driving vehicle in front; h MA It represents the headway time between the autonomous driving vehicle in front and the manually driven vehicle behind; h MM Characterizes the headway time between manually driven vehicles. From Table 1, it can be seen that the headway time (safety threshold) between manually driven vehicles is between 0.7 and 2.4 seconds, the headway time between autonomous driving vehicles is between 0.3 and 2 seconds, the headway time between autonomous driving vehicles behind manually driven vehicles is between 0.5 and 2.6 seconds, and the headway time between manually driven vehicles following autonomous driving vehicles is between 0.6 and 2.6 seconds.

[0061] Table 1

[0062] type <![CDATA[h AA ]]> <![CDATA[h AM ]]> <![CDATA[h MA ]]> <![CDATA[h MM ]]> Numeric U(0.3,2.0) U(0.5,2.6) U(0.6,2.6) U(0.7,2.4)

[0063] This embodiment proposes to use Markov chain modeling to generate mixed traffic volume. Assume that there are N vehicles in a single lane traffic flow, and the vehicle numbers are N = {1, 2, ..., n}. n ∈{0,1} represents the vehicle type of the nth vehicle. If the nth vehicle is an autonomous vehicle, then A n =1, if the nth vehicle is a manually driven vehicle, then A n = 0, then the penetration rate of autonomous driving vehicles P can be expressed as Then the penetration rate of manually driven vehicles is P0=E(1-P); where E is the coefficient.

[0064] The same P value may correspond to different vehicle types or distributions of autonomous driving queue strength. For example, when P = 0.5, there are two extreme cases. Case 1: Each autonomous driving vehicle is separated by a manually driven vehicle, such as Figure 2 Lane (a) in the middle, the strength of the vehicle queue is the weakest. In this weakest case, the vehicles form an autonomous driving-active driving isolation mode, and the number of vehicle queues reaches the maximum. Case 2: The first half of the group of vehicles are all autonomous driving vehicles, and the rest of the vehicles are all manually driven vehicles, such as Figure 2 In this case, all the autonomous vehicles form a vehicle queue, that is, the autonomous vehicles can form a minimum number of vehicle queues. In addition, the situation between these two is that the autonomous vehicles and the manually driven vehicles are randomly distributed, such as Figure 2 Lane (c).

[0065] It can be seen that under the same P value, there are many cases corresponding to different queue strengths. In each case, due to the different headway of different types of vehicles, there will be different road capacity. In order to model this random mixed traffic flow, this embodiment uses a discrete Markov chain model to specify the vehicle types of N vehicles from downstream to upstream, as shown below. In the Markov chain, A n It can be interpreted as the state variable of the nth step, and the state space is: S: = {1,0}; where 1 is the type of autonomous driving vehicle, 0 is the type of manually driven vehicle, and the probability that the first vehicle is an autonomous driving vehicle is P, that is, the penetration rate, recorded as Pr(A1) = P1. Therefore, the initial vector is: π: = [P1, P0]; the transfer matrix is ​​defined as:

[0066] Among them, t sr The probability that a car of type s is followed by a car of type r can be expressed as:

[0067]

[0068] After combining penetration rate and queue strength, we can get:

[0069]

[0070] t 11 (P,O):=1-t 10 (P,O)

[0071]

[0072] t 00 (P,O):=1-t 01 (P,O)

[0073] Markov describes the process of queue intensity from maximum to minimum as it changes from 1 to -1, taking the special case as an example:

[0074] Case 1: Maximum queue strength.

[0075] and Figure 2 Similar to the case of lane (b) in , all autonomous vehicles in this embodiment are perfectly arranged in a vehicle queue. Therefore, assuming that vehicle n is an autonomous vehicle, the probability that the vehicle n+1 following it is also an autonomous vehicle converges to 1. Similarly, assuming that vehicle n is a manually driven vehicle, the probability that the vehicle following vehicle n+1 is also a manually driven vehicle converges to 1. Therefore, in this case, the elements of the transfer matrix T are:

[0076] t 11 (P,1)=t 00 (P,1)=1

[0077] t 10 (P,1)=t 01 (P,1)=0

[0078] In this case, since the type of the following vehicles exactly matches the type of the vehicles in front, all vehicles are either manually driven vehicles or autonomous driving vehicles.

[0079] Case 2: Moderate queue intensity.

[0080] In this case, the autonomous vehicles and the manually driven vehicles are randomly mixed together, and whether the nth vehicle following is of the same type as the preceding vehicle is determined by the permeability. Therefore, the elements of the transfer matrix T are:

[0081] t 11 (P,0)=t 01 (P,0)=P

[0082] t 10 (P,0)=t 00 (P,0)=P0

[0083] Case 3: Minimum queue strength

[0084] In this case, it is the worst queue strength case for autonomous vehicles, and it is also the case with the largest number of autonomous vehicles. All autonomous vehicles are followed by manually driven vehicles, and all manually driven vehicles are followed by autonomous vehicles. Autonomous vehicles and manually driven vehicles are completely intertwined. Therefore, the elements of the transfer matrix T are:

[0085]

[0086] t11 (P,-1):=1-t 10 (P,-1)

[0087]

[0088] t 00 (P,-1):=1-t 01 (P,-1)

[0089] Through the above modeling, it is concluded that by calculating the number of different types of vehicles, based on the probability of the appearance of the front vehicle type and the rear vehicle type, the queue intensity O can be statistically obtained. The mixed traffic volume generation model based on the Markov chain can generate the rear vehicle type according to the front vehicle type through the given penetration rate and queue intensity, so as to obtain the vehicle type sequence under the specified traffic mode, which is used to observe the vehicle following situation under different queue intensities.

[0090] The system for determining the safety status of autonomous driving mixed traffic flow provided in this embodiment can avoid the situation where the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle cannot be determined by using two methods to determine the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle. When either method cannot be implemented, the other method is used to determine the first driving trajectory of each autonomous driving vehicle and the second driving trajectory of each manually driven vehicle, thereby avoiding the situation where the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle cannot be determined.

[0091] In some optional embodiments, the characteristic parameters include: road environment parameters; wherein the road environment construction module 102 includes: a simulation unit for determining a test scenario and a vehicle motion model based on the road environment parameters; and a display unit for receiving the safety status and test scenario of the safety risk assessment module 104, and visually displaying the safety status and the test scenario.

[0092] The simulation unit may include: computer graphics technology, geographic information system technology (GIS), Vissim simulation software, (Simulation of Urban Mobility, SUMO) simulation software, (Virtual Test Drive, VTD) simulation software and other traffic flow simulation software secondary development tool components. The simulation unit can determine the test scenario and vehicle motion model through road environment parameters.

[0093] The display unit may include two-dimensional components such as line graphs, bar graphs, pie charts, and scatter graphs, and may also include three-dimensional components such as radar graphs, which are not specifically limited here. Specifically, the display unit may display the test scenario generated by the simulation unit and the security status determined by the security risk assessment module 104.

[0094] The system for determining the safety status of mixed traffic flow for autonomous driving provided in this embodiment facilitates operators to view by displaying the safety status and test scenarios of the safety risk assessment module 104.

[0095] In an optional embodiment, the safety risk assessment module 104 includes: a determination unit for determining a safety factor based on the first driving trajectory and the second driving trajectory; wherein the safety factor includes: an acceleration index, a deceleration index, a collision time index, and a post-intrusion time index; a detection unit for detecting whether the safety factor meets a preset threshold; wherein, if the safety factor meets the preset threshold, the safety state is determined to be safe; if the safety factor does not meet the preset threshold, the safety state is determined to be unsafe.

[0096] The safety factor may include: an acceleration index, a deceleration index, a collision time index, and a post-intrusion time index. Among them, the acceleration index and the deceleration index can respectively characterize the acceleration and deceleration of each manually driven vehicle and the autonomous driving vehicle. Specifically, it can be determined by two adjacent time points on the driving trajectory. Since the driving trajectory is a trajectory generated within a certain period of time, the acceleration index and the deceleration index can be determined by the speed and distance corresponding to the two adjacent time points. The collision time index can be used to characterize the time when a collision occurs between adjacent vehicles. Specifically, the collision time index can be determined by the driving trajectory of each vehicle.

[0097] The preset thresholds may include: acceleration threshold, deceleration threshold, collision time index threshold, and rear intrusion time index threshold. Among them, it is possible to detect whether the acceleration index meets the acceleration threshold, whether the deceleration index meets the deceleration threshold, whether the collision time index meets the collision time index threshold, and whether the rear intrusion time index meets the rear intrusion time index threshold. Among them, only when all of the above are met, can the safety state be determined to be safe. In the case that any of the above is not met, the safety state is determined to be unsafe.

[0098] Preferably, when all of the above conditions are met, the risk level can be determined by whether the collision time indicator meets the collision time indicator threshold. The risk level can be divided into three levels: high, medium, and low risk, which are represented by red, yellow, and green on the corresponding roads, or by other colors, which are not specifically limited here. For example: if the collision time indicator is close to the collision time indicator threshold (such as the collision time indicator is 1.3s and the collision time indicator threshold is 1.31s), then the risk level is high.

[0099] In some optional embodiments, the above-mentioned device also includes: a receiving module, which is communicated with the autonomous driving mixed traffic flow generation module 103 and the safety risk assessment module 104, respectively, and is used to receive characteristic parameters and safety status; a decision module, which is communicated with the receiving module, and is used to generate an organizational optimization strategy based on the characteristic parameters and safety status.

[0100] After obtaining the characteristic parameters and the safety status, the characteristic parameters and the safety status can be received by the receiving module, and then the decision module automatically generates organizational optimization measures based on the input characteristic parameters and the safety status level, so as to achieve the purpose of reducing traffic safety risks. Among them, the organizational optimization measures are used to correct the above-mentioned characteristic parameters to reduce the safety status level. The specific generation method of the organizational optimization strategy is described in detail below.

[0101] The system for determining the safety status of mixed traffic flow in autonomous driving provided in this embodiment can adjust the safety status by organizing optimization strategies, thereby ensuring the safety of the test scenario.

[0102] In some optional embodiments, the decision module includes: a first decision unit, which is used to match the corresponding organizational optimization strategy from a preset strategy library based on characteristic parameters and safety status; or, a second decision unit, which is used to generate an organizational optimization strategy in response to the configuration operation of the target object if the first decision unit does not match the corresponding organizational optimization strategy; a parameter feature acquisition module 101, which is also used to adjust the characteristic parameters based on the organizational optimization strategy to generate target characteristic parameters; a road environment construction module 102, which is also used to determine the target test scenario based on the target characteristic parameters; an autonomous driving mixed traffic flow generation module 103, which is also used to determine the first target driving trajectory of the autonomous driving vehicle and the second target driving trajectory of the manually driven vehicle based on the target characteristic parameters and the target test scenario; a safety risk assessment module 104, which is also used to determine the target safety status of the test scenario based on the first target driving trajectory, the second target driving trajectory and the preset safety risk indicators; the device also includes: a detection module, which is used to detect whether the target safety status meets the preset safety status; an adding module, which is used to write the target characteristic parameters, the organizational optimization strategy corresponding to the second decision unit, and the target safety status into the preset strategy library if the target safety status meets the preset safety status.

[0103] The preset policy library may include multiple policies, wherein the multiple policies may be obtained according to actual scenario tests, and are not specifically limited here. Among them, if the corresponding organization optimization policy is matched from the preset policy library for the characteristic parameters and the security status, the characteristic parameters may be directly corrected by the organization optimization policy, thereby adjusting the security status, thereby ensuring the security of the test scenario.

[0104] The configuration operation can be an operation generated by a user through a mouse click, keyboard selection or touch screen. When the user issues a configuration operation, accordingly, if the first decision unit does not match the corresponding organizational optimization strategy, the second decision unit can configure the organizational optimization strategy in response to the configuration operation. After the configuration of the organization optimization strategy is completed, the organization optimization strategy needs to be verified. Specifically, the characteristic parameters are adjusted through the organization optimization strategy to generate target characteristic parameters; the target test scenario is determined through the target characteristic parameters (please refer to the above-mentioned road environment construction module 102 for details, which will not be described in detail here); the first target driving trajectory of the autonomous driving vehicle and the second target driving trajectory of the manually driven vehicle are determined by the target characteristic parameters and the target test scenario (please refer to the above-mentioned autonomous driving mixed traffic flow generation module 103 for details, which will not be described in detail here); the target safety state of the test scenario is determined through the first target driving trajectory, the second target driving trajectory and the preset safety risk index (please refer to the above-mentioned safety risk assessment module 104 for details, which will not be described in detail here); the detection module is used to detect whether the target safety state meets the preset safety state, wherein, if the target safety state meets the preset safety state, that is, the acceleration index meets the acceleration threshold, the deceleration index meets the deceleration threshold, the collision time index meets the collision time index threshold and the rear entry time index meets the rear entry time index threshold, then the organization optimization strategy is added to the preset strategy library through the adding module. Specifically, the optimized structured data table of security status can be added to the preset policy library, wherein the table supports database operations such as adding, deleting, modifying, and checking.

[0105] The system for determining the safety status of mixed traffic flow in autonomous driving provided in this embodiment can ensure the accuracy of the organizational optimization strategy by matching the corresponding organizational optimization strategy in a preset strategy library, setting the organizational optimization strategy through a target object, and verifying the way in which the organizational optimization strategy is set by the target object.

[0106] Figure 4 A schematic diagram of a system for determining the safety status of a mixed traffic flow for autonomous driving is shown. Figure 4 As shown, the system for determining the safety status of autonomous driving mixed traffic flow includes a human-computer interaction layer, a visual simulation layer, a tool model layer, an analysis application layer, and a data storage layer.

[0107] The human-computer interaction layer includes a feature parameter setting module, which is used to obtain road environment parameters, vehicle driving feature parameters, and road-vehicle fusion parameters.

[0108] The visualization simulation layer includes a road environment construction module, which is used to obtain vehicle motion models and test scenarios based on road environment parameters and in combination with GIS components and traffic flow simulation software secondary development software, and to display the test scenarios based on two- and three-dimensional visualization components.

[0109] The tool model layer includes a safety risk assessment module and an autonomous driving mixed traffic flow generation module. The autonomous driving mixed traffic flow generation module can obtain the trajectory sequence of autonomous driving vehicles and manually driven vehicles based on road environment parameters and road-vehicle fusion parameters by using single vehicle generation or aggregate generation methods; the safety risk assessment module can determine the rapid acceleration and deceleration index, collision time index and post-intrusion time index based on the trajectory sequence of autonomous driving vehicles and manually driven vehicles, and compare the rapid acceleration and deceleration index, collision time index and post-intrusion time index with the risk threshold respectively to obtain the risk level, and send the risk level to the visual simulation layer for display.

[0110] The analysis application layer includes an organization optimization decision support module (that is, the above-mentioned decision module). According to the input safety risk results and the parameters of the trajectory sequences of autonomous driving vehicles and manually driven vehicles, it searches for the corresponding organization optimization support strategy from the autonomous driving mixed traffic flow organization strategy library, and can also customize the newly generated organization optimization support strategy.

[0111] The data storage layer includes an autonomous driving mixed traffic flow organization strategy library (that is, the above-mentioned preset strategy library), which is capable of receiving newly generated customized organization optimization auxiliary strategies.

[0112] According to an embodiment of the present invention, an embodiment of a method for determining a safety status of mixed traffic flow in an autonomous driving system is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0113] In this embodiment, a method for determining the safety state of an autonomous driving mixed traffic flow is provided, which can be used in the above-mentioned system for determining the safety state of an autonomous driving mixed traffic flow. Figure 5 is a flow chart of a method for determining a safety state of a mixed traffic flow of an autonomous driving system according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:

[0114] Step S501, obtaining characteristic parameters.

[0115] Step S502: Determine the test scene and the vehicle motion model based on the characteristic parameters.

[0116] Step S503, based on the test scenario, the vehicle motion model and the characteristic parameters, determine a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle.

[0117] Step S504: determining the safety status of the test scenario based on the first driving trajectory, the second driving trajectory, and a preset safety risk indicator.

[0118] After the characteristic parameters are obtained, the test scenario and the vehicle motion model can be determined by the characteristic parameters. The test scenario can be used to characterize the environment required for the test. For example: the slope of the vehicle road, the length of the vehicle road, etc., which are not specifically limited here. The vehicle motion model may include a motion model of an autonomous driving vehicle and a motion model of a manually driven vehicle, that is, after determining the distribution of each vehicle on the vehicle road, the motion model of the autonomous driving vehicle and the motion model of the manually driven vehicle can be used to respectively determine the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle, and through the first driving trajectory of the autonomous driving vehicle, the second driving trajectory of the manually driven vehicle and the preset safety risk indicators, the safety state of the test scenario can be determined. Among them, the preset safety risk indicators can be used to characterize that the vehicle can safely pass on the road without causing harm to other traffic participants, and can safely deal with the risks caused by other traffic participants.

[0119] The method for determining the safety status of autonomous driving mixed traffic flow provided in this embodiment determines a test scenario and a vehicle motion model through characteristic parameters, determines a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle through the test scenario, the vehicle motion model and the characteristic parameters, and then determines the safety status of the test scenario through the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle. Compared with the method of only considering manually driven vehicles, this system combines the first driving trajectory of the autonomous driving vehicle and the second driving trajectory of the manually driven vehicle to more accurately determine the safety status of the test scenario.

[0120] In this embodiment, a device for determining the safety status of mixed traffic flow in an autonomous driving system is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0121] This embodiment provides a device for determining the safety state of an autonomous driving mixed traffic flow, such as Figure 6 As shown, including:

[0122] An acquisition module 601 is used to acquire characteristic parameters; a first determination module 602 is used to determine a test scenario and a vehicle motion model based on the characteristic parameters; a second determination module 603 is used to determine a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle based on the test scenario, the vehicle motion model and the characteristic parameters; a third determination module 604 is used to determine a safety status of the test scenario based on the first driving trajectory, the second driving trajectory and a preset safety risk indicator.

[0123] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0124] The device for determining the safety status of autonomous driving mixed traffic flow in this embodiment is presented in the form of a functional unit, where the functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0125] The embodiment of the present invention also provides a computer device having the above Figure 6 The device for determining the safety status of autonomous driving mixed traffic flow is shown.

[0126] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0127] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0128] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0129] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0130] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0131] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0132] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0133] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0134] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0135] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A system for determining the safety status of mixed traffic flow for autonomous driving, characterized in that: The system comprises: A parameter feature acquisition module is used to acquire feature parameters; A road environment construction module is communicatively connected to the parameter feature acquisition module, and is used to receive the feature parameters and determine a test scenario and a vehicle motion model based on the feature parameters; an autonomous driving mixed traffic flow generation module, which is communicatively connected to the parameter feature acquisition module and the road environment construction module, respectively, and is used to receive the test scenario, the vehicle motion model, and the feature parameters, and determine a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle based on the test scenario, the vehicle motion model, and the feature parameters; a safety risk assessment module, which is in communication with the autonomous driving mixed traffic flow generation module and is used to determine the safety status of the test scenario based on the first driving trajectory, the second driving trajectory and a preset safety risk indicator; The characteristic parameters include: road environment parameters and road-vehicle fusion parameters: wherein the autonomous driving mixed traffic flow generation module includes: A single vehicle determination unit, configured to determine a first vehicle fleet sequence of a vehicle fleet based on the road environment parameter and the road-vehicle fusion parameter; wherein the vehicle fleet includes a plurality of target vehicles, and the target vehicles include autonomous driving vehicles and / or manually driven vehicles; a single vehicle generating unit, configured to respectively determine a first driving trajectory of each autonomous driving vehicle and a second driving trajectory of each manually driven vehicle based on the first vehicle fleet sequence and the vehicle motion model; the first vehicle fleet sequence is used to characterize the positional order of manually driven vehicles and autonomous driving vehicles in the vehicle fleet, and the vehicle road includes an autonomous driving vehicle A and a manually driven vehicle B, and the corresponding first vehicle fleet sequence is AB or BA, and when the first vehicle fleet sequence is AB, the autonomous driving vehicle is in front and the manually driven vehicle is in the back, and when the first vehicle fleet sequence is BA, the manually driven vehicle is in front and the autonomous driving vehicle is in the back; or, an aggregate determination unit, configured to determine a second fleet sequence of the fleet according to the region based on the road environment parameter and the road-vehicle fusion parameter; wherein the number of the second fleet sequence is greater than that of the first fleet sequence; an aggregate generation unit, configured to determine a first driving trajectory of each autonomous driving vehicle and a second driving trajectory of each manually driven vehicle based on the second fleet sequence and the vehicle motion model; The safety risk assessment module includes: a determination unit, configured to determine a safety factor based on the first driving trajectory and the second driving trajectory; wherein the safety factor includes: an acceleration index, a deceleration index, a collision time index, and a post-intrusion time index; A detection unit is used to detect whether the safety factor meets a preset threshold; if the safety factor meets the preset threshold, the safety state is determined to be safe; if the safety factor does not meet the preset threshold, the safety state is determined to be unsafe.

2. The system for determining the safety status of mixed traffic flow for autonomous driving according to claim 1, characterized in that: The parameter feature acquisition module includes: a configuration unit, configured to configure the feature parameter in response to an input operation of the target object on the feature parameter based on the input operation; or The acquisition unit is used to receive a structured parameter file and acquire the characteristic parameters based on the structured parameter file; wherein the structured parameter file includes the characteristic parameters.

3. The system for determining the safety status of mixed traffic flow for autonomous driving according to claim 1, characterized in that: The characteristic parameters include: road environment parameters; wherein the road environment construction module includes: A simulation unit, used to determine a test scenario and a vehicle motion model based on the road environment parameters; The display unit is used to receive the security status of the security risk assessment module and the test scenario, and to visually display the security status and the test scenario.

4. The system for determining the safety status of mixed traffic flow for autonomous driving according to claim 1, characterized in that: Also includes: a receiving module, which is respectively connected to the autonomous driving mixed traffic flow generation module and the safety risk assessment module for receiving the characteristic parameters and the safety status; The decision module is communicatively connected with the receiving module and is used to generate an organizational optimization strategy based on the characteristic parameters and the security status.

5. The system for determining the safety status of mixed traffic flow for autonomous driving according to claim 4, characterized in that: The decision module comprises: A first decision unit is used to match a corresponding organizational optimization strategy from a preset strategy library based on the characteristic parameters and the security status; or, a second decision unit, configured to generate the organization optimization strategy in response to a configuration operation of a target object if the first decision unit does not match the corresponding organization optimization strategy; The parameter feature acquisition module is further used to adjust the feature parameters based on the tissue optimization strategy to generate target feature parameters; The road environment construction module is further used to determine a target test scenario based on the target characteristic parameters; The autonomous driving mixed traffic flow generation module is also used for target characteristic parameters and target test scenarios to determine the first target driving trajectory of the autonomous driving vehicle and the second target driving trajectory of the manually driven vehicle; The safety risk assessment module is further used to determine the target safety state of the test scenario based on the first target driving trajectory, the second target driving trajectory and a preset safety risk indicator; The device further includes: a detection module, configured to detect whether the target safety state satisfies a preset safety state; An adding module is used to write the target characteristic parameters, the organizational optimization strategy corresponding to the second decision unit, and the target security state into the preset strategy library if the target security state meets the preset security state.

6. A method for determining the safety status of mixed traffic flow in an autonomous driving system, characterized in that: include: Get feature parameters; Based on the characteristic parameters, determining a test scenario and a vehicle motion model; Determining a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle based on the test scenario, the vehicle motion model, and the characteristic parameters; The characteristic parameters include: road environment parameters and road-vehicle fusion parameters: wherein, based on the test scenario, the vehicle motion model and the characteristic parameters, determining a first driving trajectory of the autonomous driving vehicle and a second driving trajectory of the manually driven vehicle includes: Based on the road environment parameters and the road-vehicle fusion parameters, a first fleet sequence of the fleet is determined; wherein the fleet includes multiple target vehicles, and the target vehicles include autonomous driving vehicles and / or manually driven vehicles; based on the first fleet sequence and the vehicle motion model, a first driving trajectory of each autonomous driving vehicle and a second driving trajectory of each manually driven vehicle are determined respectively; the first fleet sequence is used to characterize the position sorting of manually driven vehicles and autonomous driving vehicles in the fleet, and the vehicle road includes an autonomous driving vehicle A and a manually driven vehicle B, and the corresponding first fleet sequence is AB or BA. When the first fleet sequence is AB, the autonomous driving vehicle is in front and the manually driven vehicle is in the back. When the first fleet sequence is BA, the manually driven vehicle is in front and the autonomous driving vehicle is in the back; or, Based on the road environment parameters and the road-vehicle fusion parameters, determine a second fleet sequence of the fleet according to the region; wherein the number of the second fleet sequence is greater than the first fleet sequence; based on the second fleet sequence and the vehicle motion model, determine a first driving trajectory of each autonomous driving vehicle and a second driving trajectory of each manually driven vehicle; Determining a safety status of the test scenario based on the first driving trajectory, the second driving trajectory, and a preset safety risk indicator; Determining a safety state of the test scenario based on the first driving trajectory, the second driving trajectory, and a preset safety risk indicator includes: Determining a safety factor based on the first driving trajectory and the second driving trajectory; wherein the safety factor includes: an acceleration index, a deceleration index, a collision time index, and a post-intrusion time index; Detect whether the safety factor meets a preset threshold; if the safety factor meets the preset threshold, determine that the safety state is safe; if the safety factor does not meet the preset threshold, determine that the safety state is unsafe.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for determining the safety status of autonomous driving mixed traffic flow as described in claim 6 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for determining the safety status of autonomous driving mixed traffic flow as described in claim 6.

Citation Information

Patent Citations

  • Automatic driving vehicle trajectory planning method and device, electronic equipment and storage medium

    CN114265398A