A trajectory safety assessment method, device and terminal equipment

Abstract

The application provides a trajectory safety evaluation method and device and a terminal equipment, which are suitable for the technical field of data processing. The method comprises the following steps: obtaining trajectory planning information, traffic road information and a plurality of traffic participant state information; generating occupation area prediction information and passing area prediction information according to the traffic road information, the plurality of traffic participant state information and a preset traffic area prediction model; and generating trajectory safety evaluation information according to the trajectory planning information, the occupation area prediction information and the passing area prediction information. The application realizes online real-time safety evaluation of a trajectory planned by an automatic driving vehicle, can accurately identify and actively avoid potential collision risks, has high efficiency, strong generalization and precise safety guarantee capability, and improves the safety performance and credibility of automatic driving.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of data processing, and particularly relates to a trajectory safety evaluation method and device and a terminal device. BACKGROUND

[0002] In recent years, automatic driving technology has developed rapidly and gradually promoted from the laboratory to the actual road, but safety is still the primary challenge to its large-scale landing. In the function chain of the automatic driving system, the motion planning module directly determines the precise motion state of the vehicle, and its safety needs to be guaranteed by a rigorous verification mechanism. At present, the mainstream safety verification methods in the industry mainly include offline simulation testing, closed road real testing and online verification, among which the offline method relies on a large number of mileage accumulated accident data, and the online method monitors the compliance of the trajectory in real time by formally defining safety rules.

[0003] In the prior art, the online safety verification method can be divided into two categories based on explicit safety rules and implicit safety rules. The explicit rule method is based on traffic regulations (such as traffic lights and lane lines), and the conflict between the trajectory and the rules is evaluated by simple logical formulas or temporal logic expressions. The implicit rule method includes threshold judgment based on time to collision (TTC) and responsibility sensitive safety (RSS), and a method of predicting the future occupancy area of a traffic participant based on statistical probability or a simple dynamics model, which evaluates the risk by monitoring the distance threshold or trajectory overlap.

[0004] However, the existing offline safety verification method has the problems of long verification period, high cost of accident cause analysis, and difficulty in responding to algorithm iteration and update; the online method based on explicit rules lacks scene generalization ability and cannot adapt to unstructured road environment; the threshold method based on implicit rules has high sensitivity and lacks long-term planning ability, while the existing prediction occupancy area method has insufficient prediction accuracy or is too conservative in complex scenes, resulting in an imbalance between safety protection ability and running efficiency. SUMMARY

[0005] Therefore, the embodiments of the present application provide a trajectory safety evaluation method, device and terminal device, aiming to solve the problems of low efficiency of offline verification, insufficient generalization and initiative of online rule driven method, and difficulty in balancing the accuracy and conservatism of the prediction occupancy area method in the prior art.

[0006] The first aspect of the embodiments of the present application provides a trajectory safety evaluation method, comprising:

[0007] obtaining trajectory planning information, traffic road information and a plurality of traffic participant element state information;

[0008] generating occupancy area prediction information and passing area prediction information according to the traffic road information, the plurality of traffic participant element state information and a preset traffic area prediction model.

[0009] According to the trajectory planning information, the occupation area prediction information, and the passing area prediction information, trajectory safety evaluation information is generated.

[0010] A second aspect of the embodiment of the present application provides a trajectory safety evaluation device, comprising:

[0011] An information acquisition module is configured to acquire trajectory planning information, traffic road information, and a plurality of traffic participant state information.

[0012] An occupation area prediction information and passing area prediction information generation module is configured to generate occupation area prediction information and passing area prediction information according to the traffic road information, the plurality of traffic participant state information, and a preset traffic area prediction model.

[0013] A trajectory safety evaluation information generation module is configured to generate trajectory safety evaluation information according to the trajectory planning information, the occupation area prediction information, and the passing area prediction information.

[0014] A third aspect of the embodiment of the present application provides a terminal device, comprising a memory and a processor, the memory stores a computer program that can be run on the processor, and the processor implements the steps of the trajectory safety evaluation method according to the first aspect when executing the computer program.

[0015] A fourth aspect of the embodiment of the present application provides a computer readable storage medium, comprising a computer program stored therein, and the computer program is executed by a processor to implement the steps of the trajectory safety evaluation method according to the first aspect.

[0016] Compared with the prior art, the embodiment of the present application has the beneficial effects that the present application is used to realize online real-time safety evaluation of the trajectory planned by an autonomous vehicle, can accurately identify and actively avoid potential collision risks, has high efficiency, strong generalization, and precise safety guarantee capability, is particularly suitable for unstructured road scenes, mixed traffic environments of heterogeneous traffic participants, and open driving spaces with high uncertainty of traffic rules, and significantly improves the safety performance and credibility of autonomous driving. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment One of the present application.

[0019] Figure 2 is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment Two of the present application.

[0020] Figure 3 is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment Three of the present application.

[0021] Figure 4 is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment Four of the present application.

[0022] Figure 5 is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment Five of the present application.

[0023] Figure 6 is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment Six of the present application.

[0024] Figure 7 is a schematic diagram of an implementation process of the trajectory safety evaluation method provided by Embodiment Seven of the present application.

[0025] Figure 8 is a schematic diagram of the structure of the trajectory safety evaluation device provided by the present application.

[0026] Figure 9 is a schematic diagram of the terminal device provided by the present application. DETAILED DESCRIPTION

[0027] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0028] In order to illustrate the technical solutions described in the present application, the following will be described through specific embodiments.

[0029] Figure 1 The implementation flowchart of the trajectory safety evaluation method provided by Embodiment One of the present application is shown, and is described in detail as follows:

[0030] In step S101, trajectory planning information, traffic road information, and a plurality of traffic participant element state information are acquired.

[0031] In the embodiment, the trajectory planning information can refer to an initial planning trajectory output by a motion planning module of the autonomous vehicle, in the form of a series of time-stamped trajectory points, containing the position coordinates of the vehicle at each time in the future time domain, and can be generated by the motion planning module in the autonomous vehicle as a guide for real-time operation of the vehicle, directly reflecting the future motion state of the vehicle. The traffic road information can refer to static properties and rule constraints of the road environment, including explicit traffic rule areas (such as traffic lights, lane lines, traffic signs, and prohibited areas) and implicit safety rule areas (such as safety distance between vehicles and right-of-way agreement), as well as road centerline coordinates, width, and other geometric information, which can be obtained through fusion processing of vehicle-mounted sensors (such as cameras, lidar, and high-precision maps), and used to construct static passable areas and illegally occupied areas to provide spatial constraints for trajectory planning. The traffic participant state information can refer to the real-time motion state of surrounding dynamic traffic participants (motor vehicles, non-motor vehicles, and pedestrians), including relative position, speed vector, and acceleration vector, which can be collected and updated in real time by vehicle-mounted sensing devices (such as radar and cameras), and used to construct kinematic prediction models of different types of traffic participants, and then predict their future occupied areas.

[0032] In step S102, the occupied area prediction information and the passable area prediction information are generated according to the traffic road information, the plurality of traffic participant state information, and a preset traffic area prediction model.

[0033] In the embodiment, the preset traffic area prediction model can be artificially set and can be a point mass model constructed based on kinematic characteristics. For motor vehicles and non-motor vehicles, a point mass model can be constructed based on kinematic characteristics, longitudinal and lateral accelerations are decomposed through a motion equation, maximum feasible accelerations are determined in combination with engine power, maximum acceleration and other constraints, a vehicle center is taken as a reference, future center positions are calculated according to initial positions, speeds and time, and an elliptical area is constructed through long axis and short axis parameters, a physical boundary is approximated through a convex polygon and expanded, and a dynamic occupancy area is obtained; for pedestrians, lateral motion randomness is considered, a random sector model is constructed based on initial positions, speeds and random deflection angles, sector radii and angle ranges are determined in combination with speeds and time, and a dynamic occupancy area of the pedestrian is obtained by expanding the area through acceleration. For the passing area prediction information, explicit traffic rules (such as traffic signals, lane lines and traffic signs) and implicit safety rules (such as safety distances between vehicles and yielding agreements) are integrated, a road area is defined as a rectangular area with a width parameter, illegal occupancy areas (such as traffic signal prohibited entry areas and motor vehicle lane parts outside pedestrian crossings) of motor vehicles and pedestrians are removed from the road area through set difference operation, legal passing areas of motor vehicles and pedestrians are obtained respectively, and front and rear safety areas constrained by safety distances are combined, and finally the static passable area of the autonomous vehicle is determined. The future occupancy area of the dynamic traffic participant and the static passable area are fused, and the effective passable interval in the time and space dimensions is obtained, and the generation of the occupancy area prediction information and the passing area prediction information is completed.

[0034] In step S103, trajectory safety evaluation information is generated according to the trajectory planning information, the occupancy area prediction information and the passing area prediction information.

[0035] In the embodiment, the future occupancy area of each surrounding traffic participant can be determined first, the kinematic-based dynamic occupancy area prediction result is intersected with the legal passing area defined by road traffic rules, and the safety distance area is removed to obtain the future occupancy area of the traffic participant, and then the drivable area of the autonomous vehicle that is conflict-free and complies with traffic rules is calculated, the future occupancy areas of all motor vehicles and non-motor vehicles and the future occupancy area of pedestrians are removed from the road area, and then whether each trajectory point in the initial planned trajectory is located in the drivable area of the autonomous vehicle is judged according to the trajectory safety evaluation criteria, so that the generation of the trajectory safety evaluation information is completed. If all the trajectory points are in the drivable area, the initial trajectory is safe; if there is a trajectory point not in the drivable area, online re-planning is triggered to generate a new safe trajectory, wherein each trajectory point of the new trajectory is located in the drivable area.

[0036] The trajectory safety evaluation method provided by the embodiment of the application is used for realizing online real-time safety evaluation of a trajectory planned by an automatic driving vehicle, can accurately identify and actively avoid potential collision risks, has high efficiency, strong generalization and precise safety guarantee capability, is particularly suitable for unstructured road scenes, mixed traffic environments of heterogeneous traffic participants and open driving spaces with high uncertainty of traffic rules, and significantly improves the safety performance and credibility of automatic driving.

[0037] Figure 2 An implementation flowchart of the trajectory safety evaluation method provided by the second embodiment of the application is shown, which is different from the first embodiment described above in that:

[0038] The plurality of traffic participant element state information includes a plurality of vehicle traffic element state information and a plurality of pedestrian traffic element state information;

[0039] The plurality of vehicle traffic element state information includes a plurality of vehicle traffic element deflection information, a plurality of vehicle traffic element speed information, a plurality of vehicle traffic element acceleration information, a plurality of vehicle traffic element engine power information, a plurality of vehicle traffic element mass information and a plurality of vehicle traffic element position information;

[0040] The plurality of pedestrian traffic element state information includes a plurality of pedestrian traffic element acceleration information, a plurality of pedestrian traffic element speed information and a plurality of pedestrian traffic element deflection information;

[0041] The occupancy area prediction information includes vehicle occupancy area prediction information and pedestrian occupancy area prediction information;

[0042] The preset traffic area prediction model includes a preset vehicle traffic area prediction submodel, a preset pedestrian traffic area prediction submodel and a preset static road area prediction submodel;

[0043] The step S102 specifically includes:

[0044] The step S201 includes decomposing the plurality of vehicle traffic element acceleration information based on a preset vehicle traffic element acceleration decomposition vector to obtain a plurality of vehicle traffic element horizontal acceleration information and a plurality of vehicle traffic element vertical acceleration information.

[0045] In the embodiment, for the kinematics of a vehicle (such as a car, a motorcycle or a bicycle), a point mass model can be used, and the speed and acceleration are limited. The state of a vehicle participant can be represented as The motion equation is:

[0046] ;

[0047] The preset vehicle traffic element acceleration decomposition vector can be set artificially and can include two unit vectors With , for decomposing the acceleration in the longitudinal and lateral directions. The vehicle traffic element vertical acceleration information and the vehicle traffic element horizontal acceleration information obtained by decomposing the acceleration in the longitudinal and lateral directions through the preset vehicle traffic element acceleration decomposition vector can be expressed as:

[0048] ;

[0049] The vehicle traffic element acceleration information can be expressed as a combination of the vehicle traffic element vertical acceleration information and the vehicle traffic element horizontal acceleration information :

[0050] ;

[0051] In step S202, the vehicle traffic element horizontal acceleration information and the vehicle traffic element vertical acceleration information are constrained based on preset vehicle traffic element acceleration threshold information, the plurality of vehicle traffic element deflection information, the plurality of vehicle traffic element speed information, the plurality of vehicle traffic element engine power information, and the plurality of vehicle traffic element mass information, and vehicle traffic element acceleration constraint information is calculated.

[0052] In the embodiment, the preset vehicle traffic element acceleration threshold information can be set artificially and can be the maximum acceleration constraint of the vehicle. A normalized steering input can be introduced to represent left turn or right turn . In the case of satisfying the maximum acceleration constraint , the lateral acceleration can be written as , so as to determine the maximum feasible acceleration in the longitudinal direction as:

[0053] ;

[0054] For motorized and non-motorized vehicles (such as cars, motorcycles, bicycles), the engine power also limits the longitudinal acceleration:

[0055] ;

[0056] wherein is the engine power, is the vehicle mass, is the speed. Let the critical speed be:

[0057] ;

[0058] When the speed reaches or exceeds this critical value, engine power limitation should be used instead of maximum acceleration limitation. The longitudinal acceleration constrained by engine power is:

[0059] ;

[0060] Therefore, for cars, motorcycles, and bicycles:

[0061] ;

[0062] Used to represent acceleration constraint information for vehicle traffic elements.

[0063] Step S203: Generate multiple vehicle traffic element occupancy evolution area information based on the multiple vehicle traffic element location information and the preset vehicle occupancy evolution area model.

[0064] In this embodiment, the preset vehicle occupancy evolution region model can be artificially set, and can be an elliptical region model with the vehicle center as the reference, which can be located at the vehicle center. The structure has a long axis With short axis The elliptical region, center The formula is given as follows:

[0065] ;

[0066] ;

[0067] ;

[0068] in, This is an adjustment factor for lateral acceleration. Considering that vehicles primarily move longitudinally, it is unreasonable to equate the prediction ranges of lateral and longitudinal acceleration. Therefore, incorporating an adjustment factor is necessary. This model generates information on the evolution of occupancy regions for multiple vehicle traffic elements over time.

[0069] Step S204: Generate vehicle occupancy area prediction information based on the vehicle traffic element acceleration constraint information, the occupancy evolution area information of multiple vehicle traffic elements, and the preset vehicle traffic area prediction sub-model.

[0070] In the embodiment, the preset vehicle traffic area prediction sub-model can be artificially set and can be a convex polygon over-approximation model; the acceleration boundary of vehicle motion is determined based on vehicle traffic element acceleration constraint information, the vertices of the elliptical area are determined at the initial time and the planning time domain end point respectively in combination with the occupation evolution area information of multiple vehicle traffic elements, the non-convex polygon is converted into a convex polygon by removing part of the vertices, and the physical boundary is expanded (considering the fixed width and length of the vehicle), to obtain a convex polygon area composed of six vertices, i.e., the vehicle occupation area prediction information.

[0071] In the embodiment, for simplicity and without loss of generality, in the initial state, it is assumed that the first traffic participant , for easy calculation, the acceleration prediction area is over-approximated. Initially, it is approximated as a polygon with vertices .

[0072] ;

[0073] ;

[0074] ;

[0075] ;

[0076] ;

[0077] ;

[0078] ;

[0079] ;

[0080] Since the polygon obtained by preliminary approximation is non-convex, it is difficult to calculate directly, and therefore further simplification is performed, and by removing the vertices and , it is converted into a convex polygon. The above calculation is for the occupation area of the mass point model. However, considering that the actual vehicle has a physical boundary, in order to more accurately represent the occupied space, it is necessary to expand the boundary. Specifically, a rectangular form with a fixed width and length can be used to model the boundary of the traffic participant.

[0081] The convex polygon composed of the six vertices is used to represent the kinematic-based occupation area of the surrounding traffic participant in the time interval , which is defined as follows:

[0082] ;

[0083] ;

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] wherein, represents a convex polygonal region surrounded by vertices .

[0089] In step S205, the pedestrian occupancy area prediction information is generated according to the plurality of pedestrian traffic element deflection information, the plurality of pedestrian traffic element speed information, the plurality of pedestrian traffic element acceleration information, and a preset pedestrian traffic area prediction sub-model.

[0090] In this embodiment, the preset pedestrian traffic area prediction sub-model is a random sector area model; a sector angle range is determined based on the plurality of pedestrian traffic element deflection information, a sector radius is determined in combination with the plurality of pedestrian traffic element speed information and time, a sector area under speed constraint is obtained, the area is expanded by fusing the plurality of pedestrian traffic element acceleration information, an area under acceleration constraint is obtained, and the two areas are merged by set operation to generate the pedestrian occupancy area prediction information.

[0091] In this embodiment, the transverse motion of the pedestrian is more random. Therefore, it is assumed that the position of the i-th traffic participant at the initial time is , the speed is , and the motion direction is deflected at a random angle on either side. The future occupancy area of the pedestrian is approximately modeled as a sector, denoted as , wherein represents the angle range of the sector, represents the radius. As shown in , considering the uncertainty, the area that the pedestrian can reach within a given verification period based on the current speed of the pedestrian is defined as: Figure 3

[0092] ;

[0093] wherein, the set difference is defined as ​To simplify the calculation, a further approximation strategy is adopted for longer time periods, introducing the expansion of the occupancy area due to acceleration, defined as:

[0094] ;

[0095] Finally, the kinematic-based pedestrian occupancy area prediction result can be expressed as:

[0096] ;

[0097] In step S206, the traffic road information and the preset static road area prediction sub-model are used to generate the passing area prediction information.

[0098] In this embodiment, the preset static road area prediction sub-model can be artificially set and can be a passability model that fuses explicit and implicit traffic rules. According to the road center line coordinates, width, and other geometric information in the traffic road information, the road area can be defined, the illegal area of the motor vehicle, such as the traffic signal prohibited entry area, and the illegal area of the pedestrian, such as the motor vehicle lane part, are excluded from the road area through set difference operation, the legal area of the motor vehicle and the legal area of the pedestrian are obtained, and the front and rear safety areas constrained by the artificial preset safety distance are combined to finally generate the passing area prediction information.

[0099] In this embodiment, the quantification method of the static road occupancy area comprehensively considers the explicit and implicit traffic rules. First, a rectangular area is defined, which is described by a center point, a length, and a width parameter. The road area is defined as:

[0100] ;

[0101] wherein represents the road width.

[0102] In this study, the future occupancy area of the surrounding traffic participants is defined in combination with the explicit and implicit traffic rules. For vehicle participants, the legal driving area considers the traffic signal, traffic sign, and other traffic indications, and is defined as:

[0103] ;

[0104] wherein represents the area prohibited from entering due to traffic signals or signs. In addition, during the driving of the autonomous vehicle, a certain safety distance needs to be maintained with other vehicles, and the front and rear safety areas are recorded as .

[0105] For pedestrian participants, the legal passing area is defined as:

[0106] ;

[0107] wherein, Pedestrian prohibited area, including intersection area outside the crosswalk and part of the motor vehicle lane.

[0108] The trajectory safety evaluation method provided by the embodiments of the present application further improves the accuracy of the occupancy area prediction and the precision of the passing area division, enhances the detail and reliability of the trajectory safety evaluation, and better meets the safety verification needs in complex and heterogeneous traffic environments, thereby effectively ensuring the safe driving of the autonomous vehicle in various scenarios.

[0109] Figure 3 An implementation flowchart of the trajectory safety evaluation method provided by Embodiment Three of the present application is shown, which is different from Embodiment Two described above in that the step S202 specifically includes:

[0110] Step S301: calculating a vehicle traffic element speed threshold according to the engine power information of the plurality of vehicle traffic elements, the mass information of the plurality of vehicle traffic elements, and preset vehicle traffic element acceleration threshold information.

[0111] In this embodiment, the preset vehicle traffic element acceleration threshold information is the maximum acceleration constraint of the vehicle In combination with the engine power information of the plurality of vehicle traffic elements , the mass information of the plurality of vehicle traffic elements , the vehicle traffic element speed threshold is calculated according to the formula , which is used to determine whether the vehicle acceleration is constrained by the maximum acceleration or the engine power.

[0112] Step S302: determining whether the vehicle traffic element speed information is greater than or equal to the vehicle traffic element speed threshold, if yes, proceeding to step S303; if no, proceeding to step S304.

[0113] In this embodiment, the plurality of vehicle traffic element speed information v is compared with the calculated vehicle traffic element speed threshold , if , it indicates that the current speed of the vehicle has reached or exceeded the critical value, and the engine power plays a leading role in limiting the longitudinal acceleration; if , it indicates that the maximum acceleration constraint plays a leading role.

[0114] ​Step S303, according to the plurality of vehicle traffic element speed information, the plurality of vehicle traffic element engine power information and the plurality of vehicle traffic element mass information, the vehicle traffic element acceleration constraint information is calculated.

[0115] In this embodiment, when the vehicle traffic element speed information is greater than or equal to the vehicle traffic element speed threshold value, based on the plurality of vehicle traffic element speed information , the plurality of vehicle traffic element engine power information and the plurality of vehicle traffic element mass information , according to the formula The engine power limited longitudinal acceleration is calculated, and combined with the lateral acceleration , the maximum feasible acceleration in the longitudinal direction is determined as: , that is, the maximum feasible acceleration in the longitudinal direction, as the vehicle traffic element acceleration constraint information.

[0116] Step S304, according to the plurality of vehicle traffic element deflection information and the preset vehicle traffic element acceleration threshold value information, the plurality of vehicle traffic element horizontal acceleration constraint information is calculated.

[0117] In this embodiment, based on the plurality of vehicle traffic element deflection information, the normalized steering input is determined to represent left turn or right turn According to the formula The plurality of vehicle traffic element horizontal acceleration constraint information (lateral acceleration) is calculated, which is used to reflect the lateral acceleration limit of the vehicle when turning.

[0118] Step S305, according to the plurality of vehicle traffic element horizontal acceleration constraint information and the preset vehicle traffic element acceleration threshold value information, the plurality of vehicle traffic element vertical acceleration constraint information is calculated.

[0119] In this embodiment, according to the formula The plurality of vehicle traffic element vertical acceleration constraint information (longitudinal acceleration) is calculated, which reflects the maximum feasible value of the longitudinal acceleration in the presence of lateral acceleration.

[0120] Step S306, according to the plurality of vehicle traffic element horizontal acceleration constraint information and the plurality of vehicle traffic element vertical acceleration constraint information, the vehicle traffic element acceleration constraint information is calculated.

[0121] In the embodiment, the multiple vehicle traffic element horizontal acceleration constraint information and the multiple vehicle traffic element vertical acceleration constraint information are combined to obtain acceleration limits of the vehicle in the longitudinal and lateral directions, which comprehensively constitute the vehicle traffic element acceleration constraint information for constraining the motion state of the vehicle and ensuring that the vehicle travels within a safe range.

[0122] The trajectory safety evaluation method provided in the embodiments of the present application improves the accuracy and rationality of vehicle occupancy area prediction, makes the trajectory safety evaluation more in line with the actual motion characteristics of the vehicle, especially more accurately reflects the influence of acceleration constraints on vehicle motion at different speed intervals, thereby enhancing the reliability and effectiveness of safety verification in complex traffic scenarios.

[0123] Figure 4 The implementation flowchart of the trajectory safety evaluation method provided in the fourth embodiment of the present application is shown, which is different from the second embodiment described above in that the step S205 specifically includes:

[0124] In step S401, multiple pedestrian traffic deflection area prediction information is generated according to the multiple pedestrian traffic element deflection information, preset pedestrian traffic deflection angle range information, and preset pedestrian traffic deflection radius information.

[0125] In the embodiment, the preset pedestrian traffic deflection angle range information can be an angle range of a sector The preset pedestrian traffic deflection radius information is determined based on the random deflection angle in the pedestrian traffic element deflection information, based on the random angle in the multiple pedestrian traffic element deflection information, the future occupancy area of the pedestrian is approximated as a sector by combining the preset pedestrian traffic deflection angle range information and the pedestrian traffic deflection radius information, denoted as , wherein represents the angle range of the sector, i.e., the preset pedestrian traffic deflection angle range information, represents the preset pedestrian traffic deflection radius information, and the multiple pedestrian traffic deflection area prediction information is generated in this way.

[0126] In step S402, multiple pedestrian traffic movement area prediction information is generated according to the multiple pedestrian traffic deflection area prediction information and multiple pedestrian traffic element speed information.

[0127] In the embodiment, based on the sector area in the multiple pedestrian traffic deflection area prediction information, the sector radius is updated to by combining the multiple pedestrian traffic element speed information and the time , to obtain the area that the pedestrian can reach based on the speed within a given verification period, i.e., the multiple pedestrian traffic movement area prediction information. Reflects the movement range of pedestrians under speed constraints.

[0128] In step S403, pedestrian occupancy area prediction information is generated according to the plurality of pedestrian traffic movement area prediction information, the plurality of pedestrian traffic element acceleration information, and a preset pedestrian traffic area prediction sub-model.

[0129] In this embodiment, the preset pedestrian traffic area prediction sub-model is a speed and acceleration constraint fusion area model; based on the plurality of pedestrian traffic movement area prediction information , the plurality of pedestrian traffic element acceleration information is introduced to expand the area, and the area under acceleration constraint is obtained , and the two areas are merged through set operation, which can be represented as:

[0130] ;

[0131] Pedestrian occupancy area prediction information is used to represent the pedestrian occupancy area prediction information, which is used to comprehensively cover all possible occupancy spaces of pedestrians under the influence of speed and acceleration.

[0132] The trajectory safety evaluation method provided by the embodiment of the application further refines the prediction process of the pedestrian occupancy area by modeling the deflection, speed, and acceleration information of the pedestrian traffic element, improves the accuracy and comprehensiveness of the pedestrian occupancy area prediction, makes it more suitable for the characteristics of strong randomness of pedestrian transverse movement, and thus enhances the reliability and effectiveness of the trajectory safety evaluation in complex traffic scenes containing pedestrians.

[0133] Figure 5 The implementation flowchart of the trajectory safety evaluation method provided by the fifth embodiment of the application is shown, which is different from the second embodiment described above in that:

[0134] The traffic road information includes traffic road non-prohibited passage area information and traffic road prohibited passage area information;

[0135] The traffic road prohibited passage area information includes vehicle traffic road prohibited passage area information and pedestrian traffic road prohibited passage area information;

[0136] The passage area prediction information includes vehicle passage area prediction information and pedestrian passage area prediction information;

[0137] The step S206 specifically includes:

[0138] In step S501, vehicle passage area prediction information is generated according to the traffic road non-prohibited passage area information, the vehicle traffic road prohibited passage area information, the preset vehicle front and rear safety area information, and the preset static road area prediction sub-model.

[0139] In this embodiment, the preset static road area prediction sub-model can be a vehicle accessibility model that integrates explicit and implicit traffic rules; the information on non-prohibited traffic areas of traffic roads is the road area. Information on prohibited areas for vehicle traffic For example, in areas where traffic signals or signs indicate no-entry zones, based on a pre-defined static road area prediction sub-model, the information on prohibited traffic areas is removed from the information on non-prohibited traffic areas using set difference operations, resulting in... Combined with preset vehicle front and rear safety zone information Ultimately, vehicle traffic area prediction information is generated, which reflects the legal traffic space for vehicles while adhering to traffic rules and maintaining a safe distance.

[0140] Step S502: Based on the information on non-prohibited traffic areas of the traffic roads, the information on prohibited traffic areas of pedestrian traffic roads, and the preset static road area prediction sub-model, generate pedestrian traffic area prediction information.

[0141] In this embodiment, the preset static road area prediction sub-model is a pedestrian accessibility model that integrates explicit and implicit traffic rules; the information on non-prohibited traffic areas on roads is the road area. Information on pedestrian traffic restricted areas Including intersection areas excluding pedestrian crossings and the motor vehicle lanes, based on a pre-set static road area prediction sub-model, the information on pedestrian prohibited traffic areas is removed from the information on non-prohibited traffic areas of traffic roads through set difference operations, resulting in... This generates pedestrian crossing area prediction information, which reflects the legal passage range for pedestrians in the road environment.

[0142] The trajectory safety assessment method provided in this application refines traffic road information into non-prohibited and prohibited passage areas, and generates passage area prediction information for vehicles and pedestrians respectively. This improves the accuracy and relevance of static road accessibility modeling, and makes the passage area division more in line with the different traffic rule requirements of vehicles and pedestrians, thereby enhancing the reliability and applicability of trajectory safety assessment in complex road environments.

[0143] Figure 6 The flowchart illustrating the implementation of the trajectory safety assessment method provided in Embodiment Six of this application is shown. The difference between this method and Embodiment One is that step S103 specifically includes:

[0144] Step S601: Generate drivable area information based on the occupancy area prediction information and the passage area prediction information.

[0145] In the embodiment, the occupancy area prediction information includes vehicle occupancy area prediction information and pedestrian occupancy area prediction information, and the passable area prediction information is a static passable area of the autonomous vehicle; by excluding the area covered by the occupancy area prediction information from the passable area prediction information, i.e. excluding the future occupancy area of the vehicle and the pedestrian from the static passable area, the drivable area information of the autonomous vehicle without conflict and in compliance with traffic rules is obtained, which is the space range in which the vehicle can safely drive.

[0146] In step S602, trajectory safety evaluation information is generated according to the trajectory planning information and the drivable area information.

[0147] In the embodiment, the trajectory planning information is an initial planning trajectory, which contains the position coordinates of the vehicle at each time in the future time domain; according to the trajectory safety evaluation criterion, it is judged whether each trajectory point in the initial planning trajectory is in the drivable area information, if all trajectory points are in the drivable area, the trajectory safety evaluation information is generated; if there is a trajectory point not in the drivable area, the trajectory unsafe evaluation information is generated, so as to complete the generation of the trajectory safety evaluation information.

[0148] The trajectory safety evaluation method provided by the embodiment of the application effectively identifies the potential conflict risk in the initial planning trajectory, ensures that the autonomous vehicle only drives in a safe range, effectively avoids potential collision risk, and thus enhances the safety guarantee capability of the autonomous vehicle in a complex traffic environment.

[0149] Figure 7 An implementation flowchart of the trajectory safety evaluation method provided by the seventh embodiment of the application is shown, which is different from the first embodiment in that after the step S103, it further includes:

[0150] In step S701, it is judged whether the trajectory safety evaluation information is trajectory safety confirmation information, if yes, step S702 is entered; if no, step S703 is entered.

[0151] In the embodiment, the trajectory safety evaluation information includes trajectory safety confirmation information and trajectory unsafe information; by judging the trajectory safety evaluation information, it is determined whether the initial planning trajectory is in a safe state, if the evaluation information indicates that all trajectory points of the initial trajectory are in the drivable area, it is trajectory safety confirmation information; if there is a trajectory point not in the drivable area, it is trajectory unsafe information.

[0152] In step S702, the trajectory planning information is taken as the driving trajectory information.

[0153] In the embodiment, when the trajectory safety evaluation information is the trajectory safety confirmation information, it is indicated that the initial planned trajectory meets the safety requirement, and the trajectory planning information is directly used as the driving trajectory information of the autonomous vehicle to guide the vehicle to drive according to the initial plan.

[0154] In step S703, the driving trajectory information is generated according to the occupancy area prediction information and the passable area prediction information.

[0155] In the embodiment, when the trajectory safety evaluation information is the trajectory unsafe information, a new safe trajectory is generated online as the driving trajectory information based on the occupancy area prediction information (future occupancy areas of the vehicle and the pedestrian) and the passable area prediction information (static passable areas), each trajectory point of the new trajectory is located in the drivable area, and the new trajectory meets the vehicle dynamics constraint and the smoothness requirement. The new trajectory is used as the driving trajectory information to ensure that the vehicle can safely drive.

[0156] The trajectory safety evaluation method provided in the embodiment can dynamically adjust the trajectory through the judgment of the trajectory safety state and the corresponding trajectory processing mechanism, ensure the continuity and fluency of driving while ensuring the safety, enable the autonomous driving system to flexibly cope with complex traffic scenes, and thus significantly improve the reliability and practicality of autonomous driving.

[0157] Corresponding to the method of the above embodiment, Figure 8 A structure block diagram of the trajectory safety evaluation device provided in the embodiment is shown, and only parts related to the embodiment are shown for ease of description. Figure 8 The trajectory safety evaluation device can be an execution subject of the trajectory safety evaluation method provided in the first embodiment.

[0158] Referring to Figure 8 The trajectory safety evaluation device includes:

[0159] The information acquisition module 810 is configured to acquire trajectory planning information, traffic road information, and a plurality of traffic participant state information.

[0160] The occupancy area prediction information and the passable area prediction information generation module 820 is configured to generate occupancy area prediction information and passable area prediction information according to the traffic road information, the plurality of traffic participant state information, and a preset traffic area prediction model.

[0161] The trajectory safety evaluation information generation module 830 is configured to generate trajectory safety evaluation information according to the trajectory planning information, the occupancy area prediction information, and the passable area prediction information.

[0162] The processes in which the modules in the trajectory safety evaluation device provided in the embodiment realize their respective functions can be referred to the foregoing description.Figure 1 The description of the embodiments of the first aspect shown above is not repeated here.

[0163] It should be understood that the size of the serial number of each step in the above-mentioned embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of described features, whole, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components, and / or sets thereof.

[0165] It should also be understood that the term "and / or" used in the specification and appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0166] As used in the specification and appended claims of the present application, the term "if" can be interpreted as "when" or "upon" or "in response to a determination" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted to mean "upon being determined" or "in response to being determined" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]" depending on the context.

[0167] In addition, in the description of the present application and the appended claims, the terms "first", "second", "third" and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance. It should also be understood that although the terms "first", "second" and the like are used in the text to describe various elements in some embodiments of the present application, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first table can be named the second table, and similarly, the second table can be named the first table without departing from the scope of various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0168] Reference throughout this application to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but can refer to different embodiments. The term "or" as used herein is used to mean, a(n) or inclusive or unless otherwise indicated. The term "based on" means at least one of the stated value or values, but can also mean based on two or more of the stated value or values. Unless otherwise noted, the terms "including" and / or "comprising" when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0169] The trajectory safety evaluation method provided by the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), and the like. The embodiments of the present application do not make any limitation on the specific type of the terminal device.

[0170] For example, the terminal device can be a station (STATION, ST) in a WLAN, can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device, or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite radio device, a wireless modem card, a television set top box (STB), a customer premise equipment (CPE), and / or other devices for communicating over a wireless system, and a next-generation communication system, for example, a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network.

[0171] As an example and not a limitation, when the terminal device is a wearable device, the term "wearable device" can also refer to any device that utilizes wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices worn directly on the body or integrated into a user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those with comprehensive functions, large sizes, and the ability to perform complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those focused on a specific application function that require interaction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0172] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. For example... Figure 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Figure 9 (Only one is shown in the image) a memory 91, which stores a computer program 92 that can run on the processor 90. When the processor 90 executes the computer program 92, it implements the steps in the various trajectory safety assessment method embodiments described above, for example... Figure 1 Steps S101 to S103 are shown. Alternatively, when the processor 90 executes the computer program 92, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 8 The functions of the information acquisition module 810 to the trajectory safety assessment information generation module 830 are shown.

[0173] The terminal device 9 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will understand that... Figure 9 This is merely an example of terminal device 9 and does not constitute a limitation on terminal device 9. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input transmission devices, network access devices, buses, etc.

[0174] The processor 90 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0175] The memory 91 can be an internal storage unit of the terminal device 9 in some embodiments, for example, a hard disk or a memory of the terminal device 9. The memory 91 can also be an external storage device of the terminal device 9, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 91 can also include both the internal storage unit and the external storage device of the terminal device 9. The memory 91 is used to store an operating system, application programs, a boot loader, data and other programs, for example, program codes of the computer program, etc. The memory 91 can also be used to temporarily store data that has been or will be transmitted.

[0176] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0177] The embodiments of the present application also provide a terminal device, which comprises at least one memory, at least one processor and a computer program stored in the at least one memory and executable on the at least one processor, and the processor executes the computer program to enable the terminal device to implement the steps in any of the above method embodiments.

[0178] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps in any of the above method embodiments.

[0179] The embodiment of the present application provides a computer program product, when the computer program product runs on a terminal device, causes the terminal device to execute the steps in the above-mentioned various method embodiments.

[0180] The integrated module / unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on such understanding, the present application can also be implemented by a computer program to instruct related hardware to complete all or part of the processes in the above-mentioned embodiment methods, and the computer program can be stored in a computer readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0181] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0182] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software mode depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0183] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0184] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A trajectory safety assessment method, characterized by, The method comprises the following steps: acquiring trajectory planning information, traffic road information, and a plurality of traffic participant state information; generating occupancy area prediction information and passing area prediction information according to the traffic road information, the plurality of traffic participant state information, and a preset traffic area prediction model; generating trajectory safety evaluation information according to the trajectory planning information, the occupancy area prediction information, and the passing area prediction information; the plurality of traffic participant state information comprises a plurality of vehicle traffic element state information and a plurality of pedestrian traffic element state information; the plurality of vehicle traffic element state information comprises a plurality of vehicle traffic element deflection information, a plurality of vehicle traffic element speed information, a plurality of vehicle traffic element acceleration information, a plurality of vehicle traffic element engine power information, a plurality of vehicle traffic element mass information, and a plurality of vehicle traffic element position information; the plurality of pedestrian traffic element state information comprises a plurality of pedestrian traffic element acceleration information, a plurality of pedestrian traffic element speed information, and a plurality of pedestrian traffic element deflection information; the occupancy area prediction information comprises vehicle occupancy area prediction information and pedestrian occupancy area prediction information; the preset traffic area prediction model comprises a preset vehicle traffic area prediction submodel, a preset pedestrian traffic area prediction submodel, and a preset static road area prediction submodel; the step of generating the occupancy area prediction information and the passing area prediction information according to the traffic road information, the plurality of traffic participant state information, and the preset traffic area prediction model specifically comprises: based on a preset vehicle traffic element acceleration decomposition vector, decomposing the plurality of vehicle traffic element acceleration information to obtain a plurality of vehicle traffic element horizontal acceleration information and a plurality of vehicle traffic element vertical acceleration information; based on preset vehicle traffic element acceleration threshold information, the plurality of vehicle traffic element deflection information, the plurality of vehicle traffic element speed information, the plurality of vehicle traffic element engine power information, and the plurality of vehicle traffic element mass information, performing constraint processing on the plurality of vehicle traffic element horizontal acceleration information and the plurality of vehicle traffic element vertical acceleration information to calculate vehicle traffic element acceleration constraint information; generating a plurality of vehicle traffic element occupancy evolution area information according to the plurality of vehicle traffic element position information and a preset vehicle occupancy evolution area model; generating vehicle occupancy area prediction information according to the vehicle traffic element acceleration constraint information, the plurality of vehicle traffic element occupancy evolution area information, and the preset vehicle traffic area prediction submodel; generating pedestrian occupancy area prediction information according to the plurality of pedestrian traffic element deflection information, the plurality of pedestrian traffic element speed information, the plurality of pedestrian traffic element acceleration information, and the preset pedestrian traffic area prediction submodel; generating passing area prediction information according to the traffic road information and the preset static road area prediction submodel.

2. The trajectory safety assessment method of claim 1, wherein, The step of calculating the vehicle traffic element acceleration constraint information based on the preset vehicle traffic element acceleration threshold information, the plurality of vehicle traffic element deflection information, the plurality of vehicle traffic element speed information, the plurality of vehicle traffic element engine power information, the plurality of vehicle traffic element mass information, the plurality of vehicle traffic element horizontal acceleration information and the plurality of vehicle traffic element vertical acceleration information, specifically includes: According to the plurality of vehicle traffic element engine power information, the plurality of vehicle traffic element mass information and the preset vehicle traffic element acceleration threshold information, a vehicle traffic element speed threshold is calculated; Determine whether the vehicle traffic element speed information is greater than or equal to the vehicle traffic element speed threshold; If yes, the vehicle traffic element acceleration constraint information is calculated according to the plurality of vehicle traffic element speed information, the plurality of vehicle traffic element engine power information and the plurality of vehicle traffic element mass information; If not, the plurality of vehicle traffic element horizontal acceleration constraint information is calculated according to the plurality of vehicle traffic element deflection information and the preset vehicle traffic element acceleration threshold information; According to the plurality of vehicle traffic element horizontal acceleration constraint information and the preset vehicle traffic element acceleration threshold information, the plurality of vehicle traffic element vertical acceleration constraint information is calculated; According to the plurality of vehicle traffic element horizontal acceleration constraint information and the plurality of vehicle traffic element vertical acceleration constraint information, the vehicle traffic element acceleration constraint information is calculated.

3. The trajectory safety assessment method of claim 1, wherein, The step of generating pedestrian occupancy area prediction information according to the plurality of pedestrian traffic element deflection information, the plurality of pedestrian traffic element speed information, the plurality of pedestrian traffic element acceleration information and the preset pedestrian traffic area prediction sub-model, specifically includes: According to the plurality of pedestrian traffic element deflection information, the preset pedestrian traffic deflection angle range information and the preset pedestrian traffic deflection radius information, a plurality of pedestrian traffic deflection area prediction information is generated; According to the plurality of pedestrian traffic deflection area prediction information and the plurality of pedestrian traffic element speed information, a plurality of pedestrian traffic movement area prediction information is generated; According to the plurality of pedestrian traffic movement area prediction information, the plurality of pedestrian traffic element acceleration information and the preset pedestrian traffic area prediction sub-model, the pedestrian occupancy area prediction information is generated.

4. The trajectory safety assessment method of claim 1, wherein: The traffic road information includes traffic road non-prohibited area information and traffic road prohibited area information; The traffic road prohibited area information includes vehicle traffic road prohibited area information and pedestrian traffic road prohibited area information; The traffic area prediction information includes vehicle traffic area prediction information and pedestrian traffic area prediction information; The step of generating traffic area prediction information according to the traffic road information and the preset static road area prediction sub-model, specifically includes: According to the traffic road non-ban area information, the vehicle traffic road ban area information, the preset vehicle front and rear safety area information, and the preset static road area prediction sub-model, vehicle passing area prediction information is generated; According to the traffic road non-ban area information, the pedestrian traffic road ban area information, and the preset static road area prediction sub-model, pedestrian passing area prediction information is generated.

5. The trajectory safety assessment method of claim 1, wherein, The step of generating trajectory safety evaluation information according to the trajectory planning information, the occupancy area prediction information, and the passing area prediction information specifically includes: According to the occupancy area prediction information and the passing area prediction information, drivable area information is generated; According to the trajectory planning information and the drivable area information, trajectory safety evaluation information is generated.

6. The trajectory safety assessment method of claim 1, wherein, After the step of generating trajectory safety evaluation information according to the trajectory planning information, the occupancy area prediction information, and the passing area prediction information, the method further includes: determining whether the trajectory safety evaluation information is trajectory safety confirmation information; if yes, the trajectory planning information is taken as driving trajectory information; if no, driving trajectory information is generated according to the occupancy area prediction information and the passing area prediction information.

7. A trajectory safety assessment apparatus characterized by comprising: It includes: An information acquisition module is configured to acquire trajectory planning information, traffic road information, and a plurality of traffic participant state information. An occupancy area prediction information and passing area prediction information generation module is configured to generate occupancy area prediction information and passing area prediction information according to the traffic road information, the plurality of traffic participant state information, and a preset traffic area prediction model. A trajectory safety evaluation information generation module is configured to generate trajectory safety evaluation information according to the trajectory planning information, the occupancy area prediction information, and the passing area prediction information. The plurality of traffic participant state information includes a plurality of vehicle traffic element state information and a plurality of pedestrian traffic element state information. The plurality of vehicle traffic element state information includes a plurality of vehicle traffic element deflection information, a plurality of vehicle traffic element speed information, a plurality of vehicle traffic element acceleration information, a plurality of vehicle traffic element engine power information, a plurality of vehicle traffic element mass information, and a plurality of vehicle traffic element position information. The plurality of pedestrian traffic element state information includes a plurality of pedestrian traffic element acceleration information, a plurality of pedestrian traffic element speed information, and a plurality of pedestrian traffic element deflection information. The occupancy area prediction information includes vehicle occupancy area prediction information and pedestrian occupancy area prediction information. The preset traffic area prediction model includes a preset vehicle traffic area prediction sub-model, a preset pedestrian traffic area prediction sub-model, and a preset static road area prediction sub-model. The step of generating occupancy area prediction information and passing area prediction information according to the traffic road information, the plurality of traffic participant state information, and the preset traffic area prediction model specifically includes: Based on the preset vehicle traffic element acceleration decomposition vector, the acceleration information of the multiple vehicle traffic elements is decomposed to obtain the horizontal acceleration information and the vertical acceleration information of the multiple vehicle traffic elements. Based on the preset vehicle traffic element acceleration threshold information, the deflection information of the multiple vehicle traffic elements, the speed information of the multiple vehicle traffic elements, the engine power information of the multiple vehicle traffic elements, and the mass information of the multiple vehicle traffic elements, the horizontal acceleration information and the vertical acceleration information of the multiple vehicle traffic elements are constrained to calculate the vehicle traffic element acceleration constraint information. Based on the location information of the multiple vehicle traffic elements and the preset vehicle occupancy evolution area model, multiple vehicle traffic element occupancy evolution area information is generated. Based on the acceleration constraint information of the vehicle traffic elements, the occupancy evolution area information of multiple vehicle traffic elements, and the preset vehicle traffic area prediction sub-model, vehicle occupancy area prediction information is generated. Based on the deflection information of multiple pedestrian traffic elements, the speed information of multiple pedestrian traffic elements, the acceleration information of multiple pedestrian traffic elements, and the preset pedestrian traffic area prediction sub-model, pedestrian occupancy area prediction information is generated. Based on the traffic road information and the preset static road area prediction sub-model, traffic area prediction information is generated.

8. A terminal device, comprising: The terminal device includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images