Method, device, electronic device, and storage medium for determining traffic flow information

The method of determining traffic flow information through vehicle grouping and fitting weights addresses the challenge of lane marking recognition issues in smart driving systems, enabling accurate vehicle localization and control in congested conditions.

JP7580155B2Active Publication Date: 2024-11-11UISEE SHANGHAI AUTOMOTIVE TECH LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2023527374
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2020-11-09
Publication Date
2024-11-11
Estimated Expiration
2040-11-09

AI Technical Summary

Technical Problem

Current smart driving systems face challenges in accurately recognizing lane markings due to factors such as congested traffic, limited camera view, unclear lane markings, and road construction, which affect vehicle lateral localization and target driving route generation.

Method used

A method for determining traffic flow information by grouping target vehicles based on motion and status information, calculating fitting weights, and generating current traffic flow information through fitting, allowing for vehicle localization and lateral control independent of lane markings.

Benefits of technology

Enables accurate vehicle localization and lateral control in congested environments by utilizing traffic flow information, providing a reliable basis for long-distance route planning and maintaining vehicle control without relying on lane markings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007580155000001
    Figure 0007580155000001
  • Figure 0007580155000002
    Figure 0007580155000002
  • Figure 0007580155000003
    Figure 0007580155000003
Patent Text Reader

Abstract

A method, device, electronic device, and storage medium for determining traffic flow information include a step (401) of grouping target vehicles and obtaining group information based on the movement information of the host vehicle and state information of one or more target vehicles, a step (402) of determining a fitting weight for each target vehicle based on the state information of each target vehicle and the group information, and a step (403) of generating one or more pieces of current traffic flow information through fitting based on the movement information of the host vehicle, the state information of each target vehicle, the fitting weight for each target vehicle, and the group information. The method can realize traffic flow detection by grouping multiple target vehicles, determining a fitting weight for each target vehicle, and further generating current traffic flow information through fitting based on the group information, the fitting weight, the movement information of the host vehicle, and the state information of the target vehicles.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The embodiments of the present disclosure relate to the technical field of smart driving, and in particular to a method, device, electronic device, and storage medium for determining traffic flow information. [Background technology]

[0002] In the process of sensing the driving environment, current smart driving systems for structured roads usually perform vehicle lateral position determination and target driving path generation based on lane marking information collected by a camera in front of the vehicle. It can be seen that the accuracy of vehicle lateral position determination (i.e., lane position determination in which the vehicle is located), vehicle lateral control, and target driving path generation depends on the recognition accuracy of lane markings by the smart driving system or camera.

[0003] However, currently, there are many different factors that prevent accurate recognition of lane markings. For example, when road traffic is congested, the vehicle speed between the vehicle and the preceding vehicle is low, the vehicle distance is short, and there is a high traffic flow in both lanes, the sensing distance and field of view of the camera in front of the vehicle are limited, making it difficult to recognize the lane markings based on image data acquired by the camera. In addition, various factors such as road construction, lane changes, and excessive vehicle flow may make the lane markings unclear, and old lane markings may not be sufficiently cleaned, which may hinder accurate recognition of the lane markings.

[0004] It can be seen that other sensing means are required to reduce the impact of the inability to recognize lane markings or reduced recognition accuracy on the lateral position determination of the vehicle, the lateral control of the vehicle, and the generation of a target driving path. Therefore, it is necessary to provide a new sensing means capable of sensing traffic stream information. A traffic stream can be understood as a traffic flow formed by multiple vehicles moving in the same direction in the same lane, and traffic stream information can be understood as information on the trajectory of the traffic stream. Summary of the Invention [Problem to be solved by the invention]

[0005] The present disclosure provides a new sensing means for sensing traffic flow information. At least one embodiment of the present disclosure provides a method, an apparatus, an electronic device, and a non-transitory computer-readable storage medium for determining traffic flow information. [Means for solving the problem]

[0006] In a first aspect, a method for determining traffic flow information provided by an embodiment of the present disclosure includes: Grouping each of the target vehicles based on the motion information of the host vehicle and the state information of one or more target vehicles to obtain group information; determining a fitting weight for each of the target vehicles based on the state information and the group information of each of the target vehicles; and generating one or more pieces of current traffic flow information by fitting based on the motion information of the host vehicle, the state information of each of the target vehicles, the fitting weight of each of the target vehicles, and the group information.

[0007] In some embodiments, the step of grouping each of the target vehicles and obtaining group information based on the motion information of the host vehicle and the state information of one or more target vehicles includes: determining a travel trajectory of the host vehicle based on the motion information of the host vehicle; Screening one or more valid target vehicles based on the motion information of the host vehicle and the state information of each of the target vehicles; The method includes a step of grouping each of the valid target vehicles based on the travel trajectory of the host vehicle and state information of each of the valid target vehicles, and obtaining group information.

[0008] In some embodiments, after the step of obtaining group information, the method further comprises: correcting the group information based on historical traffic flow information; Correspondingly, the method includes a step of determining a fitting weight for each of the valid target vehicles based on the historical traffic flow information, the state information of each of the valid target vehicles, and the corrected group information.

[0009] In some embodiments, the step of grouping each of the valid target vehicles based on the travel trajectory of the host vehicle and state information of each of the valid target vehicles and obtaining group information includes: For each of said available target vehicles, determining a relative lane in which the valid target vehicle is located based on state information of the valid target vehicle and a travel trajectory of the host vehicle; and determining group information of the valid target vehicle based on the relative lane.

[0010] In some embodiments, the group information includes five groups: a first lane group on the left side of the lane in which the host vehicle is located, a second lane group on the left side of the lane in which the host vehicle is located, a first lane group on the right side of the lane in which the host vehicle is located, a second lane group on the right side of the lane in which the host vehicle is located, and another group.

[0011] In some embodiments, before the step of generating one or more current traffic flow information by fitting, the method further comprises: determining whether the number of target vehicles satisfies a preset fitting number, and if so, determining whether the vehicle is traveling in a straight line; When the driving state of the host vehicle is straight, acquiring a cached historical vehicle; updating the coordinates of each of the historical vehicles and obtaining a virtual vehicle corresponding to each of the historical vehicles and state information of each of the virtual vehicles; determining a fitting weight for each of the virtual vehicles based on historical traffic flow information, motion information of the host vehicle, state information of each of the virtual vehicles, and group information of each of the virtual vehicles; Correspondingly, the step of generating one or more current traffic flow information by fitting includes a step of generating one or more current traffic flow information by fitting based on status information of each of the target vehicles, fitting weights of each of the target vehicles, status information of each of the virtual vehicles, and fitting weights of each of the virtual vehicles.

[0012] In some embodiments, the historical vehicle satisfies a caching condition, where the caching condition is used to screen for vehicles traveling in the same direction as the ego vehicle and not belonging to any other group.

[0013] In some embodiments, the caching condition is: A vehicle is located in front of the host vehicle and a relative distance between the vehicle and the host vehicle is greater than a preset relative distance threshold value; The included angle between the vehicle direction relative to the speed of the host vehicle and the traveling direction of the host vehicle is smaller than a preset included angle threshold value; The lateral distance of the vehicle relative to the host vehicle is within a preset lateral distance range.

[0014] In some embodiments, the caching condition further includes the vehicle's life cycle being greater than a pre-defined life cycle threshold.

[0015] In some embodiments, the step of determining a fitting weight for each of the target vehicles comprises: For each of said target vehicles, determining a lateral speed deviation weight of the target vehicle, a lateral displacement deviation weight of the target vehicle, a life cycle weight of the target vehicle, and a speed weight of the target vehicle based on the state information of the target vehicle and the group information of the target vehicle; multiplying the lateral speed deviation weight of the target vehicle, the lateral displacement deviation weight of the target vehicle, the life cycle weight of the target vehicle and the speed weight of the target vehicle to obtain a fitting weight for the target vehicle.

[0016] In some embodiments, the step of determining a fitting weight for each of the virtual vehicles comprises: For each of the virtual vehicles, determining a lateral speed deviation weight of the virtual vehicle, a lateral displacement deviation weight of the virtual vehicle, a life cycle weight of the virtual vehicle, a speed weight of the virtual vehicle, and a weight of the virtual vehicle based on the state information of the virtual vehicle and the group information of the virtual vehicle; multiplying the lateral speed deviation weight of the virtual vehicle, the lateral displacement deviation weight of the virtual vehicle, the life cycle weight of the virtual vehicle, the speed weight of the virtual vehicle and the weight of the virtual vehicle to obtain a fitting weight of the virtual vehicle.

[0017] In some embodiments, each group corresponds to one traffic flow, and the step of generating one or more current traffic flow information by fitting includes: For one group, selecting a fitting method based on the number of target vehicles in the group and the longitudinal distribution distances of all target vehicles in the group; and generating current traffic flow information corresponding to the group through fitting based on the selected fitting method, using the motion information of the host vehicle, the state information of each target vehicle in the group, and the fitting weights of each target vehicle in the group.

[0018] In some embodiments, the step of selecting a fitting scheme based on the number of target vehicles in the group and the longitudinal distribution distances of all target vehicles in the group comprises: Determining whether the number of target vehicles in the group satisfies a first quantity condition and whether the longitudinal distribution distance is greater than a preset first distance threshold; If the first quantity condition is met and the longitudinal distribution distance is greater than the preset first distance threshold, select the primary fitting and the secondary fitting; otherwise, determine whether the quantity of the target vehicles in the group meets the second quantity condition and whether the longitudinal distribution distance is greater than the preset second distance threshold; If the second quantity condition is met and is greater than a second preset distance threshold, selecting primary fitting, otherwise not performing fitting.

[0019] In some embodiments, when the primary fitting and the secondary fitting are selected, the step of generating current traffic flow information corresponding to the group by fitting includes: generating a primary fitting result corresponding to the group by fitting, and determining a first mean square deviation of the primary fitting result; generating a secondary fitting result corresponding to the group by fitting and determining a second mean square deviation of the secondary fitting result; The method includes a step of comparing the first mean square deviation and the second mean square deviation, and if the first mean square deviation is greater than a predetermined multiple of the second mean square deviation, selecting the secondary fitting result as the current traffic flow information corresponding to the group, and if not, selecting the primary fitting result as the current traffic flow information corresponding to the group.

[0020] In some embodiments, the step of generating current traffic flow information corresponding to the group by fitting using the motion information of the host vehicle, the state information of each target vehicle in the group, and the fitting weight of each target vehicle in the group, includes: generating initial traffic flow information corresponding to the group through fitting based on state information of each target vehicle in the group and fitting weights of each target vehicle in the group; and constraining the initial traffic flow information based on historical traffic flow information and the vehicle's motion information to obtain current traffic flow information corresponding to the group.

[0021] In some embodiments, the constraints include a position constraint, an orientation constraint and / or a curvature constraint.

[0022] In some embodiments, the location constraint includes constraining a change amount of a constant term in fitting parameters corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information; The amount of change in the constant term is inversely correlated with the reliability corresponding to the historical traffic flow information, and the amount of change in the constant term is directly correlated with the number of fittings corresponding to the initial traffic flow information.

[0023] In some embodiments, the directional constraint includes constraining a change amount of a first-order term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle; Here, there is an inverse correlation between the change in the first-order term and the reliability corresponding to the historical traffic flow information, a positive correlation between the change in the first-order term and the steering width of the vehicle, and / or a positive correlation between the change in the first-order term and the fitting number corresponding to the initial traffic flow information.

[0024] In some embodiments, the curvature constraint includes constraining a change in a quadratic term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle; Here, there is an inverse correlation between the change in the quadratic term and the reliability corresponding to the historical traffic flow information, there is an inverse correlation between the change in the quadratic term and the speed of the host vehicle, and / or there is a direct correlation between the change in the quadratic term and the steering wheel rotation speed of the host vehicle.

[0025] In some embodiments, the method further comprises: determining a confidence increment based on the current traffic flow information; determining a reliability corresponding to the current traffic flow information based on the reliability of the historical traffic flow information and the reliability increment; Here, there is an inverse correlation between the reliability increment and the fitting result mean square deviation corresponding to the current traffic flow information, a positive correlation between the reliability increment and the fitting number corresponding to the current traffic flow information, and / or a positive correlation between the reliability increment and the longitudinal distribution distance of the target vehicle corresponding to the current traffic flow information.

[0026] In some embodiments, the step of determining a confidence increment based on the current traffic flow information comprises: The method includes a step of comparing the fitting numbers and longitudinal distribution distances corresponding to the two traffic flows when there is an intersection between the two current traffic flow information, and a step of determining that the reliability increment corresponding to the current traffic flow information having a smaller fitting number or a shorter longitudinal distribution distance is negative.

[0027] In some embodiments, the method further includes determining a vehicle driving reference route based on the current traffic flow information and a reliability corresponding to the current traffic flow information; The step of determining a vehicle travel reference route includes: When the reliability corresponding to the current traffic flow information on both sides of the vehicle is higher than a preset reliability threshold, the parameter of the vehicle's reference route is determined to be a weighted average value of the fitting parameters corresponding to the current traffic flow information on both sides of the vehicle, and the weight of the fitting parameters corresponding to the current traffic flow information on both sides of the vehicle is inversely correlated with the change rate of the fitting parameters; determining that, when the reliability corresponding to the current traffic flow information on only one side of the vehicle is higher than a preset reliability threshold, the linear and quadratic terms in the parameters of the reference route of the vehicle are the same as the linear and quadratic terms in the fitting parameters corresponding to the current traffic flow information on that side, and the constant term in the parameters of the reference route of the vehicle is zero; and determining that the parameters of the vehicle's reference route are all zero if the reliability levels corresponding to the current traffic flow information on both sides of the vehicle are lower than a preset reliability threshold.

[0028] In some embodiments, the method further includes determining an auxiliary location flag based on the current traffic flow information and a reliability measure corresponding to the current traffic flow information; The step of determining an auxiliary location flag comprises: determining an auxiliary position identification flag as a first flag when the reliability corresponding to the current traffic flow information on both sides of the vehicle is higher than a preset reliability threshold; determining an auxiliary position identification flag as a second flag when a reliability corresponding to the current traffic flow information on the left side of the vehicle is higher than a preset reliability threshold; and determining the auxiliary position identification flag as a third flag when the reliability corresponding to the current traffic flow information on the right side of the host vehicle is higher than a preset reliability threshold.

[0029] In a second aspect, a traffic flow information determination device provided by an embodiment of the present disclosure includes: A grouping module is used for grouping each of the target vehicles according to the motion information of the host vehicle and the state information of one or more target vehicles, and obtaining group information; a determination module used for determining a fitting weight for each of the target vehicles based on the state information and the group information of each of the target vehicles; and a fitting module used for generating one or more current traffic flow information through fitting based on the motion information of the host vehicle, the state information of each of the target vehicles, the fitting weight of each of the target vehicles, and the group information.

[0030] In a third aspect, an electronic device provided by an embodiment of the present disclosure includes a processor and a memory, and the processor is used to execute steps of the method for determining traffic flow information described in any of the embodiments of the first aspect by calling up a program or instruction stored in the memory.

[0031] In a fourth aspect, a non-transitory computer-readable storage medium provided by an embodiment of the present disclosure is used to store a program or instructions, which causes a computer to execute steps of a method for determining traffic flow information described in any of the embodiments of the first aspect. Effect of the Invention

[0032] As can be seen, in at least one embodiment of the present disclosure, sensing of traffic flow can be achieved by grouping multiple target vehicles, determining fitting weights for each target vehicle, and further generating current traffic flow information through fitting based on group information, fitting weights, motion information of the host vehicle, and state information of the target vehicles. [Brief description of the drawings]

[0033] In order to more clearly explain the technical solutions in the embodiments of the present disclosure, the following briefly introduces drawings that may be used in the description of the embodiments or prior art. Of course, the drawings described below are merely a part of the embodiments of the present disclosure, and those skilled in the art can obtain other drawings based on these drawings. [Figure 1] 4 is an exemplary scene graph for determining traffic flow information provided by an embodiment of the present disclosure. [Diagram 2] FIG. 1 is an exemplary architecture diagram of a smart driving vehicle provided by an embodiment of the present disclosure. [Diagram 3] FIG. 2 is an exemplary block diagram of an electronic device provided in accordance with an embodiment of the present disclosure. [Figure 4] 4 is an exemplary flowchart of a method for determining traffic flow information provided by an embodiment of the present disclosure. [Diagram 5] FIG. 2 is an exemplary block diagram of a traffic flow information determining device provided by an embodiment of the present disclosure; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0034] In order to make the above-mentioned objects, features and advantages of the present disclosure clearer, the present disclosure will be described in more detail below with reference to the drawings and embodiments. It is to be understood that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. It should be understood that the specific embodiments described herein are only used to interpret the present disclosure, and do not limit the present disclosure. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art belong to the protection scope of the present disclosure.

[0035] It should be noted that, in this specification, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that any such actual relationship or order exists between those entities or operations.

[0036] With the development of smart driving technology, long-distance route planning has become an essential capability for higher-level autonomous driving systems such as L3, and such planning capability requires accurate location of the lane the vehicle is in. Current low-cost satellite positioning systems cannot accurately locate the lane the vehicle is in, and the recognition of lane marking types by smart driving systems or cameras cannot currently guarantee accurate judgment of lanes. Furthermore, currently, lane markings cannot be accurately recognized due to multiple factors, such as those described in the Background Art, and the description thereof will be omitted here.

[0037] Therefore, the embodiment of the present disclosure provides a new sensing means for sensing traffic flow information, where the traffic flow can be understood as a vehicle flow formed by multiple vehicles in the same lane moving in the same direction, and the traffic flow information can be understood as information on the trajectory of the traffic flow. Since lane markings can also be regarded as lines and trajectories can also be regarded as lines, the traffic flow information can be used, instead of lane boundary lines, to identify the lateral position of the vehicle (i.e., identify the position of the lane in which the vehicle is located), control the vehicle in the lateral direction, and generate a target driving route.

[0038] The embodiments of the present disclosure provide a method, device, electronic device, or storage medium for determining traffic flow information, which group a plurality of target vehicles, determine a fitting weight for each target vehicle, and generate current traffic flow information by fitting based on group information, fitting weight, motion information of the host vehicle, and state information of the target vehicle, thereby realizing traffic flow sensing. The embodiments of the present disclosure can be applied to a smart driving vehicle and also to an electronic device. The smart driving vehicle is a vehicle equipped with different types of smart driving systems, and the smart driving system includes, for example, an unmanned driving system, an assisted driving system, a driving assistance system, a highly automated driving system, a fully automated driving vehicle, and the like. The electronic device is equipped with a smart driving system, and for example, the electronic device can be used to test a smart driving algorithm, and for example, the electronic device can be an in-vehicle device, and in some embodiments, the electronic device can be applied to other fields. In the following, in order to make the description clearer and without errors, the embodiments of the present disclosure will be described with a smart driving vehicle as an example.

[0039] FIG. 1 is an exemplary scene graph for determining traffic flow information provided by an embodiment of the present disclosure. In FIG. 1, a host vehicle 101 is moving straight, and the left and right boundaries of the host vehicle's trajectory are indicated by 104. On the left side of the host vehicle, for example, as indicated by 103 in FIG. 1, there are three vehicles, and on the right side, there are two vehicles. It is desirable to determine traffic flow information on the left side of the host vehicle, for example, trajectory 102 corresponding to the traffic flow on the left side in FIG. 1, and also determine traffic flow information on the right side of the host vehicle, by the method for determining traffic flow information provided by an embodiment of the present disclosure.

[0040] Fig. 2 is an exemplary architecture diagram of a smart driving vehicle provided by an embodiment of the present disclosure. The smart driving vehicle shown in Fig. 2 may be embodied as the vehicle 101 in Fig. 1. As shown in Fig. 2, the smart driving vehicle includes a sensor group, a smart driving system, a vehicle floor execution system, and other components used to drive the vehicle and control the operation of the vehicle, such as a brake pedal, a steering wheel, and an accelerator pedal.

[0041] The sensor group is used to collect data of the external environment of the vehicle and detect the position data of the vehicle, for example, the sensor group includes at least one of a camera, a lidar, a millimeter wave radar, an ultrasonic radar, a global positioning system (GPS), and an inertial measurement unit (IMU), but is not limited thereto.

[0042] In some embodiments, the sensor group is further used to collect vehicle dynamics data, for example, but not limited to, at least one of a wheel rotation speed sensor, a speed sensor, an acceleration sensor, a steering wheel rotation angle sensor, and a front wheel rotation angle sensor.

[0043] The smart driving system is used to obtain sensing data from a group of sensors, including but not limited to images, videos, laser point clouds, millimeter waves, GPS information, vehicle status, etc. In some embodiments, the smart driving system performs environment sensing and vehicle localization based on the sensing data, generates sensing information and vehicle attitude, performs planning and decision-making based on the sensing information and vehicle attitude, generates planning and decision-making information, generates vehicle control commands based on the planning and decision-making information, and delivers them to a vehicle floor execution system, where the control commands can include but are not limited to steering wheel steering, lateral control commands, longitudinal control commands, etc.

[0044] In some embodiments, the smart driving system acquires data such as sensor data, vehicle to X (V2X) data, high-precision maps, etc., and performs environment sensing and localization based on at least one of the above data, and generates environment sensing and localization information. Here, the sensing information may include at least one of obstacle information, road signs / marks, pedestrian / vehicle information, and drivable area, but is not limited thereto. The localization information includes vehicle attitude.

[0045] In some embodiments, the smart driving system generates planning and decision-making information based on the sensing information and vehicle attitude, and at least one of the following data: V2X data, high-precision maps, etc., where the planning information includes, but is not limited to, a planned route, etc., and the decision-making information includes, but is not limited to, at least one of the following actions (e.g., including, but not limited to, following, overtaking, stopping, detouring, etc.), vehicle heading, vehicle speed, desired vehicle acceleration, desired steering, etc.

[0046] In some embodiments, the method for determining traffic flow information provided by the embodiments of the present disclosure can be applied to the smart driving system.

[0047] In some embodiments, the smart driving system may be a software system, a hardware system, or a combination of software and hardware systems, for example, the smart driving system may be a software system that operates on an operating system, and the in-vehicle hardware system may be a hardware system that supports the operation of the operating system.

[0048] In some embodiments, the smart driving system can interact with a cloud server. In some embodiments, the smart driving system and the cloud server interact with each other through a wireless communication network (e.g., including but not limited to a wireless communication network such as a GPRS network, a Zigbee network, a Wifi network, a 3G network, a 4G network, a 5G network, etc.).

[0049] In some embodiments, a cloud server is used to interact with the vehicle. The cloud server can transmit environmental information, location information, control information, and other information required during vehicle smart driving to the vehicle. In some embodiments, the cloud server can receive sensing data from the vehicle, vehicle status information, vehicle driving information, and information regarding vehicle requests. In some embodiments, the cloud server can remotely control the vehicle based on user settings or vehicle requests. In some embodiments, the cloud server can be one server or one server group. The server group can be centralized or distributed. In some embodiments, the cloud server can be local or remote.

[0050] The vehicle floor execution system is used to receive the vehicle control command and control the running of the vehicle according to the vehicle control command. In some embodiments, the vehicle floor execution system includes, but is not limited to, a steering system, a braking system, and a driving system. In some embodiments, the vehicle floor execution system may further include a floor controller, which is used to analyze the vehicle control command and send it to corresponding systems, such as the steering system, the braking system, and the driving system, respectively.

[0051] In some embodiments, the smart driving vehicle may further include a vehicle CAN bus, not shown in Figure 2, which is connected to the vehicle floor executive system. Information interaction between the smart driving system and the vehicle floor executive system is transmitted through the vehicle CAN bus.

[0052] 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. In some embodiments, the electronic device may be an in-vehicle device. In some embodiments, the electronic device may support the implementation of a smart driving system.

[0053] As shown in Fig. 3, the electronic device includes at least one processor 301, at least one memory 302, and at least one communication interface 303. Each component in the in-vehicle device is coupled via a bus system 304. The communication interface 303 is used for transmitting information between external devices. As can be understood, the bus system 304 is used for realizing connection communication between these components. In addition to a data bus, the bus system 304 further includes a power bus, a control bus, and a status signal bus. However, in Fig. 3, various buses are represented as the bus system 304 for the sake of clarity.

[0054] As can be appreciated, the memory 302 in this embodiment can be volatile memory or non-volatile memory, or can include both volatile and non-volatile memory.

[0055] In some embodiments, memory 302 stores an operating system and application programs, executable units or data structures, or a subset or extension thereof.

[0056] Here, the operating system includes various system programs used to realize various basic tasks and process hardware-based tasks, such as a frame layer, a core library layer, a driving layer, etc. The application programs include various application programs used to realize various application tasks, such as a media player, a browser, etc. A program for realizing the method for determining traffic flow information provided by the embodiment of the present disclosure may be included in the application programs.

[0057] In an embodiment of the present disclosure, the processor 301 is used to execute steps of each embodiment of the method for determining traffic flow information provided by an embodiment of the present disclosure by calling up a program or instruction stored in the memory 302, specifically, a program or instruction stored in an application program.

[0058] The method for determining traffic flow information provided by the embodiment of the present disclosure can be applied to or implemented by the processor 301. The processor 301 can be an integrated circuit chip and has the ability to process signals. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware or an instruction in the form of software in the processor 301. The processor 301 can be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The general-purpose processor can be a microprocessor, any ordinary processor, and so on.

[0059] The steps of the method for determining traffic flow information provided by the embodiments of the present disclosure can be directly embodied to be executed by a hardware decode processor, or can be executed by a combination of hardware and software units in the processor. The software units can be located in a storage medium matured in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 302, and the processor 301 reads the information in the memory 302 and completes the steps of the method in combination with the hardware.

[0060] 4 is an exemplary flowchart of a method for determining traffic flow information provided by an embodiment of the present disclosure. The execution body of the method is an electronic device, and in some embodiments, the execution body of the method may be a smart driving system supported by the electronic device. For ease of explanation, the flow of the method for determining traffic flow information in the following embodiments is described with the smart driving system as the execution body.

[0061] As shown in FIG. 4, in step 401, the smart driving system groups target vehicles based on the motion information of the host vehicle and the state information of one or more target vehicles, and obtains group information.

[0062] In some embodiments, the motion information of the host vehicle is dynamics information related to the running of the host vehicle. For example, the motion information of the host vehicle may include, but is not limited to, wheel rotation speed, vehicle speed, acceleration, steering wheel rotation angle, front wheel rotation angle, and yaw angular velocity. In some embodiments, the motion information of the host vehicle may be collected by the sensor group shown in FIG. 1, and the smart driving system may obtain the motion information of the host vehicle from the sensor group.

[0063] In some embodiments, the smart driving system can acquire data, such as sensor data, V2X data, high-precision maps, etc., and perform environment sensing based on at least one of the above data to acquire status information of one or more target vehicles.

[0064] In some embodiments, the state information of the target vehicle is a collective term for information such as the relative position and relative motion between the target vehicle and the host vehicle. For example, the state information of the target vehicle may include, but is not limited to, at least one of the following: lateral displacement, longitudinal displacement, lateral speed, longitudinal speed, etc. of the target vehicle relative to the host vehicle, where lateral can be understood as the lateral direction, i.e. perpendicular to the lane marking direction. In some embodiments, the state information of the target vehicle may further include, but is not limited to, one or more of an identifier (ID), a sensing type, a life cycle, and a target reliability, etc. Here, the life cycle can be understood as the time from the time the target vehicle is first sensed to the current time, i.e., the time the target vehicle appears in the "field of view" of the host vehicle. The target reliability is used to indicate the reliability of the target vehicle and is automatically generated by the sensing algorithm of the smart driving system.

[0065] In some embodiments, when grouping each target vehicle, the grouping rule adopted by the smart driving system is to group the target vehicles into five groups according to the lanes in which they are located: a first lane group on the left side of the lane in which the host vehicle is located, a second lane group on the left side of the lane in which the host vehicle is located, a first lane group on the right side of the lane in which the host vehicle is located, a second lane group on the right side of the lane in which the host vehicle is located, and another group. Here, the other group is any case other than the above-mentioned four groups. For example, the other group may be one or more of the lane in which the host vehicle is located, the third lane on the left side of the lane in which the host vehicle is located, and the third lane on the right side of the lane in which the host vehicle is located.

[0066] In some embodiments, after grouping each target vehicle, the smart driving system can perform a group mark for each target vehicle, and the group mark is used to characterize the group to which the target vehicle belongs, for example, the group mark can be a group flag bit, and different values ​​of the group flag bit indicate different groups. In this embodiment, the group information includes at least a group mark. In some embodiments, the group information can further include, but is not limited to, one or more of the target vehicle's ID, sensing type, life cycle, and target reliability, etc.

[0067] In some embodiments, when performing grouping for each target vehicle, the smart driving system determines the driving trajectory of the host vehicle based on the motion information of the host vehicle, and further determines the relative lane in which each target vehicle is located (the relative lane is relative to the lane in which the host vehicle is located) based on the driving trajectory of the host vehicle and the state information of each target vehicle, thereby grouping each target vehicle based on the relative lane in which each target vehicle is located according to the grouping rule, and obtaining group information.

[0068] In some embodiments, when determining the driving trajectory of the host vehicle, the smart driving system calculates the turning radius of the host vehicle according to the vehicle speed, steering wheel rotation angle and yaw angular velocity signals of the host vehicle after filtering, and further determines the current driving trajectory of the host vehicle according to the turning radius. Note that, determining the driving trajectory according to the turning radius is a mature technology in the field of smart driving, and the specific determination process is omitted here.

[0069] In some embodiments, it is taken into consideration that the target vehicle may be an invalid vehicle, for example, the target vehicle is driving in the opposite direction to the host vehicle and should not participate in the subsequent traffic flow information fitting. Therefore, in order to avoid the invalid vehicle participating in the subsequent traffic flow information fitting, which reduces the fitting accuracy, in this embodiment, before performing grouping, the smart driving system first screens valid target vehicles and filters out invalid target vehicles, and then groups each valid target vehicle based on the driving trajectory of the host vehicle and the status information of each valid target vehicle, and obtains group information.

[0070] In some embodiments, when screening valid target vehicles, the smart driving system screens one or more valid target vehicles based on the motion information of the host vehicle and the state information of each target vehicle. For example, the smart driving system screens in a manner to eliminate invalid target vehicles, and the invalid target vehicles include target vehicles whose longitudinal speed is negative (the speed of the host vehicle is positive) or whose longitudinal distance is greater than a preset longitudinal distance threshold. That is, the longitudinal speed of the valid target vehicle is positive (or zero) and the longitudinal distance is less than or equal to the preset longitudinal distance threshold.

[0071] In some embodiments, when grouping target vehicles, it is taken into consideration that the host vehicle may perform non-linear motion such as lane change, steering, etc., which may cause grouping errors, for example, the target vehicle should keep moving straight in the first lane to the left of the host vehicle, and the target vehicle should be divided into the first lane to the left of the lane where the host vehicle is located, but when the host vehicle rapidly steers to the right, the target vehicle should be divided into the second group lane to the left of the lane where the host vehicle is located, which may cause grouping errors, so the group information needs to be corrected to avoid grouping errors caused by the host vehicle rapidly steering.

[0072] In some embodiments, when correcting the group information, the smart driving system corrects the group information based on the historical traffic flow information. The historical traffic flow information is generated by fitting in a previous determination cycle, where the determination cycle is a cycle of traffic flow information determination preset by the smart driving system. In actual use, the determination cycle is set according to the requirement for the refresh rate of the fitting result of the use scene, and can take a value between tens of milliseconds and several seconds, for example, the determination cycle is set to 5 seconds. Each group corresponds to one traffic flow, that is, one historical traffic flow information corresponds to one group. Wherein, the historical traffic flow information includes a value of a fitting parameter, and the fitting parameter includes a quadratic term, a linear term and a constant term. If the quadratic term exists, the historical traffic flow information corresponds to a curve, and if the quadratic term is zero and the linear term is not zero, the historical traffic flow information corresponds to a straight line. In some embodiments, the historical traffic flow information further includes a reliability, and the reliability is used to indicate the reliability of the traffic flow. If there is no historical traffic flow information, for example, when the vehicle leaves the garage and enters the low-speed lane, and the historical traffic flow information has not yet been stored in the smart driving system, the reliability of the historical traffic flow information is zero, and the group information is not corrected.

[0073] In some embodiments, when correcting group information based on historical traffic flow information, the smart driving system determines whether a target vehicle exists within a preset range around the historical traffic flow information, and if so, corrects the group of the target vehicle to a group corresponding to the historical traffic flow information. Here, the preset range can be set according to actual needs, and the specific value of the preset range is not limited in this embodiment. For example, a group of a target vehicle is the second lane group on the left side, and the target vehicle is located within a predetermined range around the historical traffic flow information, and the historical traffic flow information corresponds to the first lane group on the left side, so the group of the target vehicle is corrected from the second lane group on the left side to the first lane group on the left side.

[0074] In some embodiments, after correcting the group information based on the historical traffic flow information, the smart driving system caches the vehicles that meet the cache conditions in each group after correction, and for the next determination cycle, the cached vehicles are historical vehicles. In some embodiments, the cache time can be set, and the cache time can be set based on actual needs, and the embodiment does not limit the specific value of the cache time.

[0075] Here, the cache condition is used to screen the vehicles that travel in the same direction as the vehicle and do not belong to other groups. For each determination cycle, the smart driving system caches the vehicles that meet the cache condition in each group after being corrected in the determination cycle, that is, the cache timing is within the determination cycle.

[0076] In step 402, the smart driving system determines a fitting weight for each target vehicle based on the state information and group information of each target vehicle.

[0077] In some embodiments, when determining the fitting weight of each target vehicle, for each target vehicle, the smart driving system determines a lateral speed deviation weight of the target vehicle, a lateral displacement deviation weight of the target vehicle, a life cycle weight of the target vehicle and a speed weight of the target vehicle based on the state information of the target vehicle and the group information of the target vehicle, and further multiplies the lateral speed deviation weight of the target vehicle, the lateral displacement deviation weight of the target vehicle, the life cycle weight of the target vehicle and the speed weight of the target vehicle to obtain the fitting weight of the target vehicle.

[0078] Here, the method of calculating the lateral speed deviation weight of the target vehicle is to calculate the average lateral speed of all target vehicles in the group to which the target vehicle belongs, and calculate the lateral speed deviation weight of the target vehicle based on the lateral speed of the target vehicle and the average lateral speed. In this embodiment, the larger the deviation between the lateral speed of the target vehicle and the average lateral speed, the lower the lateral speed deviation weight.

[0079] The calculation method of the lateral displacement deviation weight of the target vehicle is to calculate the average lateral displacement of all target vehicles in the group to which the target vehicle belongs, and calculate the lateral displacement deviation weight of the target vehicle based on the lateral displacement of the target vehicle and the average lateral displacement. In this embodiment, the greater the deviation between the lateral displacement of the target vehicle and the average lateral displacement, the lower the lateral displacement deviation weight.

[0080] The calculation method of the life cycle weight of the target vehicle is to calculate the life cycle weight of the target vehicle according to the life cycle and / or the target reliability of the target vehicle. In this embodiment, the longer the life cycle of the target vehicle, the higher the life cycle weight. The higher the target reliability of the target vehicle, the higher the life cycle weight.

[0081] The speed weight of the target vehicle is calculated as follows: if there is no historical traffic flow information corresponding to the group of the target vehicle, the speed weight of the target vehicle is set to 1.

[0082] In some embodiments, the lateral displacement deviation weight of the target vehicle can be determined according to the historical traffic flow information. Specifically, the lateral displacement deviation weight of the target vehicle is calculated according to the lateral displacement of the target vehicle and the historical traffic flow information corresponding to the group of the target vehicle. In this embodiment, the further the deviation between the lateral displacement of the target vehicle and the historical traffic flow is, the lower the lateral displacement deviation weight is.

[0083] In some embodiments, the speed weight of the target vehicle can be determined according to the historical traffic flow information. Specifically, the running speed of the target vehicle is synthesized according to the lateral speed and longitudinal speed of the target vehicle, and the running direction of the target vehicle is determined, and the speed weight of the target vehicle is calculated according to the running direction of the target vehicle and the historical traffic flow information corresponding to the group of the target vehicles. In this embodiment, the larger the angle between the running direction of the target vehicle and the tangent direction of the historical traffic flow, the lower the speed weight of the target vehicle.

[0084] In some embodiments, after grouping each valid target vehicle to obtain group information, and correcting the group information using historical traffic flow information, the smart driving system determines a fitting weight for each valid target vehicle based on the historical traffic flow information, the status information of each valid target vehicle, and the corrected group information.

[0085] In step 403, the smart driving system generates one or more pieces of current traffic flow information through fitting based on the motion information of the host vehicle, the state information of each target vehicle, and the fitting weight and group information of each target vehicle.

[0086] In some embodiments, each group corresponds to a traffic flow, and for each group, the smart driving system generates current traffic flow information corresponding to the group through fitting, specifically, selects a fitting method according to the number of target vehicles in the group and the longitudinal distribution distance of all target vehicles in the group, and further generates current traffic flow information corresponding to the group through fitting according to the selected fitting method using the motion information of the host vehicle, the state information of each target vehicle in the group and the fitting weight of each target vehicle in the group. The traffic flow obtained by fitting the first group lane on the left side is called the host vehicle's left traffic flow, and the traffic flow obtained by fitting the first group lane on the right side is called the host vehicle's right traffic flow.

[0087] In some embodiments, when selecting a fitting method, the smart driving system judges whether the number of target vehicles in the group meets a first quantity condition and whether the longitudinal distribution distance is greater than a preset first distance threshold, where the first quantity condition is, for example, 3, and the first distance threshold is, for example, 50 meters, to avoid over-fitting (for example, the traffic flow is actually straight, but a curved method is adopted for fitting), and the specific values ​​of the first quantity condition and the first distance threshold can be set according to actual needs.

[0088] If the first quantity condition is met and is greater than the preset first distance threshold, select primary fitting and secondary fitting; if not, judge whether the quantity of target vehicles in the group meets the second quantity condition and whether the longitudinal distribution distance is greater than the preset second distance threshold, where the second quantity condition is, for example, greater than or equal to 2 and less than 4, and the second distance threshold is, for example, 30 meters, and the specific values ​​of the first quantity condition and the first distance threshold can be set according to actual needs.

[0089] If the second quantity condition is met and is greater than the preset second distance threshold, select primary fitting; otherwise, do not perform fitting and keep the data of the previous traffic flow information determination cycle.

[0090] In some embodiments, when primary fitting and secondary fitting are selected, when the smart driving system generates current traffic flow information corresponding to the group through fitting, it generates a primary fitting result corresponding to the group through fitting, determines a first mean square deviation of the primary fitting result, generates a secondary fitting result corresponding to the group through fitting, determines a second mean square deviation of the secondary fitting result, and further compares the first mean square deviation and the second mean square deviation. If the first mean square deviation is greater than a preset multiple (e.g., 1.5 times, and the multiple can be preset according to actual circumstances) of the second mean square deviation, it selects the secondary fitting result as the current traffic flow information corresponding to the group; otherwise, it selects the primary fitting result as the current traffic flow information corresponding to the group.

[0091] In some embodiments, when using the motion information of the own vehicle, the status information of each target vehicle in the group, and the fitting weights of each target vehicle in the group to generate current traffic flow information corresponding to the group by fitting, the smart driving system generates initial traffic flow information corresponding to the group by fitting based on the status information of each target vehicle in the group and the fitting weights of each target vehicle in the group, and further constrains the initial traffic flow information based on the historical traffic flow information and the motion information of the own vehicle to obtain current traffic flow information corresponding to the group.

[0092] In some embodiments, constraining the initial traffic movement information includes a position constraint, an orientation constraint, and / or a curvature constraint.

[0093] In some embodiments, the location constraint includes constraining a change amount of a constant term in the fitting parameters corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information, where the change amount of the constant term is inversely correlated with the reliability corresponding to the historical traffic flow information, and the change amount of the constant term is positively correlated with the number of fittings corresponding to the initial traffic flow information, where the number of fittings can be understood as the number of target vehicles participating in the fitting.

[0094] In some embodiments, the directional constraint includes constraining a change in a first-order term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle, where the change in the first-order term is inversely correlated with the reliability corresponding to the historical traffic flow information, the change in the first-order term is positively correlated with the steering width of the host vehicle, and / or the change in the first-order term is positively correlated with the number of fittings corresponding to the initial traffic flow information.

[0095] In some embodiments, the curvature constraint includes constraining a change in a quadratic term in the fitting parameters corresponding to the initial traffic flow information based on a confidence level corresponding to the historical traffic flow information and / or motion information of the host vehicle, where the change in the quadratic term is inversely correlated with the confidence level corresponding to the historical traffic flow information, the change in the quadratic term is inversely correlated with the speed of the host vehicle, and / or the change in the quadratic term is directly correlated with the steering wheel rotation speed of the host vehicle.

[0096] In some embodiments, each group corresponds to a traffic flow, and before generating current traffic flow information corresponding to a group through fitting, for example, after grouping each target vehicle to obtain group information, the smart driving system ensures that the number of target vehicles in the group meets a preset fitting number, otherwise fitting cannot be performed. Therefore, the smart driving system determines whether the number of target vehicles meets the preset fitting number, and if so, determines whether the driving state of the host vehicle is straight, and if so, obtains a cached history vehicle, and the obtained history vehicle may be one or more, and the obtained history vehicle belongs to the group.

[0097] In some embodiments, the historical vehicles satisfy a caching condition, which is used to screen for vehicles traveling in the same direction as the ego vehicle and not belonging to any other group.

[0098] In some embodiments, the caching conditions include the following: (1) A vehicle is located in front of the vehicle and the relative distance between the vehicle and the vehicle is greater than a preset relative distance threshold, where the preset relative distance threshold is, for example, 20 meters. This embodiment does not limit the specific value of the relative distance threshold, and those skilled in the art can set it according to actual needs. It can be understood that when judging whether a vehicle meets the cache condition, it is based on the relative relationship between the vehicle and the vehicle at the judgment time, including the relative distance, the driving direction, the lateral distance, etc. (2) The included angle between the vehicle direction relative to the speed of the vehicle and the running direction of the vehicle is smaller than a preset included angle threshold. Here, the direction of the speed of the vehicle relative to the vehicle can be understood as the running direction of the vehicle. The running direction of the vehicle can be determined by synthesizing the speed of the vehicle (i.e., the running speed) based on the lateral speed and longitudinal speed of the vehicle at the judgment time, and further determining the running direction of the vehicle; (3) The lateral distance of the vehicle relative to the vehicle itself is within a preset lateral distance range, where the preset lateral distance range is, for example, 2 meters to 3 meters, and the present embodiment does not limit the specific value of the lateral distance range, and those skilled in the art may set it according to actual needs.

[0099] In some embodiments, the cache condition further includes the following (4): (4) The life cycle of the vehicle is greater than a preset life cycle threshold, where the preset life cycle threshold is, for example, 3 seconds, and the embodiment does not limit the specific value of the life cycle threshold, which can be set by those skilled in the art according to actual needs.

[0100] In some embodiments, after obtaining the cached historical vehicles, the smart driving system updates the coordinates of each historical vehicle, obtains the virtual vehicles corresponding to each historical vehicle and the state information of each virtual vehicle. The method of updating the coordinates is, for example, to calculate the time difference between the cache time of the historical vehicle and the current time, and update the coordinates using the state information of the historical vehicle and the calculated time difference, specifically, to use the lateral speed and longitudinal speed in the state information of the historical vehicle to synthesize the running speed of the historical vehicle, and update the coordinates according to the running speed and the calculated time difference. Here, the state information of the historical vehicle is the state information corresponding to the cache time of the historical vehicle.

[0101] In some embodiments, the state information of the virtual vehicle includes at least one of, but is not limited to, a lateral displacement, a longitudinal displacement, a lateral velocity, and a longitudinal velocity of the virtual vehicle relative to the ego-vehicle, where the lateral displacement and longitudinal displacement are determined based on the coordinate updates described above, and the lateral velocity and longitudinal velocity are the same as the lateral velocity and longitudinal velocity of the corresponding historical vehicle. In some embodiments, the state information of the virtual vehicle further includes, but is not limited to, one or more of an identifier (ID), a sensing type, a life cycle, a target reliability, and the like, which are the same as the corresponding historical vehicle, e.g., the sensing type of the virtual vehicle is the sensing type of the corresponding historical vehicle. The group information of the virtual vehicle is the same as the group information of the corresponding historical vehicle.

[0102] In some embodiments, if the driving state of the host vehicle is not straight, the historical vehicle is not screened, and therefore the relative relationship between the historical vehicle and the host vehicle cannot be determined, and the coordinates of the historical vehicle cannot be updated to obtain a virtual vehicle. Even if the coordinates of the historical vehicle are updated to obtain a virtual vehicle, the relative relationship between the historical vehicle and the host vehicle is not determined, so the relative relationship between the virtual vehicle and the host vehicle cannot be determined, and therefore the state information of the virtual vehicle cannot be determined.

[0103] In some embodiments, after determining the virtual vehicles and the state information of the virtual vehicles, the smart driving system can determine a fitting weight for each virtual vehicle based on the historical traffic flow information, the movement information of the host vehicle, the state information of each virtual vehicle, and the group information of each virtual vehicle.

[0104] In some embodiments, when determining the fitting weight of each virtual vehicle, for each virtual vehicle, the smart driving system determines a lateral speed deviation weight of the virtual vehicle, a lateral displacement deviation weight of the virtual vehicle, a life cycle weight of the virtual vehicle, a speed weight of the virtual vehicle and a weight of the virtual vehicle based on the state information of the virtual vehicle and the group information of the virtual vehicle, and further multiplies the lateral speed deviation weight of the virtual vehicle, the lateral displacement deviation weight of the virtual vehicle, the life cycle weight of the virtual vehicle, the speed weight of the virtual vehicle and the weight of the virtual vehicle to obtain the fitting weight of the virtual vehicle.

[0105] Here, the calculation methods of the lateral speed deviation weight of the virtual vehicle, the lateral displacement deviation weight of the virtual vehicle, the life cycle weight of the virtual vehicle, and the speed weight of the virtual vehicle are the same as the calculation methods of the lateral speed deviation weight of the target vehicle, the lateral displacement deviation weight of the target vehicle, the life cycle weight of the target vehicle, and the speed weight of the target vehicle described above, so detailed explanations will be omitted here. Also, the weight of the virtual vehicle is calculated based on the cache time of the virtual vehicle. The longer the cache time of the virtual vehicle, the lower the weight of the virtual vehicle.

[0106] In some embodiments, after determining the virtual vehicles and the state information of the virtual vehicles, the smart driving system generates one or more current traffic flow information by fitting according to the state information of each target vehicle, the fitting weight of each target vehicle, the state information of each virtual vehicle and the fitting weight of each virtual vehicle. The fitting generation process is similar to the fitting process based only on the target vehicles described above, and detailed description is omitted here.

[0107] In some embodiments, after generating the current traffic flow information by fitting, the smart driving system can determine a reliability increment according to the current traffic flow information, and further determine a reliability corresponding to the current traffic flow information according to the reliability and reliability increment of the historical traffic flow information. For example, obtain a reliability corresponding to the current traffic flow information according to the sum of the reliability and reliability increment of the historical traffic flow information. Note that, when the current traffic flow information and the historical traffic flow information are not both corresponding to the same group, the method of the present embodiment cannot be used to determine the reliability corresponding to the current traffic flow information.

[0108] In some embodiments, there is an inverse correlation between the confidence increment and the fitting result mean square deviation corresponding to the current traffic flow information, a positive correlation between the confidence increment and the fitting number corresponding to the current traffic flow information, and / or a positive correlation between the confidence increment and the longitudinal distribution distance of the target vehicle (if a virtual vehicle exists, the virtual vehicle should also be taken into account) corresponding to the current traffic flow information.

[0109] In some embodiments, when determining the reliability increment, the smart driving system determines whether there are two intersecting current traffic flow information, and if so, compares the fitting numbers and longitudinal distribution distances corresponding to the two traffic flows, and determines that the reliability increment corresponding to the current traffic flow information with a smaller number of fittings or a shorter longitudinal distribution distance is negative. For example, the smart driving system determines whether there is an intersection between the traffic flow on the left side of the host vehicle and the traffic flow on the right side of the host vehicle, and if so, compares the fitting numbers and longitudinal distribution distances corresponding to the two traffic flows, and determines that the reliability increment corresponding to the current traffic flow information with a smaller number of fittings or a shorter longitudinal distribution distance is negative.

[0110] In some embodiments, if the current traffic flow information determination cycle is not fitted, the confidence increment is determined to be negative, and this negative value is accumulated to the confidence of the corresponding historical traffic flow information.

[0111] In some embodiments, the smart driving system can determine a reference route for the vehicle based on the current traffic flow information and the reliability corresponding to the current traffic flow information. The step of determining the reference route for the vehicle includes: When the reliability corresponding to the current traffic flow information on both sides of the vehicle is higher than a preset reliability threshold, the parameter of the vehicle's reference route is determined to be a weighted average value of the fitting parameters corresponding to the current traffic flow information on both sides of the vehicle, and the weight of the fitting parameters corresponding to the current traffic flow information on both sides of the vehicle is inversely correlated with the change rate of the fitting parameters; determining that, when the reliability corresponding to the current traffic flow information on only one side of the vehicle is higher than a preset reliability threshold, the linear and quadratic terms in the parameters of the reference route of the vehicle are the same as the linear and quadratic terms in the fitting parameters corresponding to the current traffic flow information on that side, and the constant term in the parameters of the reference route of the vehicle is zero; and determining that the parameters of the vehicle's reference route are all zero if the reliability levels corresponding to the current traffic flow information on both sides of the vehicle are lower than a preset reliability threshold.

[0112] In some embodiments, the smart driving system can determine an auxiliary location determination flag based on the current traffic flow information and the reliability corresponding to the current traffic flow information, where the auxiliary location determination flag is used to assist in determining the lane in which the host vehicle is located. The auxiliary location determination flag is independent of the lane marking information, and can assist in determining the lane in which the host vehicle is located in some multi-lane scenes when the lane markings are insufficient to determine the only lane, thereby providing a necessary basis for long-distance route planning for the level L3 autonomous driving system.

[0113] In some embodiments, the step of determining the auxiliary location flag includes: When the reliability corresponding to the current traffic flow information on both sides of the vehicle is higher than a preset reliability threshold, the auxiliary location identification flag is determined as a first flag. The first flag indicates that there are lanes on both sides of the vehicle. The auxiliary location identification flag may be a flag bit, and the value of the flag bit corresponding to the first flag is, for example, 1. When the smart driving system determines that the auxiliary location identification flag is 1, it determines that there are lanes on both sides of the vehicle. If the reliability corresponding to the current traffic flow information on the left side of the vehicle is higher than a preset reliability threshold, the auxiliary position identification flag is determined as a second flag. The second flag indicates that a lane exists on the left side of the vehicle. The flag bit value corresponding to the second flag is, for example, 2. If the reliability corresponding to the current traffic flow information on the right side of the vehicle is higher than a preset reliability threshold, the auxiliary position identification flag is determined as a third flag. The third flag indicates that a lane exists on the right side of the vehicle. The flag bit value corresponding to the third flag is, for example, 3.

[0114] In some embodiments, the smart driving system can perform lateral control of the host vehicle based on current traffic flow information, which is advantageous in deviating from the reliance on lane marking information and maintaining lateral control of the host vehicle in a congested environment. Performing lateral control based on a route is a mature technical solution in the art, and thus will not be described in detail here.

[0115] Although the above-described method embodiments are described as a series of operations for ease of explanation, those skilled in the art will appreciate that the disclosed embodiments are not limited to the described order of operations, and that some steps may be performed in other orders or simultaneously, according to the disclosed embodiments. Additionally, those skilled in the art will appreciate that any of the embodiments described herein are alternative embodiments.

[0116] An embodiment of the present disclosure further provides a non-transitory computer-readable storage medium, in which a program or instruction is stored, the program or instruction causing a computer to execute steps of each embodiment of the method for determining traffic flow information, which will not be described here in order to avoid duplication of description.

[0117] 5 is an exemplary block diagram of a traffic flow information determining device provided by an embodiment of the present disclosure. As shown in FIG. 5, the traffic flow information determining device includes, but is not limited to, a grouping module 501, a determining module 502 and a fitting module 503.

[0118] In FIG. 5, the grouping module 501 is used for grouping each of the target vehicles based on the motion information of the host vehicle and the state information of one or more target vehicles, and obtaining group information.

[0119] The determination module 502 is used for determining a fitting weight for each of the target vehicles based on the state information of each of the target vehicles and the group information.

[0120] The fitting module 503 is used for generating one or more current traffic flow information through fitting according to the motion information of the self vehicle, the state information of each of the target vehicles, the fitting weight of each of the target vehicles and the group information.

[0121] In some embodiments, the grouping module 501 is used to determine a driving trajectory of the host vehicle based on the motion information of the host vehicle, screen one or more valid target vehicles based on the motion information of the host vehicle and the status information of each of the target vehicles, and group each of the valid target vehicles based on the driving trajectory of the host vehicle and the status information of each of the valid target vehicles to obtain group information.

[0122] In some embodiments, the grouping module 501 is further used for correcting the group information based on historical traffic flow information after obtaining the group information, and correspondingly, the determination module 502 is used for determining a fitting weight for each of the valid target vehicles based on the historical traffic flow information, the state information of each of the valid target vehicles, and the corrected group information.

[0123] In some embodiments, the grouping module 501 is used to determine, for each valid target vehicle, a relative lane in which the valid target vehicle is located based on the state information of the valid target vehicle and the driving trajectory of the host vehicle, and determine group information of the valid target vehicle based on the relative lane.

[0124] In some embodiments, the group information includes five groups: a first lane group on the left side of the lane in which the host vehicle is located, a second lane group on the left side of the lane in which the host vehicle is located, a first lane group on the right side of the lane in which the host vehicle is located, a second lane group on the right side of the lane in which the host vehicle is located, and another group.

[0125] In some embodiments, the fitting module 503 is further used for determining whether the target vehicle number meets a preset fitting number before generating one or more current traffic flow information by fitting, and if so, determining whether the driving state of the host vehicle is straight-line; if the driving state of the host vehicle is straight-line, obtaining cached historical vehicles, updating the coordinates of each of the historical vehicles, obtaining virtual vehicles corresponding to each of the historical vehicles and state information of each of the virtual vehicles; and determining a fitting weight of each of the virtual vehicles according to the historical traffic flow information, the motion information of the host vehicle, the state information of each of the virtual vehicles and the group information of each of the virtual vehicles; Correspondingly, the fitting module 503 is used to generate one or more current traffic flow information by fitting based on the state information of each of the target vehicles, the fitting weights of each of the target vehicles, the state information of each of the virtual vehicles, and the fitting weights of each of the virtual vehicles.

[0126] In some embodiments, the historical vehicle satisfies a caching condition, where the caching condition is used to screen for vehicles traveling in the same direction as the ego vehicle and not belonging to any other group.

[0127] In some embodiments, the cache conditions include: a vehicle is located in front of the host vehicle and the relative distance to the host vehicle is greater than a predetermined relative distance threshold; an included angle between the vehicle's direction relative to the host vehicle's speed and the host vehicle's driving direction is smaller than a predetermined included angle threshold; and a lateral distance of the vehicle relative to the host vehicle is within a predetermined lateral distance range.

[0128] In some embodiments, the caching condition further includes the vehicle's life cycle being greater than a pre-defined life cycle threshold.

[0129] In some embodiments, for each of the target vehicles, the determination module 502 determines a lateral speed deviation weight of the target vehicle, a lateral displacement deviation weight of the target vehicle, a life cycle weight of the target vehicle, and a speed weight of the target vehicle based on the state information of the target vehicle and the group information of the target vehicle, and multiplies the lateral speed deviation weight of the target vehicle, the lateral displacement deviation weight of the target vehicle, the life cycle weight of the target vehicle, and the speed weight of the target vehicle to obtain a fitting weight for the target vehicle.

[0130] In some embodiments, for each of the virtual vehicles, based on the state information of the virtual vehicle and the group information of the virtual vehicle, the determination module 502 determines a lateral speed deviation weight of the virtual vehicle, a lateral displacement deviation weight of the virtual vehicle, a life cycle weight of the virtual vehicle, a speed weight of the virtual vehicle and a weight of the virtual vehicle, and multiplies the lateral speed deviation weight of the virtual vehicle, the lateral displacement deviation weight of the virtual vehicle, the life cycle weight of the virtual vehicle, the speed weight of the virtual vehicle and the weight of the virtual vehicle to obtain a fitting weight of the virtual vehicle.

[0131] In some embodiments, each group corresponds to a traffic flow, and the fitting module 503 selects a fitting method for a group based on the number of target vehicles in the group and the longitudinal distribution distances of all target vehicles in the group, and generates current traffic flow information corresponding to the group through fitting based on the selected fitting method, using the motion information of the ego-vehicle, the state information of each target vehicle in the group, and the fitting weight of each target vehicle in the group.

[0132] In some embodiments, the step of the fitting module 503 selecting a fitting method based on the number of target vehicles in the group and the longitudinal distribution distance of all target vehicles in the group includes the steps of: determining whether the number of target vehicles in the group meets a first quantity condition and whether the longitudinal distribution distance is greater than a predetermined first distance threshold; if the first quantity condition is met and the longitudinal distribution distance is greater than the predetermined first distance threshold, selecting primary fitting and secondary fitting; if not, determining whether the quantity of target vehicles in the group meets a second quantity condition and whether the longitudinal distribution distance is greater than a predetermined second distance threshold; if the second quantity condition is met and the longitudinal distribution distance is greater than the predetermined second distance threshold, selecting primary fitting; if not, not performing fitting.

[0133] In some embodiments, when primary fitting and secondary fitting are selected, the step of the fitting module 503 generating current traffic flow information corresponding to the group by fitting includes the steps of generating a primary fitting result corresponding to the group by fitting and determining a first mean square deviation of the primary fitting result, generating a secondary fitting result corresponding to the group by fitting and determining a second mean square deviation of the secondary fitting result, and comparing the first mean square deviation and the second mean square deviation, and if the first mean square deviation is greater than a predetermined multiple of the second mean square deviation, selecting the secondary fitting result as the current traffic flow information corresponding to the group, and otherwise selecting the primary fitting result as the current traffic flow information corresponding to the group.

[0134] In some embodiments, the step of the fitting module 503 using the motion information of the host vehicle, the status information of each target vehicle in the group, and the fitting weights of each target vehicle in the group to generate current traffic flow information corresponding to the group by fitting includes the steps of generating initial traffic flow information corresponding to the group by fitting based on the status information of each target vehicle in the group and the fitting weights of each target vehicle in the group, and constraining the initial traffic flow information based on historical traffic flow information and the motion information of the host vehicle to obtain current traffic flow information corresponding to the group.

[0135] In some embodiments, the constraints include a position constraint, an orientation constraint and / or a curvature constraint.

[0136] In some embodiments, the position constraint includes constraining a change amount of a constant term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information, wherein the change amount of the constant term is inversely correlated with the reliability corresponding to the historical traffic flow information, and the change amount of the constant term is positively correlated with the number of fittings corresponding to the initial traffic flow information.

[0137] In some embodiments, the directional constraint includes constraining a change in a first-order term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle, wherein the change in the first-order term is inversely correlated with the reliability corresponding to the historical traffic flow information, the change in the first-order term is positively correlated with the steering width of the host vehicle, and / or the change in the first-order term is positively correlated with the number of fittings corresponding to the initial traffic flow information.

[0138] In some embodiments, the curvature constraint includes constraining a change in a quadratic term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle, wherein the change in the quadratic term is inversely correlated with a reliability corresponding to the historical traffic flow information, the change in the quadratic term is inversely correlated with a speed of the host vehicle, and / or the change in the quadratic term is directly correlated with a steering wheel rotation speed of the host vehicle.

[0139] In some embodiments, the traffic flow information determination device further includes a reliability determination unit not shown in FIG. 5, which is used for determining a reliability increment based on the current traffic flow information, and determining a reliability corresponding to the current traffic flow information based on the reliability of the historical traffic flow information and the reliability increment, wherein the reliability increment is inversely correlated with the fitting result mean square deviation corresponding to the current traffic flow information, the reliability increment is positively correlated with the fitting number corresponding to the current traffic flow information, and / or the reliability increment is positively correlated with the longitudinal distribution distance of the target vehicle corresponding to the current traffic flow information.

[0140] The step of the reliability determination unit determining a reliability increment based on the current traffic flow information includes the steps of: comparing the fitting numbers and longitudinal distribution distances corresponding to the two traffic flows when there is an intersection between the two current traffic flow information; and determining that the reliability increment corresponding to the current traffic flow information having a smaller fitting number or a shorter longitudinal distribution distance is negative.

[0141] In some embodiments, the traffic flow information determining device further includes a reference route determining unit not shown in FIG. 5, the reference route determining unit is used to determine a host vehicle driving reference route based on the current traffic flow information and a reliability corresponding to the current traffic flow information, and the step of determining the host vehicle driving reference route is a step of determining that a parameter of the host vehicle driving reference route is a weighted average value of fitting parameters corresponding to the current traffic flow information on both sides of the host vehicle when the reliability corresponding to the current traffic flow information on both sides of the host vehicle is higher than a preset reliability threshold value, and the fitting parameters corresponding to the current traffic flow information on both sides of the host vehicle are a weighted average value of fitting parameters corresponding to the current traffic flow information on both sides of the host vehicle. the step of determining that, when the reliability corresponding to the current traffic flow information on only one side of the host vehicle is higher than a preset reliability threshold, the first-order and second-order terms in the parameters of the reference route of the host vehicle are the same as the first-order and second-order terms in the fitting parameters corresponding to the current traffic flow information on that side, and the constant term in the parameters of the reference route of the host vehicle is zero; and the step of determining that, when the reliability corresponding to the current traffic flow information on both sides of the host vehicle are lower than the preset reliability threshold, the parameters of the reference route of the host vehicle are all zero.

[0142] In some embodiments, the traffic flow information determination device further includes an auxiliary position determination flag determination unit not shown in FIG. 5, which is used to determine an auxiliary position determination flag based on the current traffic flow information and a reliability corresponding to the current traffic flow information, and the step of determining an auxiliary position determination flag includes: a step of determining the auxiliary position determination flag as a first flag when the reliability corresponding to the current traffic flow information on both sides of the host vehicle is higher than a predetermined reliability threshold; a step of determining the auxiliary position determination flag as a second flag when the reliability corresponding to the current traffic flow information on the left side of the host vehicle is higher than the predetermined reliability threshold; and a step of determining the auxiliary position determination flag as a third flag when the reliability corresponding to the current traffic flow information on the right side of the host vehicle is higher than the predetermined reliability threshold.

[0143] In some embodiments, the division of each unit in the device for determining traffic flow information is merely a logical functional division, and other division manners may be used in actual implementation, for example, at least two units among the grouping module 501, the determination module 502, and the fitting module 503 may be implemented as one unit, and the grouping module 501, the determination module 502, or the fitting module 503 may be divided into multiple sub-units. As can be understood, each unit or sub-unit may be realized by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application.

[0144] It should be noted that, as used herein, the terms "comprise", "including" or any other variation thereof are intended to cover a non-exclusive inclusion, whereby a process, method, article or device that comprises a set of factors not only includes those factors, but also includes other factors not expressly listed or that are inherent to such process, method, article or device. Absent more limitations, a factor defined by the phrase "comprises..." does not exclude the presence of other identical factors in the process, method, article or device that includes that factor.

[0145] As will be understood by those skilled in the art, some embodiments described herein include some features that are included in other embodiments but not other features, but it is meant that combinations of features of different embodiments are within the scope of the present disclosure and form different embodiments.

[0146] As can be understood by those skilled in the art, the description of each embodiment has its own emphasis, and for parts that are not described in detail in one embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] Although the embodiments of the present disclosure have been described with reference to the drawings, those skilled in the art may make various modifications and changes without departing from the spirit and scope of the present disclosure, and all such modifications and changes are included in the scope of the appended claims. Industrial Applicability

[0148] In at least one embodiment of the present disclosure, a plurality of target vehicles are grouped, a fitting weight for each target vehicle is determined, and current traffic flow information is generated by fitting based on group information, the fitting weight, the motion information of the host vehicle, and the state information of the target vehicle, thereby realizing sensing of traffic flow. The embodiment of the present disclosure can determine an auxiliary position determination flag based on the current traffic flow information and a reliability corresponding to the current traffic flow information, and the auxiliary position determination flag is independent of lane marking information, and can assist in determining the lane in which the host vehicle is located in some multi-lane scenes when the lane markings are insufficient to determine the only lane, thereby providing a necessary basis for long-distance route planning of a level L3 autonomous driving system. In addition, the embodiment of the present disclosure can perform lateral control of the host vehicle based on the current traffic flow information, which is advantageous in deviating from the dependency on lane marking information and maintaining lateral control of the host vehicle in a congested environment. The present disclosure has industrial applicability.

Claims

1. A method for determining traffic flow information implemented by a processor, the method comprising the steps of: Grouping each of the target vehicles based on the motion information of the host vehicle and the state information of one or more target vehicles to obtain group information; determining a fitting weight for each of the target vehicles based on the state information and the group information of each of the target vehicles; generating one or more pieces of current traffic flow information by fitting based on the motion information of the host vehicle, the state information of each of the target vehicles, the fitting weight of each of the target vehicles, and the group information; The motion information of the host vehicle is dynamics information related to the traveling of the host vehicle, the state information of the target vehicle is information including a relative position and a relative motion between the target vehicle and the host vehicle, and the traffic flow information is information on a trajectory of a traffic flow formed by a plurality of vehicles in the same lane moving in the same direction, Before the step of generating one or more pieces of current traffic flow information by fitting, the method further includes: determining whether the number of target vehicles satisfies a preset fitting number, and if so, determining whether the vehicle is traveling in a straight line; When the driving state of the host vehicle is straight, acquiring a cached historical vehicle; updating the coordinates of each of the historical vehicles and obtaining a virtual vehicle corresponding to each of the historical vehicles and state information of each of the virtual vehicles; determining a fitting weight for each of the virtual vehicles based on historical traffic flow information, motion information of the host vehicle, state information of each of the virtual vehicles, and group information of each of the virtual vehicles; Correspondingly, the step of generating one or more pieces of current traffic flow information by fitting includes a step of generating one or more pieces of current traffic flow information by fitting based on state information of each of the target vehicles, a fitting weight of each of the target vehicles, state information of each of the virtual vehicles, and a fitting weight of each of the virtual vehicles. A method for determining traffic flow information comprising:

2. The step of grouping each of the target vehicles and obtaining group information based on the motion information of the host vehicle and the state information of one or more target vehicles includes: determining a travel trajectory of the host vehicle based on the motion information of the host vehicle; Screening one or more valid target vehicles based on the motion information of the host vehicle and the state information of each of the target vehicles; and grouping each of the valid target vehicles based on the travel trajectory of the host vehicle and state information of each of the valid target vehicles to obtain group information.

2. The method of claim 1 .

3. After the step of obtaining group information, the method further comprises: correcting the group information based on historical traffic flow information; Correspondingly, determining a fitting weight for each of the valid target vehicles based on the historical traffic flow information, the state information of each of the valid target vehicles, and the corrected group information.

3. The method of claim 2 .

4. The step of grouping each of the valid target vehicles based on the travel trajectory of the host vehicle and state information of each of the valid target vehicles and obtaining group information includes: For each of said available target vehicles, determining a relative lane in which the valid target vehicle is located based on state information of the valid target vehicle and a travel trajectory of the host vehicle; and determining group information of the valid target vehicle based on the relative lane.

3. The method of claim 2 .

5. The group information includes five groups, namely, a first lane group on the left side of the lane in which the host vehicle is located, a second lane group on the left side of the lane in which the host vehicle is located, a first lane group on the right side of the lane in which the host vehicle is located, a second lane group on the right side of the lane in which the host vehicle is located, and other groups.

5. The method according to claim 1, wherein the first and second electrodes are arranged in a first direction.

6. The historical vehicle satisfies a cache condition, where the cache condition is used to screen vehicles that travel in the same direction as the vehicle and do not belong to other groups.

6. The method of claim 5 .

7. The cache condition is: A vehicle is located in front of the host vehicle and a relative distance between the vehicle and the host vehicle is greater than a preset relative distance threshold value; The included angle between the vehicle direction relative to the speed of the host vehicle and the traveling direction of the host vehicle is smaller than a preset included angle threshold value; The lateral distance of the vehicle relative to the host vehicle is within a preset lateral distance range.

7. The method of claim 6.

8. The caching condition further includes the vehicle's life cycle being greater than a preset life cycle threshold.

8. The method of claim 7.

9. The step of determining a fitting weight for each of the target vehicles comprises: For each of said target vehicles, determining a lateral speed deviation weight of the target vehicle, a lateral displacement deviation weight of the target vehicle, a life cycle weight of the target vehicle, and a speed weight of the target vehicle based on the state information of the target vehicle and the group information of the target vehicle; multiplying the lateral speed deviation weight of the target vehicle, the lateral displacement deviation weight of the target vehicle, the life cycle weight of the target vehicle, and the speed weight of the target vehicle to obtain a fitting weight of the target vehicle.

2. The method of claim 1 .

10. The step of determining fitting weights for each of the virtual vehicles further comprises: For each of the virtual vehicles, determining a lateral speed deviation weight of the virtual vehicle, a lateral displacement deviation weight of the virtual vehicle, a life cycle weight of the virtual vehicle, a speed weight of the virtual vehicle, and a weight of the virtual vehicle based on the state information of the virtual vehicle and the group information of the virtual vehicle; multiplying the lateral speed deviation weight of the virtual vehicle, the lateral displacement deviation weight of the virtual vehicle, the life cycle weight of the virtual vehicle, the speed weight of the virtual vehicle, and the weight of the virtual vehicle to obtain a fitting weight of the virtual vehicle.

2. The method of claim 1 .

11. Each group corresponds to one traffic flow, and the step of generating one or more pieces of current traffic flow information by fitting includes: For one group, Selecting a fitting method based on the number of target vehicles in the group and the longitudinal distribution distances of all target vehicles in the group; and generating current traffic flow information corresponding to the group through fitting based on the selected fitting method, using the motion information of the host vehicle, the state information of each target vehicle in the group, and the fitting weight of each target vehicle in the group.

2. The method of claim 1 .

12. The step of selecting a fitting method based on the number of target vehicles in the group and the longitudinal distribution distances of all target vehicles in the group includes: Determining whether the number of target vehicles in the group satisfies a first quantity condition and whether the longitudinal distribution distance is greater than a preset first distance threshold; If the first quantity condition is met and the longitudinal distribution distance is greater than a preset first distance threshold, select the primary fitting and the secondary fitting; otherwise, determine whether the quantity of the target vehicles in the group meets the second quantity condition and whether the longitudinal distribution distance is greater than a preset second distance threshold; if the second quantity condition is satisfied and is greater than a second preset distance threshold, select primary fitting, otherwise do not perform fitting.

12. The method of claim 11 .

13. When the first fitting and the second fitting are selected, the step of generating current traffic flow information corresponding to the group by fitting includes: generating a primary fitting result corresponding to the group by fitting and determining a first mean square deviation of the primary fitting result; generating a secondary fitting result corresponding to the group by fitting and determining a second mean square deviation of the secondary fitting result; comparing the first mean square deviation and the second mean square deviation, and if the first mean square deviation is greater than a preset multiple of the second mean square deviation, selecting the second fitting result as the current traffic flow information corresponding to the group, and if not, selecting the first fitting result as the current traffic flow information corresponding to the group.

13. The method of claim 12.

14. the step of generating current traffic flow information corresponding to the group by fitting using the motion information of the host vehicle, the state information of each target vehicle in the group, and the fitting weight of each target vehicle in the group, generating initial traffic flow information corresponding to the group through fitting based on state information of each target vehicle in the group and fitting weights of each target vehicle in the group; and constraining the initial traffic flow information based on the historical traffic flow information and the vehicle motion information to obtain current traffic flow information corresponding to the group.

12. The method of claim 11 .

15. The constraints include a position constraint, an orientation constraint, and / or a curvature constraint.

15. The method of claim 14.

16. The position constraint includes constraining a change amount of a constant term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information; There is an inverse correlation between the change amount of the constant term and the reliability corresponding to the historical traffic flow information, and there is a positive correlation between the change amount of the constant term and the number of fittings corresponding to the initial traffic flow information.

16. The method of claim 15 .

17. The directional constraint includes constraining a change amount of a first-order term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle, wherein the change amount of the first-order term and the reliability corresponding to the historical traffic flow information are inversely correlated, the change amount of the first-order term and the steering width of the host vehicle are positively correlated, and / or the change amount of the first-order term and the number of fittings corresponding to the initial traffic flow information are positively correlated.

16. The method of claim 15 .

18. The curvature constraint includes constraining a change amount of a quadratic term in a fitting parameter corresponding to the initial traffic flow information based on a reliability corresponding to the historical traffic flow information and / or motion information of the host vehicle, wherein the change amount of the quadratic term and the reliability corresponding to the historical traffic flow information are inversely correlated, the change amount of the quadratic term and the speed of the host vehicle are inversely correlated, and / or the change amount of the quadratic term and the steering wheel rotation speed of the host vehicle are directly correlated.

16. The method of claim 15 .

19. The method further comprises: determining a confidence increment based on the current traffic flow information; determining a reliability corresponding to the current traffic flow information based on the reliability of the historical traffic flow information and the reliability increment; Wherein, there is an inverse correlation between the reliability increment and the fitting result mean square deviation corresponding to the current traffic flow information, a positive correlation between the reliability increment and the fitting number corresponding to the current traffic flow information, and / or a positive correlation between the reliability increment and the longitudinal distribution distance of the target vehicle corresponding to the current traffic flow information.

2. The method of claim 1 .

20. The step of determining a reliability increment based on the current traffic flow information includes the steps of: comparing the fitting numbers and longitudinal distribution distances corresponding to the two traffic flows when there is an intersection between the two current traffic flow information; and determining that the reliability increment corresponding to the current traffic flow information having a smaller fitting number or a shorter longitudinal distribution distance is negative.

20. The method of claim 19 .

21. The method further includes determining a vehicle driving reference route based on the current traffic flow information and a reliability corresponding to the current traffic flow information; The step of determining a vehicle travel reference route includes: When the reliability corresponding to the current traffic flow information on both sides of the vehicle is higher than a preset reliability threshold, the parameter of the vehicle's reference route is determined to be a weighted average value of the fitting parameters corresponding to the current traffic flow information on both sides of the vehicle, and the weight of the fitting parameters corresponding to the current traffic flow information on both sides of the vehicle is inversely correlated with the change rate of the fitting parameters; determining that, when the reliability corresponding to the current traffic flow information on only one side of the vehicle is higher than a preset reliability threshold, the linear and quadratic terms in the parameters of the reference route of the vehicle are the same as the linear and quadratic terms in the fitting parameters corresponding to the current traffic flow information on that side, and the constant term in the parameters of the reference route of the vehicle is zero; and determining that all parameters of the travel reference route of the vehicle are zero when the reliability corresponding to the current traffic flow information on both sides of the vehicle is lower than a preset reliability threshold.

20. The method of claim 19 .

22. The method further includes determining an auxiliary location determination flag based on the current traffic flow information and a reliability corresponding to the current traffic flow information; The step of determining an auxiliary location flag comprises: The method includes a step of determining an auxiliary position identification flag as a first flag when the reliability corresponding to the current traffic flow information on both sides of the vehicle is higher than a preset reliability threshold, a step of determining an auxiliary position identification flag as a second flag when the reliability corresponding to the current traffic flow information on the left side of the vehicle is higher than a preset reliability threshold, and a step of determining an auxiliary position identification flag as a third flag when the reliability corresponding to the current traffic flow information on the right side of the vehicle is higher than a preset reliability threshold.

20. The method of claim 19 .

23. A grouping module is used for grouping each of the target vehicles according to the motion information of the host vehicle and the state information of one or more target vehicles, and obtaining group information; a determination module used for determining a fitting weight for each of the target vehicles based on the state information and the group information of each of the target vehicles; a fitting module used for generating one or more pieces of current traffic flow information through fitting according to the motion information of the subject vehicle, the state information of each of the target vehicles, the fitting weight of each of the target vehicles and the group information; The motion information of the host vehicle is dynamics information related to the traveling of the host vehicle, the state information of the target vehicle is information including a relative position and a relative motion between the target vehicle and the host vehicle, and the traffic flow information is information on a trajectory of a traffic flow formed by a plurality of vehicles in the same lane moving in the same direction, The fitting module is further used for: before generating one or more current traffic flow information by fitting, judging whether a target vehicle number meets a preset fitting number; if met, judging whether the driving state of the host vehicle is straight; if the driving state of the host vehicle is straight, acquiring cached historical vehicles, updating coordinates of each of the historical vehicles, acquiring virtual vehicles corresponding to each historical vehicle and state information of each of the virtual vehicles; and determining a fitting weight of each of the virtual vehicles according to the historical traffic flow information, the motion information of the host vehicle, the state information of each of the virtual vehicles and the group information of each of the virtual vehicles; Correspondingly, the fitting module is used for generating one or more pieces of current traffic flow information by fitting according to the state information of each of the target vehicles, the fitting weight of each of the target vehicles, the state information of each of the virtual vehicles and the fitting weight of each of the virtual vehicles; A traffic flow information determining device comprising:

24. A processor and a memory, the processor being adapted to execute the steps of the method for determining traffic flow information according to any one of claims 1 to 22 by calling a program or instruction stored in the memory.

1. An electronic device comprising:

25. A program or instruction for causing a computer to execute the steps of the traffic flow information determination method according to any one of claims 1 to 22 is stored. A non-transitory computer-readable storage medium comprising:

Citation Information

Patent Citations

  • Traffic control method and device

    CN108171967A

  • Lane line detection method and device, electronic equipment and readable storage medium

    CN111738207A