V2v and gps based vehicle positioning method and apparatus in a garage

Abstract

The application relates to a garage vehicle positioning method and device based on V2V and GPS, and belongs to the technical field of vehicle positioning. The garage vehicle positioning method based on V2V and GPS provided by the application obtains high-precision initial state of a vehicle according to GPS signals and IMU measurement data when the vehicle drives into a target area in front of a garage entrance, continuously pre-integrates IMU measurement data according to the initial state after the vehicle drives into the garage, and obtains accurate real-time vehicle distance between any two vehicles in the garage through RTT ranging. Distance constraint equations are constructed according to IMU integral positioning and real-time vehicle distance, the current position of a parked vehicle is taken as a virtual anchor point, a factor graph is used to jointly optimize multiple factors to determine the positioning of the vehicle in the garage, optimal estimation is realized, high-precision positioning in the garage is realized only by using V2V communication and IMU cooperation between vehicles, and no additional fixed facilities are needed.

Description

Technical Field

[0001] This invention relates to the field of vehicle positioning technology, and in particular to a vehicle positioning method and device based on V2V and GPS in a garage. Background Technology

[0002] Vehicle positioning in underground garages and indoor parking lots remains a significant technical challenge in the parking industry. Global Positioning System (GPS) signals are often unable to penetrate concrete structures due to building obstructions. When GPS signals are unavailable, position estimation relies solely on inertial navigation system (INS) integration, and the error increases quadratically with the travel distance. Within a travel distance of tens of meters, the error can reach 5-10 meters, resulting in significant inaccuracies and low usability.

[0003] Existing vehicle location methods in underground parking garages mainly have the following problems: (1) Positioning methods based on fixed infrastructure mainly rely on pre-deployed UWB anchors or Bluetooth beacons, with an accuracy of 0.3-1 meters. However, they require pre-embedded hardware, power supply, and access to the backhaul network, resulting in high deployment costs and making them unsuitable for old garages and temporary parking lots.

[0004] (2) The GPS / INS integrated navigation method works well in outdoor environments, but GPS signals are lost when entering underground parking garages. The positioning relies solely on INS integration, resulting in a large error. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle positioning method and device based on V2V and GPS in a parking garage, so as to improve the positioning accuracy of underground parking garages without increasing costs.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a vehicle positioning method in a garage based on V2V and GPS, comprising: When the vehicle drives into the target area in front of the garage entrance, the initial state of the vehicle is obtained based on GPS signals and IMU measurement data; When the vehicle enters the garage, the IMU measurement data is continuously pre-integrated based on the initial state to determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The real-time distance between any two cars in the garage is obtained by RTT ranging, and a distance constraint equation is constructed based on the IMU integral positioning corresponding to each of the two cars and the real-time distance. When a parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined, and the current position of the parked vehicle is used as a virtual anchor point. The vehicle's location within the garage is determined by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs. The virtual anchor point factor is determined based on the location information broadcast by the parked vehicle. The V2V relative distance factor is determined based on the distance constraint equation.

[0007] In one possible implementation, the method of jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs to determine the vehicle's location within the garage includes: Based on a preset time window and frequency, with the goal of minimizing the sum of squared Mahalanobis distances of the residuals of each factor, the vehicle's location in the garage is determined by optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor through a sliding window.

[0008] In one possible implementation, the triggering condition for the zero-velocity detection includes: The vehicle speed is less than 0.1 m / s for more than 1 second, the IMU accelerometer variance is less than 0.01 m / s², and the vehicle is in P or N gear.

[0009] In one possible implementation, the distance constraint equation is expressed as follows:

[0010] in, This indicates the IMU integral positioning corresponding to vehicle A. This indicates the IMU integral positioning corresponding to vehicle B. This indicates the real-time distance between vehicle A and vehicle B. This represents the cumulative IMU error between vehicle A and vehicle B.

[0011] In one possible implementation, after determining the vehicle's location within the garage by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs, the method further includes: When the vehicle exits the garage, its location is determined based on GPS signals. The location determined by factor graph joint optimization and the location determined by GPS signal are progressively fused to obtain the fused location of the vehicle outside the garage.

[0012] In one possible implementation, the expression for the fused localization is as follows:

[0013] in, Indicates integrated positioning. Indicates gradual weighting. This indicates a location determined based on GPS signals. This represents the localization after joint optimization based on factor graphs.

[0014] In one possible implementation, the expression for the gradient weight is as follows:

[0015] in, Indicates gradual weighting. This indicates the moment the vehicle exits the garage.

[0016] In one possible implementation, the gradient weight increases linearly from 0 to 1 over a transition distance of 30 meters.

[0017] Secondly, the present invention also provides a vehicle positioning device in a garage based on V2V and GPS, comprising: The acquisition unit is used to acquire the initial state of the vehicle based on GPS signals and IMU measurement data when the vehicle drives into the target area in front of the garage entrance; The first determining unit is used to continuously pre-integrate the IMU measurement data based on the initial state when the vehicle enters the garage, and determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The construction unit is used to obtain the real-time distance between any two cars in the garage through RTT ranging, and to construct a distance constraint equation based on the IMU integral positioning corresponding to the two cars and the real-time distance. The second determining unit is used to determine the zero-speed detection factor when the parked vehicle in the garage meets the zero-speed detection trigger condition, and to use the current position of the parked vehicle as a virtual anchor point. The positioning unit is used to jointly optimize the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using a factor graph to determine the vehicle's positioning within the garage; the virtual anchor point factor is determined based on the location information broadcast by the parked vehicle; and the V2V relative distance factor is determined based on the distance constraint equation.

[0018] Thirdly, the present invention also provides an electronic device, including a data acquisition unit, a memory, and a processor, wherein, The data acquisition unit, the memory, and the processor are communicatively connected. The data acquisition unit is used to acquire GPS signals and IMU measurement data; The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the vehicle positioning method in the garage based on V2V and GPS as described in any of the above implementations.

[0019] The beneficial effects of this invention are as follows: The vehicle positioning method and device in a garage based on V2V and GPS provided by this invention obtains a high-precision initial state of the vehicle based on GPS signals and IMU measurement data when the vehicle drives towards the target area in front of the garage entrance. When the vehicle enters the garage, the GPS signal is lost. Based on the initial state, the IMU measurement data is continuously pre-integrated to determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The accurate real-time distance between any two vehicles in the garage is obtained through RTT ranging. A distance constraint equation is constructed based on the IMU integral positioning and real-time distance to suppress the absolute drift of the vehicle. When the parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined. The current position of the parked vehicle is used as a virtual anchor point. The IMU pre-integration factor, zero-speed detection factor, V2V relative distance factor and virtual anchor point factor are jointly optimized using factor graph to determine the vehicle's positioning in the garage and achieve optimal estimation. High-precision positioning in the garage is achieved only by using V2V communication between vehicles and IMU collaboration, without the need for additional fixed facilities. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A schematic flowchart of an embodiment of the vehicle positioning method in a garage based on V2V and GPS provided by the present invention; Figure 2 This invention provides a schematic diagram of imported GPS initialization and V2X relay. Figure 3 This is a schematic diagram of the V2V collaborative error cancellation principle provided by the present invention; Figure 4 A schematic diagram of the dynamic virtual anchor point mechanism provided by the present invention; Figure 5 A schematic diagram of the gradual fusion of the export process provided by the present invention; Figure 6 A schematic diagram of the overall architecture of the vehicle positioning system in a garage based on V2V and GPS provided by the present invention; Figure 7 This is a schematic diagram of the overall positioning method provided by the present invention; Figure 8 A schematic diagram of an embodiment of the vehicle positioning device in a garage based on V2V and GPS provided by the present invention; Figure 9 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0023] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0024] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0025] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] This invention provides a vehicle positioning method and device in a garage based on V2V and GPS, which will be described below.

[0027] Figure 1 This is a schematic flowchart of an embodiment of the vehicle positioning method in a garage based on V2V and GPS provided by the present invention, as shown below. Figure 1 As shown, the vehicle positioning methods within a garage based on V2V and GPS include: S101. When the vehicle drives into the target area in front of the garage entrance, the initial state of the vehicle is obtained based on GPS signals and IMU measurement data. S102. When the vehicle enters the garage, the IMU measurement data is continuously pre-integrated based on the initial state to determine the IMU integration positioning and IMU pre-integration factor corresponding to the vehicle. S103. Obtain the real-time distance between any two cars in the garage through RTT ranging, and construct a distance constraint equation based on the IMU integral positioning corresponding to the two cars and the real-time distance. S104. When a parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined, and the current position of the parked vehicle is used as a virtual anchor point. S105. The IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor are jointly optimized using factor graphs to determine the vehicle's location within the garage; the virtual anchor point factor is determined based on the location information broadcast by the parked vehicle; and the V2V relative distance factor is determined based on the distance constraint equation.

[0028] In S101, the target area is the GPS initialization window area 30 meters before the vehicle enters. When the vehicle enters the target area, the initial state of the vehicle is obtained based on the GPS signal and IMU measurement data. The RTK-level GPS / INS tightly coupled initialization is completed to obtain a high-precision initial state. The initial state can include the initial position, initial velocity, initial attitude and initial zero bias, and is broadcast through V2X.

[0029] If a vehicle entering the garage later has poor initialization quality, it can request and inherit that state from an existing vehicle in the garage.

[0030] Figure 2 This is a schematic diagram of the imported GPS initialization and V2X relay provided by the present invention, as shown below. Figure 2 As shown, by using imported GPS for initialization and status relay, the high-precision initial status is transmitted via V2X broadcast, which can be inherited by subsequent vehicles, thus solving the problem of poor cold start initialization quality.

[0031] In S102, when the vehicle enters the garage, the GPS signal is lost. Based on the initial state, the IMU measurement data is continuously pre-integrated to obtain the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The IMU pre-integration factor is used to constrain the continuity of motion.

[0032] In S103, vehicles in the garage use C-V2X PC5 to measure round-trip time (RTT) distances, obtaining the real-time distance between any two vehicles. Based on the IMU integral localization and real-time distance for each of the two vehicles, distance constraint equations can be constructed.

[0033] The V2V relative distance factor can be determined based on the distance constraint equation. The V2V relative distance factor is used to constrain the relative positions of the workshops.

[0034] By constructing an overdetermined set of equations through the relative constraints between multiple pairs of vehicles, the absolute drift of each vehicle can be suppressed by solving the equations together.

[0035] In S104, when a parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined. The zero-speed detection factor is used to provide an absolute speed zero constraint when parking.

[0036] The current location of the parked vehicle is used as a high-confidence virtual anchor point. The virtual anchor point factor is determined through V2X broadcast (including location, covariance, and timestamp). The virtual anchor point factor is used to constrain the absolute position of the parked vehicle broadcast.

[0037] In S105, factor graphs are used to jointly optimize the IMU pre-integration factor, zero-velocity detection factor, V2V relative distance factor, and virtual anchor point factor. The optimization objective of the factor graphs is to minimize the sum of squared Mahalanobis distances of the residuals of each factor. After optimization using a sliding window, the pose is output and feedback is used to correct the IMU bias.

[0038] In summary, the vehicle positioning method in a garage based on V2V and GPS provided in this embodiment of the invention obtains a high-precision initial state of the vehicle based on GPS signals and IMU measurement data when the vehicle drives towards the target area in front of the garage entrance. When the vehicle enters the garage, the GPS signal is lost, and the IMU measurement data is continuously pre-integrated based on the initial state to determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The accurate real-time distance between any two vehicles in the garage is obtained through RTT ranging. A distance constraint equation is constructed based on the IMU integral positioning and real-time distance to suppress the absolute drift of the vehicle. When the parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined, and the current position of the parked vehicle is used as a virtual anchor point. The IMU pre-integration factor, zero-speed detection factor, V2V relative distance factor, and virtual anchor point factor are jointly optimized using factor graph to determine the vehicle's positioning in the garage and achieve optimal estimation. High-precision positioning in the garage is achieved only by using V2V communication between vehicles and IMU collaboration, without the need for additional fixed facilities.

[0039] In some embodiments of the present invention, the expression of the distance constraint equation is as follows:

[0040] in, This indicates the IMU integral positioning corresponding to vehicle A. This indicates the IMU integral positioning corresponding to vehicle B. This indicates the real-time distance between vehicle A and vehicle B. This represents the cumulative IMU error between vehicle A and vehicle B.

[0041] The cars in the garage are measured using C-V2X PC5 for round-trip time (RTT) distance, thus obtaining the real-time vehicle-to-vehicle distance. Its accuracy is better than 0.5 meters.

[0042] Let the IMU integral positions of vehicles A and B be... , The constraint equations are:

[0043] in, It is an observable measurement of the cumulative error between the two vehicle IMUs.

[0044] Figure 3 This is a schematic diagram of the V2V collaborative error cancellation principle provided by the present invention, as shown below. Figure 3 As shown, the overdetermined equations are formed by the relative constraints between multiple pairs of vehicles, and the joint solution can suppress the absolute drift of each vehicle.

[0045] The vehicle positioning method in a garage based on V2V and GPS provided in this invention combines the relative distance measurement constraint between vehicles with the integration of multiple vehicle IMUs for joint optimization. The relative constraint is used to eliminate absolute drift, and the positioning becomes more accurate as more vehicles are involved.

[0046] In some embodiments of the present invention, the step of using factor graphs to jointly optimize the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor to determine the vehicle's location within the garage includes: Based on a preset time window and frequency, with the goal of minimizing the sum of squared Mahalanobis distances of the residuals of each factor, the vehicle's location in the garage is determined by optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor through a sliding window.

[0047] This invention provides a factor graph multi-source fusion optimization method, which uses a factor graph framework to jointly optimize four types of factors: IMU pre-integration factor, V2V relative distance factor, zero-velocity detection factor, and virtual anchor point factor.

[0048] Among them, the IMU pre-integration factor is used to constrain motion continuity, the V2V relative distance factor is used to constrain the relative position of the workshop, the zero speed detection factor is used to provide absolute speed zero constraint when parking, and the virtual anchor point factor is used to constrain the absolute position broadcast by the parked vehicle.

[0049] The objective of factor map optimization is to minimize the sum of squared Mahalanobis distances of the residuals of each factor. After optimization using a sliding window (preset time window of 10 seconds and frequency of 5Hz), the pose is output and feedback is used to correct the IMU bias.

[0050] Figure 4 This is a schematic diagram of the dynamic virtual anchor point mechanism provided by the present invention, such as... Figure 4 As shown, when a vehicle stops (at 0 speed for 2 seconds), a zero-speed update is triggered, and the current position is used as a high-confidence virtual anchor point, broadcast via V2X (including position, covariance, and timestamp). Surrounding moving vehicles receive this and add it to the factor graph as an absolute constraint. The anchor point is dynamically formed by the vehicles present and requires no fixed facilities.

[0051] The vehicle positioning method in a garage based on V2V and GPS provided in this invention achieves optimal estimation by fusing four factors—IMU pre-integration, V2V relative distance, zero-speed detection, and virtual anchor points—through multi-source factor graph fusion within a unified framework. It requires no fixed infrastructure such as UWB / Bluetooth / Wi-Fi, utilizing only existing vehicle sensors and V2X communication.

[0052] In some embodiments of the present invention, the triggering conditions for the zero-speed detection include: The vehicle speed is less than 0.1 m / s for more than 1 second, the IMU accelerometer variance is less than 0.01 m / s², and the vehicle is in P or N gear.

[0053] The zero-speed detection conditions are: vehicle speed < 0.1 m / s for 1 second, IMU accelerometer variance < 0.01 m / s², and gear position P / N.

[0054] By setting dynamic virtual anchor points, the location of a parked vehicle that triggers zero-speed detection is broadcast as a temporary virtual anchor point, providing absolute constraint with zero hardware cost.

[0055] In some embodiments of the present invention, after determining the vehicle's location in the garage by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs, the method further includes: When the vehicle exits the garage, its location is determined based on GPS signals. The location determined by factor graph joint optimization and the location determined by GPS signal are progressively fused to obtain the fused location of the vehicle outside the garage.

[0056] In some embodiments of the present invention, the expression for the fused localization is as follows:

[0057] in, Indicates integrated positioning. Indicates gradual weighting. This indicates a location determined based on GPS signals. This represents the localization after joint optimization based on factor graphs.

[0058] In some embodiments of the present invention, the expression for the gradient weight is as follows:

[0059] in, Indicates gradual weighting. This indicates the moment the vehicle exits the garage.

[0060] In some embodiments of the present invention, the gradient weight increases linearly from 0 to 1, with a transition distance of 30 meters.

[0061] Figure 5 This is a schematic diagram of the gradual fusion of the export process provided by the present invention, such as... Figure 5 As shown, when the vehicle exits the garage, a progressive weighted transition is used to locate the vehicle within the 30-meter GPS recapture zone before the exit (this area can acquire GPS signals).

[0062] Among them, asymptotic weights The distance increases linearly from 0 to 1, with a transition distance of 30 meters. At the same time, the covariance matrix is ​​updated synchronously, eliminating the positioning jumps of traditional hard handover (reducing it from 2-5 meters to within 0.3 meters).

[0063] The asymptotic weights are as follows:

[0064] The transition time for progressive weights is 2 seconds.

[0065] The vehicle positioning method in a garage based on V2V and GPS provided in this embodiment of the invention adopts progressive fusion at the garage exit and uses progressive weight transition to replace hard handover, reducing the indoor-outdoor positioning jump from 2-5 meters to less than 0.3 meters.

[0066] This invention does not rely on any fixed facilities. It utilizes vehicle-to-vehicle communication and IMU collaboration to achieve high-precision positioning in a garage. Moreover, the transition between indoor and outdoor environments must be smooth and without any abrupt changes.

[0067] Figure 6 This is a schematic diagram of the overall architecture of the vehicle positioning system in the garage based on V2V and GPS provided by the present invention. The system consists of five parts: a V2X communication module (C-V2X PC5, ranging accuracy better than 0.5 meters), an IMU and GPS module (IMU ≥ 100Hz, GPS 10Hz), a factor graph optimization processor, a state broadcasting and inheritance management module, and a progressive fusion module.

[0068] Figure 7 This is a schematic diagram of the overall positioning method provided by the present invention, such as... Figure 7 As shown, this invention proposes a parking garage location method without infrastructure based on V2V collaborative error cancellation and GPS relay. The core innovations include: (1) V2V collaborative error cancellation - using relative distance measurement between workshops to build a collaborative constraint network, the more vehicles there are, the more accurate the positioning; (2) Dynamic virtual anchor point - after the parking vehicle triggers zero speed detection, it broadcasts its position, providing absolute constraints with zero hardware cost; (3) Import GPS initialization and state relay - high-precision initial state is transmitted through V2X to solve the cold start problem; (4) Exit progressive fusion - eliminating the positioning jump when switching between indoor and outdoor environments.

[0069] The vehicle positioning method in a garage based on V2V and GPS provided by this invention will be described in detail below, taking into account specific application scenarios.

[0070] Scenario 1: Dense traffic (20 vehicles present).

[0071] During the evening rush hour in the underground parking garage, there were 20 vehicles present (5 parked). IMU integration for each vehicle exhibited drift; relative constraints were established between moving vehicles via V2V RTT; the 5 parked vehicles triggered ZUPT and broadcast virtual anchor points. After fusing all constraints using a factor graph, the average positioning error was 0.6 meters, with a maximum error of 1.2 meters, meaning that the more vehicles present, the higher the accuracy.

[0072] Scenario 2: Cold start scenario (only 1 vehicle).

[0073] Only one vehicle entered the garage in the early morning, with no V2V constraints. After completing GPS / INS initialization at the entrance, the vehicle entered the garage. Pure IMU integration resulted in an error of approximately 3 meters after traveling 50 meters. Upon exiting, progressive fusion at the exit brought the error back to GPS accuracy. Although the accuracy is lower than in densely populated scenes, the error is bounded and superior to traditional pure INS integration.

[0074] The vehicle positioning method in a garage based on V2V and GPS provided by this invention has the following advantages: (1) Zero infrastructure dependency. No need to deploy UWB, Bluetooth, or Wi-Fi, only the vehicle's existing V2X and IMU are used.

[0075] (2) The more vehicles, the more accurate the positioning. In traditional solutions, the number of vehicles has no impact. In this invention, the more vehicles there are, the richer the constraints and the more accurate the positioning. Actual measurements show that 1 vehicle is 3.2 meters, 5 vehicles are 1.5 meters, 10 vehicles are 0.9 meters, and 20 vehicles are 0.6 meters.

[0076] (3) Continuous indoor and outdoor positioning. Initialization at the inlet and gradual fusion at the outlet reduce the jump from 2-5 meters to less than 0.3 meters, so that the user does not perceive it.

[0077] (4) Enhanced dynamic virtual anchor points. ZUPT anchor points triggered by parking provide absolute position constraints for the moving vehicle at zero cost.

[0078] (5) Low computing power and low power consumption. Factor graph sliding window optimization (10-second window, 5Hz) can run on ARM core without the need for a dedicated AI chip, and the power consumption is less than 1 watt.

[0079] In addition, V2X communication and IMU / GPS data are processed locally on the vehicle side, and V2X broadcasts only transmit relative location and status information (excluding the vehicle's unique identifier), which complies with the requirements for anonymization of external data in the "Several Provisions on the Management of Vehicle Data Security (Trial)".

[0080] To better implement the vehicle positioning method in a garage based on V2V and GPS in the embodiments of the present invention, based on the vehicle positioning method in a garage based on V2V and GPS, the corresponding method is as follows: Figure 8 As shown, this embodiment of the invention also provides a vehicle positioning device in a garage based on V2V and GPS. The vehicle positioning device 800 in a garage based on V2V and GPS includes: The acquisition unit 801 is used to acquire the initial state of the vehicle based on GPS signals and IMU measurement data when the vehicle drives into the target area in front of the garage entrance; The first determining unit 802 is used to continuously pre-integrate the IMU measurement data based on the initial state when the vehicle enters the garage, and determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The construction unit 803 is used to obtain the real-time distance between any two cars in the garage through RTT ranging, and to construct a distance constraint equation based on the IMU integral positioning corresponding to the two cars and the real-time distance. The second determining unit 804 is used to determine the zero-speed detection factor when the parked vehicle in the garage meets the zero-speed detection trigger condition, and to use the current position of the parked vehicle as a virtual anchor point. The positioning unit 805 is used to determine the vehicle's positioning in the garage by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using a factor graph; the virtual anchor point factor is determined based on the location information broadcast by the parked vehicle; and the V2V relative distance factor is determined based on the distance constraint equation.

[0081] The vehicle positioning device 800 in the garage based on V2V and GPS provided in the above embodiments can realize the technical solutions described in the above embodiments of the vehicle positioning method in the garage based on V2V and GPS. The specific implementation principles of each module or unit can be found in the corresponding content in the above embodiments of the vehicle positioning method in the garage based on V2V and GPS, and will not be repeated here.

[0082] like Figure 9 As shown, the present invention also provides an electronic device 900. The electronic device 900 includes a processor 901, a memory 902, a display 903, and a data acquisition device 904. Figure 9 Only some components of the electronic device 900 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0083] In some embodiments, processor 901 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 902 or process data, such as the vehicle positioning method in a garage based on V2V and GPS in this invention.

[0084] In some embodiments, processor 901 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 901 may be local or remote. In some embodiments, processor 901 may be implemented on a cloud platform. In some embodiments, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0085] In some embodiments, memory 902 may be an internal storage unit of electronic device 900, such as a hard disk or memory of electronic device 900. In other embodiments, memory 902 may also be an external storage device of electronic device 900, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 900.

[0086] Furthermore, the memory 902 may include both internal storage units of the electronic device 900 and external storage devices. The memory 902 is used to store application software and various types of data installed on the electronic device 900.

[0087] In some embodiments, display 903 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen, etc. Display 903 is used to display information from electronic device 900 and to display a visual user interface.

[0088] In some embodiments, the data acquisition unit 904 may be a sensor used to acquire GPS signals and IMU measurement data.

[0089] Components 901-904 of electronic device 900 communicate with each other via a system bus.

[0090] In one embodiment, when processor 901 executes a V2V and GPS-based vehicle location program in garage stored in memory 902, the following steps can be performed: When the vehicle drives into the target area in front of the garage entrance, the initial state of the vehicle is obtained based on GPS signals and IMU measurement data; When the vehicle enters the garage, the IMU measurement data is continuously pre-integrated based on the initial state to determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The real-time distance between any two cars in the garage is obtained by RTT ranging, and a distance constraint equation is constructed based on the IMU integral positioning corresponding to each of the two cars and the real-time distance. When a parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined, and the current position of the parked vehicle is used as a virtual anchor point. The vehicle's location within the garage is determined by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs. The virtual anchor point factor is determined based on the location information broadcast by the parked vehicle. The V2V relative distance factor is determined based on the distance constraint equation.

[0091] It should be understood that when the processor 901 executes the vehicle positioning program in the garage based on V2V and GPS stored in the memory 902, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0092] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 900 mentioned. Electronic device 900 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 900 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0093] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the vehicle positioning method in the garage based on V2V and GPS provided in the above-described method embodiments.

[0094] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0095] The above provides a detailed description of the vehicle positioning method and device in a garage based on V2V and GPS provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A vehicle positioning method in a garage based on V2V and GPS, characterized in that, include: When the vehicle drives into the target area in front of the garage entrance, the initial state of the vehicle is obtained based on GPS signals and IMU measurement data; When the vehicle enters the garage, the IMU measurement data is continuously pre-integrated based on the initial state to determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The real-time distance between any two cars in the garage is obtained by RTT ranging, and a distance constraint equation is constructed based on the IMU integral positioning corresponding to each of the two cars and the real-time distance. When a parked vehicle in the garage meets the zero-speed detection trigger condition, the zero-speed detection factor is determined, and the current position of the parked vehicle is used as a virtual anchor point. The vehicle's location within the garage is determined by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs. The virtual anchor point factor is determined based on the location information broadcast by the parked vehicle. The V2V relative distance factor is determined based on the distance constraint equation.

2. The vehicle positioning method in a garage based on V2V and GPS according to claim 1, characterized in that, The method of using factor graphs to jointly optimize the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor to determine the vehicle's location within the garage includes: Based on a preset time window and frequency, with the goal of minimizing the sum of squared Mahalanobis distances of the residuals of each factor, the vehicle's location in the garage is determined by optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor through a sliding window.

3. The vehicle positioning method in a garage based on V2V and GPS according to claim 1, characterized in that, The triggering conditions for the zero-speed detection include: The vehicle speed is less than 0.1 m / s for more than 1 second, the IMU accelerometer variance is less than 0.01 m / s², and the vehicle is in P or N gear.

4. The vehicle positioning method in a garage based on V2V and GPS according to claim 1, characterized in that, The expression for the distance constraint equation is as follows: in, This indicates the IMU integral positioning corresponding to vehicle A. This indicates the IMU integral positioning corresponding to vehicle B. This indicates the real-time distance between vehicle A and vehicle B. This represents the cumulative IMU error between vehicle A and vehicle B.

5. The vehicle positioning method in a garage based on V2V and GPS according to claim 1, characterized in that, After determining the vehicle's location within the garage by jointly optimizing the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using factor graphs, the process further includes: When the vehicle exits the garage, its location is determined based on GPS signals. The location determined by factor graph joint optimization and the location determined by GPS signal are progressively fused to obtain the fused location of the vehicle outside the garage.

6. The vehicle positioning method in a garage based on V2V and GPS according to claim 5, characterized in that, The expression for the fused localization is as follows: in, Indicates integrated positioning. Indicates gradual weighting. This indicates a location determined based on GPS signals. This represents the localization after joint optimization based on factor graphs.

7. The vehicle positioning method in a garage based on V2V and GPS according to claim 6, characterized in that, The expression for the gradient weight is as follows: in, Indicates gradual weighting. This indicates the moment the vehicle exits the garage.

8. The vehicle positioning method in a garage based on V2V and GPS according to claim 6, characterized in that, The gradient weight increases linearly from 0 to 1, with a transition distance of 30 meters.

9. A vehicle positioning device in a garage based on V2V and GPS, characterized in that, include: The acquisition unit is used to acquire the initial state of the vehicle based on GPS signals and IMU measurement data when the vehicle drives into the target area in front of the garage entrance; The first determining unit is used to continuously pre-integrate the IMU measurement data based on the initial state when the vehicle enters the garage, and determine the IMU integral positioning and IMU pre-integration factor corresponding to the vehicle. The construction unit is used to obtain the real-time distance between any two cars in the garage through RTT ranging, and to construct a distance constraint equation based on the IMU integral positioning corresponding to the two cars and the real-time distance. The second determining unit is used to determine the zero-speed detection factor when the parked vehicle in the garage meets the zero-speed detection trigger condition, and to use the current position of the parked vehicle as a virtual anchor point. The positioning unit is used to jointly optimize the IMU pre-integration factor, the zero-speed detection factor, the V2V relative distance factor, and the virtual anchor point factor using a factor graph to determine the vehicle's positioning within the garage; the virtual anchor point factor is determined based on the location information broadcast by the parked vehicle; and the V2V relative distance factor is determined based on the distance constraint equation.

10. An electronic device, characterized in that, Includes a data acquisition unit, memory, and processor, among which, The data acquisition unit, the memory, and the processor are communicatively connected. The data acquisition unit is used to acquire GPS signals and IMU measurement data; The memory is used to store programs; The processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps of the vehicle positioning method in a garage based on V2V and GPS as described in any one of claims 1 to 8.

Images