阅读说明：本技术 用于车辆定位的方法、用于车辆定位的设备和车辆 (Method for vehicle positioning, device for vehicle positioning and vehicle ) 是由 L·莫尔特雷赫特 于 2020-04-17 设计创作，主要内容包括：本发明涉及一种用于车辆定位的方法,所述方法包括：-借助于粒子滤波器确定车辆的位置数据；-查明是否满足预定的第一状态；-如果满足预定的第一状态,那么激活优化器来确定位置数据,其中,所述优化器依赖于来自粒子滤波器的位置数据执行定位。此外,本发明还涉及一种用于车辆定位的设备、计算机可读存储介质和车辆。根据本发明一些实施例的用于车辆定位的方法和设备能够适配于不同的应用场景而灵活地调整,并且能够在保持较好的定位精确性的前提下降低计算负荷。(The invention relates to a method for vehicle localization, comprising: -determining position data of the vehicle by means of a particle filter; -ascertaining whether a predetermined first state is fulfilled; -activating an optimizer to determine the position data if a predetermined first state is fulfilled, wherein the optimizer performs the positioning in dependence of the position data from the particle filter. Furthermore, the invention relates to a device for vehicle localization, a computer-readable storage medium and a vehicle. The method and the device for vehicle positioning according to some embodiments of the invention can be flexibly adjusted to adapt to different application scenes, and can reduce the calculation load on the premise of keeping better positioning accuracy.)

1. A method for vehicle localization, the method comprising:

-determining position data of the vehicle by means of a particle filter;

-ascertaining whether a predetermined first state is fulfilled;

-activating an optimizer to determine the position data if a predetermined first state is fulfilled, wherein the optimizer performs the positioning in dependence of the position data from the particle filter.

2. The method of claim 1, wherein the optimizer performing positioning in dependence on position data from a particle filter comprises: the latest position data determined by the particle filter is set as the initial position data of the optimizer.

3. A method according to claim 1, characterized in that "activating the optimizer to determine position data" comprises "switching from determining position data by means of the particle filter to determining position data by means of the optimizer", preferably, after switching, ascertaining whether a predetermined second state is fulfilled, and if the predetermined second state is fulfilled, switching from determining position data by means of the optimizer to determining position data by means of the particle filter.

4. The method according to one of claims 1 to 3, characterized in that the optimizer comprises:

a gradient descent optimizer;

a gradient ascent optimizer; or

And a particle swarm optimizer.

5. Method according to one of claims 1 to 3, characterized in that the first state relates to a vehicle state, a vehicle software configuration and/or hardware configuration, a current driving scenario and/or a current positioning state.

6. The method of claim 5, wherein the first state comprises:

the vehicle speed is greater than a predetermined first threshold; or

When the vehicle is in a stopped state, the difference between the stored latest position data and the current GPS position data is less than a predetermined second threshold value.

7. The method of claim 3, wherein the second state comprises:

determining, by means of the optimizer, that the running time of the position data is greater than a predetermined third threshold value; and/or

The certainty, e.g. covariance, of the position data determined by means of the optimizer is below a predetermined fourth threshold; and/or

The vehicle speed is below a predetermined fifth threshold.

8. The method of claim 3, wherein when the vehicle is in a stopped condition,

acquiring detection data by means of a sensor device, for example a camera, detecting the traffic light and identifying the status of the traffic light, and

if the detection data, for example, the recognized states indicate: there is sufficient time for the particle filter to operate, then the second state is satisfied.

9. Method for vehicle localization, in particular according to claim 1, characterized in that it comprises:

-determining first position data of the vehicle by means of a particle filter;

-determining second position data of the vehicle by means of the optimizer;

-evaluating the first location data and the second location data;

-ascertaining a difference between the first position data and the second position data;

-determining whether the difference is larger than a predetermined sixth threshold, and if so, adjusting a parameter of the particle filter, e.g. increasing the number of particles of the particle filter.

10. An apparatus for vehicle localization, the apparatus comprising:

a particle filter module configured for determining position data of the vehicle by means of the particle filter;

an optimizer module configured for determining position data of the vehicle by means of the optimizer;

an analysis module configured to ascertain whether a predetermined condition is satisfied and to activate the particle filter module and/or the optimizer to determine the position data in the predetermined condition.

11. The apparatus of claim 10, wherein the analysis module is configured to ascertain:

whether a predetermined first condition is satisfied, and if the predetermined first condition is satisfied, the analysis module causes: the optimizer is activated to determine the position data,

preferably, "activating the optimizer to determine position data" comprises switching from determining position data by means of the particle filter to determining position data by means of the optimizer, wherein the optimizer performs positioning in dependence on the position data from the particle filter, preferably the particle filter module communicates the latest position data determined by the particle filter before the switching to the optimizer module as initial position data of the optimizer after the switching; and/or

Whether a predetermined second condition is satisfied, and if the predetermined second condition is satisfied, the analysis module causes: switching from determining the position data by means of the optimizer to determining the position data by means of the particle filter; and/or

Whether a predetermined third condition is satisfied, and if the predetermined third condition is satisfied, the analysis module causes: activating a particle filter to determine first position data of the vehicle and concurrently activating an optimizer to determine second position data of the vehicle; evaluating the first location data and the second location data; ascertaining a difference between the first location data and the second location data; and judging whether the difference value is larger than a preset sixth threshold value, and if so, adjusting the parameters of the particle filter, such as increasing the particle number of the particle filter.

12. The apparatus of claim 11, wherein the analysis module is configured to:

acquiring a vehicle speed and determining whether the vehicle speed is greater than a predetermined first threshold, and if so, ascertaining that a predetermined first condition is satisfied; and/or

Ascertaining a difference between the stored up-to-date location data and the current GPS location data and determining whether the difference is less than a predetermined second threshold, and if so, ascertaining that a predetermined first state is satisfied; and/or

Ascertaining a difference between the position data determined by means of the particle filter and the position data determined by means of the optimizer and determining whether the difference is greater than or equal to a predetermined sixth threshold and, if so, ascertaining that a predetermined third state is satisfied; and/or

Ascertaining a running time of the determination of the position data by means of the optimizer and determining whether the running time is greater than a predetermined third threshold value, and if so ascertaining that a predetermined second state is satisfied; and/or

Ascertaining a certainty, e.g. a covariance, of the position data determined by means of the optimizer and determining whether the certainty is below a predetermined fourth threshold value, and if so ascertaining that a predetermined second state is satisfied; and/or

Acquiring a vehicle speed and determining whether the vehicle speed is below a predetermined fifth threshold, and if so, ascertaining that a predetermined second condition is satisfied; and/or

When the vehicle is in a stopped state, detection data from a sensing device, for example, detection data from a camera detecting a traffic light, is acquired, and it is ascertained whether the detection data indicates: there is sufficient time for operating the particle filter and, if so, ascertaining that a predetermined second state is satisfied.

13. An apparatus for vehicle localization, comprising:

one or more processors; and

one or more memories configured to store a series of computer-executable instructions and computer-accessible data associated with the series of computer-executable instructions,

wherein the series of computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the method of any one of claims 1-9.

14. A computer-readable storage medium having stored thereon a series of computer-executable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform the method of any of claims 1-9.

15. A vehicle, characterized in that it comprises a device according to one of claims 10 to 13.

Technical Field

The present invention relates to the field of automated driving, in particular to a method for vehicle localization, a device for vehicle localization and a vehicle.

Background

Autonomous driving is a major subject of current vehicle research. The precondition for autonomous driving is the definition of the road network on which the vehicle is traveling and the sensing of the environment surrounding the vehicle, so that the road network concerned and objects and other traffic participants in the surrounding environment can be identified. One approach is to use cameras and lidar to acquire data for the road network and to sense the distance of objects around the vehicle.

Currently, as for the classification of automatic driving, there is a general international acceptance of the standard of SAE (society of automotive engineers) classified into six grades L0-L5. Level L0, meaning fully manual, the device provides at most some auxiliary warnings and signals, such as radar warning when backing a car, distance warning when driving a car; l1 has some transverse or longitudinal auxiliary function to intervene in the driving operation, which can be called auxiliary driving, such as adaptive cruise, automatic emergency braking, etc., and the device starts to have active control action on the vehicle; the L2 device enables automatic driving of the vehicle in both lateral and longitudinal directions, but the driver is constantly attentive and ready to take over driving of the vehicle. The automated driving of L3 enables a high degree of machine operation, the driver can completely abandon the manoeuvre and only in a few cases need to take over the car; there is a large gap between L3 and L4, i.e., the steering wheel can be completely eliminated. The L3 device needs to consider human-machine coordination, switching between human operation and machine operation, and the L4 does not consider human intervention vehicle operation. Full intelligence of the road vehicle is achieved by the highest L5.

The vehicle position can be roughly located by using the GPS, but the GPS has a deviation of several meters, and the large deviation cannot be borne during automatic driving. With the development of automatic driving technology, higher requirements are also put on the accuracy and the efficiency of positioning of the vehicle.

Disclosure of Invention

It is therefore an object of the present invention to provide a method, a device and a vehicle which enable an improved automatic driving of the vehicle.

According to a first aspect of the present invention, there is provided a method for vehicle localization, the method comprising:

-determining position data of the vehicle by means of a particle filter;

-ascertaining whether a predetermined first state is fulfilled;

-activating an optimizer to determine the position data if a predetermined first state is fulfilled, wherein the optimizer performs the positioning in dependence of the position data from the particle filter.

The method and the device for vehicle positioning according to the invention can be flexibly adjusted, for example, an adjustment algorithm, etc., to adapt to different application scenarios. In addition, the method and the device for positioning the vehicle can reduce the calculation load on the premise of keeping better positioning accuracy.

In some embodiments, the "the optimizer performing a localization in dependence on the position data from the particle filter" comprises: the latest position data determined by the particle filter is set as the initial position data of the optimizer.

In some embodiments, "activating the optimizer to determine position data" comprises "switching from determining position data by means of the particle filter to determining position data by means of the optimizer", preferably, after switching, ascertaining whether a predetermined second state is satisfied, if the predetermined second state is satisfied, switching from determining position data by means of the optimizer to determining position data by means of the particle filter.

In some embodiments, the optimizer comprises:

a gradient descent optimizer;

a gradient ascent optimizer; or

And a particle swarm optimizer.

In some embodiments, the first state is associated with a vehicle state, a vehicle software configuration and/or a hardware configuration, a current driving scenario, and/or a current location state.

In some embodiments, the first state comprises:

the vehicle speed is greater than a predetermined first threshold; or

When the vehicle is in a stopped state, the difference between the stored latest position data and the current GPS position data is less than a predetermined second threshold value.

In some embodiments, the second state comprises:

determining, by means of the optimizer, that the running time of the position data is greater than a predetermined third threshold value; and/or

The certainty, e.g. covariance, of the position data determined by means of the optimizer is below a predetermined fourth threshold; and/or

The vehicle speed is below a predetermined fifth threshold.

In some embodiments, when the vehicle is in a stopped condition,

acquiring detection data by means of a sensor device, for example a camera, detecting the traffic light and identifying the status of the traffic light, and

if the detection data, for example, the recognized states indicate: there is sufficient time for the particle filter to operate, then the second state is satisfied.

In some embodiments, the method comprises:

-determining first position data of the vehicle by means of a particle filter;

-determining second position data of the vehicle by means of the optimizer;

-evaluating the first location data and the second location data;

-ascertaining a difference between the first position data and the second position data;

-determining whether the difference is larger than a predetermined sixth threshold, and if so, adjusting a parameter of the particle filter, e.g. increasing the number of particles of the particle filter.

According to a second aspect of the present invention, there is provided an apparatus for vehicle localization, the apparatus comprising:

a particle filter module configured for determining position data of the vehicle by means of the particle filter;

an optimizer module configured for determining position data of the vehicle by means of the optimizer;

an analysis module configured to ascertain whether a predetermined condition is satisfied and to activate the particle filter module and/or the optimizer to determine the position data in the predetermined condition.

In some embodiments, an analysis module configured to ascertain:

whether a predetermined first condition is satisfied, and if the predetermined first condition is satisfied, the analysis module causes: the optimizer is activated to determine the position data,

preferably, "activating the optimizer to determine position data" comprises switching from determining position data by means of the particle filter to determining position data by means of the optimizer, wherein the optimizer performs positioning in dependence on the position data from the particle filter, preferably the particle filter module communicates the latest position data determined by the particle filter before the switching to the optimizer module as initial position data of the optimizer after the switching; and/or

Whether a predetermined second condition is satisfied, and if the predetermined second condition is satisfied, the analysis module causes: switching from determining the position data by means of the optimizer to determining the position data by means of the particle filter; and/or

Whether a predetermined third condition is satisfied, and if the predetermined third condition is satisfied, the analysis module causes: activating a particle filter to determine first position data of the vehicle and concurrently activating an optimizer to determine second position data of the vehicle; evaluating the first location data and the second location data; ascertaining a difference between the first location data and the second location data; and judging whether the difference value is larger than a preset sixth threshold value, and if so, adjusting the parameters of the particle filter, such as increasing the particle number of the particle filter.

In some embodiments, the analysis module is configured to:

acquiring a vehicle speed and determining whether the vehicle speed is greater than a predetermined first threshold, and if so, ascertaining that a predetermined first condition is satisfied; and/or

Ascertaining a difference between the stored up-to-date location data and the current GPS location data and determining whether the difference is less than a predetermined second threshold, and if so, ascertaining that a predetermined first state is satisfied; and/or

Ascertaining a difference between the position data determined by means of the particle filter and the position data determined by means of the optimizer and determining whether the difference is greater than or equal to a predetermined sixth threshold and, if so, ascertaining that a predetermined third state is satisfied; and/or

Ascertaining a running time of the determination of the position data by means of the optimizer and determining whether the running time is greater than a predetermined third threshold value, and if so ascertaining that a predetermined second state is satisfied; and/or

Ascertaining a certainty, e.g. a covariance, of the position data determined by means of the optimizer and determining whether the certainty is below a predetermined fourth threshold value, and if so ascertaining that a predetermined second state is satisfied; and/or

Acquiring a vehicle speed and determining whether the vehicle speed is below a predetermined fifth threshold, and if so, ascertaining that a predetermined second condition is satisfied; and/or

When the vehicle is in a stopped state, detection data from a sensing device, for example, detection data from a camera detecting a traffic light, is acquired, and it is ascertained whether the detection data indicates: there is sufficient time for operating the particle filter and, if so, ascertaining that a predetermined second state is satisfied.

According to a third aspect of the present invention, there is provided an apparatus for vehicle localization comprising:

one or more processors; and

one or more memories configured to store a series of computer-executable instructions and computer-accessible data associated with the series of computer-executable instructions,

wherein the series of computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the method of any one of claims 1-9.

According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a series of computer-executable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform a method according to any one of the embodiments of the present invention.

According to a fifth aspect of the invention, there is provided a vehicle, characterized in that the vehicle comprises an apparatus according to any one of the embodiments of the invention.

Drawings

Some examples of apparatus and/or methods are illustrated below with reference to the accompanying drawings, in which:

FIG. 1 illustrates an exemplary flow chart of a method for vehicle localization;

FIG. 2 illustrates another exemplary flow chart of a method for vehicle localization;

FIG. 3 illustrates an exemplary block diagram of an apparatus for vehicle localization.

Detailed Description

The present disclosure will now be described with reference to the accompanying drawings, which illustrate several embodiments of the disclosure. It should be understood, however, that the present disclosure may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, the embodiments described below are intended to provide a more complete disclosure and to fully convey the scope of the disclosure to those skilled in the art. It is also to be understood that the embodiments disclosed herein can be combined in various ways to provide further additional embodiments.

It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. All terms (including technical and scientific terms) used herein have the meaning commonly understood by one of ordinary skill in the art unless otherwise defined. Well-known functions or constructions may not be described in detail for brevity and/or clarity.

Herein, the term "a or B" includes "a and B" and "a or B" rather than exclusively including only "a" or only "B" unless otherwise specifically stated.

The term "exemplary" means "serving as an example, instance, or illustration" herein. Any implementation exemplarily described herein is not necessarily to be construed as preferred or advantageous over other implementations. Furthermore, the disclosure is not limited by any expressed or implied theory presented in the preceding technical field, background, brief summary or the detailed description.

In addition, "first," second, "and like terms may also be used herein for reference purposes only, and" first, "" second "may also refer to a plurality of" first, "" second. For example, the terms "first," "second," and other such numerical terms referring to structures or elements do not imply a sequence or order unless clearly indicated by the context.

It will be further understood that the terms "comprises/comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Unless otherwise defined, all terms (including technical and scientific terms) are used herein in their ordinary meaning in the art to which examples pertain.

It should be noted that: the order of the method steps herein may be flexibly configured, with steps labeled with numbers only for convenience of description and not for limitation.

In the automatic driving technology, a high-precision positioning technology is an extremely critical technology. As autopilot technology evolves, various forms of location technology have been developed, which may be based on different algorithms, different processing pipelines, different hardware, and/or different legal regulations. Each positioning technique may have its own application scenarios and technical effects.

The method and the device for vehicle positioning according to the invention can be flexibly adjusted, for example, an adjustment algorithm, etc., to adapt to different application scenarios. In addition, the method and the device for positioning the vehicle can reduce the calculation load on the premise of keeping better positioning accuracy.

Methods for vehicle positioning according to some embodiments of the present invention are set forth in further detail below.

FIG. 1 illustrates an exemplary flow chart of a method for vehicle localization. According to the invention, the method comprises:

step 100: determining position data of the vehicle by means of a particle filter;

step 160: ascertaining whether a predetermined first state is satisfied;

step 200: if a predetermined first state is met, an optimizer is activated to determine position data, wherein the optimizer performs positioning in dependence on the position data from the particle filter.

In the present context, the vehicle may be an autonomous vehicle (also referred to as a main vehicle or a self-vehicle, an ego car), i.e. a mobile conveyance with autonomous driving capability, which may be a car, a passenger car, a truck, a van, a train, a ship, a motorcycle, a tricycle, or other mobile conveyance.

The particle filter means: the method is characterized in that a group of random samples which are propagated in a state space are searched to approximately represent a probability density function, the mean value of the samples is used for replacing integral operation, and then the minimum variance estimation process of the system state is obtained.

The particle filter is an implementation of a bayesian filter or a markov positioning filter. A particle filter may generally comprise four steps: the method comprises an initialization step, a prediction step, a particle weight updating step and a resampling step.

In an initialization step, N particles surrounding the GPS positioning data, for example with a gaussian distribution, can be derived from the GPS positioning data.

In the prediction step, a motion manipulation may be applied to the N particles. In some embodiments, the motion manipulation may be derived from a wheel speed sensor or an inertial measurement unit IMU. In some embodiments, the motion manipulation may also be derived from the predicted results of a multiple degree of freedom (e.g., seven degree of freedom) full vehicle model.

In the particle weight updating step, the degree of matching, referred to as the weight, is measured based on the degree of matching between the actual measurement and the predicted measurement. In other words, the weight means how close the actual measurement of the particle is to the predicted measurement. In the particle filter, the larger the particle weight, the higher the survival probability. In other words, the probability of survival for each particle is proportional to the weight.

In the resampling step, the resampling technique is used to randomly extract N new particles from the old particles and perform permutation according to the weight proportion. After resampling, the heavier particles may stay and other particles may disappear. The particles are clustered in regions where the posterior probability is relatively high.

The particle filter may continue to update the loop iteration until it converges to an optimized value as the actual position of the vehicle. In some embodiments, the particle filter has the advantage of accurate localization and a high probability of being able to converge to a global optimum. Furthermore, in some embodiments, the particle filter is easy to program and flexible. Nevertheless, the particle number of the particle filter has a closer relationship with the final positioning accuracy, and as the particle number increases, the calculation amount of the update loop iteration process is larger, which increases the calculation load of the positioning system to a certain extent. Therefore, the particle filter may also be associated with a large computational load, with high requirements on computation time and computation configuration, such as processor performance and number of processors.

In machine learning, there are many optimization methods (optimizers) that attempt to find the optimal solution for the model. In general, the optimizer may include: a gradient descent optimizer (including a random gradient descent optimizer), a gradient ascent optimizer (including a random gradient ascent optimizer), and a particle swarm optimizer. Taking the gradient descent optimizer as an example, the core of the gradient descent optimizer is to minimize the objective function J (θ), where θ is a parameter of the model. In each iteration of the gradient descent optimizer, for each variable, the corresponding parameter value is updated in the opposite direction of the gradient of the variable according to the objective function. Wherein the learning rate η determines the number of iterations for which the function reaches a (local) minimum. In other words, on the hyperplane of the objective function, the slope decreases until a "valley" is encountered. The computational load of the optimizer is relatively low compared to particle filters, and the computational time and computational configuration requirements are reduced. However, the optimizer may converge to a local optimum, rather than a global optimum. In other words, the probability of the optimizer converging to the global optimum is relatively low.

The method for vehicle localization according to the invention combines the advantages of particle filters and optimizers, while at least partly avoiding the disadvantages of both, thereby reducing the computational load while maintaining a good localization accuracy.

In some embodiments, an optimizer is activated to determine position data when a predetermined first condition is satisfied. Activating the optimizer may mean switching from determining the position data by means of the particle filter to determining the position data by means of the optimizer. At this time, the latest position data determined by the particle filter is set as the initial position data of the optimizer. The latest position data determined on the basis of the particle filter can be considered relatively accurate and can be converged to an optimum, in particular a global optimum, more quickly when the optimizer takes this as initial position data. In other embodiments, activating the optimizer may mean determining the position data by means of the optimizer in parallel with determining the position data by means of the particle filter (see the detailed description of fig. 2 for this).

According to the present invention, the predetermined first state for activating the optimizer may be related to a vehicle state, a vehicle hardware/software configuration, a current driving scenario and/or a current positioning state, etc. For example, the first state may be related to a vehicle speed, and it is ascertained that the first state is fulfilled when the vehicle speed is greater than a predetermined first threshold value, for example 20 km/h. This is advantageous in that as the vehicle speed increases, the computational load that the vehicle needs to bear per unit time increases rapidly, and activating the optimizer, in particular switching from determining the position data by means of the particle filter to determining the position data by means of the optimizer, can effectively reduce the computational load of the vehicle.

Furthermore, when the vehicle is in a stopped state, for example, when temporarily parking (red light) or when parking for a long time (parking lot), the latest position data is stored in the relevant memory of the vehicle. When a restart is required, the stored up-to-date position data may be considered accurate when the vehicle remains stationary during a stop, for example when the difference between the stored up-to-date position data and the current GPS position data is less than a predetermined second threshold value (e.g. 0.1m), so that the first condition may be considered satisfied and the optimizer may be directly activated to determine the position data.

In some embodiments, after switching from determining the position data by means of the particle filter to determining the position data by means of the optimizer, it is necessary to ascertain whether a predetermined second state is satisfied, and if the predetermined second state is satisfied, then switching from determining the position data by means of the optimizer back to determining the position data by means of the particle filter. The second state may relate to a vehicle state or an operation time and positioning certainty of the optimizer.

In some embodiments, when the running time of the determination of the position data by means of the optimizer is greater than a predetermined third threshold (e.g. 10 minutes or 1 hour), then the second state is considered to be satisfied, so that a switch is made from the determination of the position data by means of the optimizer back to the determination of the position data by means of the particle filter. This is advantageous because as the optimizer run time increases, the cumulative error generated by the optimizer also increases, thereby affecting the accuracy of the positioning.

In some embodiments, a certainty, e.g. a covariance, of the position data determined by means of the optimizer may be ascertained, and when the certainty is below a predetermined fourth threshold value, then the second state is considered to be satisfied, so that a switch is made from determining the position data by means of the optimizer back to determining the position data by means of the particle filter.

In some embodiments, when the vehicle speed is below a predetermined fifth threshold (e.g. 10km/h), then the second condition is considered satisfied, switching from determining the location data by means of the optimizer back to determining the location data by means of the particle filter.

In some embodiments, the traffic light may be detected by means of a sensing device, such as a camera, when the vehicle is in a stopped state, and the state of the traffic light is recognized, if the recognized state indicates: there is sufficient time for the particle filter to operate, then the second state is satisfied. For example, when a yellow light is recognized from traffic lights photographed by a camera, it is judged that the second state is not satisfied. For example, when it is recognized from the traffic light photographed by the camera that the red light is left for, for example, less than 3 seconds, it is judged that the second state is not satisfied.

FIG. 2 illustrates another exemplary flow chart of a method for vehicle localization. The method for vehicle positioning also combines the advantages of particle filters and optimizers, while at least partially avoiding the disadvantages of both, thereby reducing the computational load while maintaining good positioning accuracy. According to the invention, the method comprises:

step 100': determining first position data of the vehicle by means of a particle filter;

step 200': determining second position data of the vehicle by means of the optimizer;

step 300': evaluating the first position data and the second position data, finding a difference between the first position data and the second position data, determining whether said difference is larger than a predetermined sixth threshold, and if so, adjusting a parameter of the particle filter (indicated by the dashed line), e.g. increasing the number of particles of the particle filter.

In some embodiments, to reduce the computational load of the particle filter, the particle filter may be run at a reduced number of particles at a particular stage, e.g., after a good initial positioning is obtained (e.g., as in step 100'). To ensure reliable positioning, the optimizer may be run in parallel with the particle filter (e.g., as in step 200') for a certain period of time or periodically (e.g., every unit time, such as 1 minute or 10 minutes). In the parallel operation stage, when it is determined that the difference between the first position data obtained by the particle filter and the second position data obtained by the optimizer is greater than a predetermined sixth threshold, for example, 0.1m, the parameters of the particle filter may be adjusted, for example, the number of particles of the particle filter may be increased, so as to obtain a more accurate positioning result.

An apparatus for vehicle localization in accordance with some embodiments of the present invention is set forth in further detail below. FIG. 3 illustrates an exemplary block diagram of an apparatus for vehicle localization. The vehicle 10 includes an onboard sensor 12 and a device 14 for vehicle localization. The in-vehicle sensors 12 may communicate their own sensed real-time vehicle surroundings data to the device 14. As shown in fig. 3, the apparatus 14 includes a storage device 16 and a processing device 18. The processing device 18 may include one or more processors (e.g., CPUs and/or GPUs). The storage device 16 may store detection data (vehicle speed, GPS, camera data, lidar data, etc.) of the in-vehicle sensor.

It should be understood that the processing device 18 may be configured as any device having data processing and analysis functionality including a processor. For example, the processing device 18 may be configured as one or more processors, or the processing device 18 may be configured as a computer, server, or even other intelligent handheld device. The processor may be connected to the memory module via an interconnection bus. The memory modules may include main memory, read only memory, and mass storage devices, such as various disk drives, tape drives, and the like. A "processor" or "controller" is not limited to a CPU or GPU, but may include Digital Signal Processor (DSP) hardware, network processors, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), etc. The storage device 16 may be a Read Only Memory (ROM), a Random Access Memory (RAM), and a non-volatile memory for storing software. Other hardware, conventional and/or custom, may also be included.

The processing device 18 may include a plurality of functional modules. For example, processing device 18 may include a particle filter module 20, an optimizer module 22, and an analysis module 24. The particle filter module may be configured for determining position data of the vehicle by means of the particle filter; the optimizer module may be configured for determining position data of the vehicle by means of the optimizer; the analysis module may be configured to ascertain whether a predetermined condition is satisfied and to activate the particle filter module and/or the optimizer to determine the position data at the predetermined condition. For example, the analysis module may send an activation instruction to the filter module and/or the optimizer module to activate the filter module and/or the optimizer.

In some embodiments, the analysis module may be configured to ascertain whether a predetermined first condition is satisfied, and if the predetermined first condition is satisfied, the analysis module causes: an optimizer is activated to determine position data. For example, the analysis module may send an activation instruction to the optimizer module to activate the optimizer module.

In some embodiments, "activating the optimizer to determine position data" may comprise switching from determining position data by means of the particle filter to determining position data by means of the optimizer. The optimizer may perform the positioning in dependence on position data from the particle filter, preferably the particle filter module communicates the latest position data determined by the particle filter before the switch to the optimizer module as initial position data of the optimizer after the switch. The latest position data determined on the basis of the particle filter can be considered relatively accurate and can be converged to an optimum, in particular a global optimum, more quickly when the optimizer takes this as initial position data.

In some embodiments, the analysis module may be configured to ascertain whether a predetermined second condition is satisfied, and if the predetermined second condition is satisfied, the analysis module causes: switching from determining the position data by means of the optimizer to determining the position data by means of the particle filter. For example, the analysis module may send an activation instruction to the particle filter to activate the particle filter.

In some embodiments, the analysis module may be configured to ascertain whether a predetermined third condition is satisfied, and if the predetermined third condition is satisfied, the analysis module causes: activating a particle filter to determine first position data of the vehicle and concurrently activating an optimizer to determine second position data of the vehicle; evaluating the first location data and the second location data; ascertaining a difference between the first location data and the second location data; and judging whether the difference value is larger than a preset sixth threshold value, and if so, adjusting the parameters of the particle filter, such as increasing the particle number of the particle filter.

In some embodiments, the analysis module may be configured to obtain a vehicle speed and determine whether the vehicle speed is greater than a predetermined first threshold, and if so, ascertain that a predetermined first condition is satisfied.

In some embodiments, the analysis module may be configured to ascertain a difference between the stored up-to-date location data and the current GPS location data, and determine whether the difference is less than a predetermined second threshold, and if so, ascertain that a predetermined first condition is satisfied.

In some embodiments, the analysis module may be configured to ascertain a difference between the position data determined by means of the particle filter and the position data determined by means of the optimizer and to determine whether the difference is greater than or equal to a predetermined sixth threshold and, if so, to ascertain that a predetermined third state is satisfied.

In some embodiments, the analysis module can be configured to ascertain a running time for determining the position data by means of the optimizer and to determine whether the running time is greater than a predetermined third threshold value, and if so, to ascertain that a predetermined second state is satisfied.

In some embodiments, the analysis module may be configured for ascertaining a certainty, e.g. a covariance, of the location data determined by means of the optimizer and determining whether the certainty is below a predetermined fourth threshold value, and if so, ascertaining that a predetermined second state is satisfied.

In some embodiments, the analysis module may be configured to obtain the vehicle speed and determine whether the vehicle speed is below a predetermined fifth threshold, and if so, to ascertain that a predetermined second condition is satisfied.

In some embodiments, the analysis module may be configured to acquire detection data from a sensing device, such as a camera detecting a traffic light, while the vehicle is in a stopped state, to ascertain whether the detection data indicates: there is sufficient time for operating the particle filter and, if so, ascertaining that a predetermined second state is satisfied.

The functions of the various elements shown in the figures may be implemented in the form of dedicated hardware, such as a "signal provider", "signal processing unit", "processor", "controller", etc., as well as hardware capable of executing software in association with appropriate software. When provided by a processor, the functions may be provided by a dedicated processor, by a shared processor, or by a plurality of individual processors, some or all of which may be shared. However, the term "processor" or "controller" is by no means limited to hardware capable of executing only software, but may include Digital Signal Processor (DSP) hardware, network processors, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), Read Only Memories (ROMs) for storing software, Random Access Memories (RAMs) and non-volatile memories. Other hardware, conventional and/or custom, may also be included.

The block diagram may illustrate, for example, a high-level circuit diagram implementing the principles of the present disclosure. Similarly, flowcharts, state transition diagrams, pseudocode, and the like may represent various processes, operations, or steps which may be substantially represented in computer readable media and so executed by a computer or processor, whether or not such computer or processor is explicitly represented. The methods disclosed in the specification and claims may be implemented by a device having means for performing each respective action of the methods.

It is to be understood that the disclosure of various actions, processes, operations, steps or functions disclosed in the specification or claims are not to be interpreted as being in a particular order unless explicitly or implicitly indicated as such, for example, for technical reasons. Thus, the disclosure of multiple acts or functions does not limit the multiple acts or functions to a particular order unless such acts or functions are not interchangeable for technical reasons. Further, in some examples, a single action, function, process, operation, or step may include or be divided into multiple sub-actions, sub-functions, sub-processes, sub-operations, or sub-steps, respectively. Unless expressly excluded, such sub-actions can be included in, and part of, the disclosure of the individual action.

Although exemplary embodiments of the present disclosure have been described, it will be understood by those skilled in the art that various changes and modifications can be made to the exemplary embodiments of the present disclosure without substantially departing from the spirit and scope of the present disclosure. Accordingly, all changes and modifications are intended to be included within the scope of the present disclosure.