WO2022257310A1

WO2022257310A1 - Method and apparatus for estimating weight of vehicle

Info

Publication number: WO2022257310A1
Application number: PCT/CN2021/122796
Authority: WO
Inventors: 庄登祥; 王泽旭; 于宁; 薛晶晶
Original assignee: 阿波罗智联(北京)科技有限公司
Priority date: 2021-06-08
Filing date: 2021-10-09
Publication date: 2022-12-15
Also published as: CN113392518B; CN113392518A

Abstract

A method and apparatus for estimating the weight of a vehicle, relating to the technical field of computers and in particular, to the field of autonomous driving. The specific implementation solution is: obtaining a rim torque value of a vehicle according to the current speed of the vehicle and a control instruction for the vehicle by using a speed-instruction-rim torque mapping relationship (S110); and estimating the weight of the vehicle on the basis of a vehicle longitudinal dynamics equation by using the obtained rim torque value (S120).

Description

Method and apparatus for estimating vehicle weight

This application claims the priority of the Chinese patent application with application number 202110650457.7 filed on June 8, 2021, the entire contents of which are incorporated in this application by reference.

technical field

The present disclosure relates to the field of computer technology, specifically to the field of automatic driving, and in particular to a method and device for estimating vehicle weight.

Background technique

With the development of vehicle automatic driving technology, the requirements for the effect of vehicle automatic control are gradually increasing. Compared with small cars, heavy vehicles include self-driving buses, self-driving trucks, etc., and the range of weight changes is relatively large. The weight change to full load can even reach 300%. Vehicle weight is a key parameter for automatic driving software to perform vehicle dynamics control, parking gear decision-making, parking and parking, and vehicle operating status monitoring. If the vehicle weight is used to properly regulate the automatic driving control software and monitoring software, it will further improve the performance of the vehicle. safety, comfort and power.

Using hardware sensors to measure vehicle weight is expensive and has problems with its service life; using software algorithms can directly estimate vehicle weight, which is very economical and convenient. In the technique of estimating the vehicle weight using a software algorithm, wheel torque parameters of the vehicle need to be provided to estimate the vehicle weight. If the system cannot provide a wheel torque signal, the weight estimation software will not work.

Contents of the invention

The present disclosure provides a method, device, device and storage medium for estimating the weight of a vehicle.

According to a first aspect, there is provided a method of estimating the weight of a vehicle, the method comprising: using a speed-command-wheel torque mapping relationship to obtain the and estimating the weight of the vehicle based on the vehicle longitudinal dynamics equation using the obtained wheel torque value.

According to a second aspect, there is provided an apparatus for estimating the weight of a vehicle, the apparatus comprising: a wheel torque value obtaining module configured to use speed-command - a wheel side torque mapping relationship obtains a wheel side torque value of the vehicle; and a weight estimation module configured to use the obtained wheel side torque value to estimate the weight of the vehicle based on a vehicle longitudinal dynamics equation.

According to a third aspect, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor , the instructions are executed by the at least one processor, so that the at least one processor can execute the above method.

According to a fourth aspect, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the above method.

According to a fifth aspect there is provided a computer program product comprising a computer program which, when executed by a processor, implements the above method.

According to the method and apparatus for estimating vehicle weight of the present disclosure, the vehicle weight can be estimated more efficiently and accurately.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will be readily understood through the following description.

Description of drawings

The accompanying drawings are used to better understand the present solution, and do not constitute a limitation to the present disclosure. in:

FIG. 1 shows a flowchart of a method for estimating vehicle weight according to an embodiment of the present disclosure;

Fig. 2 shows a schematic diagram of a speed-command-wheel torque calibration table according to an embodiment of the present disclosure;

Fig. 3 shows a schematic diagram of determining a control command and a vehicle acceleration to be adopted in consideration of a control command delay and a filtering delay of the vehicle acceleration according to an embodiment of the present disclosure;

4 shows a flowchart of a method for obtaining wheel torque values of a vehicle using a speed-command-wheel torque mapping relationship;

Fig. 5 shows a schematic diagram of obtaining wheel torque values by performing linear interpolation in the speed-command-wheel torque calibration table;

FIG. 6 shows a flow chart of a method for estimating the weight of a vehicle based on vehicle longitudinal dynamics equations according to an embodiment of the present disclosure;

7 shows a flow chart of a method for estimating a road slope angle based on an Extended Kalman Filter (EKF) according to an embodiment of the present disclosure;

FIG. 8 shows a block diagram of an apparatus for estimating vehicle weight according to an embodiment of the present disclosure; and

FIG. 9 shows a block diagram of an example electronic device that may be used to implement embodiments of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the field of autonomous driving, vehicle weight estimation is performed by determining the vehicle weight as a function of the input-output time of the autonomous vehicle system. Vehicle weight estimation requires the creation of a mathematical model of the entire vehicle, where the vehicle weight is an important parameter in the mathematical model. Based on the input and output data of the system on the mathematical model, the vehicle weight is estimated using a specific estimation algorithm. If the system cannot provide wheel torque signals, the weight estimation algorithm will not work. In autonomous driving software, the wheel torque signal is the core signal of the vehicle chassis, and the core characteristic indicators of the vehicle chassis can be inferred from the wheel torque, so most suppliers of autonomous vehicle chassis tend not to provide the wheel torque signal .

FIG. 1 shows a flowchart of a method 100 for estimating vehicle weight according to an embodiment of the disclosure.

In step S110, according to the current speed of the vehicle and the control command for the vehicle, the wheel torque value of the vehicle is obtained using the speed-command-wheel torque mapping relationship.

In some embodiments, the speed-command-wheel torque mapping relationship may include a speed-command-wheel torque scaling table. In some embodiments, the speed-command-wheel torque calibration table may be predetermined according to previously collected vehicle control commands and vehicle sensory data corresponding to the vehicle control commands. For example, vehicle sensor data can be collected by vehicle sensors on a flat standard field, and the sensor data includes vehicle speed. A flat standard site may include a site with a ground slope of less than 0.1 degrees and a maximum length of the site that can accelerate linearly greater than 100m. In some embodiments, after the vehicle sensor data is collected, the speed-command-wheel torque calibration table can be prepared offline using data processing technology.

In step S120, the weight of the vehicle is calculated based on the vehicle longitudinal dynamics equation using the obtained wheel torque value. In some embodiments, the vehicle longitudinal dynamics equation may be created based on vehicle driving state data, and the vehicle driving state data may include at least one of the following: vehicle speed v, vehicle acceleration

Moment of inertia J, angular acceleration

and road slope angle β.

According to the embodiments of the present disclosure, the vehicle weight can be estimated more efficiently and accurately. Furthermore, according to embodiments of the present disclosure, vehicle weight may be estimated without wheel torque feedback signals.

In some embodiments, the vehicle longitudinal dynamics equation may be:

Among them, m represents the weight of the vehicle in kg,

is the derivative of the vehicle speed, that is, the vehicle acceleration, the unit is m/s ² ,

v is the vehicle speed in m/s,

J is moment of inertia, unit is kg·m ² ,

is the derivative of the vehicle's yaw rate, that is, the vehicle's angular acceleration, in rad/m ² ,

T _wheel is the wheel torque, the unit is N m,

r is the wheel rolling radius of the vehicle, in m,

That is, the equivalent drag coefficient, where ρ is the air resistance coefficient, A is the effective frontal area of the vehicle, C _D is the drag coefficient,

β is the slope angle of the road, the unit is rad,

μ is the coefficient of rolling resistance,

g is the gravitational acceleration, and the unit is m/s ² .

In some embodiments, the steering wheel judgment condition can be used when performing data processing on the above vehicle longitudinal dynamics equation, so

Correspondingly, the above equation (1) can be further simplified as:

In Equation (2), β _μ represents the ground friction resistance coefficient. Apart from this, other parameters in equation (2) have the same physical meaning as the same parameters in equation (1).

FIG. 2 shows a schematic diagram of a speed-command-wheelside torque calibration table according to an embodiment of the present disclosure.

As shown in Figure 2, the x-axis represents the vehicle speed in m/s. Vehicle speed may be obtained from vehicle sensors. The y-axis represents commands for controlling the vehicle (ie, control commands). For example, the control instruction may include a pedal instruction obtained by the user stepping on the accelerator pedal of the vehicle. In this case, the control command is expressed as a percentage opening of the accelerator pedal of the vehicle in %. The z-axis represents the wheel torque value, and the unit is N·m.

In some embodiments, the instructions may be divided into 10-20 equal parts according to the maximum-minimum range, so as to obtain 10-20 instructions evenly spaced. According to these commands, the vehicle is controlled to accelerate from stationary to the highest speed or decelerate from the highest speed to stationary, so as to obtain the mapping relationship between speed, command and wheel torque, that is, the speed-command-wheel torque mapping relationship. In the case that the command is expressed as the percentage opening of the vehicle accelerator pedal, the speed-command-wheel torque mapping relationship can be expressed as the speed-command-wheel torque calibration table shown in Figure 2, that is, speed- Pedal opening-wheel torque calibration table.

According to the embodiments of the present disclosure, sensory data collection and speed-command-wheel torque calibration table creation can be performed offline, while vehicle weight estimation can be performed online. When performing vehicle weight estimation in a real-time online manner, due to the delay of the control command and the filtering delay of the vehicle acceleration, and the delays of the two may be inconsistent, the vehicle acceleration collected in real time for the control command does not match the control command. , so it is necessary to consider the control command delay and the filtering delay of the vehicle acceleration to determine the control command and vehicle acceleration to be adopted.

FIG. 3 shows a schematic diagram of determining a control command and a vehicle acceleration to be adopted in consideration of a control command delay and a filtering delay of the vehicle acceleration according to an embodiment of the present disclosure.

FIG. 3 shows two cache queues, namely, a command (Cmd) cache queue Quene1 and an acceleration (Acc) cache queue Quene2. The lengths of the instruction cache queue Quene1 and the acceleration cache queue Quene2 are L1 and L2 respectively. L1 and L2 are calculated according to the delay of the control command and the filter delay of the vehicle acceleration, namely:

The cache queues Quene1 and Quene2 cache data in a first-in first-out manner. In Figure 3, the rightmost data in the buffer queues Quene1 and Quene2 is the latest data. Since the direct use of the latest data may cause a mismatch between the delayed control command and the delayed filtered acceleration data, therefore, according to the embodiment of the present disclosure, using the command cache queue Quene1 and the acceleration cache queue Quene2, the obtained first The L1 control command matches the L2 filtered acceleration data. Therefore, for the L1 th control instruction, using the L2 th filtered acceleration data as input data for performing vehicle weight estimation can obtain more accurate results.

According to some embodiments, the validity of the collected data can also be judged. For example, the validity of the collected data can be judged according to the condition: the actual steering wheel steering angle<the maximum steering wheel steering angle*3%. If the actual steering wheel steering angle satisfies the above conditions, then for the corresponding control command, the vehicle acceleration obtained by the above cache method, the vehicle speed obtained by the sensor and the road slope angle measurement value obtained by the sensor (if it exists) are used as valid data. use.

FIG. 4 shows a flowchart of a method for obtaining a wheel torque value of a vehicle using a speed-command-wheel torque mapping relationship.

In step S411, according to the current speed of the vehicle and the control command, determine the calibration interval to which the current speed belongs and the calibration range to which the control command belongs in the speed-command-wheel torque mapping relationship. In some embodiments, the speed-command-wheel torque mapping relationship may include a speed-command-wheel torque scaling table. In some embodiments, the speed-command-wheel torque scaling table may be expressed as a speed-pedal opening-wheel torque scaling table.

In step S412, according to the speed-command-wheel torque mapping relationship, based on the calibration range to which the current speed belongs and the calibration range to which the control command belongs, a plurality of wheel torque values corresponding to the determined calibration ranges are respectively obtained.

In step S413, a wheel torque value corresponding to the current speed of the vehicle and the control command is calculated according to the multiple wheel torque values.

According to the embodiments of the present disclosure, the method for obtaining the wheel torque value of the vehicle using the speed-command-wheel torque mapping relationship can omit the hardware sensor for measuring the vehicle weight while providing accurate wheel torque values.

In some embodiments, the wheel torque value can be obtained by performing linear interpolation in the speed-command-wheel torque calibration table according to the current speed of the vehicle and the control command.

FIG. 5 shows a schematic diagram of obtaining wheel torque values through linear interpolation in the speed-command-wheel torque calibration table.

In FIG. 5 , v represents the current speed of the vehicle, Cmd represents the control command, and T _wheel represents the wheel torque value corresponding to the current speed v and the control command Cmd. As shown in Figure 5, in the speed-command-wheel torque calibration table, according to the current speed v of the vehicle and the control command Cmd, find the calibration interval [v _t-1 , v _t ], [Cmd _t-1 , Cmd _t ], where v _t and v _t-1 are the speeds in the calibration interval to which the current speed belongs, and Cmd _t and Cmd _t-1 are the speeds in the calibration interval to which the control command belongs. Control instruction.

As shown in Fig. 5, in the speed-command-wheel torque calibration table, the four points around the point represented as {v, Cmd} correspond to (v _t-1 , Cmd _t-1 ), ( v _t-1 , Cmd _t ), (v _t , Cmd _t-1 ), (v _t , Cmd _t ). After that, find the calibration wheel edges corresponding to (v _t-1 , Cmd _t-1 ), (v _t-1 , Cmd _t ), (v _t , Cmd _t-1 ), (v _t , Cmd _t ) respectively Torque values T ₁ , T ₂ , T ₃ , T ₄ . Then the wheel torque value T _wheel to be calculated is obtained by the following formula:

T _wheel =(T ₁ ζ ₁ +T ₂ (1-ζ ₁ ))ζ ₂ +(T ₃ ζ ₁ +T ₄ (1-ζ ₁ ))(1-ζ ₂ )...(7)

According to embodiments of the present disclosure, hardware sensors for measuring vehicle weight can be omitted while providing accurate wheel torque values.

FIG. 6 shows a flow chart of a method for estimating the weight of a vehicle based on vehicle longitudinal dynamics equations according to an embodiment of the present disclosure.

In step S621, a least squares recursive equation (RLS) with a forgetting factor is created for the vehicle longitudinal dynamics equation. Here, the vehicle longitudinal dynamics equation may be the equation shown in equation (1) or (2) above.

In step S622, the weight of the vehicle is obtained by iterative calculation using the least squares recursive equation (RLS) with a forgetting factor.

In some embodiments, the least squares recurrence equation (RLS) with forgetting factor can be expressed as:

in,

(m is the weight of the vehicle, for example, the initial value of m can be set according to the vehicle model, brand, etc.),

is the variable to be estimated in the RLS algorithm, k represents the kth iterative calculation,

y(k) is the quantity to be observed by the RLS algorithm, here it represents the vehicle acceleration observed for the kth time

for

The transposition of , where T _wheel is the wheel torque of the vehicle, r is the wheel rolling radius of the vehicle, v is the vehicle speed,

L(k) represents the gain calculated for each iteration,

P(k) represents the intermediate variable calculated by RLS, and

λ is the forgetting factor and 0<λ<1. In some embodiments, λ is set to 0.97.

According to an embodiment of the present disclosure, the weight of the vehicle can be estimated more accurately by using the RLS algorithm.

In addition, as shown in the vehicle longitudinal dynamics equation described above, the road slope angle β is a key parameter for estimating the vehicle weight, which is highly coupled with the vehicle weight. If the slope angle parameter error reaches 20%, then the weight estimation result error will reach 50%. In some embodiments, the road slope angle β can be obtained by vehicle sensors. In other embodiments, the road slope angle β can be estimated based on an Extended Kalman Filter (EKF).

A method of estimating the road slope angle β based on the Extended Kalman Filter (EKF) will be described in detail below.

FIG. 7 shows a flowchart of a method 700 for estimating road slope angle based on Extended Kalman Filter (EKF) according to an embodiment of the present disclosure.

In step S710, the road slope angle is estimated according to the EKF system state equation and the EKF system measurement equation. In some embodiments, the system state equation for estimating the road slope angle is:

in,

Indicates the derivative of the road slope angle β derivative. Besides, other parameters in equation (11) have the same physical meanings as the same parameters in equation (1).

Assuming that the system noise vector and measurement noise vector of EKF are W and V respectively, and W and V can be independent Gaussian white noise with zero mean value, the system state equation of EKF is obtained as:

In addition, the system measurement equation to obtain EKF is:

In the above equation (12), v(k) and v(k-1) are the vehicle speeds calculated by the kth iteration and the k-1th iteration respectively, and Δt represents the iterative calculation cycle when the EKF is actually used, β(k), β(k-1), β(k-2) and β(k-3) are calculated for the k-th, k-1, k-2, and k-3 iterations respectively Out of the road slope angle. In some embodiments, if there is a road gradient angle obtained by the vehicle sensor, the initial values of β(k), β(k-1), β(k-2) and β(k-3) are set to be determined by Road slope angle obtained by vehicle sensors. If there is no road gradient angle obtained by the vehicle sensor, the initial values of β(k), β(k−1), β(k−2), and β(k−3) are set to 0. Besides, the other parameters in equation (12) have the same physical meaning as the same parameters in equation (1).

In the above equation (13), z(k) represents the vehicle speed to be measured by the EKF, H is the measurement matrix, when there is the road slope angle obtained by the sensor, H=[1 1], when there is no H＝[1 0] at road slope angle.

According to one embodiment, the method 700 for estimating road slope angle based on Extended Kalman Filter (EKF) may further include step S720.

In step S720, when the EKF is used for iterative calculation, the EKF is updated by using the time update equation and the measurement update equation of the EKF. Specifically, the state-space expression of the EKF is obtained by combining Equation (12) and Equation (13):

Among them, x(k)=[v(k), β(k)]', f(x(k-1)) is the process state nonlinear function, f(x(k-1)) represents the equation (12 ) in the expression

EKF needs to linearize f(x(k-1)) when performing iterative calculations, so each update needs to calculate the Jacobian (Jacobian) matrix F(k):

Assuming that the system noise covariance matrix of EKF is Q, the time update equation of EKF is obtained as:

Assuming that the measurement noise covariance matrix of the EKF is R, the measurement update equation of the EKF is obtained as:

Among them, x(k)=[v(k), β(k)]' represents the system state of EKF. In addition, when setting the initial parameters of the EKF, set P(0) to 10, and set the R matrix to

And the Q matrix is set according to the noise characteristics of the actual sensing data.

According to the embodiments of the present disclosure, estimating the road slope angle based on EKF can provide accurate road slope angle while reducing the cost of hardware sensors for measuring the road slope angle.

According to the embodiments of the present disclosure, sensory data collection and speed-command-wheel torque calibration table creation can be performed offline, while vehicle weight estimation and road gradient angle estimation can be performed online. Based on the speed-command-wheel torque calibration table, wheel torque information can be provided for vehicle weight estimation and road gradient angle estimation. In addition, vehicle weight estimation and road slope angle estimation are iteratively computed independently and in parallel during each vehicle duty cycle. In each vehicle working cycle, the estimated weight value of the vehicle weight is used as an internal parameter for the next calculation cycle of the road slope angle estimation. Similarly, the road slope angle estimated for the road slope angle is used as an internal parameter for the next calculation cycle of the vehicle weight estimation.

Embodiments according to the present disclosure can provide accurate vehicle weight and road slope angle information. In the energy optimization application of large heavy-duty vehicles, accurate weight and slope angle information can support the vehicle controller to allocate energy reasonably, reduce energy consumption, and greatly increase the cruising range of autonomous vehicles. In addition, the embodiments according to the present disclosure can replace the vehicle weight sensor with the same precision, greatly reducing the hardware cost.

FIG. 8 shows a block diagram of an apparatus 800 for estimating vehicle weight according to an embodiment of the present disclosure.

As shown in FIG. 8 , an apparatus 800 for estimating vehicle weight includes a wheel torque value obtaining module 810 and a weight estimating module 820 .

The wheel side torque value obtaining module 810 is configured to obtain the wheel side torque value of the vehicle according to the current speed of the vehicle and the control command for the vehicle using a speed-command-wheel side torque mapping relationship. In some embodiments, the speed-command-wheel torque mapping relationship may include a speed-command-wheel torque scaling table. In some embodiments, the speed-command-wheel torque calibration table may be predetermined according to previously collected vehicle control commands and vehicle sensory data corresponding to the vehicle control commands.

The weight estimation module 820 is configured to estimate the weight of the vehicle based on the vehicle longitudinal dynamics equation using the obtained wheel torque values. In some embodiments, the vehicle longitudinal dynamics equation may be created based on vehicle driving state data, and the vehicle driving state data may include at least one of the following: vehicle speed v, vehicle acceleration

Moment of inertia J, angular acceleration

and road slope angle β.

In some embodiments, the wheel edge torque value obtaining module 810 may include a first submodule, a second submodule and a third submodule. The first sub-module determines the calibration interval to which the current speed belongs and the calibration interval to which the control command belongs in the speed-command-wheel torque mapping relationship according to the current speed of the vehicle and the control command. The second sub-module obtains a plurality of wheel torque values corresponding to the determined calibration intervals according to the speed-command-wheel torque mapping relationship, based on the calibration interval to which the current speed belongs and the calibration interval to which the control command belongs. The third sub-module calculates the wheel torque value corresponding to the current speed of the vehicle and the control command according to the plurality of wheel torque values.

In some embodiments, the weight estimation module 820 may include a fourth submodule and a fifth submodule. A fourth submodule creates a least squares recurrence equation with a forgetting factor for the vehicle longitudinal dynamics equation. The fifth sub-module uses the least square recursive equation with forgetting factor to perform iterative calculation to obtain the weight of the vehicle.

According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

FIG. 9 shows a schematic block diagram of an example electronic device 900 that may be used to implement embodiments of the present disclosure. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 9 , the device 900 includes a computing unit 901 that can execute according to a computer program stored in a read-only memory (ROM) 902 or loaded from a storage unit 908 into a random-access memory (RAM) 903. Various appropriate actions and treatments. In the RAM 903, various programs and data necessary for the operation of the device 900 can also be stored. The computing unit 901, ROM 902, and RAM 903 are connected to each other through a bus 904. An input/output (I/O) interface 905 is also connected to the bus 904 .

Multiple components in the device 900 are connected to the I/O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc. ; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.

The computing unit 901 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 901 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 executes the various methods and processes described above, such as a method for estimating the weight of a vehicle. For example, in some embodiments, a method for estimating vehicle weight may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 908 . In some embodiments, part or all of the computer program may be loaded and/or installed on the device 900 via the ROM 902 and/or the communication unit 909. When the computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of the method for estimating vehicle weight described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured in any other suitable way (eg, by means of firmware) to execute the method for estimating the vehicle weight.

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

In the technical solution of the present disclosure, the acquisition, storage and application of the user's personal information involved are in compliance with relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good customs.

The specific implementation manners described above do not limit the protection scope of the present disclosure. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

A method of estimating vehicle weight comprising:

obtaining a wheel torque value of the vehicle using a speed-command-wheel torque mapping relationship based on the current speed of the vehicle and a control command for the vehicle; and

Using the obtained wheel torque values, the weight of the vehicle is estimated based on vehicle longitudinal dynamics equations.
The method according to claim 1, wherein said obtaining the wheel torque value of the vehicle using the speed-command-wheel torque mapping relationship comprises:

According to the current speed of the vehicle and the control command, determine the calibration interval to which the current speed belongs and the calibration range to which the control command belongs in the speed-command-wheel torque mapping relationship;

According to the speed-instruction-wheel torque mapping relationship, based on the calibration interval to which the current speed belongs and the calibration interval to which the control command belongs, respectively obtain a plurality of wheel torque values corresponding to the determined calibration intervals; as well as

A wheel-side torque value corresponding to a current speed of the vehicle and a control command is calculated according to the plurality of wheel-side torque values.
The method according to claim 2, wherein calculating the wheel torque value corresponding to the current speed of the vehicle and the control command according to the plurality of wheel torque values comprises:

T wheel = (T 1 ζ 1 +T 2 (1-ζ 1 )) ζ 2 +(T 3 ζ 1 +T 4 (1-ζ 1 ))(1-ζ 2 ),

in,

v is the current speed of the vehicle, v t and v t-1 are respectively the speeds in the calibration interval to which the current speed belongs,

Cmd is the control command, Cmd t and Cmd t-1 are the control commands in the calibration interval to which the control command belongs, respectively,

T wheel is a wheel torque value, and T1, T2, T3 and T4 are multiple wheel torque values corresponding to the determined calibration interval.
The method of claim 1 , wherein said estimating vehicle weight based on said vehicle longitudinal dynamics equations comprises:

creating a least squares recurrence equation with a forgetting factor for said vehicle longitudinal dynamics equation;

The weight of the vehicle is obtained by using the least square recursive equation with forgetting factor to perform iterative calculation.
The method according to claim 1, wherein the vehicle longitudinal dynamics equation is created based on vehicle driving state data, and the vehicle driving state data includes at least one of the following:

Vehicle speed v, vehicle acceleration
Moment of inertia J, angular acceleration
and road slope angle β.
The method according to claim 5, wherein the road slope angle is estimated based on an extended Kalman filter (EKF).
The method according to claim 6, wherein estimating the road slope angle based on the Extended Kalman Filter EKF comprises:

Estimate the road slope angle according to the system state equation of EKF and the system measurement equation of EKF,

The state equation of the system is:

in,

m is the weight of the vehicle in kg,

v is the vehicle speed in m/s,

v(k), v(k-1) are the vehicle speeds calculated by the kth iteration and the k-1th iteration respectively,

Δt represents the cycle of iterative calculation when actually using EKF;

J is the moment of inertia of the vehicle, the unit is kg·m 2 ,

is the angular acceleration of the vehicle in rad/m 2 ,

T wheel is the wheel torque of the vehicle, in N m,

r is the wheel rolling radius of the vehicle, in m,

That is, the equivalent drag coefficient, where ρ is the air resistance coefficient, A is the effective frontal area of the vehicle, C D is the drag coefficient,

β is the slope angle of the road, the unit is rad,

β(k), β(k-1), β(k-2) and β(k-3) are calculated for the k-th, k-1, k-2, and k-3 iterations respectively out of the road slope angle,

μ is the coefficient of rolling resistance,

g is the acceleration due to gravity in m/s 2 , and

W is the system noise vector of EKF,

The system measurement equation of the EKF is:

in,

z(k) represents the vehicle speed to be measured by the EKF,

V is the measurement noise vector of the EKF,

H is the measurement matrix, H=[1 1] when there is a road slope angle obtained by the sensor, and H=[1 0] when there is no road slope angle obtained by the sensor.
The method according to claim 7, wherein the system noise vector W and the measurement noise vector V are Gaussian white noises that are independent of each other and whose mean values are both zero.
The method according to claim 1, wherein the speed-command-wheel torque mapping relationship is predetermined according to previously collected vehicle control commands and vehicle sensory data corresponding to the vehicle control commands,

Wherein the vehicle sensor data includes vehicle speed collected by vehicle sensors.
A device for estimating the weight of a vehicle comprising:

a wheel side torque value obtaining module configured to use a speed-command-wheel side torque mapping relationship to obtain a wheel side torque value of the vehicle according to the current speed of the vehicle and a control command for the vehicle;

A weight estimation module configured to estimate the weight of the vehicle based on vehicle longitudinal dynamics equations using the obtained wheel torque values.
The device according to claim 10, wherein the wheel edge torque value obtaining module comprises:

The first sub-module, according to the current speed of the vehicle and the control command, determines the calibration interval to which the current speed belongs and the calibration range to which the control command belongs in the speed-command-wheel torque mapping relationship;

The second sub-module, according to the speed-command-wheel side torque mapping relationship, based on the calibration interval to which the current speed belongs and the calibration interval to which the control command belongs, obtains a plurality of wheels corresponding to the determined calibration intervals respectively. side torque values; and

The third sub-module calculates the wheel torque value corresponding to the current speed of the vehicle and the control command according to the multiple wheel torque values.
The device according to claim 11, wherein the third submodule calculates the wheel torque value corresponding to the current speed of the vehicle and the control command according to the following formula:

T wheel = (T 1 ζ 1 +T 2 (1-ζ 1 )) ζ 2 +(T 3 ζ 1 +T 4 (1-ζ 1 ))(1-ζ 2 ),

in,

v is the current speed of the vehicle, v t and v t-1 are respectively the speeds in the calibration interval to which the current speed belongs,

Cmd is the control command, Cmd t and Cmd t-1 are the control commands in the calibration interval to which the control command belongs, respectively,

T wheel is a wheel torque value, and T1, T2, T3 and T4 are multiple wheel torque values corresponding to the determined calibration interval.
The apparatus of claim 10, wherein the weight estimation module comprises:

A fourth submodule, creating a least squares recursive equation with a forgetting factor for the vehicle longitudinal dynamics equation;

The fifth sub-module uses the least squares recursive equation with forgetting factor to perform iterative calculation to obtain the weight of the vehicle.
An electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-9. Methods.
A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.
A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.