An online identification method for autonomous driving vehicle load

Abstract

The embodiment of the present invention relates to an online identification method for the load of an autonomous driving vehicle, the method comprising: determining a vehicle load identification function; obtaining the engine type, vehicle drive system state, vehicle acceleration, vehicle speed, road pitch angle and engine torque at any time; setting a load identification switch according to the engine type and vehicle speed when the vehicle drive system state is a continuous working state and the vehicle acceleration is in a stable acceleration range; estimating the vehicle load at the current moment according to the vehicle acceleration, vehicle speed, road pitch angle, engine torque and vehicle load identification function when it is in the on state; performing a first-order low-pass filter based on the vehicle load at the previous moment and the estimated load to obtain the vehicle load at the current moment; limiting the vehicle load based on a preset maximum load value and using the limiting processing result as an online identification output result. Through the present invention, the control accuracy of the control module can be improved and the safety risk of the control module can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an online identification method for an autonomous driving vehicle load. Background Art

[0002] During the actual operation of an autonomous vehicle or an unmanned vehicle, the actual load of the vehicle will change accordingly with the changes in the number of passengers and cargo. When the control module of the vehicle's autonomous driving system performs state processing on the vehicle's throttle / brake and other control quantities, it first obtains the planned trajectory and planned speed from its upstream planning module, and then sets the vehicle's throttle / brake and other control quantities based on the planned trajectory and planned speed. In this process, if the control module does not consider the actual load changes of the vehicle and only identifies the vehicle load as a constant, it may cause large errors in the throttle / brake and other control quantities output by the control module, which in turn leads to an increase in the error between the actual output speed of the vehicle and the planned speed, and an increase in the deviation between the actual driving trajectory of the vehicle and the planned trajectory, resulting in a decrease in control accuracy and an increase in safety risks. Summary of the invention

[0003] The purpose of the present invention is to provide an online identification method, electronic device and computer-readable storage medium for the load of an autonomous driving vehicle in view of the defects of the prior art. The vehicle load identification function is determined based on the force formula of classical mechanics: vehicle motion force = engine output power - gravity component - air resistance - tire friction (wheel rolling resistance); and the vehicle load at the current moment is identified based on the vehicle load identification function and the relevant vehicle parameters obtained in real time. Through the present invention, the actual load of the vehicle can be updated in real time during the driving process of the vehicle. The actual load of the vehicle output by the present invention is used as the control reference data of the control module to improve the control accuracy of the control module and reduce the safety risk of the control module.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present invention provides an online identification method for an autonomous driving vehicle load, the method comprising:

[0005] determining a vehicle load identification function;

[0006] At any time k during the driving process of the autonomous driving vehicle, obtain the engine type, vehicle drive system status, and vehicle acceleration a of the autonomous driving vehicle k , vehicle speed v k 、Road pitch angle θ k and engine torque T k ;

[0007] When the vehicle drive system is in a continuous working state and the vehicle acceleration a kWhen in a preset stable acceleration range, according to the engine type and the vehicle speed v k A load identification switch is provided; the load identification switch includes an on state and an off state;

[0008] When the load identification switch is turned on, according to the vehicle acceleration a k , vehicle speed v k 、Road pitch angle θ k , engine torque T k The vehicle load identification function is used to estimate the vehicle load at the current moment to obtain the corresponding estimated load m' k ;

[0009] Based on the vehicle load m at the previous moment k-1 and the estimated load m' k Perform a first-order low-pass filter to obtain the vehicle load m at the current moment k ;

[0010] The vehicle load m is calculated based on a preset maximum load value. k A limiting process is performed, and the limiting process result is used as the online identification output result of the vehicle load at the current moment.

[0011] Preferably, the determining of the vehicle load identification function specifically includes:

[0012] The force formula for determining the vehicle driving process based on the principles of classical mechanics is:

[0013] ma=F x -mg sinθ-F aero -R x ;

[0014] Where m is the vehicle load, a is the vehicle acceleration, g is the acceleration of gravity, θ is the road pitch angle, ma is the vehicle motion force, and F x is the engine output power, mg sinθ is the component of the vehicle's gravity parallel to the ground, F aero is the air resistance, R x is the wheel rolling resistance;

[0015] The engine output power F is determined by vehicle dynamics and aerodynamics. x , the air resistance F aero and the wheel rolling resistance R x The expression is:

[0016] F x =ratio×T / r,

[0017] F aero =kv 2,

[0018] R x =μmg+cmv;

[0019] Wherein, ratio is the predetermined main reduction ratio coefficient, T is the engine torque, r is the predetermined wheel radius, v is the vehicle speed, k is the wind resistance coefficient, μ and c are the wheel rolling resistance coefficients;

[0020] The engine output power F x , the air resistance F aero and the wheel rolling resistance R x Substitute the expression into the force formula to obtain the corresponding transformation formula:

[0021]

[0022] The vehicle load identification function is determined by arranging the transformation formula as follows:

[0023]

[0024] Preferably, the engine types include electric motor types and internal combustion engine types.

[0025] Preferably, the engine type and the vehicle speed v k Set the load identification switch, including:

[0026] Identify the engine type; when the engine type is an electric motor type, if the vehicle speed v k If the vehicle speed is within the preset electric vehicle speed range, the load identification switch is set to the on state, otherwise the load identification switch is set to the off state; when the engine type is an internal combustion engine type, if the vehicle speed v k If the vehicle is in the preset fuel vehicle speed range, the load identification switch is set to the on state; otherwise, the load identification switch is set to the off state.

[0027] Preferably, the vehicle acceleration a k , vehicle speed v k 、Road pitch angle θ k , engine torque T k The vehicle load identification function is used to estimate the vehicle load at the current moment to obtain the corresponding estimated load m' k , specifically including:

[0028] Get the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * ;

[0029] The vehicle acceleration a k , the vehicle speed v k , the road pitch angle θ k , the engine torque T k , and the latest drag coefficient k * and the wheel rolling resistance coefficient μ * 、c * , substitute into the vehicle load identification function to calculate the corresponding estimated load m' k ,

[0030]

[0031] Preferably, the vehicle load m based on the last moment k-1 and the estimated load m' k Perform a first-order low-pass filter to obtain the vehicle load m at the current moment k , specifically including:

[0032] The vehicle load m k-1 and the estimated load m' k Substitute the preset first-order filter formula to calculate the vehicle load m k ,

[0033] m k =ωm k-1 +(1-ω)m′ k ;

[0034] Wherein, ω is a predetermined filter coefficient.

[0035] Preferably, the vehicle load m is calculated based on a preset maximum load value. k Perform limiting processing, including:

[0036] Determine the vehicle load m k Is it lower than the preset vehicle unloaded mass or exceeds the maximum load value? If the vehicle load m k If the vehicle load is greater than the unloaded mass of the vehicle and does not exceed the maximum load value, the vehicle load m k As the result of the limiting processing output; if the vehicle load m k If the vehicle load is lower than the unloaded mass of the vehicle, the vehicle load m k Assume that the unloaded mass of the vehicle, if the vehicle load m k If the maximum load value is exceeded, the vehicle load m k Set it as the maximum load value, and set the modified vehicle load m k It is output as the result of the clipping process.

[0037] A second aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0038] The processor is used to be coupled to the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;

[0039] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0040] A third aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed by a computer, the computer executes the instructions of the method described in the first aspect above.

[0041] The embodiment of the present invention provides an online identification method for the load of an autonomous driving vehicle, an electronic device, and a computer-readable storage medium. The vehicle load identification function is determined based on the force formula: vehicle motion force = engine output power - gravity component - air resistance - tire friction (wheel rolling resistance) based on the principle of classical mechanics; when the vehicle drive system is in a continuous working state and the vehicle acceleration a is stable, whether to start the online identification of the vehicle load is determined based on the engine type and the vehicle speed v; if it is determined to enter the online identification, the vehicle load m at the current moment is estimated based on the vehicle load identification function and relevant vehicle parameters (vehicle acceleration a, vehicle speed v, road pitch angle θ, and engine torque T) obtained in real time, and the estimation result is first-order filtered in combination with the identification load result at the previous moment, and the filtering result is limited, and finally the result after the limiting processing is output as the load identification result at the current moment. Through the present invention, the actual load of the vehicle can be updated in real time during the driving process of the vehicle; using the actual load of the vehicle output by the present invention as the control reference data of the control module solves the problem of decreased control accuracy caused by fluctuations in the actual load of the vehicle when the control module uses a fixed load value as a reference, thereby improving the control accuracy of the control module and reducing the safety risk of the control module. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of an online identification method for an autonomous driving vehicle load provided in the first embodiment of the present invention;

[0043] Figure 2 A schematic diagram of the structure of an electronic device provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Embodiment 1 of the present invention provides an online identification method for an autonomous driving vehicle load, such as Figure 1 As shown in the schematic diagram of an online identification method for an autonomous driving vehicle load provided in the first embodiment of the present invention, the method mainly includes the following steps:

[0046] Step 1, determining a vehicle load identification function;

[0047] Here, the autonomous driving system of the autonomous vehicle or unmanned vehicle must first determine the vehicle load identification function for online identification before performing online identification;

[0048] Specifically including: Step 11, determining the force formula of the vehicle driving process based on the principle of classical mechanics:

[0049] ma=F x -mg sinθ-F aero -R x ;

[0050] Where m is the vehicle load, a is the vehicle acceleration, g is the acceleration of gravity, θ is the road pitch angle, ma is the vehicle motion force, and F x is the engine output power, mg sinθ is the component of the vehicle's gravity parallel to the ground, F aero is the air resistance, R x is the wheel rolling resistance;

[0051] Here, from the three laws of classical mechanics, we know that the force relationship that causes the vehicle to move is the positive force-reverse force, that is, the vehicle motion force that causes the vehicle to move = (positive force-reverse force), and the vehicle motion force can be represented by the product ma of the mass of the object, that is, the vehicle load m and the vehicle acceleration a; the positive force of the vehicle is identified. The positive force of the vehicle during driving is the power output by the engine, that is, the engine output power F x ; Identify the reverse force of the vehicle. The reverse force that the vehicle is subjected to during driving mainly includes air resistance F aero , friction and the weight component of the vehicle when driving on a slope. The friction can be further expressed as the wheel rolling resistance R xThe gravity component on the slope road surface is represented by the ratio of gravity (mg) and road slope, that is, the road pitch angle θ, in the form of mg sinθ;

[0052] Step 12: Determine the engine output power F based on vehicle dynamics and aerodynamics x , air resistance F aero and wheel rolling resistance R x The expression is:

[0053] F x =ratio×T / r,

[0054] F aero =kv 2 ,

[0055] R x =μmg+cmv;

[0056] Wherein, ratio is the predetermined main reduction ratio coefficient, T is the engine torque, r is the predetermined wheel radius, v is the vehicle speed, k is the wind resistance coefficient, μ and c are the wheel rolling resistance coefficients;

[0057] Here, the engine output power F x , air resistance F aero and wheel rolling resistance R x The expressions can be determined by the mechanical formulas in automobile dynamics and aerodynamics;

[0058] The main reduction ratio coefficient ratio is the gear ratio of the main reducer in the automobile drive axle. It is equal to the ratio of the rotational angular velocity of the transmission shaft to the rotational angular velocity of the upper axle half shaft, and is also equal to the ratio of their rotational speeds. The main reduction ratio coefficient is a fixed known coefficient under the premise that the vehicle brand and model are confirmed; similarly, the wheel radius r is also a fixed known coefficient under the premise that the vehicle brand and model are confirmed;

[0059] The engine torque T is an index parameter reflecting the acceleration capability of the engine. It refers to the torque of the piston doing work in the cylinder in one reciprocating motion, and the unit is Nm. In the subsequent processing steps, the engine torque T will be obtained from the vehicle chassis module. The drag coefficient k and the wheel rolling resistance coefficient μ and c are the conventional coefficients of air resistance and wheel rolling resistance, which can be set in the form of fixed coefficients or obtained by fitting according to the historical load, historical speed, historical engine torque, and historical road pitch angle information in the subsequent processing steps.

[0060] Step 13: The engine output power F x , air resistance F aero and wheel rolling resistance R xSubstitute the expression into the force formula to obtain the corresponding transformation formula:

[0061]

[0062] Here, the actual F x =ratio×T / r, F aero =kv 2 , R x =μmg+cmvSubstitute into ma=F x -mg sinθ-F aero -R x , for F x 、F aero , R x The above transformation formula can be obtained by substitution;

[0063] Step 14, sort out the transformation formula to determine the vehicle load identification function:

[0064]

[0065] Here, the derivation process of the sorting transformation formula is as follows:

[0066] By the transformation formula

[0067] We can get:

[0068] Then we can get:

[0069] Then the above vehicle load identification function can be obtained.

[0070] Step 2: At any time k during the driving process of the autonomous driving vehicle, obtain the engine type, vehicle drive system status, and vehicle acceleration a of the autonomous driving vehicle. k , vehicle speed v k 、Road pitch angle θ k and engine torque T k ;

[0071] The engine type includes an electric motor type and an internal combustion engine type; the vehicle drive system state includes a continuous working state and a non-working state;

[0072] Here, the engine type of the autonomous driving vehicle is a fixed system parameter under the premise that the vehicle brand and model are confirmed, which can be obtained from the system parameter area of ​​the autonomous driving system. The engine type includes electric motor type and internal combustion engine type. If it is an electric motor type, it means that the current vehicle is an electric vehicle, and if it is an internal combustion engine type, it means that the current vehicle is a fuel vehicle;

[0073] The vehicle drive system state is used to characterize the working state of the throttle or brake, which can be obtained from the system parameter area of ​​the automatic driving system. The state includes a continuous working state and a non-working state. If it is a continuous working state, it means that the throttle or brake of the current vehicle is continuously working. If it is a non-working state, it means that the throttle or brake of the current vehicle is not involved in the vehicle control, which is similar to the parking or coasting state.

[0074] The vehicle acceleration a at time k k , vehicle speed v k can be obtained in real time from the vehicle chassis module of the autonomous driving system; the road pitch angle θ k It can be obtained from the Inertial Measurement Unit (IMU) of the autonomous driving system, or from the map module of the autonomous driving system by querying the road slope;

[0075] Engine torque T k For vehicles whose chassis modules use online identification (real-time) means to output feedback torque, the real-time feedback torque output by the chassis module is directly obtained as the engine torque T k For some vehicles whose chassis modules use offline identification (non-real-time) means to output feedback torque, the feedback torque output by the chassis module at time k-△k can be calculated based on the delay time △k of its offline identification. As the engine torque T k For example, if the delay time △k is known to be 0.3 seconds, then at the current time k, the feedback torque output by the vehicle chassis module at (k-0.3) should be As the engine torque T k ;

[0076] Step 3: When the vehicle drive system is in a continuous working state and the vehicle acceleration is a k In the preset stable acceleration range, according to the engine type and vehicle speed v k Set the load identification switch;

[0077] Wherein, the load identification switch includes an on state and an off state;

[0078] Specifically, when the vehicle drive system is in a continuous working state and the vehicle acceleration a k When the vehicle is in the preset stable acceleration range, the engine type is identified; when the engine type is an electric motor type, if the vehicle speed v k If the vehicle speed is within the preset electric vehicle speed range, the load identification switch is set to the on state, otherwise the load identification switch is set to the off state; when the engine type is an internal combustion engine type, if the vehicle speed v kIf the vehicle is within the preset fuel vehicle speed range, the load identification switch is set to the on state; otherwise, the load identification switch is set to the off state.

[0079] Here, the stable acceleration range is a preset acceleration range, such as ±0.3 m / s 2 The speed range of an electric vehicle is a pre-set speed range, such as 20-30 m / s; the speed range of a fuel vehicle is a pre-set speed range corresponding to the highest gear of the vehicle, such as a range greater than 25 m / s;

[0080] The embodiment of the present invention provides a start switch, i.e., a load identification switch, for online identification of vehicle loads. If the switch is in an on state, it indicates that the online identification operation of the vehicle load can be started. If the switch is in an off state, it indicates that the online identification operation of the vehicle load is suspended.

[0081] Correspondingly, the embodiment of the present invention also provides a set of automatic state switching processing procedures for the load identification switch: when the vehicle drive system is in a continuous working state and the vehicle acceleration is a k If the vehicle is in the preset stable acceleration range, it means that the vehicle is currently in a stable acceleration or deceleration state, and the load identification switch can be set; when the load identification switch is set, it is classified based on the engine type; if the engine type is an electric motor type, it means that the current vehicle is an electric vehicle. At this time, if the vehicle speed v k If the speed is within the set electric vehicle speed range, the online identification operation of the vehicle load is started by setting the load identification switch to the on state. Otherwise, the online identification operation of the vehicle load is suspended by setting the load identification switch to the off state. If the engine type is an internal combustion engine type, it means that the current vehicle is a fuel vehicle. At this time, if the vehicle speed v k If the speed is within the set fuel vehicle speed range, the online identification operation of the vehicle load is started by setting the load identification switch to the on state, otherwise the online identification operation of the vehicle load is suspended by setting the load identification switch to the off state.

[0082] Step 4: When the load identification switch is on, according to the vehicle acceleration a k , vehicle speed v k 、Road pitch angle θ k , engine torque T k The vehicle load identification function is used to estimate the vehicle load at the current moment to obtain the corresponding estimated load m' k ;

[0083] Specifically including: Step 41, obtaining the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * ;

[0084] Here, the embodiment of the present invention has two modes for setting the wind resistance coefficient k and the wheel rolling resistance coefficient μ, c;

[0085] One is to use a fixed coefficient method to set it, only do periodic updates without dynamic identification. If in this case the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * In fact, there will be no change in an update cycle, and the set value can be directly read from the system parameter area;

[0086] The other is an offline dynamic identification method that uses the least squares problem fitting based on historical load, historical speed, historical engine torque, and historical road pitch angle information. If the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * The actual data will continue to change and needs to be updated before each vehicle load estimation;

[0087] Furthermore, the embodiment of the present invention also provides specific implementation steps for the above-mentioned offline dynamic identification method, namely: according to the historical load, speed, engine torque and road pitch angle information, the drag coefficient k and the wheel rolling resistance coefficient μ, c are fitted by the least squares problem to obtain the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * , specifically including:

[0088] Step A1, obtaining a specified number n of historical sampling information before the current moment to form a historical sampling information sequence;

[0089] Among them, the historical sampling information sequence consists of n groups of historical sampling information (m i ,v i ,T i ,a i ,θ i ); each group of historical sampling information (m i ,v i ,T i ,a i ,θ i ) is composed of the vehicle load sampling value m corresponding to the same time i , vehicle speed sampling value v i , engine torque sampling value T i , vehicle acceleration sampling value a i and road pitch angle sampling value θ i constitute;

[0090] Here, it should be noted that if there is not enough vehicle load obtained through online identification before the current moment as m i , then the default initial value m0 is used instead. The initial value m0 can be the empty mass of the vehicle or the average load mass of the vehicle in normal statistics;

[0091] Step A2: According to the force formula and the engine output power F x , air resistance F aero and wheel rolling resistance R x The expression of and the historical sampling information sequence are used to construct the second-order objective function f(v) of the least squares problem with vehicle speed v as the independent variable:

[0092]

[0093] Among them, ratio, r, g are the known main reduction ratio coefficient, vehicle radius and gravity acceleration; n is the number of historical sampling information;

[0094] Step A3, solving the least squares problem for the second-order objective function f(v), and taking the drag coefficient k, wheel rolling resistance coefficient μ, and c values ​​that make the second-order objective function f(v) reach the minimum value as the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * ;

[0095] Here, the expression to be solved is actually:

[0096]

[0097] When solving the above expression, a variety of methods can be used to solve it. It can be exhaustively enumerated based on iteration; it can also be calculated using an intelligent model; it can also be solved using a least squares polynomial fitting function provided by a third party, for example, the polyfit function based on the numpy package of the Python language; when using the polyfit function, the independent variable sequence parameter x={v i} and dependent variable sequence parameters Set the function's fitting polynomial parameter deg to 2nd order, and set the other parameters of the function to default values. Then input the independent variable sequence parameter x and the dependent variable sequence parameter y into the polyfit function for 2nd order polynomial fitting operation to obtain an output sequence {a1, a2, a3} with a length of deg+1, that is, a length of 3. Then use a1 in the output sequence as the latest drag coefficient k * , a2 as the latest wheel rolling resistance coefficient c *, a3 as the latest wheel rolling resistance coefficient μ * ;

[0098] Step 42: Set the vehicle acceleration a k , vehicle speed v k 、Road pitch angle θ k , engine torque T k , and the latest drag coefficient k * and wheel rolling resistance coefficient μ * 、c * , substitute into the vehicle load identification function to calculate the corresponding estimated load m' k ,

[0099]

[0100] Step 5: Based on the vehicle load m at the previous moment k-1 and estimated load m' k Perform a first-order low-pass filter to obtain the vehicle load m at the current moment k ;

[0101] Specifically include: the vehicle load m k-1 and estimated load m' k Substitute the preset first-order filter formula to calculate the vehicle load m k ,

[0102] m k =ωm k-1 +(1-ω)m′ k ;

[0103] Wherein, ω is a predetermined filter coefficient.

[0104] Here, for the estimated load m' k First-order filtering can maintain good data robustness; it should be noted that if the vehicle load is not obtained as m through online identification at the previous moment k-1 , then the default initial value m0 is used instead. The initial value m0 can be the unladen mass of the vehicle or the average load mass of the vehicle.

[0105] Step 6: Based on the preset maximum load value, the vehicle load m k A limiting process is performed, and the limiting process result is used as the online identification output result of the vehicle load at the current moment.

[0106] Among them, based on the preset maximum load value, the vehicle load m k Perform amplitude limiting processing, specifically including: judging the vehicle load m k Is it lower than the preset vehicle unloaded mass or exceeds the maximum load value? kIf the vehicle load is higher than the unladen mass of the vehicle and does not exceed the maximum load value, the vehicle load m k Output as the result of the limiting process; if the vehicle load m k If the vehicle load is lower than the unladen mass of the vehicle, the vehicle load m k Assume that the vehicle has no load mass. If the vehicle load is m k If the maximum load value is exceeded, the vehicle load m k Set it as the maximum load value and set the modified vehicle load m k Output as the result of the limiting processing.

[0107] Here, the maximum load value is a preset vehicle mass under the vehicle's maximum load. The purpose of limiting is to ensure that the final online identification output result does not exceed the data interval formed by the vehicle's unloaded mass and the maximum load value, so as to maintain good data stability.

[0108] In summary, by processing steps 1-6 above, the actual load of the vehicle can be updated in real time during the driving process of the vehicle; using the real-time updated actual load of the vehicle as the control reference data of the automatic driving system control module can solve the problem of decreased control accuracy caused by the control module using a fixed load value as a reference.

[0109] It should be noted that in real-life scenarios, vehicles may also be illegally overloaded, i.e., the vehicle load m k The vehicle load exceeds the preset maximum load value. At this time, an alarm message should be given for safe driving. However, this situation will be lost through the limit processing in step 6. Therefore, the embodiment of the present invention also provides a method for implementing an alarm for vehicle load overload, namely: after step 5, the vehicle load m k Whether it exceeds the preset maximum load value is judged; if it exceeds, the load state o corresponding to the current moment k is k Set to overload state and perform the operation for the specified number of load states o k The state value is the load state of overload state o k The number of overload warnings is counted to generate a corresponding first number. If the first number exceeds a set threshold, an overload warning is initiated locally in the vehicle and a corresponding warning message is also sent to a remote management platform connected to the current vehicle. The warning information should at least include vehicle coding information, vehicle location information, vehicle speed information, vehicle acceleration information and warning type information specifically for overload warning.

[0110] Figure 2 This is a schematic diagram of the structure of an electronic device provided in the second embodiment of the present invention. The electronic device may be the aforementioned terminal device or server, or may be a terminal device or server connected to the aforementioned terminal device or server to implement the method of the embodiment of the present invention. Figure 2As shown, the electronic device may include: a processor 301 (such as a CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiver 303. Various instructions may be stored in the memory 302 to complete various processing functions and implement the processing steps described in the aforementioned method embodiment. Preferably, the electronic device involved in the embodiment of the present invention also includes: a power supply 304, a system bus 305 and a communication port 306. The system bus 305 is used to realize the communication connection between components. The above-mentioned communication port 306 is used for connecting and communicating between the electronic device and other peripherals.

[0111] exist Figure 2 The system bus 305 mentioned in the figure can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The term "communication interface" is represented by only one thick line, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize the communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk storage.

[0112] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a graphics processing unit (GPU), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0113] It should be noted that an embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the method and processing process provided in the above embodiments.

[0114] An embodiment of the present invention further provides a chip for executing instructions, wherein the chip is used to execute the processing steps described in the aforementioned method embodiment.

[0115] The embodiment of the present invention provides an online identification method for the load of an autonomous driving vehicle, an electronic device, and a computer-readable storage medium. The vehicle load identification function is determined based on the force formula: vehicle motion force = engine output power - gravity component - air resistance - tire friction (wheel rolling resistance) based on the principle of classical mechanics; when the vehicle drive system is in a continuous working state and the vehicle acceleration a is stable, whether to start the online identification of the vehicle load is determined based on the engine type and the vehicle speed v; if it is determined to enter the online identification, the vehicle load m at the current moment is estimated based on the vehicle load identification function and relevant vehicle parameters (vehicle acceleration a, vehicle speed v, road pitch angle θ, and engine torque T) obtained in real time, and the estimation result is first-order filtered in combination with the identification load result at the previous moment, and the filtering result is limited, and finally the result after the limiting processing is output as the load identification result at the current moment. Through the present invention, the actual load of the vehicle can be updated in real time during the driving process of the vehicle; using the actual load of the vehicle output by the present invention as the control reference data of the control module solves the problem of decreased control accuracy caused by fluctuations in the actual load of the vehicle when the control module uses a fixed load value as a reference, thereby improving the control accuracy of the control module and reducing the safety risk of the control module.

[0116] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0117] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0118] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An online identification method for an autonomous driving vehicle load, characterized in that: The method comprises: determining a vehicle load identification function; At any time k during the driving process of the autonomous driving vehicle, obtain the engine type, vehicle drive system status, and vehicle acceleration a of the autonomous driving vehicle k , vehicle speed v k 、Road pitch angle θ k and engine torque T k ; When the vehicle drive system is in a continuous working state and the vehicle acceleration a k When in a preset stable acceleration range, according to the engine type and the vehicle speed v k A load identification switch is provided; the load identification switch includes an on state and an off state; When the load identification switch is turned on, according to the vehicle acceleration a k , vehicle speed v k 、Road pitch angle θ k , engine torque T k The vehicle load identification function is used to estimate the vehicle load at the current moment to obtain the corresponding estimated load m' k ; Based on the vehicle load m at the previous moment k-1 and the estimated load m' k Perform a first-order low-pass filter to obtain the vehicle load m at the current moment k ; The vehicle load m is calculated based on a preset maximum load value. k A limiting process is performed, and the limiting process result is used as the online identification output result of the vehicle load at the current moment.

2. The online identification method of the automatic driving vehicle load according to claim 1, characterized in that: The determining of the vehicle load identification function specifically includes: The force formula for determining the vehicle driving process based on the principles of classical mechanics is: ma=F x -mg sinθ-F aero -R x ; Where m is the vehicle load, a is the vehicle acceleration, g is the acceleration of gravity, θ is the road pitch angle, ma is the vehicle motion force, and F x is the engine output power, mg sinθ is the component of the vehicle's gravity parallel to the ground, F aero is the air resistance, R x is the wheel rolling resistance; The engine output power F is determined by vehicle dynamics and aerodynamics. x , the air resistance F aero and the wheel rolling resistance R x The expression is: F x =ratio×T / r, F aero =kv 2 , R x =μmg+cmv; Wherein, ratio is the predetermined main reduction ratio coefficient, T is the engine torque, r is the predetermined wheel radius, v is the vehicle speed, k is the wind resistance coefficient, μ and c are the wheel rolling resistance coefficients; The engine output power F x , the air resistance F aero and the wheel rolling resistance R x Substitute the expression into the force formula to obtain the corresponding transformation formula: The vehicle load identification function is determined by arranging the transformation formula as follows:

3. The online identification method of the automatic driving vehicle load according to claim 1, characterized in that: The engine types include an electric motor type and an internal combustion engine type.

4. The online identification method of the automatic driving vehicle load according to claim 3 is characterized in that: The method according to the engine type and the vehicle speed v k Set the load identification switch, including: Identify the engine type; when the engine type is an electric motor type, if the vehicle speed v k If the vehicle speed is within the preset electric vehicle speed range, the load identification switch is set to the on state, otherwise the load identification switch is set to the off state; when the engine type is an internal combustion engine type, if the vehicle speed v k If the vehicle is in the preset fuel vehicle speed range, the load identification switch is set to the on state; otherwise, the load identification switch is set to the off state.

5. The online identification method of the automatic driving vehicle load according to claim 2, characterized in that: The vehicle acceleration a k , vehicle speed v k 、Road pitch angle θ k , engine torque T k The vehicle load identification function is used to estimate the vehicle load at the current moment to obtain the corresponding estimated load m' k , specifically including: Get the latest drag coefficient k * , wheel rolling resistance coefficient μ * and c * ; The vehicle acceleration a k , the vehicle speed v k , the road pitch angle θ k , the engine torque T k , and the latest drag coefficient k * and the wheel rolling resistance coefficient μ * 、c * , substitute into the vehicle load identification function to calculate the corresponding estimated load m' k , 6. The online identification method of the automatic driving vehicle load according to claim 1, characterized in that: The vehicle load m based on the last moment k-1 and the estimated load m' k Perform a first-order low-pass filter to obtain the vehicle load m at the current moment k , specifically including: The vehicle load m k-1 and the estimated load m' k Substitute the preset first-order filter formula to calculate the vehicle load m k , m k =ωm k-1 +(1-ω)m′ k ; Wherein, ω is a predetermined filter coefficient.

7. The online identification method of the automatic driving vehicle load according to claim 1, characterized in that: The vehicle load m is calculated based on the preset maximum load value. k Perform limiting processing, including: Determine the vehicle load m k Is it lower than the preset vehicle unloaded mass or exceeds the maximum load value? If the vehicle load m k If the vehicle load is greater than the unloaded mass of the vehicle and does not exceed the maximum load value, the vehicle load m k As the result of the limiting processing output; if the vehicle load m k If the vehicle load is lower than the unloaded mass of the vehicle, the vehicle load m k Assume that the unloaded mass of the vehicle, if the vehicle load m k If the maximum load value is exceeded, the vehicle load m k Set it as the maximum load value, and set the modified vehicle load m k It is output as the result of the clipping process.

8. An electronic device, characterized in that: include: memory, processors, and transceivers; The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method steps described in any one of claims 1 to 7; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when executed by a computer, enable the computer to execute the method according to any one of claims 1 to 7.

Images