Multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method and device

Abstract

This invention discloses a multi-sensor fusion longitudinal control method and device for unmanned IGV vehicles. The method involves setting a pre-parking position within a predetermined distance from the target bridge equipment. The unmanned vehicle acquires the target parking distance from its current position. Then, it uses multiple sensors from the vehicle's onboard motor speed sensor and IMU inertial navigation system to fit the traveled distance and the distance to be braked, summing them and comparing the sum with the target parking distance. If the sum is less than the target parking distance, PID speed control is applied; otherwise, emergency braking control is initiated. This invention solves the problem of inaccurate parking of unmanned transport vehicles due to poor weather and road conditions, achieving precise parking with a positioning accuracy of 5cm even in adverse weather and road conditions.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method and apparatus for longitudinal control of multi-sensor fusion autonomous IGV vehicles. Background Technology

[0002] In the actual production operations of vehicles in the port, there are two main processes: unloading and loading. Unloading refers to the process where vehicles receive containers from the ship at the quay crane and then unload them at the yard crane. Loading refers to the process where vehicles receive containers from the yard crane and then load them at the quay crane. During the loading or unloading of containers at the yard crane and quay crane, the unmanned transport vehicles in between need to be able to stop precisely at the corresponding positions of the yard crane and quay crane. Therefore, the alignment and parking of unmanned transport vehicles with the yard crane and quay crane is particularly important.

[0003] Existing unmanned parking methods for port yard cranes are illustrated in Chinese Patent No. CN118092459B, which discloses a multi-scenario unmanned vehicle yard crane positioning control method and device. This patent uses real-time reading of the target parking distance and performs emergency braking when the target parking distance is less than the ideal braking distance. This method relies heavily on real-time and rapid, accurate updates of the target parking distance. However, this data is obtained by the bridge equipment scanning the vehicle and the vehicle equipment scanning the bridge. The target parking distance is easily affected by distance, weather, road conditions, and the vehicle's real-time movement. When the distance is far, the weather is bad, or the road conditions are poor, accurate data cannot be output quickly and in real-time, leading to inaccurate parking of the unmanned transport vehicle. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and apparatus for longitudinal alignment control of an unmanned IGV vehicle using multi-sensor fusion technology. The steps of the method are as follows:

[0005] S10. Set up a pre-parking location in an area at a predetermined distance from the target location;

[0006] S20, the driverless vehicle proceeds to the pre-parking location and stops;

[0007] S30: The autonomous vehicle obtains the target parking distance from the current vehicle location to the target location;

[0008] S40: The driverless vehicle starts and moves toward the target location. It uses its onboard motor speed sensor and IMU inertial navigation positioning equipment to fit the distance already traveled from the current position to the pre-stop position and the braking distance to the target location.

[0009] S50. Calculate the sum of the distance traveled and the distance to be braked, and compare the sum of the distance traveled and the distance to be braked with the target stopping distance obtained in step S30:

[0010] When the sum of the traveled distance and the braking distance is less than the target stopping distance, braking is performed through the longitudinal PID speed control module;

[0011] Emergency braking control is triggered when the sum of the distance traveled and the distance to be braked is greater than or equal to the target stopping distance.

[0012] Preferably, the fitting method for the distance traveled and the braking distance to be braked in step S40 includes:

[0013] S41. Determine the vehicle's direction of travel and speed (positive or negative) based on the motor speed and gear information;

[0014] S42. Calculate the real-time driving speed of the unmanned vehicle based on the motor speed, gear information and driving direction;

[0015] S43. Based on the real-time driving speed, calculate the distance already traveled by the autonomous vehicle using the following formula:

[0016] ,in:

[0017] S move S represents the current distance traveled by the driverless vehicle. add V represents the cumulative distance traveled by the currently autonomous vehicle from its pre-stop position; speed t represents the real-time driving speed of the autonomous vehicle; t is the set control period.

[0018] The braking distance of the current autonomous vehicle is calculated using the following formula:

[0019] ,in:

[0020] S brake The distance to be braked;

[0021] V speed This represents the current real-time speed of the driverless vehicle.

[0022] M represents the vehicle's load capacity;

[0023] K1, K2, K3, and K4 are preset parameters.

[0024] Preferably, the distance already traveled by the autonomous vehicle is corrected for errors, and the corrected distance already traveled by the autonomous vehicle is S. move1 , , where: S addC1 represents the cumulative distance traveled by the current autonomous vehicle from the pre-parking position; C2 are preset parameters.

[0025] Preferably, step S41 specifically includes:

[0026] The current motor speed is measured by a motor speed sensor installed inside the drive motor;

[0027] When the autonomous vehicle is in forward gear and the motor speed is positive, or when the autonomous vehicle is in reverse gear and the motor speed is negative, it is determined that the current driving direction of the autonomous vehicle is consistent with the expected driving direction, the vehicle speed is positive, and the driving speed coefficient value K5 is 1.

[0028] When the autonomous vehicle is in drive and the motor speed is negative, or when the autonomous vehicle is in reverse and the motor speed is positive, it is determined that the current driving direction of the autonomous vehicle is inconsistent with the expected driving direction, the vehicle speed is negative, and the driving speed coefficient value K5 is -1.

[0029] Preferably, the two axles of the unmanned vehicle are drive axles, and the drive axles are equipped with drive motors. Step S42 specifically includes:

[0030] The speed of each motor is measured by a speed sensor installed inside each drive motor;

[0031] Read the absolute value of the motor speed and the current gear information of each drive motor. Multiply the absolute value of the motor speed of each drive motor by the corresponding speed ratio to obtain speed V1 and speed V2. According to the formula... Calculate the real-time driving speed V speed Where: K5 is the driving speed coefficient value.

[0032] Preferably, when the drive shaft spins freely, or when spinning freely and coupling with a slope, the real-time travel speed V is... speed Make corrections, the corrected V speed as follows:

[0033] ,in:

[0034] V4 is obtained by integrating the acceleration output of the IMU through the vehicle's IMU inertial navigation positioning device;

[0035] V min12 The smaller of velocities V1 and V2;

[0036] K5 is the driving speed coefficient value.

[0037] Preferably, the longitudinal PID speed control module includes:

[0038] The receiving unit is used to receive the initial target velocity V. tar1;

[0039] A limiting unit is used to determine the jump step value K based on the configuration of the autonomous vehicle. tar For the initial target velocity V tar1 To achieve the planned speed V, constraints are imposed. tar2 ;

[0040] Deviation calculation unit, used to calculate the planned velocity V tar2 Current speed V as reflected by the chassis veh The speed deviation V between diff ;

[0041] The acceleration control unit processes the velocity deviation V through a PID acceleration controller. diff To obtain the target acceleration A tar ;

[0042] The filtering unit processes the differential speed A from the chassis feedback. speed_ori A first-order low-pass filter is applied, and the acceleration value A output from the positioning IMU sensor is combined. imu The current acceleration A is solved by complementary filtering. veh ;

[0043] The acceleration deviation calculation unit is used to calculate the current acceleration A. veh With target acceleration A tar The acceleration deviation A between diff ;

[0044] The throttle increment / decrease control unit processes the acceleration deviation A through a PID throttle increment / decrease controller. diff To obtain the throttle increase / decrease T comp ;

[0045] The target throttle total calculation unit uses the current throttle total T fed back from the chassis. now and throttle increase / decrease T comp Calculate the initial target total switch value T tar1 .

[0046] Preferably, the longitudinal PID speed control module further includes a verification unit, which verifies the initial target total throttle value Ttar1, including verification based on the braking priority principle, verification of setting maximum and minimum values, verification in the case of negative numbers, and judgment and output of the minimum total throttle value.

[0047] Preferably, in the limiting unit, if the initial planned target speed V tar1 Compared with the target velocity V at the previous moment tar_last If the difference is greater than the set speed difference value, then the target speed V at the current moment will be set. tar2 Set as the target velocity V at the previous moment tar_lastAdd the set speed difference.

[0048] Another device provided by the present invention includes:

[0049] A processor; and a memory for storing executable instructions of the processor;

[0050] The processor is configured to execute the multi-sensor fusion autonomous IGV vehicle alignment longitudinal control method described above by executing the executable instructions.

[0051] The multi-sensor fusion longitudinal control method for unmanned IGV vehicles provided by this invention solves the problem of inaccurate parking of unmanned transport vehicles due to poor weather and road conditions. Tests have shown that the multi-sensor fusion longitudinal control method for unmanned IGV vehicles provided by this invention can achieve precise parking with a positioning accuracy of 5cm under adverse weather and road conditions. Attached Figure Description

[0052] Figure 1 Flowchart of the multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method provided by the present invention;

[0053] Figure 2 This is a structural diagram of an autonomous vehicle.

[0054] Figure 3 A schematic diagram illustrating the normal operation of an autonomous vehicle.

[0055] Figure 4 A diagram illustrating a situation where an unmanned vehicle rolls off a slope.

[0056] Figure 5 This is a diagram illustrating a situation where the wheels of an autonomous vehicle are spinning freely.

[0057] Figure 6 A schematic diagram illustrating the wheel spinning coupling situation when an autonomous vehicle rolls down a slope.

[0058] Figure 7 The control flowchart for the PID control module;

[0059] Figure 8 Here is the filtering flowchart;

[0060] Figure 9 This is a structural block diagram of the device in the embodiments of this disclosure. Detailed Implementation

[0061] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention is further described below in conjunction with specific embodiments. However, the following embodiments are merely preferred embodiments of this invention and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments in the implementation methods without creative effort are all within the protection scope of this invention. Unless otherwise specified, the experimental methods in the following embodiments are conventional methods. Unless otherwise specified, the materials and reagents used in the following embodiments can be obtained commercially.

[0062] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," "front end," "rear end," "both ends," "one end," and "the other end," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0063] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installed," "equipped with," "connected," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0064] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0065] like Figure 1 As shown, embodiments of the present invention provide a method and apparatus for longitudinal alignment control of an unmanned IGV vehicle using multi-sensor fusion, wherein the steps of the method for longitudinal alignment control of an unmanned IGV vehicle using multi-sensor fusion are as follows:

[0066] S10. The unmanned vehicle generates a driving path based on the current vehicle location and the location information of the bridge equipment at the target parking location. It sets a pre-parking position in an area at a set distance from the target location. The set distance is approximately 1m before the actual operation (which can be adjusted according to the actual situation). The unmanned vehicle generating a driving path based on the current vehicle location and the location information of the target location is an existing technology in this field and will not be described in detail here.

[0067] S20. The driverless vehicle travels along the driving path to the pre-parking position and stops. By stopping, the signal reception of the driverless vehicle can be more stable and accurate.

[0068] S30. The autonomous vehicle obtains the target parking distance from the current vehicle position to the target location. In this step, the autonomous vehicle receives guidance information, which is obtained from existing autonomous detection / bridge equipment / manual issuance. The target parking distance is obtained through the guidance information.

[0069] S40. The autonomous vehicle starts and moves towards the target location. Using its built-in motor speed sensor and IMU inertial navigation positioning device (the IMU inertial navigation positioning device includes various sensors such as accelerometers, gyroscopes, and magnetometers. The IMU inertial navigation positioning device is existing technology in the field of autonomous vehicles and will not be described in detail here), the distance traveled by the autonomous vehicle from its current position to the pre-stop position and the braking distance to the target location are fitted. The pre-stop position is set at about 1m before the actual operation by the above steps. When the alignment accuracy requirement is ±5cm, the positioning device cannot be used directly for alignment (the positioning device output deviation is large). Therefore, the vehicle's built-in sensors are used for detection.

[0070] S50. Calculate the sum of the distance traveled and the distance to be braked, and compare the sum of the distance traveled and the distance to be braked with the target stopping distance obtained in step S30:

[0071] When the sum of the traveled distance and the braking distance is less than the target stopping distance, braking is performed through the longitudinal PID speed control module;

[0072] Emergency braking control is triggered when the sum of the distance traveled and the distance to be braked is greater than or equal to the target stopping distance.

[0073] In the above steps, the autonomous vehicle receives guidance information and executes it after parking. This refers to how far the vehicle should go. Autonomous vehicles cannot stop and go as they please like humans. Therefore, the concept of longitudinal vehicle control is introduced.

[0074] When the sum of the traveled distance and the braking distance is less than the target stopping distance, PID control is performed. By using PID speed control (controlling the vehicle accelerator according to the target speed to make it reach the target speed), the control accuracy is improved, which can meet the needs of high-precision application scenarios, and can achieve fast response and stable control, so that the vehicle can smoothly transition to the target speed.

[0075] When the sum of the distance traveled and the distance to be braked is greater than or equal to the target stopping distance, emergency braking is initiated. Emergency braking, simply put, means pressing the brake pedal to 100%. Due to the vehicle's inertia during braking, it cannot stop immediately after braking; there is a certain braking distance. This distance is related to the vehicle's current speed and load, hence the formula S. brake .

[0076] In specific implementation, the fitting method for the distance traveled and the braking distance in step S40 includes:

[0077] S41. Based on the motor speed and gear information, determine the vehicle's driving direction and speed (positive or negative). In this step, the motor speed is used to determine the current speed (to address situations where the vehicle rolls off a slope, it's necessary to know if the vehicle's current driving direction matches the desired direction; a motor speed sensor is typically installed inside the motor to calculate the motor's rotational speed, and the vehicle speed can be calculated by multiplying the speed by a certain gear ratio based on the different gear ratios of the transmission). Examples of unmanned container truck models used in ports include... Figure 2 As shown, this vehicle model features a dual-motor drive system (mid and rear). Taking the motor with the lower speed as the driving wheel, the following judgments are made: When the vehicle is in D gear and the current motor speed is positive, or when the vehicle is in R gear and the current motor speed is negative, the current driving direction is considered to be consistent with the desired driving direction, therefore the vehicle's speed is positive, and the speed coefficient K5 is 1. When the vehicle is in D gear and the current motor speed is negative, or when the vehicle is in R gear and the current motor speed is positive, the current driving direction is considered to be consistent with the desired driving direction, therefore the vehicle's speed is negative, and the speed coefficient K5 is -1. (This judgment is made because if the road has a slope, when the vehicle is in D gear and the starting throttle is low or nonexistent, the vehicle may roll backwards. In this rolling backward situation, the vehicle travels in the opposite direction to the desired direction, hence the speed is negative, and the theoretical travel distance is also negative. At this time, the vehicle's throttle will continue to increase until it reaches a certain level, after which the vehicle will stop rolling backwards and continue traveling in the desired direction.)

[0078] S42. Calculate the real-time driving speed of the autonomous vehicle based on the motor speed, gear information, and driving direction. In this step, the absolute values ​​of the current speeds of the middle and rear drive motors and the current gear are read. The absolute values ​​of the speeds of the middle and rear dual motors are multiplied by the corresponding speed ratio to obtain V1 and V2. The sign of the above driving speed is then obtained to obtain the original vehicle speed. (The unmanned container trucks in the port also have gearboxes and therefore different gears. The current speed of the vehicle can be directly obtained through the speed ratio.)

[0079] When the vehicle spins freely, V is applied. speed The correction is as follows: Combining the vehicle's IMU (Inertial Measurement Unit) positioning equipment (to address the issue of a single motor idling), the acceleration information output by the IMU is integrated to obtain the vehicle speed information V4 (the positioning equipment can only obtain the absolute speed value, not the speed direction). At this point, the speed difference between the middle and rear dual drive motors is used to determine whether idling has occurred. If the vehicle is determined to be spinning freely, then the speed of the smaller of the two drive motors, V, is used. min12 The positioning speed is then used to correct the vehicle speed, resulting in the corrected vehicle speed. At this time, V speed =V5, if no idling occurs, the original vehicle speed can be used directly, i.e., V speed =V3; The threshold value in this step can be set to 2m / s. When the vehicle is not idling, the normal speeds of the two motors, V1 and V2, should be the same, i.e.

[0080] However, during normal driving, it is impossible to guarantee that the speeds of the two motors are completely consistent (due to the complex and undulating road conditions, the sensor output itself has a certain deviation from the actual speed). But when idling occurs, since the idling vehicle has no road resistance, it will spin very fast (so the threshold is set to 2m / s), it is judged that the axle of the autonomous vehicle is idling.

[0081] When the autonomous vehicle is in forward gear and the motor speed is negative, or when the autonomous vehicle is in reverse gear and the motor speed is positive, it is determined that the current driving direction of the autonomous vehicle is inconsistent with the expected driving direction, and the vehicle's driving speed is negative, which is when it is rolling downhill.

[0082] When a single motor idles and a slope coupling occurs, V is performed. speed The correction is as follows: The determination of the positive or negative speed of the wheels with lower rotational speeds using the dual drive motors (mid and rear) can still be performed using the above process to obtain the feasible vehicle speed V. speed ;

[0083] Vehicle speed calculation in four scenarios:

[0084] 1. Under normal circumstances, such as Figure 3 As shown, at this time ;

[0085] 2. Slope conditions as follows Figure 4 As shown, at this time ;

[0086] 3. Idling situation as follows Figure 5 As shown, at this time ;

[0087] 4. The situation of coupling between slope slip and idle speed is as follows: Figure 6 As shown, at this time ;

[0088] The real-time driving speed V of the vehicle under different driving conditions can be obtained by following the above steps. speed ;

[0089] S43. Based on the real-time driving speed, calculate the distance already traveled by the autonomous vehicle using the following formula:

[0090] ,in:

[0091] V speed The vehicle's real-time speed is given by t. When the control module cycle is set to 0.02s, t is 0.02s. At this point, t is multiplied by V. speed If the distance traveled by the vehicle within one control cycle is considered, then the cumulative distance traveled during the execution of guidance information can be expressed as: However, only one vehicle speed can be acquired within a control cycle, such as 0.02s. The vehicle speed may change within this control cycle, therefore S... add There is a certain deviation. To reduce this deviation, S was obtained through actual testing. add There is a certain linear relationship between the distance traveled and the actual distance traveled, therefore it is necessary to correct the error of the current distance traveled by the autonomous vehicle. The corrected current distance traveled by the autonomous vehicle, S, is... move1 It can be expressed as C1 and C2 are preset parameters, which can be set by those skilled in the art based on prior experience;

[0092] The braking distance of the current autonomous vehicle is calculated using the following formula:

[0093] ,in:

[0094] S brake The distance to be braked;

[0095] V speed This represents the current real-time speed of the driverless vehicle.

[0096] M represents the vehicle's load capacity;

[0097] K1, K2, K3, and K4 are preset parameters. Braking distance S brake The parameters K1, K2, K3, and K4 are related to the current vehicle speed and vehicle load M. These parameters can be set by those skilled in the art based on prior experience.

[0098] In specific implementation, the longitudinal PID speed control module includes:

[0099] The receiving unit is used to receive the initial target velocity V. tar1 ;

[0100] A limiting unit is used to determine the jump step value K based on the configuration of the autonomous vehicle. tar For the initial target velocity V tar1 To achieve the planned speed V, constraints are imposed. tar2 ;

[0101] Deviation calculation unit, used to calculate the planned velocity V tar2 Current speed V as reflected by the chassis veh The speed deviation V between diff ;

[0102] The acceleration control unit processes the velocity deviation V through a PID acceleration controller. diff To obtain the target acceleration A tar ;

[0103] The filtering unit processes the differential speed A from the chassis feedback. speed_ori A first-order low-pass filter is applied, and the acceleration value A output from the positioning IMU sensor is combined. imu The current acceleration A is solved by complementary filtering. veh ;

[0104] The acceleration deviation calculation unit is used to calculate the current acceleration A. veh With target acceleration A tar The acceleration deviation A between diff ;

[0105] The throttle increment / decrease control unit processes the acceleration deviation A through a PID throttle increment / decrease controller. diff To obtain the throttle increase / decrease T comp ;

[0106] The target throttle total calculation unit uses the current throttle total T fed back from the chassis. now and throttle increase / decrease T comp Calculate the initial target total switch value T tar1 ;

[0107] The verification unit verifies the initial target total number of switches T. tar1 Verification is performed, including verification based on the braking priority principle, verification with maximum and minimum values, verification in the case of negative numbers, and judgment and output of the minimum total throttle value.

[0108] Specifically, the longitudinal PID speed control module controls the vehicle's speed by controlling the brakes and accelerator. Its control process is as follows: Figure 7 As shown:

[0109] 1) First, the receiving unit receives the initial target velocity V from the planning layer. tar1 To prevent the initial planned target speed V from being input tar1 If the jump is too large when the value is increased, the limiting unit will limit the jump step value K according to the vehicle configuration. tar The planned speed is obtained by imposing constraints. In practical applications, the change in the target speed within a control time period cannot exceed the set speed (e.g., 4 m / s). If (initial planned target speed V) tar1- The target velocity V at the previous moment tar_last If a vehicle speed is set (e.g., 4 m / s), then the target speed at the current moment is V. tar2 (Target velocity V at the previous moment) tar_last +4m / s (only for acceleration);

[0110] 2) Then the deviation calculation unit uses the planned speed V tar2 The vehicle's current speed V, as fed back from the chassis. veh Subtraction yields the velocity deviation V diff The target acceleration A is then obtained through the acceleration control unit. tar ;like Figure 8 As shown, the chassis feedback speed differential A is then processed by the filtering unit. speed_ori And the acceleration value A after first-order low-pass filtering speed ( A speed The current acceleration value is output, where 'a' is a weighting factor. In practical applications, it can be as follows: 0.5, A speed_ori The original acceleration value is obtained by differentiating the chassis feedback speed, A. speed_last The acceleration value A is obtained by combining the acceleration value output at the previous moment with the positioning IMU sensor. imu Solving for the current acceleration A after complementary filtering veh ,( b is a weighting factor (in practical applications, it can be as low as 0.35), used to adjust the contribution ratio of the two sensor data. (The vehicle acceleration obtained by the vehicle speed derivative has a high frequency of change but many minor steps, while the acceleration information output by the positioning IMU sensor is a low-frequency, slowly changing signal. Therefore, combining the two can obtain a high-frequency vehicle acceleration with fewer minor steps.) Using the current acceleration A veh And target acceleration A tar Subtraction yields acceleration deviation A diff The throttle increment / decrease T is obtained through the throttle increment / decrease control unit. comp (When deceleration is required, the throttle increment / decrease is negative). To prevent sudden acceleration / deceleration, the throttle increment / decrease T is set. compThe maximum value is ±8; the current total throttle T is fed back from the chassis. now The initial target total throttle value T is obtained by solving for the throttle increase / decrease. tar1 .

[0111] 3) Finally, verify the target throttle quantity, including: based on the braking priority principle, setting the target throttle quantity to 0 when the chassis has a braking output; setting the target throttle quantity T. tar1 The maximum and minimum values ​​are ±100; there exists an initial target total switch value T. tar1 When the value is negative, the absolute value of the throttle is set as the output value of the brake; the initial target total throttle value T tar1 Greater than 0 and less than the set minimum switch quantity T tar2 (Based on actual debugging, the throttle increment T under no-load conditions is...) add1 The value is 5. Under heavy load, the switch increment is related to the weight M of the enclosure, T. add1 for M is in tons. In actual production, when a task to transport a container is issued, the container weight M will be issued simultaneously. In cases of road slope, the ignition speed increment T will be applied. add2 for Theta is the road gradient, which can be calculated using the vehicle's IMU positioning device. According to the minimum total gate value T tar2 Output.

[0112] The multi-sensor fusion longitudinal control method for unmanned IGV vehicles provided by this invention solves the problem of inaccurate parking of unmanned transport vehicles due to poor weather and road conditions. Tests have shown that the multi-sensor fusion longitudinal control method for unmanned IGV vehicles provided by this invention can achieve precise parking with a positioning accuracy of 5cm under adverse weather and road conditions.

[0113] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method as described above.

[0114] The present invention also provides an apparatus comprising:

[0115] A processor; and a memory for storing executable instructions of the processor;

[0116] The processor is configured to perform longitudinal alignment control of an unmanned IGV vehicle as described above by executing the executable instructions.

[0117] In a further embodiment, a device is provided, comprising:

[0118] Processor; and

[0119] Memory for storing the executable instructions of the processor;

[0120] The processor is configured to execute the multi-sensor fusion autonomous IGV vehicle alignment longitudinal control method described above by executing the executable instructions.

[0121] The device in this embodiment can realize the above-described multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method. For specific implementation details, please refer to the method embodiment, which will not be repeated here.

[0122] The following reference Figure 9 The apparatus 900 according to this embodiment of the present invention will be described. Figure 9 The device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0123] like Figure 9 As shown, the device 900 is presented in the form of a general-purpose computing device. The components of the device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, and a bus 930 connecting different system components (including storage unit 920 and processing unit 910).

[0124] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 910 can perform actions such as... Figure 1 The multi-sensor fusion longitudinal control method for autonomous IGV vehicles shown is illustrated.

[0125] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 9201 and / or cache memory 9202, and may further include read-only memory (ROM) 9203.

[0126] The storage unit 920 may also include a program / utility 9204 having a set (at least one) program module 9205, such program module 9205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0127] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0128] Device 900 can also communicate with one or more external devices 1000 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with device 900, and / or with any device that enables device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. Figure 9 As shown, network adapter 960 communicates with other modules of device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0129] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0130] In another embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method described in any of the preceding embodiments.

[0131] This embodiment provides a computer-readable storage medium storing a program product capable of implementing the methods described above in this specification. In some possible implementations, various aspects of the present invention can also be implemented as a program product comprising program code, which, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention.

[0132] A program product for implementing the above-described method according to embodiments of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or apparatus.

[0133] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, device, or apparatus.

[0135] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0136] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0137] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0138] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0139] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0140] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A multi-sensor fusion longitudinal control method for positioning of an unmanned IGV vehicle, characterized in that, The steps are as follows: S10. Set up a pre-parking location in an area at a predetermined distance from the target location; S20, the driverless vehicle proceeds to the pre-parking location and stops; S30: The autonomous vehicle obtains the target parking distance from the current vehicle location to the target location; S40. The autonomous vehicle starts and moves towards the target location. Using its onboard motor speed sensor and IMU inertial navigation positioning equipment, it calculates the distance already traveled from the current position to the pre-stop position and the braking distance to the target location. The methods for fitting the traveled distance and the braking distance include: S41. Based on the motor speed and gear information, determine the vehicle's driving direction and speed (positive or negative); step S41 specifically includes: The current motor speed is measured by a motor speed sensor installed inside the drive motor; When the autonomous vehicle is in forward gear and the motor speed is positive, or when the autonomous vehicle is in reverse gear and the motor speed is negative, it is determined that the current driving direction of the autonomous vehicle is consistent with the expected driving direction, the vehicle speed is positive, and the driving speed coefficient value K5 is 1. When the autonomous vehicle is in forward gear and the motor speed is negative, or when the autonomous vehicle is in reverse gear and the motor speed is positive, it is determined that the current driving direction of the autonomous vehicle is inconsistent with the expected driving direction, the vehicle speed is negative, and the driving speed coefficient value K5 is -1. S42. Calculate the real-time driving speed of the unmanned vehicle based on the motor speed, gear information, and driving direction; where the real-time driving speed V is calculated when the drive shaft spins freely or when free spin is coupled with a slope. speed Make corrections, the corrected V speed as follows: ,in: V4 is obtained by integrating the acceleration output of the IMU through the vehicle's IMU inertial navigation positioning device; V min12 The speed is the smaller of speeds V1 and V2. The two shafts of the unmanned vehicle are drive shafts, and each drive shaft is equipped with a drive motor. The speed of each motor is measured by a speed sensor installed in each drive motor. The absolute value of the motor speed and the current gear information of each drive motor are read. The absolute value of the motor speed of each drive motor is multiplied by the corresponding speed ratio to obtain speeds V1 and V2. K5 is the driving speed coefficient value; S43. Based on the real-time driving speed, calculate the distance already traveled by the autonomous vehicle using the following formula: ,in: S move S represents the current distance traveled by the driverless vehicle. add V represents the cumulative distance traveled by the currently autonomous vehicle from its pre-stop position; speed t represents the real-time driving speed of the autonomous vehicle; t is the set control period. The braking distance of the current autonomous vehicle is calculated using the following formula: ,in: S brake The distance to be braked; V speed This represents the current real-time speed of the driverless vehicle. M represents the vehicle's load capacity; K1, K2, K3, and K4 are preset parameters; S50. Calculate the sum of the distance traveled and the distance to be braked, and compare the sum of the distance traveled and the distance to be braked with the target stopping distance obtained in step S30: When the sum of the traveled distance and the braking distance is less than the target stopping distance, braking is performed through the longitudinal PID speed control module; Emergency braking control is triggered when the sum of the distance traveled and the distance to be braked is greater than or equal to the target stopping distance.

2. The multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method according to claim 1, characterized in that: Error corrections are applied to the distance already traveled by the autonomous vehicle. The corrected distance is S. move1 , , where: S add C1 represents the cumulative distance traveled by the current autonomous vehicle from the pre-parking position; C2 are preset parameters.

3. The multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method according to claim 1, characterized in that: The unmanned vehicle has two drive shafts, each equipped with a drive motor. During normal driving, step S42 specifically includes: The speed of each motor is measured by a speed sensor installed inside each drive motor; Read the absolute value of the motor speed and the current gear information of each drive motor. Multiply the absolute value of the motor speed of each drive motor by the corresponding speed ratio to obtain speed V1 and speed V2. According to the formula... Calculate the real-time driving speed V speed Where: K5 is the driving speed coefficient value.

4. The multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method according to any one of claims 1-3, characterized in that: The longitudinal PID speed control module includes: The receiving unit is used to receive the initial target velocity V. tar1 ; A limiting unit is used to determine the jump step value K based on the configuration of the autonomous vehicle. tar For the initial target velocity V tar1 To achieve the planned speed V, constraints are imposed. tar2 ; Deviation calculation unit, used to calculate the planned velocity V tar2 Current speed V as reflected by the chassis veh The speed deviation V between diff ; The acceleration control unit processes the velocity deviation V through a PID acceleration controller. diff To obtain the target acceleration A tar ; The filtering unit processes the differential speed A from the chassis feedback. speed_ori A first-order low-pass filter is applied, and the acceleration value A output from the positioning IMU sensor is combined. imu The current acceleration A is solved by complementary filtering. veh ; The acceleration deviation calculation unit is used to calculate the current acceleration A. veh With target acceleration A tar The acceleration deviation A between diff ; The throttle increment / decrease control unit processes the acceleration deviation A through a PID throttle increment / decrease controller. diff To obtain the throttle increase / decrease T comp ; The target throttle total calculation unit uses the current throttle total T fed back from the chassis. now and throttle increase / decrease T comp Calculate the initial target total switch value T tar1 .

5. The multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method according to claim 4, characterized in that: The longitudinal PID speed control module also includes a verification unit, which verifies the initial target switch total T. tar1 Verification is performed, including verification based on the braking priority principle, verification with maximum and minimum values, verification in the case of negative numbers, and judgment and output of the minimum total throttle value.

6. The multi-sensor fusion unmanned IGV vehicle alignment longitudinal control method according to claim 4, characterized in that: In the limiting unit, if the initial planned target speed V tar1 Compared with the target velocity V at the previous moment tar_last If the difference is greater than the set speed difference value, then the target speed V at the current moment will be set. tar2 Set as the target velocity V at the previous moment tar_last Add the set speed difference.

7. A control device, characterized in that, include: processor; and memory for storing the executable instructions of the processor; The processor is configured to execute the multi-sensor fusion autonomous IGV vehicle alignment longitudinal control method of any one of claims 1-6 by executing the executable instructions.

Images