CN114265416B

CN114265416B - AGV trolley control method and device, electronic equipment and storage medium

Info

Publication number: CN114265416B
Application number: CN202210188031.9A
Authority: CN
Inventors: 袁悦; 付鑫; 范朝龙
Original assignee: Individual
Current assignee: Individual
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-06-28
Anticipated expiration: 2042-02-28
Also published as: CN114265416A

Abstract

The application belongs to the technical field of robot control and discloses an AGV trolley control method, an AGV trolley control device, electronic equipment and a storage medium, wherein 6 ultrasonic sensors are respectively arranged right in front of, left in front of, right in back of, left in back of and right in back of a chassis of the AGV trolley, visual equipment or other equipment is not required to be arranged, and implementation cost is greatly reduced; comparing the obstacle distance data detected by 6 ultrasonic sensors with a first preset distance threshold value, selecting a preset basic obstacle avoidance rule according to a comparison result to acquire a system instruction, or acquiring the system instruction by adopting a pre-trained prediction model, and controlling the AGV trolley to move according to the system instruction; the method can adapt to uncertain factors in the actual operation environment, so that the AGV trolley can simply and quickly realize autonomous obstacle avoidance.

Description

AGV trolley control method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of robot control, in particular to an AGV trolley control method and device, electronic equipment and a storage medium.

Background

In recent years, robots and artificial intelligence technologies are rapidly developed, safe, reliable and flexible AGV (automated Guided vehicle) trolleys play an increasingly important role in aspects of intelligent routing inspection, article taking and delivering in hotels/restaurants and the like, and the key problems in the application of the AGV trolleys are path planning and dynamic obstacle avoidance capabilities, wherein the dynamic obstacle avoidance capabilities are the basis of the AGV trolleys having self-navigation capabilities, because the AGV trolleys often have more or less uncertain factors in the actual running environment, for example, when the AGV trolleys encounter obstacles equidistant from left and right sensors, the AGV trolleys swing left and right and even stop moving, so that the articles cannot be delivered to destinations in time, and therefore, the adaptability of the AGV trolleys to the environment and the self-obstacle avoidance capabilities are of great importance. The autonomous obstacle avoidance control function and navigation of the AGV can be realized by using a vision technology at present, but the implementation cost is high, so that the AGV is not widely applied.

Disclosure of Invention

The application aims to provide an AGV trolley control method, an AGV trolley control device, electronic equipment and a storage medium, which can simply and quickly realize autonomous obstacle avoidance, adapt to uncertain factors in an actual operation environment and are low in implementation cost.

In a first aspect, the application provides an AGV trolley control method, which is applied to an AGV trolley control system, wherein the AGV trolley comprises 6 ultrasonic sensors, and the 6 ultrasonic sensors are respectively arranged right in front of a chassis of the AGV trolley, left in front of the chassis, right in back of the chassis, left in back of the chassis and right in back of the chassis of the AGV trolley; the AGV trolley control method comprises the following steps:

acquiring obstacle detection data including obstacle distance data detected by 6 ultrasonic sensors;

comparing the obstacle detection data with a first preset distance threshold value;

acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to a comparison result;

and controlling the AGV to move according to the system instruction.

According to the AGV trolley control method, the 6 ultrasonic sensors are respectively arranged right in front of, left in front of, right in back of, left in back of and right in back of the chassis of the AGV trolley, the ultrasonic sensors are selected and used for measuring rapidly, calculating is simple, real-time control is easy to achieve, the industrial and practical requirements can be met in the aspect of measuring precision, visual equipment or other equipment is not needed, and the implementation cost is greatly reduced; the method comprises the steps of comparing obstacle distance data detected by 6 ultrasonic sensors with a first preset distance threshold value, selecting preset basic obstacle avoidance rules according to a comparison result to acquire system instructions, controlling the AGV to move through the system instructions, or acquiring the system instructions by adopting a pre-trained prediction model to further control the AGV to move, and adapting to uncertain factors in an actual operation environment through the pre-trained prediction model, so that the AGV can simply and quickly realize autonomous obstacle avoidance.

Preferably, the step of obtaining the system instruction by using a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result comprises:

if the obstacle distance data detected by at least one ultrasonic sensor is smaller than a first preset distance threshold value, acquiring a system instruction by adopting a preset basic obstacle avoidance rule;

and if the obstacle distance data detected by all the ultrasonic sensors are not smaller than a first preset distance threshold value, acquiring a system instruction by adopting a pre-trained prediction model.

When the AGV car actually runs, considering the transmission time delay of the data of the ultrasonic sensors and the time delay of the prediction model for outputting a system instruction result, setting a first preset distance threshold value for ensuring that the running AGV car does not collide with a barrier and ensuring the safety of the running AGV car, and when the barrier distance data detected by at least one ultrasonic sensor is smaller than the first preset distance threshold value, acquiring a system instruction by adopting a preset basic barrier avoiding rule, so that the efficiency of acquiring the system instruction is improved, and the reaction time is reduced; when the distance data of the obstacles detected by all the ultrasonic sensors are not smaller than a first preset distance threshold value, a pre-trained prediction model is adopted to obtain a system instruction, so that the obstacles can be effectively avoided.

Preferably, the preset basic obstacle avoidance rule is as follows:

when the AGV trolley moves forwards, if the obstacle distance data detected by the ultrasonic sensors right in front of the AGV trolley are smaller than a second preset distance threshold value, the obstacle distance data detected by the ultrasonic sensors right in front of the AGV trolley are respectively compared with a third preset distance threshold value, and the operation required to be executed is determined according to the comparison result;

when the AGV trolley retreats, if the obstacle distance data detected by the ultrasonic sensors at the right back part are smaller than the second preset distance threshold value, the obstacle distance data detected by the ultrasonic sensors at the left back part and the right back part are respectively compared with the third preset distance threshold value, and the operation required to be executed is determined according to the comparison result;

the step of obtaining the system instruction by adopting the preset basic obstacle avoidance rule comprises the following steps:

and acquiring a corresponding system instruction according to the operation to be executed.

Preferably, when the AGV trolley moves forward, if the obstacle distance data detected by the ultrasonic sensors right in front are smaller than a second preset distance threshold, the obstacle distance data detected by the ultrasonic sensors right in front and left are respectively compared with a third preset distance threshold, and the operation to be executed is determined according to the comparison result, specifically:

If the obstacle distance data detected by the ultrasonic sensor at the front left is larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are different, the operation to be executed is a left-turn operation;

if the obstacle distance data detected by the ultrasonic sensor at the front right is larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensor at the front left is not larger than the third preset distance threshold value, the operation to be executed is a right-turn operation;

if the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are not greater than a third preset distance threshold, the operation to be executed is a backward operation;

if the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are both larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are the same, the operation to be executed is a stop operation.

Preferably, when the AGV is retreated, if the obstacle distance data detected by the ultrasonic sensors right behind is smaller than the second preset distance threshold, the obstacle distance data detected by the ultrasonic sensors right behind and left behind are respectively compared with the third preset distance threshold, and the operation to be executed is determined according to the comparison result, specifically:

If the obstacle distance data detected by the ultrasonic sensors at the left rear part are larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are different, the operation to be executed is a left-turn operation;

if the obstacle distance data detected by the ultrasonic sensor at the rear right side is larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensor at the rear left side is not larger than the third preset distance threshold value, the operation to be executed is a right-turn operation;

if the obstacle distance data detected by the ultrasonic sensors on the left rear side and the right rear side are not larger than a third preset distance threshold value, the operation to be executed is a forward operation;

if the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are both larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are the same, the operation to be executed is a stopping operation.

Preferably, if the obstacle distance data detected by all the ultrasonic sensors are not less than a first preset distance threshold, the step of obtaining a system instruction by using a pre-trained prediction model includes:

And inputting the obstacle distance data detected by the 6 ultrasonic sensors into a pre-trained prediction model to obtain a system instruction output by the prediction model.

Preferably, the prediction model is trained by:

controlling the AGV trolley to move by adopting a preset basic obstacle avoidance rule so as to acquire running data serving as a training data set; the operation data comprises the obstacle distance data detected by the 6 ultrasonic sensors and corresponding system instructions;

adjusting the training data set: manually adjusting system instructions in running data in which the obstacle distance data detected by the ultrasonic sensors at the front right and the front left are both larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are the same; manually adjusting system instructions in operation data, wherein the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are both larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are the same;

And training a prediction model by using the training data set after the adjustment processing.

When the AGV trolley runs in a special scene in actual operation, the training data set is adjusted, namely the AGV trolley runs when the distance data of the obstacles detected by the ultrasonic sensors in the left front and the right front are the same, or the distance data of the obstacles detected by the ultrasonic sensors in the left back and the right back are the same, the AGV trolley can swing left and right or stop moving, at the moment, the system instruction of the AGV trolley is adjusted manually, the AGV trolley can continue to run normally, and the training data set after adjustment processing is used for training a prediction model, so that the AGV trolley can adapt to uncertain factors in the actual operation environment, and the automatic obstacle avoidance can be realized simply and quickly.

In a second aspect, the application provides an AGV dolly control device is applied to the control system of AGV dolly, the AGV dolly includes 6 ultrasonic sensor, 6 ultrasonic sensor installs respectively the AGV dolly chassis the dead ahead, left place ahead, right front, dead behind, left rear, right rear, include:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring obstacle detection data, and the obstacle detection data comprises obstacle distance data detected by 6 ultrasonic sensors;

The detection module is used for comparing the obstacle detection data with a first preset distance threshold value;

the second acquisition module is used for acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result;

and the control module is used for controlling the AGV to move according to the system instruction.

According to the AGV trolley control device, the 6 ultrasonic sensors are respectively arranged right in front of, left in front of, right in back of, left in back of and right in back of the chassis of the AGV trolley, the ultrasonic sensors are selected for use, based on the measurement, the measurement is rapid, the calculation is simple, the real-time control is easy to achieve, the industrial and practical requirements can be met in the aspect of measurement precision, visual equipment or other equipment is not required to be arranged, and the implementation cost is greatly reduced; the method comprises the steps of comparing obstacle distance data detected by 6 ultrasonic sensors with a first preset distance threshold value, selecting preset basic obstacle avoidance rules according to a comparison result to acquire system instructions, controlling the AGV to move through the system instructions, or acquiring the system instructions by adopting a pre-trained prediction model to further control the AGV to move, and adapting to uncertain factors in an actual operation environment through the pre-trained prediction model, so that the AGV can simply and quickly realize autonomous obstacle avoidance.

In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor executes the computer program to perform the steps of the AGV cart control method as described above.

In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, which when executed by a processor, performs the steps of the AGV car control method as described above.

Has the beneficial effects that:

according to the AGV trolley control method, the AGV trolley control device, the electronic equipment and the storage medium, the 6 ultrasonic sensors are respectively arranged in the front right, the front left, the front right, the rear left and the rear right of the AGV trolley chassis, the ultrasonic sensors are selected and used for measuring rapidly, calculating simply and easily achieving real-time control, the industrial practical requirement can be achieved in the aspect of measuring precision, visual equipment or other equipment is not needed, and the implementation cost is greatly reduced; obstacle distance data detected by 6 ultrasonic sensors are compared with a first preset distance threshold value, a preset basic obstacle avoidance rule is selected according to a comparison result to acquire a system instruction, the AGV trolley is controlled to move through the system instruction, or a pre-trained prediction model is adopted to acquire the system instruction and further control the AGV trolley to move, the pre-trained prediction model can adapt to uncertain factors in an actual operation environment, and the AGV trolley can simply and quickly realize autonomous obstacle avoidance.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application.

Drawings

FIG. 1 is a flowchart of an AGV trolley control method provided in the present application.

FIG. 2 is a schematic diagram of an AGV trolley control apparatus according to the present disclosure.

Fig. 3 is a schematic structural diagram of an electronic device provided in the present application.

Fig. 4 is a schematic diagram illustrating a position where the ultrasonic sensor provided in the present application is installed.

1, a first acquisition module; 2. a detection module; 3. a second acquisition module; 4. a control module; 5. an ultrasonic sensor; 301. a processor; 302. a memory; 303. a communication bus.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.

Referring to fig. 1, fig. 1 is a flowchart of an AGV cart control method in some embodiments of the present application, which can implement autonomous obstacle avoidance simply and quickly, adapt to uncertain factors in an actual operating environment, and is low in implementation cost.

In a first aspect, the application provides an AGV trolley control method, which is applied to an AGV trolley control system, wherein the AGV trolley comprises 6 ultrasonic sensors 5, and the 6 ultrasonic sensors 5 are respectively arranged in the front right, the front left, the front right, the rear left and the rear right of a chassis of the AGV trolley; the AGV trolley control method comprises the following steps:

s1, obstacle detection data are obtained, wherein the obstacle detection data comprise obstacle distance data detected by 6 ultrasonic sensors 5;

s2, comparing the obstacle detection data with a first preset distance threshold;

S3, acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result;

and S4, controlling the AGV trolley to move according to the system instruction.

In some embodiments, the specific mounting positions of the 6 ultrasonic sensors 5 are as shown in fig. 4; the ultrasonic ranging principle is as follows: the ultrasonic transmitter transmits ultrasonic waves to a certain direction, timing is started at the same time of transmitting time, the ultrasonic waves propagate in the air and return immediately when encountering an obstacle in the process, and the ultrasonic receiver stops timing immediately when receiving reflected waves. The propagation speed of the ultrasonic wave in the air is v, and the distance s = (v × t)/2 of the transmitting point from the obstacle can be calculated according to the time t recorded by the timer. Since the direction of the ultrasonic sensor 5 affects the distance measurement data, the left front, right front, left back and right back of the AGV car are respectively arranged at the four corners of the AGV car, which are arranged to make the data measured by the ultrasonic sensor 5 more accurate, wherein the ultrasonic sensor 5 in the front left inclines and installs on the car angle of AGV dolly, the ultrasonic sensor 5 in the front right inclines and installs on the car angle of AGV dolly, the ultrasonic sensor 5 in the rear left inclines and installs on the car angle of AGV dolly, the ultrasonic sensor 5 in the rear right inclines and installs on the car angle of AGV dolly, this example is preferred, the central axis of the ultrasonic sensor 5 on four angles of AGV dolly all inclines 45 degrees towards the outside, as shown in fig. 4, the specific position of the ultrasonic sensor 5 is not limited to this, which avoids the corner of the AGV from easily colliding with the obstacle; the ultrasonic sensor 5 is selected based on the measurement speed, the calculation is simple, the real-time control is easy to realize, the requirement of industrial practicality can be met in the aspect of measurement precision, visual equipment or other equipment is not required to be arranged, and the implementation cost is greatly reduced; obstacle distance data detected by 6 ultrasonic sensors 5 are compared with a first preset distance threshold value, a preset basic obstacle avoidance rule is selected according to a comparison result to acquire a system instruction, the AGV trolley is controlled to move through the system instruction, or a pre-trained prediction model is adopted to acquire the system instruction and further control the AGV trolley to move, the pre-trained prediction model can adapt to uncertain factors in an actual operation environment, and the AGV trolley can simply and quickly realize autonomous obstacle avoidance.

In some embodiments, in order to ensure that the running AGV does not collide with the obstacle and ensure the safety of the AGV, a first preset distance threshold needs to be set; according to the comparison result, the step of acquiring the system instruction by adopting a preset basic obstacle avoidance rule or the step of acquiring the system instruction by adopting a pre-trained prediction model comprises the following steps:

if the obstacle distance data detected by at least one ultrasonic sensor 5 is smaller than a first preset distance threshold value, acquiring a system instruction by adopting a preset basic obstacle avoidance rule;

if the obstacle distance data detected by all the ultrasonic sensors 5 are not smaller than the first preset distance threshold value, a pre-trained prediction model is adopted to obtain a system instruction.

In practical application, in consideration of the transmission time delay of data of the ultrasonic sensors 5 and the time delay of the instruction result of the prediction model output system, in order to ensure that the running AGV does not collide with the obstacle and ensure the safety of the AGV, a first preset distance threshold value can be set according to the size of the AGV body, for example, the first preset distance threshold value can be set to be 50cm for the AGV body with the length of 0.5m and the width of the AGV body of 60cm, and if the obstacle distance data detected by at least one ultrasonic sensor 5 is less than 50cm, a preset basic obstacle avoidance rule is adopted to obtain a system instruction, wherein the logic of the preset basic obstacle avoidance rule is simple, the system instruction is rapidly obtained, and the reaction time is shortened; if the obstacle distance data detected by all the ultrasonic sensors 5 are not less than 50cm, a pre-trained prediction model is adopted to obtain a system instruction.

In some embodiments, the preset basic obstacle avoidance rule is:

when the AGV trolley moves forwards, if the obstacle distance data detected by the ultrasonic sensors 5 in front of the AGV trolley are smaller than a second preset distance threshold value, the obstacle distance data detected by the ultrasonic sensors 5 in front of the left side and the right side are respectively compared with a third preset distance threshold value, and the operation required to be executed is determined according to the comparison result;

when the AGV retreats, if the obstacle distance data detected by the ultrasonic sensors 5 at the right back side are smaller than a second preset distance threshold value, the obstacle distance data detected by the ultrasonic sensors 5 at the left back side and the right back side are respectively compared with a third preset distance threshold value, and the operation to be executed is determined according to the comparison result;

the method for acquiring the system instruction by adopting the preset basic obstacle avoidance rule comprises the following steps:

and acquiring a corresponding system instruction according to the operation required to be executed.

In practical application, the second preset distance threshold and the third preset distance threshold may be set according to a size of an AGV car body, for example, for an AGV car with a car body length of 0.5m and a car body width of 60cm, the second preset distance threshold may be set to 30cm, the third preset distance threshold may be set to 10cm, when the AGV car advances, and when the obstacle distance data detected by the ultrasonic sensor 5 in front is less than 30cm, the obstacle distance data detected by the ultrasonic sensor 5 in front of the AGV car is compared with 10cm, and the operation to be executed is determined according to the comparison result.

In some embodiments, when the AGV cart advances, if the obstacle distance data detected by the front ultrasonic sensor is smaller than the second preset distance threshold, the obstacle distance data detected by the front left and right ultrasonic sensors are respectively compared with the third preset distance threshold, and the operation to be executed is determined according to the comparison result, specifically:

if the obstacle distance data detected by the ultrasonic sensor 5 at the front left is greater than the third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensor 5 at the front left and the ultrasonic sensor 5 at the front right are different, the operation to be executed is a left-turn operation (thus, the corresponding system instruction is a left-turn instruction);

if the obstacle distance data detected by the ultrasonic sensor 5 at the front right is greater than a third preset distance threshold, and the obstacle distance data detected by the ultrasonic sensor 5 at the front left is not greater than the third preset distance threshold, the operation to be executed is a right turn operation (thus, the corresponding system instruction is a right turn instruction);

if the obstacle distance data detected by the ultrasonic sensors 5 at the front left and the front right are not greater than the third preset distance threshold, the operation to be executed is a backward operation (thus, the corresponding system instruction is a backward instruction);

If the obstacle distance data detected by the ultrasonic sensors 5 at the front left and right are both greater than the third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors 5 at the front left and right are the same, the operation to be performed is a stop operation (thus, the corresponding system command is a stop command).

For example, when the third preset distance threshold is 10cm, when the obstacle distance data detected by the ultrasonic sensor 5 in the front left is greater than 10cm and the obstacle distance data detected by the ultrasonic sensors 5 in the front left and the front right are different, the operation to be performed is a left-turn operation, so that the AGV is controlled to move left to avoid an obstacle;

when the distance data of the obstacle detected by the ultrasonic sensor 5 at the front right is more than 10cm and the distance data of the obstacle detected by the ultrasonic sensor 5 at the front left is not more than 10cm, the operation to be executed is a right-turning operation, so that the AGV trolley is controlled to move rightwards to avoid the obstacle;

when the distance data of the obstacles detected by the ultrasonic sensors 5 at the front left and the front right are not more than 10cm, the operation to be executed is a backward operation, so that the AGV trolley is controlled to move backward to avoid the obstacles;

When the obstacle distance data detected by the ultrasonic sensors 5 at the front left and right are both greater than 10cm and the obstacle distance data detected by the ultrasonic sensors 5 at the front left and right are the same, the operation to be performed is a stop operation, thereby controlling the AGV cart to stop moving.

In this embodiment, when the AGV cart is retreated, if the obstacle distance data detected by the ultrasonic sensors right behind is smaller than the second preset distance threshold, the obstacle distance data detected by the ultrasonic sensors right behind and left behind are respectively compared with the third preset distance threshold, and the operation to be executed is determined according to the comparison result, which specifically includes:

if the obstacle distance data detected by the ultrasonic sensor 5 at the left rear side is greater than the third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors 5 at the left rear side and the right rear side are different, the operation to be executed is a left turn operation (so that the corresponding system instruction is a left turn instruction);

if the obstacle distance data detected by the right rear ultrasonic sensor 5 is greater than a third preset distance threshold, and the obstacle distance data detected by the left rear ultrasonic sensor 5 is not greater than the third preset distance threshold, the operation to be executed is a right turn operation (so that the corresponding system instruction is a right turn instruction);

If the obstacle distance data detected by the ultrasonic sensors 5 at the left rear side and the right rear side are not greater than the third preset distance threshold, the operation to be executed is a forward operation (thus, the corresponding system instruction is a forward instruction);

if the obstacle distance data detected by the ultrasonic sensors 5 at the left rear and the right rear are both greater than the third preset distance threshold, and the obstacle distance data detected by the ultrasonic sensors 5 at the left rear and the right rear are the same, the operation to be executed is a stop operation (thus, the corresponding system instruction is a stop instruction).

For example, when the third preset distance threshold is 10cm, when the obstacle distance data detected by the ultrasonic sensor 5 at the left rear is greater than 10cm and the obstacle distance data detected by the ultrasonic sensors 5 at the left rear and the right rear are different, the operation to be executed is a left-turn operation, so that the AGV trolley is controlled to turn left to avoid an obstacle;

when the obstacle distance data detected by the ultrasonic sensor 5 at the rear right part is larger than 10cm and the obstacle distance data detected by the ultrasonic sensor 5 at the rear left part is not larger than 10cm, the operation to be executed is a right-turning operation, so that the AGV trolley is controlled to turn right to avoid the obstacle;

When the distance data of the obstacles detected by the ultrasonic sensors 5 at the left back and the right back are not more than 10cm, the operation to be executed is a forward operation, so that the AGV trolley is controlled to move forward;

when the obstacle distance data detected by the ultrasonic sensors 5 at the left back and the right back are both larger than 10cm and the obstacle distance data detected by the ultrasonic sensors 5 at the left back and the right back are the same, the operation to be executed is a stopping operation, so that the AGV trolley is controlled to stop moving;

in some embodiments, if the obstacle distance data detected by all the ultrasonic sensors 5 is not less than the first preset distance threshold, the step of obtaining the system instruction by using the pre-trained prediction model includes:

obstacle distance data detected by 6 ultrasonic sensors 5 are input into a pre-trained prediction model to obtain a system instruction output by the prediction model.

In practical applications, the prediction model is a model based on a machine learning algorithm (such as, but not limited to, a decision tree, naive bayes, a support vector machine, etc.).

In this embodiment, the prediction model is trained by:

controlling the AGV to move by adopting a preset basic obstacle avoidance rule so as to acquire operation data serving as a training data set; the operation data comprises obstacle distance data detected by 6 ultrasonic sensors 5 and corresponding system instructions;

Adjusting the training data set: manually adjusting system instructions in running data in which the obstacle distance data detected by the ultrasonic sensors 5 at the front right and the front left are both larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors 5 at the front left and the front right are the same; the obstacle distance data detected by the ultrasonic sensors 5 at the left back and the right back are both larger than a third preset distance threshold value, and system instructions in the operation data with the same obstacle distance data detected by the ultrasonic sensors 5 at the left back and the right back are manually adjusted;

and training the prediction model by using the training data set after the adjustment processing.

The method comprises the following steps of controlling the AGV trolley to move by adopting a preset basic obstacle avoidance rule so as to acquire operation data serving as a training data set, wherein the steps comprise:

periodically acquiring barrier distance data detected by 6 ultrasonic sensors 5 at a preset period (which can be set according to actual needs);

acquiring system instructions according to the obstacle distance data detected by the 6 ultrasonic sensors 5 (in the specific process, reference is made to the step of acquiring the system instructions by adopting a preset basic obstacle avoidance rule), and controlling the AGV trolley to move according to the system instructions;

The obstacle distance data detected by 6 ultrasonic sensors 5 and the corresponding system command acquired each time are taken as a training data sample, and a plurality of training data samples are taken as a training data set.

The step of performing adjustment processing on the training data set comprises:

A1. if one of the following conditions of the training data samples exists, displaying the corresponding training data samples, and sending out a reminding signal to prompt that the system instruction of the training data samples needs to be manually adjusted:

the method comprises the following steps that under the condition that an AGV is in a forward movement process, barrier distance data detected by ultrasonic sensors 5 in the front right and the front left are both larger than a third preset distance threshold value, and the barrier distance data detected by the ultrasonic sensors 5 in the front left and the front right are the same;

the AGV trolley is in a backward movement process, the obstacle distance data detected by the ultrasonic sensors 5 on the left rear side and the right rear side are both larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors 5 on the left rear side and the right rear side are the same;

A2. acquiring adjustment information; the adjustment information comprises manually adjusted system instruction information of the training data sample;

A3. and adjusting the system instruction of the training data sample according to the adjusting information.

Specifically, when the prediction model is trained using the adjusted training data set, the distance data of the obstacle detected by the 6 ultrasonic sensors 5 in each training data sample is used as a feature, and the system command is input to the prediction model as a tag for training. The essence of the training is to find the mapping relationship between the features and the tags, and when the system is used, the tags (i.e. system instructions) are output according to the relationship between the features and the tags of the trained prediction model by the obstacle distance data (i.e. the features) of the current AGV, so as to obtain the system instructions for controlling the movement of the AGV.

According to the AGV control method, obstacle detection data are obtained, and the obstacle detection data comprise obstacle distance data detected by 6 ultrasonic sensors 5; comparing the obstacle detection data with a first preset distance threshold value; acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to a comparison result; controlling the AGV to move according to a system instruction; therefore, autonomous obstacle avoidance can be simply and quickly realized, uncertain factors in the actual operation environment are adapted, and the implementation cost is low.

Please refer to fig. 2, the present application provides an AGV dolly control device, which is applied to a control system of an AGV dolly, the AGV dolly includes 6 ultrasonic sensors 5, the 6 ultrasonic sensors 5 are respectively installed at the front, the left front, the right front, the left back and the right back of the chassis of the AGV dolly, the AGV dolly control device includes:

the system comprises a first acquisition module 1, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring obstacle detection data, and the obstacle detection data comprises obstacle distance data detected by 6 ultrasonic sensors 5;

the detection module 2 is used for comparing the obstacle detection data with a first preset distance threshold value;

the second obtaining module 3 is used for obtaining the system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result;

and the control module 4 is used for controlling the AGV to move according to the system instruction.

In some embodiments, the specific mounting positions of the 6 ultrasonic sensors 5 are as shown in fig. 4; the ultrasonic ranging principle is as follows: the ultrasonic transmitter transmits ultrasonic waves to a certain direction, timing is started at the same time of transmitting time, the ultrasonic waves propagate in the air and return immediately when encountering an obstacle in the process, and the ultrasonic receiver stops timing immediately when receiving reflected waves. The propagation speed of the ultrasonic wave in the air is v, and the distance s = (v × t)/2 of the transmitting point from the obstacle can be calculated according to the time t recorded by the timer. Since the direction of the ultrasonic sensor 5 affects the distance measurement data, the left front, right front, left back and right back of the AGV car are respectively arranged at the four corners of the AGV car, which are arranged to make the data measured by the ultrasonic sensor 5 more accurate, wherein the ultrasonic sensor 5 in the front left inclines and installs on the car angle of AGV dolly, the ultrasonic sensor 5 in the front right inclines and installs on the car angle of AGV dolly, the ultrasonic sensor 5 in the rear left inclines and installs on the car angle of AGV dolly, the ultrasonic sensor 5 in the rear right inclines and installs on the car angle of AGV dolly, this example is preferred, the central axis of the ultrasonic sensor 5 on four angles of AGV dolly all inclines 45 degrees towards the outside, as shown in fig. 4, the specific position of the ultrasonic sensor 5 is not limited to this, which avoids the corner of the AGV from easily colliding with the obstacle; the ultrasonic sensor 5 is selected based on the measurement speed, the calculation is simple, the real-time control is easy to realize, the requirement of industrial practicality can be met in the aspect of measurement precision, visual equipment or other equipment is not required to be arranged, and the implementation cost is greatly reduced; when the obstacle distance data is compared with the first preset distance threshold value, the preset basic obstacle avoidance rule is selected according to the comparison result to acquire the system instruction, the AGV trolley is controlled to move through the system instruction, or the pre-trained prediction model is adopted to acquire the system instruction and further control the AGV trolley to move, the pre-trained prediction model can adapt to uncertain factors in the actual operation environment, and therefore the AGV trolley can simply and quickly achieve autonomous obstacle avoidance.

In some embodiments, in order to ensure that the running AGV does not collide with the obstacle and ensure the safety of the AGV, a first preset distance threshold needs to be set; the second obtaining module 3 executes the following steps when obtaining the system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result:

In practical application, in consideration of the transmission delay of data of the ultrasonic sensor 5 and the delay of a prediction model output system instruction result, in order to ensure that an AGV trolley in operation does not collide with a barrier and ensure the safety of the AGV trolley, a first preset distance threshold value can be set according to the size of the AGV trolley, for example, for the AGV trolley with the length of 0.5m and the width of 60cm, the first preset distance threshold value can be set to be 50cm, and if the barrier distance data detected by at least one ultrasonic sensor 5 is smaller than 50cm, a preset basic barrier avoiding rule is adopted to obtain a system instruction, wherein the logic of the preset basic barrier avoiding rule is simple, the system instruction is rapidly obtained, and the reaction time is shortened; if the obstacle distance data detected by all the ultrasonic sensors 5 are not less than 50cm, a pre-trained prediction model is adopted to obtain a system instruction.

In some embodiments, the preset basic obstacle avoidance rule is:

In practical application, the second preset distance threshold and the third preset distance threshold may be set according to the size of the AGV car body, for example, for an AGV car with a car body length of 0.5m and a car body width of 60cm, the second preset distance threshold may be set to 30cm, the third preset distance threshold may be set to 10cm, when the AGV car advances, and when the obstacle distance data detected by the ultrasonic sensor 5 in front is less than 30cm, the obstacle distance data detected by the ultrasonic sensors 5 in front of the left and right are respectively compared with 10cm, the operation to be executed is determined according to the comparison result, and thus the operation to be executed is obtained as the corresponding system instruction.

In some embodiments, when the AGV moves forward, if the obstacle distance data detected by the front ultrasonic sensor is smaller than the second preset distance threshold, the obstacle distance data detected by the front ultrasonic sensors are respectively compared with the third preset distance threshold, and the operation to be performed is determined according to the comparison result, specifically:

if the obstacle distance data detected by the ultrasonic sensor 5 at the front left is greater than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors 5 at the front left and the front right are different, the operation to be executed is a left-turn operation (so that the corresponding system instruction is a left-turn instruction);

When the obstacle distance data detected by the ultrasonic sensors 5 at the front left and right are both larger than 10cm and the obstacle distance data detected by the ultrasonic sensors 5 at the front left and right are the same, the operation to be performed is a stop operation, so that the AGV cart is controlled to stop moving.

in some embodiments, when executing that if all the obstacle distance data detected by the ultrasonic sensors 5 are not less than the first preset distance threshold, the second obtaining module 3 obtains a system instruction by using a pre-trained prediction model, specifically executes:

In practical applications, the prediction model is a model based on a machine learning algorithm (such as a decision tree, naive bayes, a support vector machine, and the like, but is not limited thereto).

In this embodiment, the prediction model is obtained by training as follows:

Controlling the AGV trolley to move by adopting a preset basic obstacle avoidance rule so as to acquire running data serving as a training data set; the operation data comprises obstacle distance data detected by 6 ultrasonic sensors 5 and corresponding system instructions;

adjusting the training data set: manually adjusting system instructions in the operation data in which the obstacle distance data detected by the ultrasonic sensors 5 in the front left and the front right are both larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors 5 in the front left and the front right are the same; manually adjusting system instructions in the operation data in which the obstacle distance data detected by the ultrasonic sensors 5 at the left rear part and the right rear part are both larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors 5 at the left rear part and the right rear part are the same;

and training the prediction model by using the adjusted training data set.

periodically acquiring obstacle distance data detected by 6 ultrasonic sensors 5 at a preset period (which can be set according to actual needs);

the obstacle distance data detected by 6 ultrasonic sensors 5 and the corresponding system instructions acquired at a time are taken as a training data sample, and a plurality of training data samples are taken as a training data set.

The step of adjusting the training data set comprises:

Therefore, according to the AGV control device provided by the application, obstacle detection data are obtained, and the obstacle detection data comprise obstacle distance data detected by 6 ultrasonic sensors 5; comparing the obstacle detection data with a first preset distance threshold value; acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to a comparison result; controlling the AGV to move according to a system instruction; therefore, autonomous obstacle avoidance can be simply and quickly realized, uncertain factors in the actual operation environment are adapted, and the implementation cost is low.

Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure, where the electronic device includes: the processor 301 and the memory 302, the processor 301 and the memory 302 are interconnected and intercommunicated through the communication bus 303 and/or other types of connection mechanisms (not shown), and the memory 302 stores a computer program executable by the processor 301, and when the electronic device is running, the processor 301 executes the computer program to execute the AGV cart control method in any alternative implementation manner of the above embodiment to realize the following functions: obstacle detection data are obtained, wherein the obstacle detection data comprise obstacle distance data detected by 6 ultrasonic sensors; comparing the obstacle detection data with a first preset distance threshold value; acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to a comparison result; and controlling the AGV to move according to the system instruction.

The embodiment of the present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the AGV cart control method in any optional implementation manner of the foregoing embodiment is executed, so as to implement the following functions: acquiring obstacle detection data, wherein the obstacle detection data comprises obstacle distance data detected by 6 ultrasonic sensors; comparing the obstacle detection data with a first preset distance threshold value; acquiring a system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to a comparison result; and controlling the AGV to move according to the system instruction. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. The AGV comprises 6 ultrasonic sensors, and the 6 ultrasonic sensors are respectively arranged right in front, left in front, right in back, left in back and right in back of a chassis of the AGV; the AGV trolley control method comprises the following steps:

comparing the obstacle detection data with a first preset distance threshold;

the step of acquiring the system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result comprises the following steps:

if the distance data of the obstacles detected by at least one ultrasonic sensor is smaller than the first preset distance threshold value, acquiring a system instruction by adopting a preset basic obstacle avoidance rule;

if the obstacle distance data detected by all the ultrasonic sensors are not smaller than the first preset distance threshold value, acquiring a system instruction by adopting a pre-trained prediction model;

if the obstacle distance data detected by all the ultrasonic sensors are not smaller than the first preset distance threshold, the step of acquiring system instructions by adopting a pre-trained prediction model comprises the following steps:

inputting the obstacle distance data detected by 6 ultrasonic sensors into the pre-trained prediction model to obtain a system instruction output by the prediction model;

the prediction model is obtained by training in the following way:

Controlling the AGV trolley to move by adopting the preset basic obstacle avoidance rule so as to acquire running data serving as a training data set; the operation data comprises the obstacle distance data detected by the 6 ultrasonic sensors and corresponding system instructions;

adjusting the training data set: manually adjusting system instructions in running data in which the obstacle distance data detected by the ultrasonic sensors at the front right and the front left are both larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are the same; the obstacle distance data detected by the ultrasonic sensors at the left back and the right back are both larger than a third preset distance threshold value, and system instructions in running data with the same obstacle distance data detected by the ultrasonic sensors at the left back and the right back are manually adjusted;

taking obstacle distance data detected by the 6 ultrasonic sensors and corresponding system instructions acquired each time as a training data sample, and taking a plurality of training data samples as the training data set;

A1. if one of the following conditions of the training data samples exists, displaying the corresponding training data samples, and sending out a reminding signal to prompt that system instructions of the training data samples need to be manually adjusted:

the method comprises the following steps that firstly, when the AGV trolley is in a forward movement process, barrier distance data detected by the ultrasonic sensors at the front right and the front left are both larger than a third preset distance threshold value, and the barrier distance data detected by the ultrasonic sensors at the front left and the front right are the same;

the AGV trolley is in a backward movement process, the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are both larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are the same;

A2. acquiring adjustment information, wherein the adjustment information comprises manually adjusted system instruction information of the training data sample;

A3. adjusting a system instruction of the training data sample according to the adjustment information;

training the prediction model by using the training data set after adjustment processing;

And controlling the AGV to move according to the system instruction.

2. The AGV car control method of claim 1, wherein the preset basic obstacle avoidance rules are:

3. The AGV cart control method according to claim 2, wherein when the AGV cart is moving forward, if the obstacle distance data detected by the front ultrasonic sensor is smaller than a second preset distance threshold, the obstacle distance data detected by the front left and right ultrasonic sensors are compared with a third preset distance threshold, respectively, and the operation to be performed is determined according to the comparison result, specifically:

4. The AGV cart control method according to claim 2, wherein when the AGV cart is moving backward, if the obstacle distance data detected by the ultrasonic sensors right behind is smaller than the second preset distance threshold, the obstacle distance data detected by the ultrasonic sensors right behind and left behind are compared with the third preset distance threshold, and the operations to be performed are determined according to the comparison result, specifically:

if the distance data of the obstacles detected by the ultrasonic sensors at the left rear part and the right rear part are not greater than a third preset distance threshold, the operation to be executed is a forward operation;

5. The utility model provides a AGV dolly controlling means is applied to the control system of AGV dolly, a serial communication port, the AGV dolly includes 6 ultrasonic sensor, 6 ultrasonic sensor installs respectively the front, left the place ahead, right front, rear, left rear, right rear on AGV dolly chassis, AGV dolly controlling means includes:

The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring obstacle detection data which comprises obstacle distance data detected by 6 ultrasonic sensors;

the second acquisition module executes the following steps when acquiring the system instruction by adopting a preset basic obstacle avoidance rule or a pre-trained prediction model according to the comparison result:

if the obstacle distance data detected by at least one ultrasonic sensor is smaller than the first preset distance threshold value, acquiring a system instruction by adopting a preset basic obstacle avoidance rule;

if all the obstacle distance data detected by the ultrasonic sensors are not smaller than the first preset distance threshold, the step of acquiring system instructions by adopting a pre-trained prediction model comprises the following steps:

the prediction model is obtained by training in the following way:

controlling the AGV trolley to move by adopting the preset basic obstacle avoidance rule so as to acquire operation data serving as a training data set; the operation data comprises the obstacle distance data detected by 6 ultrasonic sensors and corresponding system instructions;

adjusting the training data set: manually adjusting system instructions in operation data in which the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are both larger than a third preset distance threshold value and the obstacle distance data detected by the ultrasonic sensors at the front left and the front right are the same; manually adjusting system instructions in operation data, wherein the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are both larger than a third preset distance threshold value, and the obstacle distance data detected by the ultrasonic sensors at the left rear part and the right rear part are the same;

A2. acquiring adjustment information, wherein the adjustment information comprises system instruction information of the training data sample after manual adjustment;

training the prediction model by using the training data set after adjustment processing; and the control module is used for controlling the AGV to move according to the system instruction.

6. An electronic device comprising a processor and a memory, said memory storing a computer program executable by said processor, said processor executing the steps of the AGV cart control method according to any one of claims 1-4.

7. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the AGV cart control method according to any one of claims 1-4.