CN110297484B

CN110297484B - Unmanned control method, device, computer equipment and storage medium

Info

Publication number: CN110297484B
Application number: CN201810246035.1A
Authority: CN
Inventors: 周文立; 查鸿山; 邱明喆; 林小敏; 王晓波; 翁诗晶
Original assignee: Guangzhou Automobile Group Co Ltd
Current assignee: Guangzhou Automobile Group Co Ltd
Priority date: 2018-03-23
Filing date: 2018-03-23
Publication date: 2021-04-27
Anticipated expiration: 2038-03-23
Also published as: CN110297484A

Abstract

The application relates to an unmanned control method, an unmanned control device, computer equipment and a storage medium. The method comprises the following steps: acquiring a decision instruction and perception information, and calculating an initial control quantity corresponding to the decision instruction according to the decision instruction; checking the decision instruction according to the sensing information to obtain a checking result, and calculating according to the checking result and the initial control quantity to obtain a control instruction; and sending the control instruction to a driving execution device. By adopting the method, whether the acquired decision instruction corresponds to the perception information at the same moment or not can be judged, whether the acquired decision instruction is suitable for the current perception information within a certain time period or not can be judged, and the control instruction can be obtained by calculation according to the check result and the initial control quantity, so that the problem of execution error caused by failure of the decision instruction is prevented, and the safety of the unmanned system is improved.

Description

Unmanned control method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of intelligent traffic technologies, and in particular, to a method and an apparatus for controlling unmanned vehicles, a computer device, and a storage medium.

Background

Along with the rapid development of intelligent transportation technology, unmanned systems are also rapidly developed, and the unmanned systems are used as advanced passenger transportation systems to guide the development trend of urban rail transit. A perception module, a decision-making module and a control module in the unmanned system are three relatively independent control units. The output of the sensing module is the input of the decision module, the output of the decision module is the input of the control module, and the output of the control module directly determines the driving behavior of the vehicle. One ring is buckled in the information transmission, and once the information fails, a safety problem can be caused. In the current mainstream unmanned system architecture, a control module absolutely obeys a decision module without question. Once the decision information fails, the control module will also execute the error.

The traditional unmanned system only provides a solution when perception information and a control instruction fail, but in the practical application process, the decision information fails due to the fact that the period for processing the single-frame decision information is far longer than the period for processing the single-frame control information by the control module, the algorithm is still imperfect, the data transmission link fails and the like, so that the driving control of the vehicle is executed wrongly, when the decision information fails, the traditional unmanned system does not have a corresponding emergency scheme, and the system safety is low.

Disclosure of Invention

In view of the above, it is desirable to provide an unmanned control method, apparatus, computer device, and storage medium capable of improving safety of an unmanned system.

An unmanned control method comprising the steps of:

acquiring a decision instruction and perception information, wherein the perception information is obtained by carrying out data processing on collected driving reference data, and the decision instruction is obtained by carrying out decision on the perception information;

calculating an initial control quantity corresponding to the decision instruction according to the decision instruction;

checking the decision instruction according to the sensing information to obtain a checking result, and calculating according to the checking result and the initial control quantity to obtain a control instruction;

and sending the control instruction to a driving execution device.

In one embodiment, after the step of checking the decision instruction according to the sensing information to obtain a check result and calculating the control instruction according to the check result and the initial control amount, the method further includes the following steps:

and generating corresponding feedback checking information according to the checking result and the perception information, and performing feedback adjustment on the decision instruction according to the feedback checking information.

In one embodiment, the control instruction includes an emergency control instruction, an original control instruction and a target control instruction, the step of checking the decision instruction according to the sensing information to obtain a checking result, and the step of checking the initial control quantity according to the checking result to obtain the control instruction includes the following steps:

when the decision instruction is judged to contain the instruction which can cause the serious safety accident according to the perception information, generating an emergency control instruction according to the checking strength for checking the decision instruction; the emergency control instruction is used for controlling the driving execution device to adopt emergency braking;

when the decision instruction is judged to contain an instruction which can exceed the maximum driving threshold of the unmanned equipment according to the perception information, generating an original control instruction according to the checking strength for checking the decision instruction; the original control instruction is used for controlling the driving execution device to run or stop running according to a preset speed;

when the decision instruction is judged to contain the instruction which can violate the traffic regulation according to the perception information, generating a target control instruction according to the checking strength for checking the decision instruction; the target control instruction is used for controlling the driving execution device to run or stop running according to the target track.

In one embodiment, the emergency control instruction is generated according to the checking strength for checking the decision instruction, and the method comprises the following steps:

and when the checking strength for checking the decision instruction is a preset strength, generating an emergency control instruction, wherein the preset strength is used for reflecting the execution degree of the decision instruction.

In one embodiment, the original control instruction comprises a preset maximum value control instruction, a preset running value control instruction and a running stopping control instruction, and the original control instruction is generated according to the check strength of the decision instruction, and the method comprises the following steps:

when the checking strength for checking the decision instruction is a first preset strength, generating a preset maximum control instruction;

when the checking strength for checking the decision instruction is a second preset strength, generating a preset driving value control instruction;

and when the checking intensity for checking the decision instruction is a third preset intensity, generating a driving stopping control instruction.

In one embodiment, the target control instruction includes an initial control instruction, a deceleration running control instruction, and a stop running control instruction, and the target control instruction is generated according to the check strength of the decision instruction, including the steps of:

when the checking strength for checking the decision instruction is a first preset strength, generating an initial control instruction;

when the checking strength for checking the decision instruction is a second preset strength, generating a deceleration driving control instruction;

An unmanned control device comprising:

the acquisition module is used for acquiring decision instructions and perception information, the perception information is obtained by carrying out data processing on the acquired driving reference data, and the decision instructions are obtained by carrying out decision on the perception information;

the calculation module is used for calculating the initial control quantity corresponding to the decision instruction according to the decision instruction;

the checking module is used for checking the decision instruction according to the sensing information to obtain a checking result, and calculating according to the checking result and the initial control quantity to obtain a control instruction;

and the sending module is used for sending the control instruction to the corresponding execution device.

In one embodiment, the unmanned control device further comprises:

and the feedback module is used for generating corresponding feedback checking information according to the checking result and the perception information, and performing feedback adjustment on the decision instruction according to the feedback checking information.

A computer device comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the unmanned control method.

A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to perform the steps of the unmanned control method.

According to the unmanned control method, the unmanned control device, the computer equipment and the storage medium, after the decision instruction and the perception information are obtained, the initial control quantity corresponding to the decision instruction is calculated according to the obtained decision instruction, the received perception information decision instruction is checked, the control instruction is obtained through calculation according to the check result and the initial control quantity, and the obtained control instruction is sent to the driving execution device. The decision instruction is checked by acquiring the perception information, whether the acquired decision instruction corresponds to the perception information at the same moment or not can be judged, whether the acquired decision instruction is suitable for the current perception information within a certain time period or not can be judged, and the control instruction is obtained by calculation according to the check result and the initial control quantity, so that the problem of execution error caused by failure of the decision information is solved, and the safety of the unmanned system is improved.

Drawings

FIG. 1 is a schematic flow diagram of a method for drone control in one embodiment;

FIG. 2 is a schematic flow chart of a method for drone control in another embodiment;

FIG. 3 is a schematic flow chart of a method for drone control in another embodiment;

FIG. 4 is a schematic flow chart of a method for drone control in another embodiment;

FIG. 5 is a block diagram of the unmanned control device in one embodiment;

FIG. 6 is a block diagram showing the construction of an unmanned control unit according to another embodiment;

FIG. 7 is a block diagram showing the construction of a drone controlling device in another embodiment;

FIG. 8 is a block diagram showing the structure of an original control module in another embodiment;

FIG. 9 is a block diagram showing the structure of a target control module in another embodiment;

FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The unmanned control method provided by the embodiments of the application can be applied to control of unmanned equipment, the unmanned equipment generally relates to an environment sensing system and a control terminal, and the environment sensing system and the control terminal can be connected in a wired or wireless mode to carry out data communication. The control terminal may be a vehicle-mounted terminal or a mobile terminal, and the mobile terminal may be a mobile phone, a tablet computer, a notebook computer, or the like. The unmanned device comprises a vehicle, an unmanned aerial vehicle and the like.

In one embodiment, as shown in fig. 1, there is provided an unmanned control method comprising the steps of:

and step S100, obtaining a decision instruction and perception information.

The perception information is obtained by processing the collected driving reference data, and the decision instruction is obtained by making a decision on the perception information. The specific manner of obtaining the decision instruction and the perception information is not unique. Specifically, the perception information can obtain sensor data through a controller in the unmanned equipment, the sensor data is subjected to data processing to obtain the perception information, then decision is made on the perception information to obtain a decision instruction, namely the controller in the unmanned equipment obtains the corresponding perception information and the decision instruction; the perception information and the decision instruction can also be obtained by calculation and decision of an external processor and then sent to a controller in the unmanned equipment, namely the controller directly receives the perception information and the decision instruction calculated and decided by the external processor.

And acquiring perception information obtained by performing data processing on the acquired driving reference data and a decision instruction obtained by making a decision on the perception information. The driving reference data can be acquired through a sensor of the unmanned equipment, when the unmanned equipment is a vehicle, the sensor can be formed by combining one or more of a camera, a laser radar, a millimeter wave radar, a high-precision map module, an inertial vehicle sensor and a vehicle ground plate electronic sensor, and the perception information specifically comprises necessary information required by the vehicle in driving, such as lane lines, traffic signs, obstacles, drivable areas and the like. Specifically, the perception information is obtained by calculating and fusing collected driving reference data, the driving reference data may be from a plurality of sensors, the data calculation is a process of processing the driving reference data according to a relationship established by a certain mode, and the data fusion is a process of combining, correlating and combining the driving reference data to excavate hidden information and valid data. The decision instruction is to make a decision on the perception information, namely, a decision on how to control the unmanned equipment is made on the basis of all perception information. Decision instructions refer to a series of waypoints representing a target location at which the drone is expected to travel, which may be represented by absolute location coordinates or device coordinates. Each waypoint information can be accompanied by information such as target speed, target acceleration, target light horn and the like so as to further control the unmanned equipment.

And step S200, calculating an initial control quantity corresponding to the decision instruction according to the decision instruction.

After a decision instruction is obtained by making a decision on the perception information, the controller calculates an initial control quantity corresponding to the decision instruction according to the obtained decision instruction and a certain control algorithm, specifically, the decision instruction is interpreted into the initial control quantity corresponding to the decision instruction, and the initial control quantity comprises specific control information on the unmanned equipment. More specifically, the calculated initial control amount is path information over a certain period of time obtained for the acquired perception information. The route information specifically refers to a track that the unmanned aerial vehicle travels within a certain period of time. The track not only comprises position information, but also comprises time information and equipment posture of the whole track: i.e. the time of arrival at each position, the velocity, and the associated motion variables such as acceleration, curvature, higher order derivatives of curvature, etc.

And step S300, checking the decision instruction according to the sensing information to obtain a checking result, and calculating according to the checking result and the initial control quantity to obtain a control instruction.

The decision instruction is obtained by making a decision on the sensing information, and when the controller checks the decision instruction, the decision instruction can be checked according to the sensing information at the same time as the decision instruction, or the decision instruction can be checked according to the sensing information acquired at the current time. Therefore, whether the acquired decision instruction corresponds to the perception information at the same moment or not is judged, or whether the acquired decision instruction is suitable for the current perception information within a certain time period or not is judged, so that whether the decision instruction fails or not can be found at the first time, and when the decision instruction fails, reasonable countermeasures can be taken timely, and potential hazards caused by decision failure are avoided or reduced. And calculating according to the checking result and the calculated initial control quantity, when the obtained decision instruction corresponds to the perception information at the same moment, or the obtained decision instruction is applicable to the current perception information within a certain time period, directly calculating according to the calculated initial control quantity to obtain the control instruction, and when the obtained decision instruction is inconsistent with the perception information at the same moment, or the obtained decision instruction is inconsistent with the current perception information within a certain time period, correspondingly modifying the initial control quantity according to the checking result to obtain the corresponding control instruction. And checking the decision instruction according to the sensing information is only a flow in one checking period, and entering the next checking period for checking after the current checking period is finished.

In step S400, a control command is sent to the driving execution device.

And checking the decision instruction according to the sensing information to obtain a checking result, checking the initial control quantity according to the checking result to obtain a control instruction, sending the control instruction to a driving execution device of the unmanned equipment by the controller, and executing corresponding driving operation according to the received control instruction by the driving execution device of the unmanned equipment.

According to the unmanned control method, after the decision instruction and the perception information are obtained, the initial control quantity corresponding to the decision instruction is calculated according to the obtained decision instruction, the decision instruction is checked according to the received perception information, the control instruction is obtained through calculation according to the check result and the initial control quantity, and the obtained control instruction is sent to the driving execution device. The decision instruction is checked by acquiring the perception information, whether the acquired decision instruction corresponds to the perception information at the same moment or not can be judged, whether the acquired decision instruction is suitable for the current perception information within a certain time period or not can be judged, and the control instruction is obtained by calculation according to the check result and the initial control quantity, so that the problem of execution error caused by failure of the decision information is solved, and the safety of the unmanned system is improved.

In one embodiment, as shown in fig. 2, step S500 is further included after step S400.

And S500, generating corresponding feedback checking information according to the checking result and the perception information, and performing feedback adjustment on the decision instruction according to the feedback checking information.

When the acquired decision instruction is inconsistent with the perception information at the same moment or the acquired decision instruction is inconsistent with the current perception information within a certain time period, the controller generates corresponding feedback checking information according to the checking result and the perception information, the feedback checking information comprises relevant error codes for checking the decision instruction according to the perception information, and the decision instruction is subjected to feedback regulation according to the feedback checking information, so that the contradiction between the decision instruction and the perception information is solved, and the control accuracy of the unmanned equipment is improved.

In one embodiment, as shown in FIG. 3, step S300 includes step S320, step S340, and step S360.

Step S320, when the decision instruction is judged to contain the instruction which can cause serious safety accident according to the perception information, generating an emergency control instruction according to the checking strength for checking the decision instruction; the emergency control instruction is used for controlling the driving execution device to adopt emergency braking.

The control instructions comprise emergency control instructions, original control instructions and target control instructions, and when the decision instructions are judged to contain the instructions which can cause serious safety accidents according to the sensing information, the emergency control instructions are generated according to the checking strength for checking the decision instructions. In one embodiment, as shown in fig. 4, a step of determining whether the decision instruction includes an instruction that may cause a serious security accident according to the sensing information is further included before step S320, and when it is determined that the decision instruction includes an instruction that may cause a serious security accident according to the sensing information, step S320 is performed.

Specifically, the criterion for judging whether the decision instruction contains an instruction which can cause a serious safety accident according to the perception information comprises the following steps: whether an obstacle appears in the target track of the unmanned equipment and the time of collision with the obstacle is lower than a preset time threshold value, and whether the target track of the unmanned equipment exits the travelable area. Namely, when the control instruction generated according to the current decision instruction is judged to enable the obstacle to appear in the target track of the unmanned equipment and the collision time with the obstacle is lower than the preset time threshold, the emergency control instruction is generated. The emergency control instruction is used for controlling the driving execution device to adopt emergency braking.

Step S340, when the decision instruction is judged to contain the instruction which can exceed the maximum driving threshold of the unmanned equipment according to the perception information, generating an original control instruction according to the checking strength for checking the decision instruction; the original control instruction is used for controlling the driving execution device to run or stop running according to the preset speed.

And when the decision instruction is judged to contain an instruction which can exceed the maximum driving threshold of the unmanned equipment according to the perception information, generating an original control instruction according to the checking strength of the decision instruction. In one embodiment, as shown in fig. 4, a step of determining whether the decision instruction includes an instruction that would exceed the maximum driving threshold of the unmanned aerial vehicle according to the sensing information is further included before step S340, and when it is determined that the decision instruction includes an instruction that would exceed the maximum driving threshold of the unmanned aerial vehicle according to the sensing information, step S340 is performed.

Specifically, the maximum driving threshold of the unmanned aerial vehicle can also be understood as the limit capability of the unmanned aerial vehicle, and the judgment criterion for judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned aerial vehicle according to the perception information comprises the following steps: whether the target speed of the unmanned device exceeds the maximum speed of the unmanned device, whether the target acceleration of the unmanned device exceeds the maximum acceleration of the unmanned device, whether the target deceleration of the unmanned device exceeds the maximum deceleration of the unmanned device, whether the target trajectory curvature of the unmanned device is less than the minimum turning radius of the unmanned device, and whether the distance of the unmanned device from the closest point of the target trajectory is greater than a preset distance threshold. When the target speed of the unmanned device exceeds the maximum speed of the unmanned device or the target acceleration of the unmanned device exceeds the maximum acceleration of the unmanned device or the target deceleration of the unmanned device exceeds the maximum deceleration of the unmanned device or the target track curvature of the unmanned device is smaller than the minimum turning radius of the unmanned device or the distance between the unmanned device and the closest point of the target track is larger than a preset distance threshold value, an original control instruction is generated according to the checking strength for checking the decision instruction, and the original control instruction is used for controlling the driving execution device to run or stop running according to the preset speed.

Step S360, when the decision instruction is judged to contain the instruction which can violate the traffic regulation according to the perception information, a target control instruction is generated according to the checking strength for checking the decision instruction; the target control instruction is used for controlling the driving execution device to run or stop running according to the target track.

And when the decision-making command is judged to contain a command which can violate the traffic regulation according to the perception information, generating a target control command according to the checking strength of the decision-making command. In one embodiment, as shown in fig. 4, before step S360, a step of determining whether the decision instruction includes an instruction that violates a traffic regulation according to the sensing information is further included, and when it is determined that the decision instruction includes an instruction that violates a traffic regulation according to the sensing information, step S360 is performed.

Specifically, the criterion for judging whether the decision instruction contains an instruction which can violate the traffic regulation according to the perception information includes: whether the unmanned equipment runs through a red light or not according to a control instruction generated according to the current decision instruction, whether the target speed of the unmanned equipment exceeds the speed of a speed limit sign or not, whether the target track of the unmanned equipment is inconsistent with traffic signs such as steering, straight running and turning around and whether the target track of the unmanned equipment crosses a solid line or a double solid line or not. When it is judged that the unmanned equipment runs to run a red light according to a control instruction generated according to the current decision instruction, the target speed of the unmanned equipment exceeds the speed of a speed limit sign, the target track of the unmanned equipment is inconsistent with traffic signs such as steering, straight running and turning, and the target track of the unmanned equipment crosses a solid line/double solid lines, generating a target control instruction according to the checking strength for checking the decision instruction; the target control instruction is used for controlling the driving execution device to run or stop running according to the target track.

In one embodiment, when it is determined that the decision instruction does not include an instruction that may cause a serious safety accident based on the sensory information, a step of determining whether the decision instruction includes an instruction that may exceed a maximum driving threshold of the unmanned aerial vehicle based on the sensory information is performed. And when the decision instruction is judged not to contain the instruction which can exceed the maximum driving threshold of the unmanned equipment according to the perception information, judging whether the decision instruction contains the instruction which can violate the traffic regulation or not according to the perception information.

In one embodiment, as shown in fig. 4, the emergency control instruction is generated according to the check strength of the decision instruction, including step S322.

In step S322, when the check strength for checking the decision instruction is the preset strength, an emergency control instruction is generated.

Judging whether the decision instruction contains an instruction which can cause a serious safety accident according to the sensing information, and when the decision instruction is judged to contain the instruction which can cause the serious safety accident and the checking result of checking the decision instruction is preset intensity, namely the checking intensity of checking the decision instruction is first preset intensity, second preset intensity or third preset intensity, generating an emergency control instruction, wherein the preset intensity value is used for reflecting the execution degree of the decision instruction.

Further, the checking strength for checking the decision instruction according to the sensing information may be set according to actual needs, and in one embodiment, the checking strength for checking the decision instruction is set to three levels, which are a first preset strength, a second preset strength and a third preset strength, respectively, where the checking strength represented by the first preset strength is lower than the checking strength represented by the second preset strength, and the checking strength represented by the second preset strength is lower than the checking strength represented by the third preset strength. Specifically, each preset intensity may refer to table 1.

TABLE 1 check Strength Classification Table

By setting the checking strength to three levels, the flexibility of the system can be improved, and when the software maturity of the decision module is low, for example, in a test stage, the control module can select strong checking. When the software maturity of the decision-making module is general, the control module can select the middle check. When the software maturity of the decision-making module is higher, the control module can select strong check. And when the check intensity value is the first preset intensity, indicating weak check. On the basis of ensuring the basic safety of vehicle running, the decision instruction is still heard as far as possible when the decision instruction conflicts with the perception information. The confidence to the decision module is high. And when the check intensity value is the second preset intensity, indicating the middle check. On the basis of ensuring the basic safety of vehicle running, the decision instruction is partially met when the decision instruction conflicts with the perception information. Generally, the trust of the decision module is expected to be recovered to normal in a short time. And when the check intensity value is a third preset intensity, indicating strong check. On the basis of ensuring the basic safety of the vehicle running, the decision-making instruction is not executed when the decision-making instruction conflicts with the perception information. The confidence of the decision module is low, and the decision module is not expected to be recovered to be normal in a short time, so that the decision instruction is not executed, and greater risk is avoided. And when the check strength value is other values, no check is indicated. The system is equivalent to a traditional control module, has extremely high trust degree on a decision module, but has larger risk.

In an embodiment, as shown in fig. 4, after the decision instruction is determined to include an instruction that may cause a serious safety accident, the method further includes a step of determining whether a checking strength for checking the decision instruction is a preset strength value, and when the checking strength for checking the decision instruction is not the preset strength value, the step of determining that the decision instruction includes an instruction that may exceed a maximum driving threshold of the unmanned equipment according to the sensing information is performed.

In one embodiment, when the decision instruction is judged to include an instruction which can cause a serious safety accident, namely when the unmanned equipment runs according to a control instruction generated according to the current decision instruction, an obstacle appears in a target track of the unmanned equipment and the collision time of the obstacle is lower than a preset time threshold, an emergency control instruction is generated and is used for controlling the unmanned equipment to adopt emergency braking. When the unmanned equipment runs according to the control command generated according to the current decision command and the target track of the unmanned equipment runs out of the drivable area, an emergency control command is generated and used for controlling the unmanned equipment to adopt emergency braking.

In one embodiment, as shown in fig. 4, the original control instruction includes a preset maximum value control instruction, a preset running value control instruction, and a stop running control instruction, and is generated according to the check strength of the decision instruction, including step S342, step S344, and step S346.

In step S342, when the check strength for checking the decision instruction is the first preset strength, a preset maximum control instruction is generated.

Judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment or not according to the sensing information, when the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment and when the checking strength for checking the decision instruction is a first preset strength, namely the checking strength for checking the decision instruction is the first preset strength, generating a preset maximum control instruction, wherein the preset maximum control instruction is used for controlling the unmanned equipment to drive according to the maximum speed allowed by the equipment and can be understood as controlling the unmanned equipment to drive according to the limit capacity of the equipment. In an embodiment, as shown in fig. 4, after the decision instruction is determined to include an instruction that would exceed the maximum driving threshold of the unmanned aerial vehicle, the method further includes a step of determining whether the checking result is a first preset intensity value, and when the checking intensity for checking the decision instruction is not the first preset intensity value, determining whether the checking intensity is a second preset intensity value.

In step S344, when the check strength for checking the decision instruction is the second preset strength, the preset driving value control instruction is generated.

Judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment or not according to the sensing information, when the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment and the check strength for checking the decision instruction is a second preset strength, generating a preset driving value control instruction, wherein the preset driving value control instruction is used for controlling the unmanned equipment to drive according to the original speed or the preset speed of the equipment, and can be understood as controlling the unmanned equipment to drive according to the original value or the default value of the equipment. In one embodiment, after the decision instruction is judged to include an instruction which exceeds the maximum driving threshold of the unmanned aerial vehicle, the method further includes a step of judging whether the checking strength is a second preset strength, and when the checking strength for checking the decision instruction is not the second preset strength, judging whether the checking strength is a third preset strength.

In step S346, when the check strength of checking the decision command is the third preset strength, the stop driving control command is generated.

And judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment or not according to the sensing information, and when the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment and the checking strength for checking the decision instruction is a third preset strength, generating a driving stopping control instruction which is used for controlling the unmanned equipment to stop driving. In one embodiment, after the decision instruction is judged to include an instruction which exceeds the maximum driving threshold of the unmanned aerial vehicle, the method further comprises the step of judging whether the checking strength is a third preset strength, and when the checking strength for checking the decision instruction is not the third preset strength, judging whether the decision instruction includes an instruction which violates a traffic regulation according to the perception information.

In one embodiment, when the decision instruction includes an instruction that may exceed the maximum driving threshold of the unmanned aerial vehicle, and when the check strength for checking the decision instruction is not a preset strength value, the step of determining whether the decision instruction includes an instruction that may violate the traffic regulation according to the sensing information is performed. And when the decision instruction comprises an instruction which can exceed the maximum driving threshold of the unmanned equipment, and after a preset maximum control instruction or a preset driving value control instruction is generated, judging whether the decision instruction comprises an instruction which can violate the traffic regulation or not according to the perception information.

In one embodiment, when the decision instruction comprises an instruction which exceeds a maximum driving threshold of the unmanned equipment, namely the unmanned equipment drives according to a control instruction generated according to the current decision instruction, and when the target speed of the unmanned equipment exceeds the maximum speed of the equipment, and the check strength is a first preset strength, the generated preset maximum control instruction is used for controlling the unmanned equipment to drive according to the maximum speed of the equipment, namely the maximum speed allowed by the equipment; when the check strength is a second preset strength, the generated preset driving value control instruction is used for controlling the unmanned equipment to drive according to the original speed or the preset speed; and when the check intensity is a third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

In one embodiment, when the decision instruction comprises an instruction which can exceed a maximum driving threshold of the unmanned equipment, namely the unmanned equipment drives according to a control instruction generated according to the current decision instruction, and when the target acceleration of the unmanned equipment exceeds the maximum acceleration of the equipment, and when the check intensity is a first preset intensity, the generated preset maximum control instruction is used for controlling the unmanned equipment to drive according to the maximum acceleration allowed by the equipment; when the check strength is a second preset strength, the generated preset driving value control instruction is used for controlling the unmanned equipment to drive according to the preset acceleration; and when the check intensity is a third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

In one embodiment, when the decision instruction includes an instruction that would exceed the maximum driving threshold of the unmanned aerial vehicle, that is, the unmanned aerial vehicle drives according to the control instruction generated according to the current decision instruction, and when the target deceleration of the unmanned aerial vehicle exceeds the maximum deceleration of the unmanned aerial vehicle, when the checking strength is the preset strength, that is, when the checking strength is the first preset strength, the second preset strength or the third preset strength, the generated preset maximum control instruction, the preset driving value control instruction and the driving stopping control instruction are all used for controlling the unmanned aerial vehicle to decelerate and drive according to the maximum deceleration allowed by the unmanned aerial vehicle, and for safety reasons, the deceleration/braking instruction included in the decision instruction should be completed as much as possible.

In one embodiment, when the decision instruction comprises an instruction which exceeds a maximum driving threshold of the unmanned equipment, namely the unmanned equipment drives according to a control instruction generated according to the current decision instruction, and when the curvature of the target track of the unmanned equipment is smaller than the minimum turning radius of the equipment, and the check intensity is a first preset intensity, the generated preset maximum control instruction is used for controlling the unmanned equipment to follow the target track according to the minimum turning radius allowed by the equipment; and when the check intensity is the second preset intensity or the third preset intensity, the generated preset driving value control instruction and the driving stopping control instruction are used for controlling the unmanned equipment to stop driving.

In one embodiment, when the decision instruction includes an instruction which exceeds a maximum driving threshold of the unmanned equipment, that is, the unmanned equipment drives according to a control instruction generated according to the current decision instruction, and when the distance between the unmanned equipment and the closest point of the target track is greater than a preset distance value, and the check intensity is a first preset intensity, the generated preset maximum control instruction is used for controlling the unmanned equipment to approach the target track; when the check result is a second preset intensity, the generated preset driving value control instruction is used for controlling the unmanned equipment to approach the track at a low speed; and when the checking result is the third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

In one embodiment, as shown in fig. 4, the target control instruction includes an initial control instruction, a deceleration running control instruction, and a stop running control instruction, the target control instruction is generated according to the check strength of the decision instruction, and the step S360 includes steps S362, S364, and S366.

In step S362, when the check strength for checking the decision instruction is the first preset strength, the initial control instruction is generated.

Judging whether the decision instruction contains an instruction which can violate a traffic regulation or not according to the perception information, generating an initial control instruction when the decision instruction contains the instruction which can violate the traffic regulation and the checking strength for checking the decision instruction is a first preset strength, wherein the initial control instruction is used for controlling the unmanned equipment to run according to the control instruction generated according to the currently acquired decision instruction, and can be understood as generating a corresponding control instruction according to the initial control quantity and controlling the unmanned equipment to run according to the generated control instruction. In one embodiment, after the decision instruction is determined to include an instruction that violates a traffic regulation, the method further includes a step of determining whether the check strength is a first preset strength, and when the check strength for checking the decision instruction is not the first preset strength, determining whether the check strength is a second preset strength.

In step S364, when the check strength for checking the decision instruction is the second preset strength, the deceleration running control instruction is generated.

And judging whether the decision instruction contains an instruction which can violate the traffic regulation or not according to the perception information, and generating a deceleration running control instruction when the decision instruction contains the instruction which can violate the traffic regulation and the checking strength for checking the decision instruction is a second preset strength, wherein the deceleration running control instruction is used for controlling the unmanned equipment to run according to the target track after decelerating. In one embodiment, after the decision instruction is determined to include an instruction that violates a traffic regulation, the method further includes a step of determining whether the check strength is a second preset strength, and when the check strength for checking the decision instruction is not the second preset strength, determining whether the check strength is a third preset strength.

In step S366, when the check strength for checking the decision command is the third preset strength, the stop driving control command is generated.

And judging whether the decision instruction contains an instruction which can violate the traffic regulation or not according to the perception information, and generating a driving stopping control instruction when the decision instruction contains the instruction which can violate the traffic regulation and the checking strength for checking the decision instruction is a third preset strength, wherein the driving stopping control instruction is used for controlling the unmanned equipment to stop driving. In one embodiment, after the decision instruction is determined to include an instruction which violates a traffic regulation, the method further includes a step of determining whether the checking strength is a third preset strength, and when the checking strength for checking the decision instruction is not the third preset strength, the checking of the current checking period is ended.

In one embodiment, when the decision instruction comprises an instruction which can violate a traffic regulation, that is, the unmanned equipment runs according to a control instruction generated according to the current decision instruction, and when the unmanned equipment runs a red light, and the check intensity is a first preset intensity, the generated initial control instruction is used for controlling the unmanned equipment to run according to the control instruction generated according to the currently acquired decision instruction; when the check intensity is a second preset intensity, the generated deceleration driving control instruction is used for controlling the unmanned equipment to decelerate and then drive according to the target track; and when the check intensity is a third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

In one embodiment, when the decision instruction comprises an instruction which can violate a traffic regulation, namely the unmanned equipment runs according to a control instruction generated according to the current decision instruction, and when the target speed of the unmanned equipment exceeds the speed of the speed limit sign, and the check strength is a first preset strength, the generated initial control instruction is used for controlling the unmanned equipment to run according to the target speed; when the check strength is a second preset strength, the generated deceleration running control instruction is used for controlling the unmanned equipment to run according to the speed of the speed limit sign; and when the check intensity is a third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

In one embodiment, when the decision instruction comprises an instruction which can violate a traffic regulation, namely the unmanned equipment runs according to a control instruction generated according to the current decision instruction, and the target track of the unmanned equipment is inconsistent with traffic signs such as steering, straight running, turning and the like, and when the checking strength is a first preset strength, the generated initial control instruction is used for controlling the unmanned equipment to run according to the control instruction generated according to the currently acquired decision instruction; when the check intensity is a second preset intensity, the generated deceleration driving control instruction is used for controlling the unmanned equipment to decelerate and then drive according to the target track; and when the check intensity is a third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

In one embodiment, when the decision instruction comprises an instruction which can violate a traffic regulation, namely the unmanned equipment runs according to a control instruction generated according to the current decision instruction, and when the target track of the unmanned equipment crosses a solid line/a double solid line, and the checking intensity is a first preset intensity, the generated initial control instruction is used for controlling the unmanned equipment to run according to the control instruction generated according to the currently acquired decision instruction; when the check intensity is a second preset intensity, the generated deceleration driving control instruction is used for controlling the unmanned equipment to decelerate and then drive according to the target track; and when the check intensity is a third preset intensity, the generated driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

It should be understood that although the various steps in the flow charts of fig. 1-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 5, there is provided an unmanned control device including: the device comprises an acquisition module 100, a calculation module 200, a check module 300 and a sending module 400.

An obtaining module 100, configured to obtain a decision instruction and perception information.

The perception information is obtained by processing the collected driving reference data, and the decision instruction is obtained by making a decision on the perception information. And acquiring perception information obtained by performing data processing on the acquired driving reference data and a decision instruction obtained by making a decision on the perception information. The driving reference data can be acquired through a sensor of the unmanned equipment, when the unmanned equipment is a vehicle, the sensor can be formed by combining one or more of a camera, a laser radar, a millimeter wave radar, a high-precision map module, an inertial vehicle sensor and a vehicle ground plate electronic sensor, and the perception information specifically comprises necessary information required by the vehicle in driving, such as lane lines, traffic signs, obstacles, drivable areas and the like. The decision instruction is to make a decision on the perception information, namely, a decision on how to control the unmanned equipment is made on the basis of all perception information. The specific manner of obtaining the decision instruction and the perception information is not unique. Specifically, the perception information and the decision instruction can be obtained through internal calculation and decision, and the perception information and the decision instruction can be directly obtained by receiving information sent from the outside.

And the calculating module 200 is configured to calculate an initial control amount corresponding to the decision instruction according to the decision instruction.

After a decision instruction is obtained by making a decision on the perception information, the controller calculates an initial control quantity corresponding to the decision instruction according to the obtained decision instruction and a certain control algorithm, specifically, the decision instruction is interpreted into the initial control quantity corresponding to the decision instruction, and the initial control quantity comprises specific control information on the unmanned equipment. More specifically, the calculated initial control amount is path information over a certain period of time obtained for the acquired perception information.

The checking module 300 checks the decision instruction according to the sensing information to obtain a checking result, and calculates to obtain the control instruction according to the checking result and the initial control quantity.

The decision instruction is obtained by making a decision on the sensing information, and when the controller checks the decision instruction, the decision instruction can be checked according to the sensing information at the same time as the decision instruction, or the decision instruction can be checked according to the sensing information acquired at the current time. Therefore, whether the acquired decision instruction corresponds to the perception information at the same moment or not is judged, or whether the acquired decision instruction is suitable for the current perception information within a certain time period or not is judged.

A sending module 400, configured to send the control instruction to the driving execution device.

In one embodiment, as shown in FIG. 6, the drone control device further includes a feedback module 500.

And the feedback module 500 is configured to generate corresponding feedback check information according to the check result and the sensing information, and perform feedback adjustment on the decision instruction according to the feedback check information.

In one embodiment, as shown in FIG. 7, the verification module 300 includes an emergency control module 320, a source control module 340, and a destination control module 360.

The emergency control module 320 is configured to generate an emergency control instruction according to the checking strength for checking the decision instruction when it is determined that the decision instruction includes an instruction that may cause a serious safety accident according to the sensing information; the emergency control instruction is used for controlling the driving execution device to adopt emergency braking.

The control instructions comprise emergency control instructions, original control instructions and target control instructions, and when the decision instructions are judged to contain the instructions which can cause serious safety accidents according to the sensing information, the emergency control instructions are generated according to the checking strength for checking the decision instructions. The judgment criteria for judging whether the decision instruction contains an instruction which can cause a serious safety accident according to the perception information comprises the following steps: whether an obstacle appears in the target track of the unmanned equipment and the time of collision with the obstacle is lower than a preset time threshold value, and whether the target track of the unmanned equipment exits the travelable area.

The original control module 340 is configured to generate an original control instruction according to the checking strength for checking the decision instruction when it is determined that the decision instruction includes an instruction that may exceed the maximum driving threshold of the unmanned device according to the sensing information; the original control instruction is used for controlling the driving execution device to run or stop running according to the preset speed.

And when the decision instruction is judged to contain an instruction which can exceed the maximum driving threshold of the unmanned equipment according to the perception information, generating an original control instruction according to the checking strength of the decision instruction. The maximum driving threshold of the unmanned device can also be understood as the limit capacity of the unmanned device, and the judgment standard for judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned device according to the perception information comprises the following steps: whether the target speed of the unmanned device exceeds the maximum speed of the unmanned device, whether the target acceleration of the unmanned device exceeds the maximum acceleration of the unmanned device, whether the target deceleration of the unmanned device exceeds the maximum deceleration of the unmanned device, whether the target trajectory curvature of the unmanned device is less than the minimum turning radius of the unmanned device, and whether the distance of the unmanned device from the closest point of the target trajectory is greater than a preset distance threshold.

The target control module 360 is configured to generate a target control instruction according to the checking strength for checking the decision instruction when it is determined that the decision instruction includes an instruction that may violate a traffic regulation according to the sensing information; the target control instruction is used for controlling the driving execution device to run or stop running according to the target track.

And when the decision-making command is judged to contain a command which can violate the traffic regulation according to the perception information, generating a target control command according to the checking strength of the decision-making command. The judgment criterion for judging whether the decision instruction contains an instruction which can violate the traffic regulation according to the perception information comprises the following steps: whether the unmanned equipment runs through a red light or not according to a control instruction generated according to the current decision instruction, whether the target speed of the unmanned equipment exceeds the speed of a speed limit sign or not, whether the target track of the unmanned equipment is inconsistent with traffic signs such as steering, straight running and turning around and whether the target track of the unmanned equipment crosses a solid line or a double solid line or not.

In one embodiment, the emergency control module 320 is further configured to generate the emergency control instruction when the check strength when checking the decision instruction is a preset strength.

And judging whether the decision instruction contains an instruction which can cause a serious safety accident according to the sensing information, and generating an emergency control instruction when the decision instruction is judged to contain the instruction which can cause the serious safety accident and the checking strength for checking the decision instruction is a preset strength value.

In one embodiment, as shown in FIG. 8, the raw control module 340 includes a preset maximum control module 342, a preset travel value control module 344, and a first stop module 346.

The preset maximum control module 342 is configured to generate a preset maximum control instruction when the check strength for checking the decision instruction is the first preset strength.

And judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment or not according to the sensing information, and when the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment and the checking strength for checking the decision instruction is a first preset strength, generating a preset maximum control instruction which is used for controlling the unmanned equipment to drive according to the maximum speed allowed by the equipment and controlling the unmanned equipment to drive according to the limit capacity of the equipment.

The preset driving value control module 344 is configured to generate the preset driving value control instruction when the check strength for checking the decision instruction is the second preset strength.

And judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment or not according to the sensing information, and generating a preset driving value control instruction when the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment and the checking strength for checking the decision instruction is a second preset strength, wherein the preset driving value control instruction is used for controlling the unmanned equipment to drive according to the original speed or the preset speed of the equipment.

The first stopping module 346 is configured to generate the stop driving control instruction when the check strength for checking the decision instruction is a third preset strength.

And judging whether the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment or not according to the sensing information, and when the decision instruction contains an instruction which can exceed the maximum driving threshold of the unmanned equipment and the checking strength for checking the decision instruction is a third preset strength, generating a driving stopping control instruction which is used for controlling the unmanned equipment to stop driving.

In one embodiment, as shown in FIG. 9, the target control module 360 includes an initial control module 362, a deceleration control module 364, and a second stop module 366.

The initial control module 362 is configured to generate the initial control instruction when the check strength for checking the decision instruction is a first preset strength.

Judging whether the decision instruction contains an instruction which can violate the traffic regulation or not according to the perception information, and generating an initial control instruction when the decision instruction contains the instruction which can violate the traffic regulation and the checking strength for checking the decision instruction is a first preset strength, wherein the initial control instruction is used for controlling the unmanned equipment to run according to the control instruction generated according to the currently acquired decision instruction.

The deceleration control module 364 is configured to generate a deceleration driving control instruction when the check strength for checking the decision instruction is the second preset strength.

And judging whether the decision instruction contains an instruction which can violate the traffic regulation or not according to the perception information, and generating a deceleration running control instruction when the decision instruction contains the instruction which can violate the traffic regulation and the checking strength for checking the decision instruction is a second preset strength, wherein the deceleration running control instruction is used for controlling the unmanned equipment to run according to the target track after decelerating.

The second stopping module 366 is configured to generate the driving stopping control instruction when the checking strength for checking the decision instruction is the third preset strength.

And judging whether the decision instruction contains an instruction which can violate the traffic regulation or not according to the perception information, and generating a driving stopping control instruction when the decision instruction contains the instruction which can violate the traffic regulation and the checking strength for checking the decision instruction is a third preset strength, wherein the driving stopping control instruction is used for controlling the unmanned equipment to stop driving.

For specific limitations of the drone control device, reference may be made to the above limitations of the drone control method, which are not described in detail here. The various modules in the above described drone control device may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of drone control. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

and sending the control instruction to a driving execution device.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

and sending the control instruction to a driving execution device.

After the unmanned control device, the computer equipment and the storage medium acquire the decision instruction and the perception information, the initial control quantity corresponding to the decision instruction is calculated according to the acquired decision instruction, the decision instruction is checked according to the received perception information, the control instruction is calculated according to the check result and the initial control quantity, and the obtained control instruction is sent to the driving execution device. The decision instruction is checked by acquiring the perception information, whether the acquired decision instruction corresponds to the perception information at the same moment or not can be judged, whether the acquired decision instruction is suitable for the current perception information within a certain time period or not can be judged, and the control instruction is obtained by calculation according to the check result and the initial control quantity, so that the problem of execution error caused by failure of the decision information is solved, and the safety of the unmanned system is improved.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. The unmanned control method is characterized by being applied to a control module in an unmanned system; the unmanned system also comprises a perception module and a decision-making module; the method comprises the following steps:

acquiring a decision instruction and perception information, wherein the perception information is obtained by processing data of acquired driving reference data through a perception module, and the decision instruction is obtained by making a decision on the perception information through a decision module;

checking the decision instruction according to the perception information and the corresponding checking strength to obtain a checking result, and calculating according to the checking result and the initial control quantity to obtain a control instruction; the checking result is used for representing whether the decision instruction corresponds to the perception information at the same moment or not, or whether the decision instruction is suitable for the current perception information within a certain time period or not; the checking strength is determined based on the software maturity of the decision module;

and sending the control instruction to a driving execution device.

2. The unmanned control method of claim 1, wherein after the step of checking the decision-making command according to the perception information to obtain a check result and checking the initial control amount according to the check result to obtain a control command, the method further comprises the steps of:

3. The unmanned control method according to claim 1, wherein the control instruction includes an emergency control instruction, an original control instruction, and a target control instruction, the step of checking the decision instruction according to the perception information to obtain a check result, and calculating to obtain the control instruction according to the check result and the initial control amount includes the steps of:

when the decision instruction is judged to contain an instruction which can cause a serious safety accident according to the perception information, generating an emergency control instruction according to the checking strength for checking the decision instruction; the emergency control instruction is used for controlling the driving execution device to adopt emergency braking;

when the decision-making command is judged to contain a command which can violate the traffic regulation according to the perception information, generating a target control command according to the checking strength for checking the decision-making command; the target control instruction is used for controlling the driving execution device to run or stop running according to a target track.

4. The unmanned control method of claim 3, wherein the generating of the emergency control command according to the check strength for checking the decision command comprises:

and when the checking strength for checking the decision-making instruction is a preset strength, generating an emergency control instruction, wherein the preset strength is used for reflecting the execution degree of the decision-making instruction.

5. The unmanned control method of claim 3, wherein the raw control commands comprise a preset maximum control command, a preset driving value control command and a driving stopping control command, and the generating of the raw control commands according to the check strength of the decision commands comprises the following steps:

when the checking intensity for checking the decision instruction is a first preset intensity, generating a preset maximum value control instruction;

when the checking intensity for checking the decision instruction is a second preset intensity, generating a preset driving value control instruction;

6. The unmanned control method according to claim 3, wherein the target control command includes an initial control command, a deceleration running control command, and a stop running control command, and the generation of the target control command based on the check strength for the decision command includes:

when the checking intensity for checking the decision-making command is a second preset intensity, generating a deceleration driving control command;

7. An unmanned control device is characterized in that the device is applied to a control module in an unmanned system; the unmanned system also comprises a perception module and a decision-making module; the device comprises:

the acquisition module is used for acquiring a decision instruction and perception information, the perception information is obtained by data processing of collected driving reference data through the perception module, and the decision instruction is obtained by decision of the perception information through the decision module;

the checking module is used for checking the decision instruction according to the sensing information and the corresponding checking strength to obtain a checking result, and calculating to obtain a control instruction according to the checking result and the initial control quantity; the checking result is used for representing whether the decision instruction corresponds to the perception information at the same moment or not, or whether the decision instruction is suitable for the current perception information within a certain time period or not; the checking strength is determined based on the software maturity of the decision module;

and the sending module is used for sending the control instruction to a corresponding execution device.

8. The unmanned control device of claim 7, further comprising:

and the feedback module is used for generating corresponding feedback checking information according to the checking result and the perception information and carrying out feedback adjustment on the decision instruction according to the feedback checking information.

9. A computer device comprising a processor and a memory, the memory storing a computer program, wherein the computer program, when executed by the processor, causes the processor to perform the steps of the method of any one of claims 1 to 6.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 6.