CN115685978A

CN115685978A - Unmanned vehicle control method and device, storage medium and electronic equipment

Info

Publication number: CN115685978A
Application number: CN202110838218.4A
Authority: CN
Inventors: 丁文玲; 虞航仲; 苏程愷; 杨磊; 夏华夏
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2021-07-23
Filing date: 2021-07-23
Publication date: 2023-02-03

Abstract

The disclosure relates to an unmanned vehicle control method, an unmanned vehicle control device, a storage medium and an electronic device. Detecting whether the communication quality of a communication link between an unmanned vehicle and a remote control terminal in a remote control mode is lower than a preset quality; under the condition that the communication quality of the communication link is detected to be lower than the preset quality, determining a target control mode capable of controlling the unmanned vehicle to safely run in the current environment from a plurality of control modes preset by the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, wherein the environment evaluation value is determined according to sensing data acquired by a sensor of the unmanned vehicle; and switching the unmanned vehicle from the remote control mode to the target control mode, and controlling the unmanned vehicle based on the target control mode. By adopting the method disclosed by the invention, the driving safety of the unmanned vehicle can be improved.

Description

Unmanned vehicle control method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of unmanned vehicles, and in particular, to an unmanned vehicle control method, apparatus, storage medium, and electronic device.

Background

The unmanned vehicle is an intelligent vehicle which senses road environment through a vehicle-mounted sensing system and automatically plans a driving route based on a sensing result so as to enable the vehicle to reach a destination. In practical applications, unmanned vehicles may encounter scenarios where driving control decisions cannot be made based on the vehicle surroundings. Under the scene, the unmanned vehicle can request the remote terminal to carry out manual remote control. In the process that the unmanned vehicle is operated and controlled by remote workers, if the unmanned vehicle cannot be controlled by a remote end, in order to guarantee the safety of the unmanned vehicle, a near-field safety worker needs to enter the field in time to perform manual processing.

Disclosure of Invention

The purpose of the present disclosure is to provide an unmanned vehicle control method, apparatus, storage medium, and electronic device, so as to reduce dependence of an unmanned vehicle on manual emergency processing of a near-field security officer when a remote end cannot control the vehicle, and avoid a safety risk caused by the manual emergency processing, thereby improving safety of the unmanned vehicle.

In order to achieve the above object, in a first aspect of the embodiments of the present disclosure, there is provided an unmanned vehicle control method, including:

detecting whether the communication quality of a communication link between the unmanned vehicle and the remote control terminal in the remote control mode is lower than a preset quality;

under the condition that the communication quality of the communication link is detected to be lower than the preset quality, determining a target control mode capable of controlling the unmanned vehicle to safely run under the current environment from a plurality of control modes preset by the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, wherein the environment evaluation value is determined according to sensing data collected by an unmanned vehicle sensor;

and switching the unmanned vehicle from the remote control mode to the target control mode, and controlling the unmanned vehicle based on the target control mode.

Optionally, the determining, according to an environment evaluation value representing complexity of an environment around the unmanned vehicle and a performance evaluation value representing an automatic driving capability of the unmanned vehicle, a target control mode capable of controlling the unmanned vehicle to safely run in a current environment from a plurality of control modes preset by the unmanned vehicle includes:

setting a degraded control mode to the target control mode in a case where it is determined that the environment evaluation value is greater than or equal to an environment threshold value or in a case where it is determined that the performance evaluation value is less than a performance threshold value, wherein the plurality of control modes preset by the unmanned vehicle include the degraded control mode, the degraded control mode being used to control the unmanned vehicle to stop.

and in the case that the environment evaluation value is determined to be smaller than an environment threshold value and the performance evaluation value is determined to be larger than or equal to a performance threshold value, setting an automatic driving control mode as the target control mode, wherein the plurality of preset control modes of the unmanned vehicle comprise the automatic driving control mode, and the automatic driving control mode is used for controlling the unmanned vehicle to execute an instruction of an automatic driving system.

Optionally, in a case that the target control mode is the degraded control mode, the controlling the unmanned vehicle based on the target control mode includes:

under the condition that the transverse distance between the unmanned vehicle and the parking reference line is determined to be smaller than or equal to a preset transverse distance threshold value, controlling the unmanned vehicle to decelerate and park forwards;

and under the condition that the transverse distance between the unmanned vehicle and the parking reference line is determined to be larger than the preset transverse distance threshold value, controlling the unmanned vehicle to approach to the parking reference line and decelerating and parking.

Optionally, under a condition that the parking reference line is located on the right side of the driving direction of the unmanned vehicle, the controlling the unmanned vehicle to approach to the parking reference line and to decelerate and park includes:

detecting whether a forward moving barrier exists within a preset distance behind the unmanned vehicle in real time;

controlling the front direction of the unmanned vehicle to decelerate under the condition that the forward direction moving barrier exists in the preset distance behind the unmanned vehicle;

and under the condition that the fact that the forward moving barrier does not exist within the preset distance behind the unmanned vehicle is detected, calculating a target parking position and a target reference deceleration, and controlling the unmanned vehicle to move close to the parking reference line according to the target reference deceleration so as to reach the target parking position.

Optionally, the calculating the target parking position and the target reference deceleration includes:

calculating a parking distance according to the current running speed and a preset deceleration of the unmanned vehicle;

calculating a parking position on the parking reference line according to the parking distance and the transverse distance between the unmanned vehicle and the parking reference line;

determining that the parking position is indicative of the target parking position and the preset deceleration is indicative of the target reference deceleration in case no obstacle is present within a preset range of the parking position; or, in the case where an obstacle exists within a preset range of the parking position, the target parking position where no obstacle exists within the preset range is determined from the front of the parking position, and the target reference deceleration is calculated based on the current traveling speed of the unmanned vehicle and the straight-line distance between the unmanned vehicle and the target parking position.

Alternatively, the environment evaluation value is calculated by:

determining the type of a road section where the unmanned vehicle is located currently according to sensing data acquired by the unmanned vehicle sensor;

and determining the environment evaluation value according to the type of the road section where the unmanned vehicle is located and the preset corresponding relation between the road section type and the evaluation value.

Optionally, the environment assessment value is determined according to at least one of the following conditions:

the number of obstacles in a preset range around the unmanned vehicle is in relation with the threshold value of the preset number;

a risk assessment value of collision between the unmanned vehicle and an obstacle;

the location where the unmanned vehicle collides with the obstacle;

wherein the obstacle is determined based on sensing data collected by the unmanned vehicle sensor.

Alternatively, the performance evaluation value is determined by:

acquiring output information of a function module of the unmanned vehicle when the unmanned vehicle is in an automatic driving control mode last time, wherein the function module comprises at least one of a positioning module, a sensing module, a decision planning module and a component control module;

and determining the performance evaluation value for representing the automatic driving capability of the unmanned vehicle according to the output information of the unmanned vehicle function module.

In a second aspect of the disclosed embodiments, there is provided an unmanned vehicle control apparatus, the apparatus including:

the remote control system comprises a detection module, a processing module and a control module, wherein the detection module is configured to be used for detecting whether the communication quality of a communication link between an unmanned vehicle and a remote control terminal in a remote control mode is lower than a preset quality;

an execution module configured to determine, in a case where it is detected that the communication quality of the communication link is lower than the preset quality, a target control mode capable of controlling the unmanned vehicle to safely travel in the current environment from a plurality of control modes preset by the unmanned vehicle, according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, wherein the environment evaluation value is determined according to sensing data acquired by an unmanned vehicle sensor;

a switching module configured to switch the unmanned vehicle from the remote control mode to the target control mode and control the unmanned vehicle based on the target control mode.

Optionally, the execution module includes:

a first determination sub-module configured to set a degradation control mode to the target control mode in a case where it is determined that the environmental evaluation value is greater than or equal to an environmental threshold value or in a case where it is determined that the performance evaluation value is less than a performance threshold value, wherein a plurality of control modes preset by the unmanned vehicle include the degradation control mode for controlling the unmanned vehicle to stop.

Optionally, the execution module includes:

a second determination sub-module configured to set an automatic driving control mode as the target control mode in a case where it is determined that the environment evaluation value is less than an environment threshold value and the performance evaluation value is greater than or equal to a performance threshold value, the plurality of control modes preset by the unmanned vehicle including the automatic driving control mode, the automatic driving control mode being for controlling the unmanned vehicle to execute an instruction of an automatic driving system.

Optionally, in a case that the target control mode is the degraded control mode, the switching module includes:

a first control submodule configured to control the unmanned vehicle to decelerate and park forward if it is determined that a lateral distance between the unmanned vehicle and a parking reference line is less than or equal to a preset lateral distance threshold;

a second control submodule configured to control the unmanned vehicle to approach the parking reference line and decelerate to park if it is determined that the lateral distance between the unmanned vehicle and the parking reference line is greater than the preset lateral distance threshold.

Optionally, in a case where the parking reference line is located on the right side of the unmanned vehicle traveling direction, the second control submodule is further configured to:

detecting whether a forward moving barrier exists in a preset distance behind the unmanned vehicle in real time; under the condition that the forward moving barrier exists in the preset distance behind the rear right of the unmanned vehicle, controlling the unmanned vehicle to run at a forward speed reduction state; and under the condition that the fact that the forward moving barrier does not exist within the preset distance behind the unmanned vehicle is detected, calculating a target parking position and a target reference deceleration, and controlling the unmanned vehicle to move close to the parking reference line according to the target reference deceleration so as to reach the target parking position.

Optionally, the second control sub-module is further configured to:

calculating a parking distance according to the current running speed and a preset deceleration of the unmanned vehicle; calculating a parking position on the parking reference line according to the parking distance and the transverse distance between the unmanned vehicle and the parking reference line; determining that the parking position is indicative of the target parking position and the preset deceleration is indicative of the target reference deceleration in case no obstacle is present within a preset range of the parking position; or, in a case where an obstacle exists within the preset range of the parking position, the target parking position where no obstacle exists within the preset range is determined from the front of the parking position, and the target reference deceleration is calculated based on the current traveling speed of the unmanned vehicle and the straight-line distance between the unmanned vehicle and the target parking position.

Alternatively, the environment evaluation value is calculated by:

the location where the unmanned vehicle collides with the obstacle;

Alternatively, the performance evaluation value is determined by:

In a third aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and the program, when executed by a processor, implements the steps of the method in any one of the first aspect.

In a fourth aspect of the embodiments of the present disclosure, an electronic device is provided, including:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to implement the steps of the method of any of the first aspects above.

By adopting the technical scheme, the following technical effects can be at least achieved:

under the condition that the communication quality of a communication link between the unmanned vehicle and the remote control terminal in the remote control mode is detected to be lower than the preset quality, a target control mode capable of controlling the unmanned vehicle to continuously and safely run in the current environment is determined from a plurality of control modes preset by the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle. And switching the unmanned vehicle from the remote control mode to a target control mode, and controlling the unmanned vehicle based on the target control mode. According to the method for controlling the unmanned vehicle based on the environment evaluation value and the performance evaluation value, when the unmanned vehicle is in a far and distant weak scene, the target control mode is decided based on the environment evaluation value and the performance evaluation value, and the unmanned vehicle is controlled based on the target control mode, so that the unmanned vehicle does not need to enter a near-field safety personnel for manual emergency treatment when the remote vehicle cannot control the unmanned vehicle, the dependence of the unmanned vehicle on the manual emergency treatment of the near-field safety personnel is reduced, the safety risk caused by the manual emergency treatment is avoided, and the safety of the unmanned vehicle is improved.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows.

Drawings

The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure, but do not constitute a limitation of the disclosure. In the drawings:

fig. 1 is a flow chart illustrating an unmanned vehicle control method according to an exemplary embodiment of the present disclosure.

FIG. 2 is a flowchart illustrating a method of determining a target control mode according to an exemplary embodiment of the present disclosure.

Fig. 3 is a flowchart illustrating a method of calculating a target parking position and a target reference deceleration according to an exemplary embodiment of the present disclosure.

Fig. 4 is a block diagram illustrating an unmanned vehicle control apparatus according to an exemplary embodiment of the present disclosure.

Fig. 5 is a block diagram illustrating an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.

As background art shows, in the process of remote manual operation of an unmanned vehicle, if a remote situation (such as poor communication signal, failure of a communication module of the unmanned vehicle, etc.) is encountered, in order to ensure the safety of the unmanned vehicle, a near-field security officer needs to enter the field in time to perform manual processing. However, this approach requires near field security personnel to track and focus on the condition of the unmanned vehicle in real time. If the near-field security officer does not find and process the situation of the unmanned vehicle with the remote vehicle incapable of being controlled for the first time, the safety accident is very easy to happen because the unmanned vehicle is not controlled. Moreover, the strong dependence of this approach on near field security personnel results in a paradox with the original purpose of unmanned control of unmanned vehicles. In addition, if the unmanned vehicle is applied to the scenes of goods transportation such as takeaway and express delivery, the mode can also prevent the human-vehicle ratio from being reduced in the scenes of unmanned delivery and the control of the human cost of near-field security personnel.

In view of the above, the present disclosure provides an unmanned vehicle control method, an unmanned vehicle control apparatus, a storage medium, and an electronic device, so as to at least partially solve the problems in the related art.

Fig. 1 is a flow chart illustrating an unmanned vehicle control method according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the unmanned vehicle control method includes the steps of:

s11, detecting whether the communication quality of a communication link between the unmanned vehicle and the remote control terminal in the remote control mode is lower than preset quality.

The method comprises the steps of detecting whether the unmanned vehicle is in a far and weak scene, wherein the far and weak scene represents that the communication quality between the unmanned vehicle and a remote control terminal in a remote control mode is lower than a preset quality.

The remote control terminal is an unmanned vehicle remote control system or a remote controller.

It should be noted that the communication quality between the unmanned vehicle and the remote control terminal in the remote control mode is determined by the intensity of the communication signal and/or whether the unmanned vehicle communication module is faulty.

The communication quality can be evaluated in several ways as follows. In the first mode, the time difference value is calculated according to the time stamp of the video data sent to the remote control terminal by the unmanned vehicle and the time stamp of the video data actually received by the remote control terminal (fed back to the unmanned vehicle). And comparing the difference with a preset time length, and determining that the communication quality between the unmanned vehicle and the remote control terminal in the remote control mode is lower than the preset quality when the difference is greater than the preset time length. When the difference is less than or equal to the preset time length, it can be determined that the communication quality between the unmanned vehicle and the remote control terminal in the remote control mode is not lower than the preset quality.

And secondly, calculating a time difference value according to the time stamp of the control instruction sent by the remote control terminal and the time stamp of the unmanned vehicle actually receiving the control instruction, comparing the time difference value with a preset time length, and determining that the communication quality between the unmanned vehicle and the remote control terminal is lower than the preset quality in the remote control mode when the time difference value is greater than the preset time length. When the difference is less than or equal to the preset time length, it can be determined that the communication quality between the unmanned vehicle and the remote control terminal in the remote control mode is not lower than the preset quality.

And in the mode III, if the unmanned vehicle does not receive the instruction of the remote control terminal within the preset time length in the remote control mode, the communication quality between the unmanned vehicle and the remote control terminal in the remote control mode is determined to be lower than the preset quality. The reason why the unmanned vehicle does not receive the instruction of the remote control terminal within the preset time period may be that a communication module of the unmanned vehicle fails, or that the communication signal strength of the current position of the unmanned vehicle is weak.

One possible implementation manner, the detecting whether the communication quality of the communication link between the unmanned vehicle and the remote control terminal in the remote control mode is lower than a preset quality includes: and under the condition that the unmanned vehicle is in a remote control mode, detecting whether the communication quality of the unmanned vehicle is lower than preset quality in real time.

And S12, under the condition that the communication quality of the communication link is lower than the preset quality, determining a target control mode capable of controlling the unmanned vehicle to safely run under the current environment from a plurality of preset control modes of the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, wherein the environment evaluation value is determined according to sensing data collected by an unmanned vehicle sensor.

In the case that the unmanned vehicle is detected to be in the remote weak scene, a target control mode capable of controlling the unmanned vehicle to continuously and safely run in the current environment is automatically determined from a plurality of control modes preset by the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle.

Optionally, the determining, according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, a target control mode capable of controlling the unmanned vehicle to safely run in the current environment from a plurality of control modes preset by the unmanned vehicle includes:

The environment threshold and the performance threshold can be preset based on requirements. For example, the threshold (environmental threshold or performance threshold) may be determined based on test control data and historical actual control data of the unmanned vehicle. For example, an initial threshold value is determined in a test stage, and then in the actual application process of the unmanned vehicle, after the unmanned vehicle is controlled according to the initial threshold value, the initial threshold value may be updated according to a control result fed back by the unmanned vehicle. Therefore, iterative updating and adjusting can be performed on the threshold value according to the actual driving control data of the unmanned vehicle, so that the threshold value is more consistent with the actual driving scene of the unmanned vehicle, and the control accuracy of the unmanned vehicle is improved.

The complete implementation of determining the target control mode from the plurality of control modes preset by the unmanned vehicle according to the environment evaluation value representing the complexity of the environment around the unmanned vehicle and the performance evaluation value representing the automatic driving capability of the unmanned vehicle is shown in fig. 2, and details are not repeated here.

And S13, switching the unmanned vehicle from the remote control mode to the target control mode, and controlling the unmanned vehicle based on the target control mode.

After a target control mode capable of controlling the unmanned vehicle to safely run in the current environment is determined from a plurality of control modes preset by the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, the unmanned vehicle can be switched from a remote control mode to the target control mode, and the unmanned vehicle is controlled based on the target control mode.

By adopting the method, when the unmanned vehicle is detected to be in a remote weak scene, the target control mode is determined from a plurality of preset control modes of the unmanned vehicle according to the environment evaluation value representing the complexity of the environment around the unmanned vehicle and the performance evaluation value representing the automatic driving capability of the unmanned vehicle. And switching the unmanned vehicle from the remote control mode to a target control mode, and controlling the unmanned vehicle based on the target control mode. According to the method for controlling the unmanned vehicle based on the environment evaluation value and the performance evaluation value, when the unmanned vehicle is in a far and remote weak scene, the target control mode is decided based on the environment evaluation value and the performance evaluation value, and the unmanned vehicle is controlled based on the target control mode, when the unmanned vehicle cannot be controlled at a far end, a near-field security worker is not required to enter the field for manual emergency treatment, dependence of the unmanned vehicle on the manual emergency treatment of the near-field security worker is reduced, safety risks caused by the manual emergency treatment are avoided, and therefore safety of the unmanned vehicle is improved.

In addition, by adopting the method disclosed by the invention, when the unmanned vehicle is in a far and remote weak scene, because the near-field security officer is not required to enter the scene for manual emergency treatment, the safety problem of the unmanned vehicle caused by the fact that the near-field security officer does not find and treat the condition that the vehicle cannot be controlled by the far end in the first time can be avoided, and therefore, the safety of the unmanned vehicle is improved by the method disclosed by the invention. Similarly, by adopting the method disclosed by the invention, when the unmanned vehicle is in a far and remote weak scene, because the unmanned vehicle does not need a near-field security officer to enter for manual emergency treatment, the dependence of the unmanned vehicle on the manual emergency treatment of the near-field security officer is reduced, and the intelligent emergency capacity of the unmanned vehicle is improved. The unmanned vehicle applying the method disclosed by the invention is applied to the scenes of cargo transportation such as takeaway and express delivery, and the man-vehicle ratio and the labor cost in the scenes of unmanned delivery can be indirectly reduced.

under the condition that the transverse distance between the unmanned vehicle and the parking reference line is determined to be smaller than or equal to a preset transverse distance threshold value, controlling the unmanned vehicle to decelerate and park forwards; and under the condition that the transverse distance between the unmanned vehicle and the parking reference line is determined to be larger than the preset transverse distance threshold value, controlling the unmanned vehicle to approach the parking reference line and decelerating and parking.

It should be noted that the parking reference line may be determined based on a lane curb (also called a cliff). Illustratively, the parking reference line is a virtual reference line on the lane equidistant from the roadway curb of the lane by 0cm or 30cm or 20 cm. As another example, the parking reference line may be a solid parking line marked on the lane. As another example, the parking reference line may be a road curb.

The preset lateral distance threshold is determined based on a driving specification manual. Typically, the predetermined lateral distance threshold is 10 centimeters (centimeters). Of course, the preset lateral distance threshold may also be set to 15 centimeters, 20 centimeters, etc. for safety reasons, and the disclosure is not particularly limited thereto.

For example, in the case where it is determined that the lateral distance between the unmanned vehicle and the parking reference line is less than or equal to 10 cm, it is described that the unmanned vehicle can be directly decelerated to park without turning to the parking reference line, and in this case, the unmanned vehicle is controlled to be decelerated forward to park. The unmanned vehicle decelerates forwards and stops, and the unmanned vehicle does not need to turn to a parking reference line and move close to the parking reference line. As another example, in the case where it is determined that the lateral distance between the unmanned vehicle and the parking reference line is greater than 10 cm, it is described that the unmanned vehicle does not satisfy the condition for direct deceleration parking, and in this case, the unmanned vehicle needs to be controlled to approach the parking reference line and decelerate to park. The process of controlling the unmanned vehicle to approach to the parking reference line and stop at a reduced speed refers to controlling the unmanned vehicle to turn to the parking reference line to travel towards the parking reference line at a reduced speed and approach until the unmanned vehicle stops when the transverse distance between the unmanned vehicle and the parking reference line is less than or equal to 10 centimeters.

Optionally, in a case that the target control mode is the automatic driving control mode, the controlling the unmanned vehicle based on the target control mode includes: and controlling the unmanned vehicle to continue running or stop based on the instruction of the automatic driving system. The instruction of the automatic driving system is obtained by a preset decision planning algorithm based on the sensing result of the environment sensing system, which may be referred to in the related art, and is not described herein.

detecting whether a forward moving barrier exists within a preset distance behind the unmanned vehicle in real time; controlling the front direction of the unmanned vehicle to decelerate under the condition that the forward direction moving barrier exists in the preset distance behind the unmanned vehicle; and under the condition that the front moving obstacle is not detected within the preset distance behind the right of the unmanned vehicle, calculating a target parking position and a target reference deceleration, and controlling the unmanned vehicle to approach the parking reference line to run according to the target reference deceleration so as to reach the target parking position. The process of controlling the unmanned vehicle to approach the parking reference line to travel to the target parking position according to the target reference deceleration is to control the unmanned vehicle to steer to the right (or the right front) and simultaneously decelerate according to the target reference deceleration.

The preset distance is determined according to the braking distance of the front moving barrier within the preset distance at the rear right of the unmanned vehicle. It should be understood that the greater the speed of the forward moving obstacle, the greater the stopping distance of the forward moving obstacle.

It is easy to understand that, under the condition that the parking reference line is positioned on the right side of the driving direction of the unmanned vehicle, in the process of controlling the unmanned vehicle to approach to the parking reference line and decelerating and parking, whether a forward moving obstacle exists in the preset distance behind the unmanned vehicle or not needs to be detected in real time. Under the condition that the existence of the forward moving barrier in the preset distance behind the rear right of the unmanned vehicle is detected, the unmanned vehicle is controlled to run at a reduced speed in the forward direction, so that the risk that the unmanned vehicle collides with the forward moving barrier due to steering running towards the parking reference line is avoided. And under the condition that no forward moving barrier exists within a preset distance behind the unmanned vehicle, calculating a target parking position and a target reference deceleration, and controlling the unmanned vehicle to approach to a parking reference line according to the target reference deceleration so as to reach the target parking position.

Optionally, when the parking reference line is located on the left side of the driving direction of the unmanned vehicle, the controlling the unmanned vehicle to approach the parking reference line and decelerate to park includes:

detecting whether a forward moving barrier exists within a preset distance behind the left of the unmanned vehicle in real time; controlling the front direction of the unmanned vehicle to decelerate under the condition that the existence of the forward moving barrier in the preset distance at the left rear of the unmanned vehicle is detected; under the condition that the fact that the forward moving barrier does not exist within the preset distance behind the left of the unmanned vehicle is detected, a target parking position and a target reference deceleration are calculated, and the unmanned vehicle is controlled to move close to the parking reference line according to the target reference deceleration so as to reach the target parking position.

Referring to fig. 3, the calculating the target parking position and the target reference deceleration may specifically include the following steps:

and S301, calculating the parking distance according to the current running speed and the preset deceleration of the unmanned vehicle.

The preset deceleration can be determined according to the current running speed of the unmanned vehicle and the preset corresponding relation between the running speed and the deceleration of the unmanned vehicle. The stopping distance refers to a distance required for the unmanned vehicle to decelerate from a current running speed to zero according to a preset deceleration.

S302, calculating a parking position on the parking reference line according to the parking distance and the transverse distance between the unmanned vehicle and the parking reference line.

The specific implementation mode of calculating the parking position on the parking reference line according to the parking distance and the transverse distance is that a right-angled triangle is constructed by taking the parking distance as a hypotenuse and the transverse distance as a right-angled side so as to determine the parking position on the parking reference line.

And S303, judging whether an obstacle exists in the preset range of the parking position.

The preset range of the parking position can be 3 meters in front of and/or behind the parking position, 5 meters in front of and behind the parking position, 4 meters around the parking position, and 2 meters in front of, behind and beside the unmanned vehicle.

S304, when there is no obstacle within the preset range of the parking position, taking the parking position as the target parking position, and taking the preset deceleration as the target reference deceleration.

If no obstacle exists within the preset range of the parking position, the situation that the parking position meets the parking requirement and the obstacle is not collided is explained. In this case, the parking position is directly taken as the target parking position, and the preset deceleration is taken as the target reference deceleration.

S305, under the condition that an obstacle exists in a preset range of the parking position, determining the target parking position without the obstacle in the preset range from the front of the parking position, and calculating the target reference deceleration based on the current running speed of the unmanned vehicle and the straight-line distance between the unmanned vehicle and the target parking position.

When an obstacle exists in the preset range of the parking position, the parking position does not meet the parking requirement, namely, the parking position is in collision with the obstacle, at the moment, a target parking position without the obstacle in the preset range needs to be determined from the front of the parking position, and the target reference deceleration is calculated based on the current running speed of the unmanned vehicle and the straight-line distance between the unmanned vehicle and the target parking position.

It should be understood that a deceleration at which the unmanned vehicle decelerates to 0 at a constant speed may be calculated based on a straight-line distance between the unmanned vehicle and the target parking position, the current traveling speed of the unmanned vehicle, and the target reference deceleration may be determined based on the deceleration. Illustratively, the target reference deceleration is the deceleration. As another example, the target reference deceleration includes a plurality of values, e.g., the target reference deceleration includes a value greater than the deceleration and a value less than the deceleration.

It should be noted that the method shown in fig. 3 is also applicable to the case where the parking reference line is on the left side in the unmanned vehicle traveling direction.

Under the condition that the unmanned vehicle is in a far and weak scene and cannot be automatically driven, the unmanned vehicle can be controlled to safely stop by adopting the degradation control mode so as to wait for the indication of a remote control terminal or the processing of near-field personnel.

Alternatively, the environment assessment value may be calculated by: determining the type of a road section where the unmanned vehicle is located currently according to sensing data acquired by the unmanned vehicle sensor; and determining the environment evaluation value according to the type of the road section where the unmanned vehicle is located and the preset corresponding relation between the road section type and the evaluation value. The road section types include an intersection type, a school road section type, a district entrance and exit road section type and the like.

Further, the environment evaluation value may also be calculated as follows. The environment assessment value is determined according to the size relation between the number of obstacles in a preset range around the unmanned vehicle (or one side or multiple sides) and a preset number threshold, and specifically, the environment assessment value is determined according to the number interval in which the number of obstacles in the preset range around the unmanned vehicle falls, and the corresponding relation between the numerical value interval and the assessment value. Alternatively, the environment evaluation value is determined based on the evaluation value of the risk of collision of the unmanned vehicle with the obstacle. And determining an environment evaluation value according to the collision direction of the unmanned vehicle and the obstacle, wherein if the unmanned vehicle collides with the obstacle behind the unmanned vehicle, the unmanned vehicle cannot be stopped urgently. The obstacles, or the number of the obstacles, or the directions of the obstacles, or the collision risks of the obstacles can be determined based on the sensing data acquired by the unmanned vehicle sensor.

Alternatively, the performance evaluation value is determined by:

acquiring output information of a function module of the unmanned vehicle when the unmanned vehicle is in an automatic driving control mode last time, wherein the function module comprises at least one of a positioning module, a sensing module, a decision planning module and a component control module; and determining the performance evaluation value for representing the automatic driving capability of the unmanned vehicle according to the output information of the unmanned vehicle function module.

Wherein determining the performance evaluation value for characterizing the automatic driving capability of the unmanned vehicle according to the output information of the unmanned vehicle function module comprises: determining a plurality of measurement values for representing the single control capacity of the unmanned vehicle according to the output information of the unmanned vehicle function module, wherein the single control capacity comprises the positioning capacity, the path planning capacity, the obstacle sensing capacity and the driving direction control capacity of the unmanned vehicle; specifically, a first metric value representing the unmanned vehicle positioning capacity is determined according to the positioning information output by the positioning module; determining a second metric value representing the obstacle sensing capability of the unmanned vehicle according to the obstacle information output by the sensing module; determining a third metric value representing the unmanned vehicle path planning capability according to the automatic driving path output by the decision planning module; and determining a fourth metric value representing the driving direction control capability of the unmanned vehicle according to the steering wheel control information output by the component control module. And determining a target control value for representing the automatic driving capability of the unmanned vehicle according to the four measurement values and a preset score rule.

The embodiment of the disclosure can provide different evaluation modes for different functional modules, and the evaluation accuracy of the single control capability of the unmanned vehicle is ensured. For example, whether the positioning converges or not may be evaluated according to a variance between positioning information output by a plurality of positioning sensors included in the positioning module, i.e., the first metric value may represent a degree of positioning convergence. For example, the larger the first metric value is, the higher the localization convergence degree is, and conversely, the lower the localization convergence degree is. On the other hand, whether the current sensing capability is stable or not can be evaluated by determining whether the same obstacle jumps or not, whether the size of the same obstacle is stable or not and whether the change of the same obstacle is smooth or not in a continuous time period according to the obstacle information output by the sensing module, namely the second metric value can represent the stability degree of the current sensing capability. For example, the larger the second metric value is, the higher the stability of the current sensing capability is, and conversely, the lower the stability of the current sensing capability is. Further, whether the vehicle is obstructed, whether the path is smooth, etc. may be evaluated according to the length of the autonomous driving path and the curvature between points output by the decision planning module. And, according to the steering wheel control information output by the component control module, the derivative of the steering wheel angle in the continuous time period can be determined to judge whether the vehicle runs left and right, and the like.

Based on the same inventive concept, the disclosed embodiments provide an unmanned vehicle control device, which may be a part or all of an unmanned vehicle through software, hardware or a combination of both. Referring to fig. 4, the unmanned vehicle control device 400 includes:

a detection module 410 configured to detect whether a communication quality of a communication link between the unmanned vehicle and the remote control terminal in the remote control mode is lower than a preset quality;

an execution module 420, configured to, in a case where it is detected that the communication quality of the communication link is lower than the preset quality, determine, from a plurality of control modes preset by the unmanned vehicle, a target control mode capable of controlling the unmanned vehicle to safely travel in the current environment according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, where the environment evaluation value is determined according to sensing data collected by an unmanned vehicle sensor;

a switching module 430 configured to switch the unmanned vehicle from the remote control mode to the target control mode and control the unmanned vehicle based on the target control mode.

By adopting the device, when the unmanned vehicle is detected to be in a far and distant weak scene, the target control mode is determined from a plurality of preset control modes of the unmanned vehicle according to the environment evaluation value representing the complexity of the surrounding environment of the unmanned vehicle and the performance evaluation value representing the automatic driving capability of the unmanned vehicle. And switching the unmanned vehicle from the remote control mode to a target control mode, and controlling the unmanned vehicle based on the target control mode. According to the method, when the unmanned vehicle is in a remote weak scene, the target control mode is decided based on the environment evaluation value and the performance evaluation value, and the unmanned vehicle is controlled based on the target control mode, so that manual emergency processing is performed without the need of a near-field security worker when the unmanned vehicle cannot control the vehicle at the remote end, and the dependence of the unmanned vehicle on the manual emergency processing of the near-field security worker is reduced.

Optionally, the executing module 420 includes:

a first determination sub-module configured to set a degraded control mode to the target control mode in a case where it is determined that the environmental evaluation value is greater than or equal to an environmental threshold value or in a case where it is determined that the performance evaluation value is less than a performance threshold value, wherein the plurality of control modes preset by the unmanned vehicle include the degraded control mode, the degraded control mode being used to control the unmanned vehicle to stop.

Optionally, the executing module 420 includes:

Optionally, in a case that the target control mode is the degraded control mode, the switching module 430 includes:

detecting whether a forward moving barrier exists within a preset distance behind the unmanned vehicle in real time; controlling the front direction of the unmanned vehicle to decelerate under the condition that the forward direction moving barrier exists in the preset distance behind the unmanned vehicle; and under the condition that the fact that the forward moving barrier does not exist within the preset distance behind the unmanned vehicle is detected, calculating a target parking position and a target reference deceleration, and controlling the unmanned vehicle to move close to the parking reference line according to the target reference deceleration so as to reach the target parking position.

Optionally, the second control sub-module is further configured to:

calculating a parking distance according to the current running speed and a preset deceleration of the unmanned vehicle; calculating a parking position on the parking reference line according to the parking distance and the transverse distance between the unmanned vehicle and the parking reference line; determining that the parking position is indicative of the target parking position and the preset deceleration is indicative of the target reference deceleration in case no obstacle is present within a preset range of the parking position; or, in the case where an obstacle is present within the preset range of the parking position, the target parking position where no obstacle is present within the preset range is determined from the front of the parking position, and the target reference deceleration is calculated based on the current traveling speed of the unmanned vehicle and the straight-line distance between the unmanned vehicle and the target parking position.

Alternatively, the environment evaluation value is calculated by:

determining the type of a road section where the unmanned vehicle is located currently according to sensing data acquired by the unmanned vehicle sensor; and determining the environment evaluation value according to the type of the road section where the unmanned vehicle is located and the preset corresponding relation between the road section type and the evaluation value.

the number of obstacles in a preset range around the unmanned vehicle is in a size relation with a preset number threshold;

the location where the unmanned vehicle collides with the obstacle;

wherein the obstacle is determined based on sensing data acquired by the unmanned vehicle sensor.

Alternatively, the performance evaluation value is determined by:

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Fig. 5 is a block diagram illustrating an electronic device 700, which may be an unmanned vehicle or a partial component of an unmanned vehicle, according to an example embodiment. As shown in fig. 5, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.

The processor 701 is configured to control the overall operation of the electronic device 700, so as to complete all or part of the steps in the above-mentioned unmanned vehicle control method. The memory 702 is used to store various types of data to support operation at the electronic device 700, such as instructions for any application or method operating on the electronic device 700 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The Memory 702 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia components 703 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 702 or transmitted through the communication component 705. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, near Field Communication (NFC for short), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, which is not limited herein. The corresponding communication component 705 may thus include: wi-Fi module, bluetooth module, NFC module, etc.

In an exemplary embodiment, the electronic Device 700 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described unmanned vehicle control method.

In another exemplary embodiment, a computer readable storage medium including program instructions which, when executed by a processor, implement the steps of the above-described unmanned vehicle control method is also provided. For example, the computer readable storage medium may be the memory 702 described above including program instructions executable by the processor 701 of the electronic device 700 to perform the above-described unmanned vehicle control method.

In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described unmanned vehicle control method when executed by the programmable apparatus.

The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. To avoid unnecessary repetition, the disclosure does not separately describe various possible combinations.

In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure as long as it does not depart from the gist of the present disclosure.

Claims

1. An unmanned vehicle control method, comprising:

under the condition that the communication quality of the communication link is detected to be lower than the preset quality, determining a target control mode capable of controlling the unmanned vehicle to safely run in the current environment from a plurality of control modes preset by the unmanned vehicle according to an environment evaluation value representing the complexity of the environment around the unmanned vehicle and a performance evaluation value representing the automatic driving capability of the unmanned vehicle, wherein the environment evaluation value is determined according to sensing data acquired by a sensor of the unmanned vehicle;

2. The method according to claim 1, wherein the determining a target control mode capable of controlling the unmanned vehicle to safely travel under the current environment from a plurality of control modes preset by the unmanned vehicle according to the environment evaluation value representing the complexity of the environment around the unmanned vehicle and the performance evaluation value representing the automatic driving capability of the unmanned vehicle comprises:

3. The method according to claim 1, wherein the determining a target control mode capable of controlling the unmanned vehicle to safely travel under the current environment from a plurality of control modes preset by the unmanned vehicle according to the environment evaluation value representing the complexity of the environment around the unmanned vehicle and the performance evaluation value representing the automatic driving capability of the unmanned vehicle comprises:

4. The method of claim 2, wherein, in the case that the target control mode is the degraded control mode, the controlling the unmanned vehicle based on the target control mode comprises:

and under the condition that the transverse distance between the unmanned vehicle and the parking reference line is determined to be larger than the preset transverse distance threshold value, controlling the unmanned vehicle to approach the parking reference line and decelerating and parking.

5. The method according to claim 4, wherein in a case where the parking reference line is located on the right side of the unmanned vehicle traveling direction, the controlling the unmanned vehicle to approach to the parking reference line and decelerate to park includes:

detecting whether a forward moving barrier exists in a preset distance behind the unmanned vehicle in real time;

and under the condition that the front moving obstacle is not detected within the preset distance behind the right of the unmanned vehicle, calculating a target parking position and a target reference deceleration, and controlling the unmanned vehicle to approach the parking reference line to run according to the target reference deceleration so as to reach the target parking position.

6. The method of claim 5, wherein the calculating a target parking position and a target reference deceleration comprises:

in the absence of an obstacle within a preset range of the parking position, determining that the parking position is indicative of the target parking position and that the preset deceleration is indicative of the target reference deceleration; or, in a case where an obstacle exists within the preset range of the parking position, the target parking position where no obstacle exists within the preset range is determined from the front of the parking position, and the target reference deceleration is calculated based on the current traveling speed of the unmanned vehicle and the straight-line distance between the unmanned vehicle and the target parking position.

7. The method according to any one of claims 1 to 6, wherein the environment assessment value is calculated by:

8. The method according to any one of claims 1 to 6, wherein the environment assessment value is determined according to at least one of the following conditions:

the location where the unmanned vehicle collides with the obstacle;

9. The method according to any one of claims 1 to 6, wherein the performance assessment value is determined by:

10. An unmanned vehicle control apparatus, characterized in that the apparatus comprises:

11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.

12. An electronic device, comprising:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-9.