CN112990758B - Method and device for remotely controlling unmanned equipment - Google Patents
Method and device for remotely controlling unmanned equipment Download PDFInfo
- Publication number
- CN112990758B CN112990758B CN202110397322.4A CN202110397322A CN112990758B CN 112990758 B CN112990758 B CN 112990758B CN 202110397322 A CN202110397322 A CN 202110397322A CN 112990758 B CN112990758 B CN 112990758B
- Authority
- CN
- China
- Prior art keywords
- operator
- target area
- operators
- route
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The specification discloses a method and a device for remotely controlling unmanned equipment, a service platform can acquire each route in a target area, and inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted remote control times corresponding to the target area, and aiming at the number of each candidate operator, according to the remote control times, determining the average waiting time of the unmanned equipment for the operators with the candidate operator number to remotely control the unmanned equipment as the average waiting time corresponding to the candidate operator number, and selecting the configuration number of the operators from the candidate operator numbers according to the average waiting time corresponding to the candidate operator numbers, and allocating the operators to the target area according to the configuration number of the operators, and remotely controlling the unmanned equipment in the target area through the operator allocated to the target area. The method can select the appropriate number of operators for the target area.
Description
Technical Field
The present disclosure relates to the field of unmanned driving, and more particularly, to a method and an apparatus for remotely controlling an unmanned device.
Background
In the field of unmanned driving, when the unmanned equipment has running risks or may have running risks and the unmanned equipment cannot solve the running risks by itself, an operator (also called a safety operator) can remotely control the unmanned equipment to run, and the unmanned equipment can be ensured to continue running safely.
In the prior art, a plurality of operators can be allocated to each geographic area, so that an operator in charge of each geographic area can take over such unmanned equipment when the unmanned equipment in each geographic area is in an emergency, for one geographic area, the number of operators in the geographic area can be set manually according to experience, but if the set number is too large, the problem of labor cost waste is caused, and if the set number is too small, the unmanned equipment in the geographic area needs too much time to wait for the take over of the operators when driving risks occur in the driving process.
Therefore, how to determine the appropriate number of operators and ensure the safe driving of the unmanned equipment is an urgent problem to be solved.
Disclosure of Invention
The present disclosure provides a method and apparatus for remotely controlling an unmanned aerial vehicle, which partially solve the above problems in the prior art.
The technical scheme adopted by the specification is as follows:
the present specification provides a method of remotely controlling an unmanned device, comprising:
obtaining each route in a target area;
inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted times of each unmanned device in the target area needing to be remotely controlled by an operator, wherein the predicted times are used as the remote control times corresponding to the target area;
for each candidate operator number, determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times, wherein the average waiting time is taken as the average waiting time corresponding to the candidate operator number;
and selecting the configured number of operators from the number of the candidate operators according to the average waiting time corresponding to the number of the candidate operators, allocating operators to the target area according to the configured number of the operators, and remotely controlling the unmanned equipment in the target area through the operators allocated to the target area.
Optionally, inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted number of times that each unmanned device in the target area needs to be remotely controlled by an operator, and specifically includes:
for each route, determining each section related to the route;
inputting the road section information of each road section into the prediction model, and predicting the times of remote control required by an operator when the unmanned equipment runs on the route;
and determining the times of remote control required by the operator of each unmanned device in the target area according to the predicted times of remote control required by the operator when the unmanned device runs on each route.
Optionally, the prediction model comprises: a feature extraction sub-model and a decision sub-model;
inputting the road section information of each road section into the prediction model, predicting the times of remote control required by an operator when the unmanned equipment runs on the route, and specifically comprising the following steps:
inputting the road section information corresponding to each road section into the feature extraction submodel to obtain the route feature corresponding to the route;
and inputting the route characteristics into the decision submodel, and predicting the times of the unmanned equipment needing to be remotely controlled by an operator when the unmanned equipment runs on the route.
Optionally, the road section information includes at least one of historical road condition information, real-time road condition information, weather information corresponding to the road section, and date information.
Optionally, for each candidate number of operators, determining, according to the number of remote controls, an average waiting time of the unmanned aerial vehicle when the unmanned aerial vehicle is remotely controlled by the target area by the candidate number of operators, specifically includes:
determining an average processing efficiency of each operator in the target area historically completing a remote control task for the unmanned aerial vehicle;
and determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times, the average processing efficiency and the candidate operator number.
Optionally, determining, according to the number of remote controls, the average processing efficiency, and the number of candidate operators, an average waiting time of the unmanned aerial vehicle when the unmanned aerial vehicle is remotely controlled by the operators with the number of candidate operators in the target area, specifically includes:
determining a working strength characteristic value of each operator in the target area according to the remote control times, the average processing efficiency and the number of the candidate operators, wherein the remote control times and the working strength characteristic value are in a positive correlation relationship, and the average processing efficiency and the number of the candidate operators and the working strength characteristic value are in a negative correlation relationship;
determining the probability that each operator in the target area does not need to remotely control the unmanned equipment under the candidate operator number as an idle probability according to the working strength characterization value, the candidate operator number, the remote control times and the average processing efficiency;
determining the average waiting number of the unmanned equipment needing the operator to carry out remote control in the target area according to the idle probability, the working strength characterization value and the number of the candidate operators;
and determining the average waiting time length of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the average waiting number and the remote control times, wherein the average waiting number and the average waiting time length have a positive correlation, and the remote control times and the average waiting time length have a negative correlation.
Optionally, selecting the configured number of operators from the number of candidate operators according to the average waiting duration corresponding to the number of candidate operators, specifically including:
and selecting the operator configuration number from the candidate operator numbers by taking the condition that the average waiting time length does not exceed the set waiting time length and the operator configuration number corresponding to the target area is the minimum as a target.
Optionally, training the prediction model specifically includes:
acquiring historical route information of each route and historical times of the unmanned equipment which needs to be remotely controlled by an operator when the unmanned equipment runs on each route;
inputting the historical route information into the prediction model to obtain the predicted times of the unmanned equipment which needs to be remotely controlled by an operator when the unmanned equipment runs on each route, wherein the predicted times are used as prediction times;
and training the prediction model by taking the minimized deviation between the prediction times and the historical times as an optimization target.
This specification provides an apparatus for remotely controlling an unmanned device, comprising:
the acquisition module is used for acquiring each route in the target area;
the prediction module is used for inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted times of each unmanned device in the target area needing to be remotely controlled by an operator, and the predicted times are used as the remote control times corresponding to the target area;
the determining module is used for determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times aiming at each candidate operator number, and the average waiting time is used as the average waiting time corresponding to the candidate operator number;
the allocation module is used for selecting the configured number of operators from the number of the candidate operators according to the average waiting time corresponding to the number of the candidate operators, allocating the operators to the target area according to the configured number of the operators, and remotely controlling the unmanned equipment in the target area through the operators allocated to the target area.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described method of remotely controlling an unmanned device.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-described method of remotely controlling an unmanned device when executing the program.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the method for remotely controlling an unmanned aerial vehicle provided in this specification, a service platform may obtain each route in a target area, input route information corresponding to each route into a pre-trained prediction model, obtain predicted times that each unmanned aerial vehicle in the target area needs to be remotely controlled by an operator, as remote control times corresponding to the target area, determine, for each candidate operator number, an average waiting time of the unmanned aerial vehicle when the unmanned aerial vehicle is remotely controlled by the operator with the candidate operator number in the target area according to the remote control times, as an average waiting time corresponding to the candidate operator number, and select an operator configuration number from the candidate operator numbers according to the average waiting time corresponding to the candidate operator numbers, and configure the number according to the operator, assigning an operator to the target area, and remotely controlling the unmanned aerial device in the target area by the operator assigned to the target area.
According to the method, the service platform can predict the times that each unmanned device in the target area needs to be remotely controlled, namely the remote control times corresponding to the target area, and determines the average waiting time of the unmanned devices in the target area when the unmanned devices need to be remotely controlled under different candidate operator numbers according to the remote control times, so that the appropriate candidate operator numbers are selected, and the driving safety of the unmanned devices is ensured under the condition of saving the cost.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
FIG. 1 is a schematic flow diagram of a method for remotely controlling an unmanned aerial device of the present disclosure;
FIG. 2 is a schematic illustration of an assignment of operators to unmanned devices provided herein;
FIG. 3 is a schematic illustration of segments involved in a route provided herein;
FIG. 4 is a schematic diagram of a prediction model provided herein;
FIG. 5 is a schematic diagram of an apparatus for remotely controlling an unmanned aerial device provided herein;
fig. 6 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for remotely controlling an unmanned aerial vehicle, which includes the following steps:
s101: and acquiring each route in the target area.
S102: and inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted times of each unmanned device in the target area needing to be remotely controlled by an operator, wherein the predicted times are used as the remote control times corresponding to the target area.
In practical application, a plurality of operators can be configured in each geographic area, and when the unmanned device runs at risk or cannot control the unmanned device to run continuously, the service platform can allocate the operator to the unmanned device, so that the operator controls the unmanned device to run continuously, as shown in fig. 2.
Fig. 2 is a schematic diagram of an assignment of an operator to an unmanned aerial vehicle provided by the present specification.
In fig. 2, from left to right, it indicates that the unmanned device a needs to be remotely controlled by an operator, the service platform allocates the unmanned device a to the operator a, then the unmanned device B needs to be remotely controlled by the operator, and the service platform allocates the unmanned device B to the operator B.
For different geographic areas, the service platform may determine the number of operators assigned within the geographic area to assign operators to the geographic area. Based on this, the service platform can acquire each route in the target area, and input route information corresponding to each route into a pre-trained prediction model, so as to obtain the predicted number of times that each unmanned device in the target area needs to be remotely controlled by the operator, and the predicted number of times is used as the remote control number of times corresponding to the target area. The target area referred to herein may refer to a geographic area in which the drone operates, and may be a target area for each geographic area in which the drone operates. Each route in the target area acquired by the service platform may refer to each historical route obtained after each unmanned device has historically run in the target area.
The predicted number of remote controls corresponding to the target area is the number of times that the unmanned device cannot travel by itself and needs an operator to perform remote control in the target area. Specifically, the service platform may determine, for each route, each link related to the route, input link information of each link into the prediction model, predict the number of times that the operator needs to perform remote control when the drone travels on the route, and then determine, according to the predicted number of times that the operator needs to perform remote control when the drone travels on each route, the number of times that each drone needs to perform remote control by the operator in the target area, that is, the number of times of remote control corresponding to the target area.
That is to say, the service platform may predict, through the prediction model, the number of times that the unmanned aerial vehicle may need to be remotely controlled by the operator during driving in each route in the target area, that is, determine the number of times of remote control corresponding to each route, and then may determine the number of times of remote control corresponding to the target area according to the predicted total number of times that the unmanned aerial vehicle needs to be remotely controlled in each route.
Each link involved in one route may refer to a plurality of links divided on the route, and the specific dividing manner may be various. For example, the route may be divided equally to obtain the segments involved in the route. For another example, each route related to the route may be determined according to the structure of the road, as shown in fig. 3.
Fig. 3 is a schematic diagram of the sections involved in one route provided in the present specification.
As can be seen from fig. 3, a complete route is obtained from point a to point B, and the service platform may divide the route into a plurality of segments by using each intersection in the route as a dividing point, so that the segments involved in the route are a segment from point a to point C, a segment from point C to point D, a segment from point D to point E, and a segment from point E to point B.
In this specification, the prediction model may include a feature extraction submodel and a decision submodel, where the feature extraction submodel is configured to obtain a feature of a route, and the decision submodel is configured to predict the number of times of remote control corresponding to the route according to the feature obtained by the feature extraction submodel. When the number of times of remote control corresponding to a route is predicted, the service platform can input the section information corresponding to each section related to the route into the feature extraction submodel to obtain the route feature corresponding to the route. The road section information may include historical road condition information, real-time road condition information, lane information of the road section, weather information corresponding to the road section, date information, and information indicating whether the current time is a morning peak or an evening peak. The date information may indicate whether the current date is a specific date, such as holiday, weekend, etc., and the weather information corresponding to the link may indicate whether the current time is rainy, whether it is sunny, etc.
The historical traffic information and the real-time traffic information may include the number of surrounding obstacles, the speed, acceleration, direction, trajectory, and the like of each obstacle while the unmanned aerial vehicle travels historically and in real time. For example, if the route is a route from 10 to 10 points and 10 minutes, the real-time traffic information may indicate the traffic conditions around the unmanned aerial vehicle when driving on the route from 10 to 10 points and 10 minutes, and the historical traffic information may indicate the traffic conditions around the unmanned aerial vehicle when driving on the route after a period of time has elapsed from 10 points.
In this specification, the section information of each section related to the route may be divided into two parts, one part is traffic information, and the other part is non-traffic information. The traffic information corresponding to a road segment may include historical traffic information, real-time traffic information, and lane information of the road segment corresponding to the road segment. The non-road condition information of each road section may include weather information, date information, information indicating whether it is a morning-evening peak, and the like. Since the non-road condition information is uniform for each road segment, the non-road condition information of each road segment may be uniform, that is, the non-road condition information of each dimension is one for each road segment, and certainly, each road segment may correspond to one non-road condition information, and the feature extraction sub-model may include two parts for respectively processing the road condition information and the non-road condition information, as shown in fig. 4.
Fig. 4 is a schematic structural diagram of a prediction model provided in this specification.
As can be seen from fig. 4, in the prediction model, the feature extraction submodel includes a Long Short-Term Memory network (LSTM), and feature extraction may be performed on the road condition information corresponding to each road segment through the LSTM to obtain a first feature corresponding to the road segment, where the road condition information corresponding to each road segment may be input into the LSTM in a matrix form, each line or each column of the matrix includes road condition information corresponding to one road segment, the feature extraction submodel further includes a part for encoding non-road condition information, the part is referred to as an encoding module included in the feature extraction submodel, after the encoding module performs feature extraction on the non-road condition information, a second feature corresponding to the road segment may be obtained, and the first feature and the second feature may be fused, for example, spliced or added, to obtain a route feature corresponding to the route, and then inputting the route characteristics into a decision submodel to obtain the predicted times that the unmanned equipment needs to be remotely controlled by an operator when the unmanned equipment runs on the route.
It should be noted that the above-mentioned number of times of remote control corresponding to the target area may be the number of times that each unmanned aerial device in the target area needs to perform remote control in a unit time, and therefore, when determining the number of times of remote control, each route in the target area that is acquired may be a route obtained after each unmanned aerial device in the target area travels in a unit time, and the unit time may be set, for example, 1 hour.
Of course, a certain time period may be shifted forward from the current time to obtain each route traveled by the unmanned aerial vehicle in the target area within the time period, and when determining the number of remote control times corresponding to the target area, the predicted total number of times that the unmanned aerial vehicle needs to be remotely controlled in each route may be divided by the time period to obtain the number of times that the unmanned aerial vehicle needs to be remotely controlled in the target area within the unit time as the number of remote control times corresponding to the target area.
The more the number of remote control times corresponding to the target area is, the more the number of operators required in the target area may be, and the less the number of remote control times corresponding to the target area is, the less the number of operators required in the target area may be, therefore, when the number of operators required to be allocated in the target area is determined in the following, the determination needs to be performed by the number of remote control times corresponding to the target area.
In this specification, the prediction model may be trained in a supervised training manner, and specifically, the service platform may obtain historical route information of each route and historical times that the unmanned aerial vehicle needs to be remotely controlled by an operator when traveling on each route, and input the historical route information into the prediction model to obtain predicted times that the unmanned aerial vehicle needs to be remotely controlled by the operator when traveling on each route as the prediction times, and train the prediction model with an optimization target of minimizing a deviation between the prediction times and the historical times.
The unmanned equipment mentioned above may refer to equipment capable of realizing automatic driving, such as unmanned vehicles, unmanned aerial vehicles, automatic distribution equipment, and the like. Based on this, the remote control method provided by the specification can determine the number of operators in each geographic area, and when the unmanned device in one geographic area needs to be remotely controlled, the service platform can distribute the operators to the unmanned device to remotely control the unmanned device, and the unmanned device can be particularly applied to the field of delivery through the unmanned device, such as business scenes of delivery such as express delivery, logistics and takeout using the unmanned device.
S103: and for each candidate operator number, determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times, and taking the average waiting time as the average waiting time corresponding to the candidate operator number.
After the service platform determines the number of remote control times corresponding to the target area, the number of each candidate operator can be determined, the number of each candidate operator in the target area is determined according to the number of remote control times, if the number of the candidate operators is used for remotely controlling the unmanned equipment, the average waiting time of the unmanned equipment is used as the average waiting time corresponding to the number of the candidate operators.
The average waiting time corresponding to the candidate number of operators may be an average time for which, when the number of operators of the candidate number of operators controls the unmanned devices in the target area, each unmanned device needs to wait for the operator to control when the operator needs to perform remote control.
Therefore, the service platform can determine the average processing efficiency of the remote control tasks of the unmanned equipment which are historically completed by each operator in the target area, and determine the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate number of operators in the target area according to the remote control times, the average processing efficiency and the candidate number of operators corresponding to the target area, wherein the remote control task mentioned here can be a task of the operators for remotely controlling the unmanned equipment once.
Specifically, the service platform may determine the working strength characteristic value of each operator in the target area according to the number of remote controls, the average processing efficiency, and the number of candidate operators, where the number of remote controls and the working strength characteristic value form a positive correlation, the average processing efficiency, the number of candidate operators, and the working strength characteristic value form a negative correlation, and the working strength characteristic value may be determined specifically by the following formula.
Wherein ρ is a working strength characterization value, s is the number of the candidate operators, λ is the number of remote controls corresponding to the target area, and μ is the average processing efficiency. As can be seen from the above formula, the working strength characteristic value can be a ratio of the time of the operator handling the remote control task to the total time of the operator working, wherein the ratio is between the remote control task required to be handled each day and the average handling efficiency of the operator in the target area.
Then, the service platform may determine, according to the working strength characterization value, the number of candidate operators, the number of remote control times, and the average processing efficiency, a probability that each operator in the target area does not need to perform remote control on the unmanned aerial vehicle under the number of candidate operators as an idle probability, that is, the idle probability is a probability that no unmanned aerial vehicle needs to perform remote control on the unmanned aerial vehicle in the target area, and may specifically be calculated by the following formula.
Wherein, in the formula
And the idle probability is set, s is the number of the candidate operators, lambda is the remote control times corresponding to the target area, mu is the average processing efficiency, and rho is a working strength characterization value.
After the service platform determines the idle probability, an average waiting number of the unmanned devices in the target area, which need to be remotely controlled by the operator, may be determined according to the idle probability, the working strength characterization value, and the number of candidate operators, where the average waiting number indicates an average number of the unmanned devices waiting when each operator in the target area needs to process a remote control task, and the average waiting number may be specifically determined according to the following formula.
Wherein, in the above formula
In order to average the number of waits,
and the idle probability is set, s is the number of the candidate operators, lambda is the remote control times corresponding to the target area, and rho is a working strength characterization value.
After determining the average waiting number, the service platform may determine an average waiting time, and specifically, the service platform may determine the average waiting time corresponding to the number of the candidate operators according to the average waiting number and the remote control times, where the average waiting number and the average waiting time have a positive correlation, the remote control times and the average waiting time have a negative correlation, and the average waiting time may be determined specifically by the following formula.
In the above-mentioned formula,
in order to average the length of the wait period,
for average number of waiting personsAnd λ is the above remote control times.
S104: and selecting the configured number of operators from the number of the candidate operators according to the average waiting time corresponding to the number of the candidate operators, allocating operators to the target area according to the configured number of the operators, and remotely controlling the unmanned equipment in the target area through the operators allocated to the target area.
After the service platform determines the average waiting time corresponding to each candidate operator number, the operator configuration number can be selected from the candidate operator numbers according to the average waiting time corresponding to each candidate operator number. Specifically, the service platform may take as a target that the average waiting time does not exceed the set waiting time and the number of operator configurations corresponding to the target area is the minimum, and select the number of operator configurations corresponding to the target area from the number of candidate operators.
After determining the configuration number of the operators corresponding to the target area, the service platform can allocate the operators to the target area according to the configuration number of the operators, and remotely control the unmanned equipment in the target area through the operators allocated to the target area.
According to the method, the service platform can predict the times that each unmanned device in the target area needs to be remotely controlled, namely the remote control times corresponding to the target area, and determines the average waiting time of the unmanned devices in the target area when the unmanned devices need to be remotely controlled under different candidate operator numbers according to the remote control times, so that the appropriate candidate operator numbers are selected, and the driving safety of the unmanned devices is ensured under the condition of saving the cost.
Based on the same idea, the present specification also provides a corresponding apparatus for remotely controlling an unmanned aerial vehicle, as shown in fig. 5.
Fig. 5 is a schematic diagram of an apparatus for remotely controlling an unmanned aerial vehicle provided by the present specification, including:
an obtaining module 501, configured to obtain each route in a target area;
the prediction module 502 is configured to input route information corresponding to each route into a pre-trained prediction model, and obtain predicted times that each unmanned device in the target area needs to be remotely controlled by an operator, where the predicted times are used as remote control times corresponding to the target area;
a determining module 503, configured to determine, for each candidate number of operators, an average waiting duration of the unmanned aerial vehicle when the unmanned aerial vehicle is remotely controlled by the candidate number of operators in the target area according to the remote control times, where the average waiting duration is used as an average waiting duration corresponding to the candidate number of operators;
the allocating module 504 is configured to select an operator configuration number from the candidate operator numbers according to an average waiting duration corresponding to each candidate operator number, allocate an operator to the target area according to the operator configuration number, and remotely control the unmanned equipment in the target area through the operator allocated to the target area.
Optionally, the prediction module 502 is specifically configured to, for each route, determine each segment related to the route; inputting the road section information of each road section into the prediction model, and predicting the times of remote control required by an operator when the unmanned equipment runs on the route; and determining the times of remote control required by the operator of each unmanned device in the target area according to the predicted times of remote control required by the operator when the unmanned device runs on each route.
Optionally, the prediction model comprises: a feature extraction sub-model and a decision sub-model;
the prediction module 502 is specifically configured to input the road information corresponding to each road segment into the feature extraction submodel, so as to obtain a route feature corresponding to the route; and inputting the route characteristics into the decision submodel, and predicting the times of the unmanned equipment needing to be remotely controlled by an operator when the unmanned equipment runs on the route.
Optionally, the road section information includes at least one of historical road condition information, real-time road condition information, weather information corresponding to the road section, and date information.
Optionally, the determining module 503 is specifically configured to determine an average processing efficiency of each operator in the target area for completing a remote control task for the unmanned aerial vehicle historically; and determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times, the average processing efficiency and the candidate operator number.
Optionally, the determining module 503 is specifically configured to determine a working strength characterizing value of each operator in the target area according to the number of remote controls, the average processing efficiency, and the number of candidate operators, where the number of remote controls and the working strength characterizing value are in a positive correlation, and the average processing efficiency and the number of candidate operators and the working strength characterizing value are in a negative correlation; determining the probability that each operator in the target area does not need to remotely control the unmanned equipment under the candidate operator number as an idle probability according to the working strength characterization value, the candidate operator number, the remote control times and the average processing efficiency; determining the average waiting number of the unmanned equipment needing the operator to carry out remote control in the target area according to the idle probability, the working strength characterization value and the number of the candidate operators; and determining the average waiting time length of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the average waiting number and the remote control times, wherein the average waiting number and the average waiting time length have a positive correlation, and the remote control times and the average waiting time length have a negative correlation.
Optionally, the allocating module 504 is specifically configured to select the operator configuration number from the candidate operator numbers by taking that the average waiting time does not exceed the set waiting time and the operator configuration number corresponding to the target area is the minimum as a target.
Optionally, the apparatus further comprises:
the training module 505 is configured to obtain historical route information of each route, and historical times that the unmanned equipment needs to be remotely controlled by an operator when the unmanned equipment runs on each route; inputting the historical route information into the prediction model to obtain the predicted times of the unmanned equipment which needs to be remotely controlled by an operator when the unmanned equipment runs on each route, wherein the predicted times are used as prediction times; and training the prediction model by taking the minimized deviation between the prediction times and the historical times as an optimization target.
The present specification also provides a computer readable storage medium having stored thereon a computer program operable to execute a method of remotely controlling an unmanned aerial device as provided in figure 1 above.
This specification also provides a schematic block diagram of an electronic device corresponding to that of figure 1, shown in figure 6. As shown in fig. 6, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the method for remotely controlling the unmanned aerial vehicle described above with reference to fig. 1. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (11)
1. A method of remotely controlling an unmanned device, comprising:
obtaining each route in a target area;
inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted times of each unmanned device in the target area needing to be remotely controlled by an operator, wherein the predicted times are used as the remote control times corresponding to the target area;
for each candidate operator number, determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times, wherein the average waiting time is taken as the average waiting time corresponding to the candidate operator number;
and selecting the configured number of operators from the number of the candidate operators according to the average waiting time corresponding to the number of the candidate operators, allocating operators to the target area according to the configured number of the operators, and remotely controlling the unmanned equipment in the target area through the operators allocated to the target area.
2. The method according to claim 1, wherein inputting route information corresponding to each route into a pre-trained prediction model to obtain the predicted number of times that each unmanned device in the target area needs to be remotely controlled by an operator, specifically comprises:
for each route, determining each section related to the route;
inputting the road section information of each road section into the prediction model, and predicting the times of remote control required by an operator when the unmanned equipment runs on the route;
and determining the times of remote control required by the operator of each unmanned device in the target area according to the predicted times of remote control required by the operator when the unmanned device runs on each route.
3. The method of claim 2, wherein the predictive model comprises: a feature extraction sub-model and a decision sub-model;
inputting the road section information of each road section into the prediction model, predicting the times of remote control required by an operator when the unmanned equipment runs on the route, and specifically comprising the following steps:
inputting the road section information corresponding to each road section into the feature extraction submodel to obtain the route feature corresponding to the route;
and inputting the route characteristics into the decision submodel, and predicting the times of the unmanned equipment needing to be remotely controlled by an operator when the unmanned equipment runs on the route.
4. The method as claimed in claim 3, wherein the road section information includes at least one of historical road condition information, real-time road condition information, weather information corresponding to the road section, and date information.
5. The method according to claim 1, wherein for each candidate number of operators, determining an average waiting time of the unmanned aerial vehicle when the unmanned aerial vehicle is remotely controlled by the candidate number of operators in the target area according to the remote control times specifically comprises:
determining an average processing efficiency of each operator in the target area historically completing a remote control task for the unmanned aerial vehicle;
and determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times, the average processing efficiency and the candidate operator number.
6. The method according to claim 5, wherein determining an average waiting time of the unmanned aerial vehicle when the unmanned aerial vehicle is remotely controlled by the number of candidate operators in the target area according to the number of remote controls, the average processing efficiency and the number of candidate operators comprises:
determining a working strength characteristic value of each operator in the target area according to the remote control times, the average processing efficiency and the number of the candidate operators, wherein the remote control times and the working strength characteristic value are in a positive correlation relationship, and the average processing efficiency and the number of the candidate operators and the working strength characteristic value are in a negative correlation relationship;
determining the probability that each operator in the target area does not need to remotely control the unmanned equipment under the candidate operator number as an idle probability according to the working strength characterization value, the candidate operator number, the remote control times and the average processing efficiency;
determining the average waiting number of the unmanned equipment needing the operator to carry out remote control in the target area according to the idle probability, the working strength characterization value and the number of the candidate operators;
and determining the average waiting time length of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the average waiting number and the remote control times, wherein the average waiting number and the average waiting time length have a positive correlation, and the remote control times and the average waiting time length have a negative correlation.
7. The method of claim 1, wherein selecting the operator configuration number from the candidate operator numbers according to the average waiting time corresponding to the candidate operator numbers comprises:
and selecting the operator configuration number from the candidate operator numbers by taking the condition that the average waiting time length does not exceed the set waiting time length and the operator configuration number corresponding to the target area is the minimum as a target.
8. The method of claim 1, wherein training the predictive model comprises:
acquiring historical route information of each route and historical times of the unmanned equipment which needs to be remotely controlled by an operator when the unmanned equipment runs on each route;
inputting the historical route information into the prediction model to obtain the predicted times of the unmanned equipment which needs to be remotely controlled by an operator when the unmanned equipment runs on each route, wherein the predicted times are used as prediction times;
and training the prediction model by taking the minimized deviation between the prediction times and the historical times as an optimization target.
9. An apparatus for remotely controlling an unmanned aerial device, comprising:
the acquisition module is used for acquiring each route in the target area;
the prediction module is used for inputting the route information corresponding to each route into a pre-trained prediction model to obtain the predicted times of each unmanned device in the target area needing to be remotely controlled by an operator, and the predicted times are used as the remote control times corresponding to the target area;
the determining module is used for determining the average waiting time of the unmanned equipment when the unmanned equipment is remotely controlled by the operators with the candidate operator number in the target area according to the remote control times aiming at each candidate operator number, and the average waiting time is used as the average waiting time corresponding to the candidate operator number;
the allocation module is used for selecting the configured number of operators from the number of the candidate operators according to the average waiting time corresponding to the number of the candidate operators, allocating the operators to the target area according to the configured number of the operators, and remotely controlling the unmanned equipment in the target area through the operators allocated to the target area.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 8.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 8 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110397322.4A CN112990758B (en) | 2021-04-14 | 2021-04-14 | Method and device for remotely controlling unmanned equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110397322.4A CN112990758B (en) | 2021-04-14 | 2021-04-14 | Method and device for remotely controlling unmanned equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112990758A CN112990758A (en) | 2021-06-18 |
| CN112990758B true CN112990758B (en) | 2021-09-07 |
Family
ID=76338314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110397322.4A Active CN112990758B (en) | 2021-04-14 | 2021-04-14 | Method and device for remotely controlling unmanned equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990758B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114464006B (en) * | 2022-04-13 | 2022-06-28 | 新石器慧通（北京）科技有限公司 | Method and device for allocating automatic driving vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610448A (en) * | 2017-08-21 | 2018-01-19 | 深圳市海梁科技有限公司 | A kind of automatic driving vehicle and its dispatching method and scheduling system |
| CN107765691A (en) * | 2017-10-18 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling automatic driving vehicle |
| CN110708677A (en) * | 2018-07-09 | 2020-01-17 | 上海擎感智能科技有限公司 | Vehicle front cabin intelligent service interaction method, vehicle-mounted equipment and storage medium |
| CN110969857A (en) * | 2019-12-27 | 2020-04-07 | 华为技术有限公司 | Traffic information processing method and device |
| CN112389445A (en) * | 2020-11-05 | 2021-02-23 | 腾讯科技（深圳）有限公司 | Vehicle driving regulation and control method and device, vehicle-mounted equipment and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10712163B2 (en) * | 2017-02-23 | 2020-07-14 | International Business Machines Corporation | Vehicle routing and notifications based on characteristics |
-
2021
- 2021-04-14 CN CN202110397322.4A patent/CN112990758B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610448A (en) * | 2017-08-21 | 2018-01-19 | 深圳市海梁科技有限公司 | A kind of automatic driving vehicle and its dispatching method and scheduling system |
| CN107765691A (en) * | 2017-10-18 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling automatic driving vehicle |
| CN110708677A (en) * | 2018-07-09 | 2020-01-17 | 上海擎感智能科技有限公司 | Vehicle front cabin intelligent service interaction method, vehicle-mounted equipment and storage medium |
| CN110969857A (en) * | 2019-12-27 | 2020-04-07 | 华为技术有限公司 | Traffic information processing method and device |
| CN112389445A (en) * | 2020-11-05 | 2021-02-23 | 腾讯科技（深圳）有限公司 | Vehicle driving regulation and control method and device, vehicle-mounted equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112990758A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111208838B (en) | Control method and device of unmanned equipment | |
| CN110674723B (en) | Method and device for determining driving track of unmanned vehicle | |
| CN111076739B (en) | Path planning method and device | |
| CN113296541B (en) | Future collision risk based unmanned equipment control method and device | |
| CN112306059A (en) | Training method for control model, control method and device | |
| CN112990758B (en) | Method and device for remotely controlling unmanned equipment | |
| CN111238523A (en) | Method and device for predicting motion trail | |
| CN112327864A (en) | Control method and control device of unmanned equipment | |
| CN113064451A (en) | Unmanned equipment control method and device, storage medium and electronic equipment | |
| CN114548772A (en) | Distribution task scheduling method and device, storage medium and electronic equipment | |
| CN110956375A (en) | Order processing method and device | |
| CN113110526A (en) | Model training method, unmanned equipment control method and device | |
| CN113968243A (en) | Obstacle trajectory prediction method, device, equipment and storage medium | |
| CN112947495B (en) | Model training method, unmanned equipment control method and device | |
| CN111123957B (en) | Method and device for planning track | |
| CN113298445B (en) | Method and device for model training and unmanned equipment scheduling | |
| CN110895406A (en) | Method and device for testing unmanned equipment based on interferent track planning | |
| CN114153207A (en) | Control method and control device of unmanned equipment | |
| CN113848913B (en) | Control method and control device of unmanned equipment | |
| AU2023207182A1 (en) | Method and apparatus for allocating beacon codes in unmanned aerial vehicle airport, and unmanned aerial vehicle landing method and apparatus | |
| CN114296456A (en) | Network training and unmanned equipment control method and device | |
| CN114019971A (en) | Unmanned equipment control method and device, storage medium and electronic equipment | |
| CN114280960A (en) | Automatic driving simulation method and device, storage medium and electronic equipment | |
| CN114118904A (en) | Unmanned vehicle distribution method and device | |
| CN114489976A (en) | Cross-edge service migration method, device, equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |