CN117289723B - Method, device, equipment and medium for controlling movement state of cross-medium aircraft - Google Patents
Method, device, equipment and medium for controlling movement state of cross-medium aircraft Download PDFInfo
- Publication number
- CN117289723B CN117289723B CN202311581428.5A CN202311581428A CN117289723B CN 117289723 B CN117289723 B CN 117289723B CN 202311581428 A CN202311581428 A CN 202311581428A CN 117289723 B CN117289723 B CN 117289723B
- Authority
- CN
- China
- Prior art keywords
- data
- cross
- medium
- motion state
- target
- 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
- 230000033001 locomotion Effects 0.000 title claims abstract description 277
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000007781 pre-processing Methods 0.000 claims description 30
- 230000015654 memory Effects 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 230000002123 temporal effect Effects 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012300 Sequence Analysis Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 18
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 17
- 238000010586 diagram Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000006403 short-term memory Effects 0.000 description 4
- 238000012876 topography Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000011049 filling Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The embodiment of the application provides a method, a device, equipment and a medium for controlling the motion state of a cross-medium aircraft, wherein the method comprises the following steps: acquiring actual motion state data, surrounding environment data and target motion state data of a cross-medium aircraft; under the condition that the cross-medium aircraft meets the preset position maintaining condition, determining a target route path for the cross-medium aircraft to travel to a target position according to the surrounding environment data and the actual position data; generating a control instruction according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data; according to the control instruction, the motion state of the cross-medium aircraft is adjusted; in the event that the movement state of the cross-medium vehicle coincides with the target movement state, it is determined that the cross-medium vehicle has traveled to the target location in accordance with the target course path. According to the embodiment of the application, the motion state of the cross-medium aircraft can be accurately controlled in complex and changeable environments.
Description
Technical Field
The application belongs to the technical field of aircrafts, and particularly relates to a method, a device, equipment and a medium for controlling a movement state of a cross-medium aircrafts.
Background
The cross-medium craft is capable of sailing in both water and air media. Because of the unreachable flexibility and diversity on land, the cross-medium aircraft has wide application prospect in the fields of marine survey, emergency rescue, topography and topography mapping and the like.
Because of the need for a cross-medium vehicle to switch rapidly between water and air, the complexity and variability of the water-air environment presents a significant challenge for controlling the state of motion of the cross-medium vehicle. Therefore, how to realize accurate control of the motion state of a cross-medium aircraft in a complex and changeable environment is a technical problem to be solved currently.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a medium for controlling the movement state of a cross-medium aircraft, which can realize the accurate control of the movement state of the cross-medium aircraft in a complex and changeable environment.
In a first aspect, an embodiment of the present application provides a method for controlling a motion state of a cross-medium aircraft, where the method for controlling a motion state of a cross-medium aircraft includes: acquiring actual motion state data, surrounding environment data and target motion state data of a cross-medium aircraft; the actual motion state data comprises actual gesture data and actual position data of the cross-medium aircraft, and the target motion state data comprises target gesture data and target position data of the cross-medium aircraft; under the condition that the cross-medium aircraft meets the preset position maintaining condition, determining a target route path for the cross-medium aircraft to travel to a target position according to the surrounding environment data and the actual position data; generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data; according to the control instruction, the motion state of the cross-medium aircraft is adjusted; in the event that the movement state of the cross-medium vehicle coincides with the target movement state, it is determined that the cross-medium vehicle has traveled to the target location in accordance with the target course path.
According to an embodiment of the first aspect of the present application, in a case where the movement state of the cross-medium vehicle is inconsistent with the target movement state, the actual movement state data, the surrounding environment data and the target movement state data of the cross-medium vehicle are acquired in a returning manner until the movement state of the cross-medium vehicle is consistent with the target movement state.
According to any of the foregoing embodiments of the first aspect of the present application, determining a target course path for a cross-medium vehicle to travel to a target location based on ambient environment data and actual location data, comprises: constructing an environment model of the cross-medium aircraft according to the surrounding environment data; determining a route path calculation algorithm of the cross-medium aircraft according to the environment model; the ambient data and the actual position data are input to a route path computation algorithm that determines a target route path traveled across the medium craft to a target location.
According to any of the foregoing embodiments of the first aspect of the present application, before constructing the environment model of the cross-medium vehicle according to the ambient environment data, the method for controlling the movement state of the cross-medium vehicle further includes: performing data preprocessing on surrounding environment data; the data preprocessing includes at least one of data cleaning, denoising, and filtering.
According to any of the foregoing embodiments of the first aspect of the present application, constructing an environment model of a cross-medium vehicle from ambient environment data includes: and constructing an environment model of the cross-medium aircraft according to the surrounding environment data after the data preprocessing.
According to any of the foregoing embodiments of the first aspect of the present application, the actual motion state data further includes actual speed data and actual angular speed data of the cross-medium craft; generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data, wherein the control instruction comprises the following steps: determining attitude control data of the cross-medium aircraft according to the first difference value and the actual angular velocity data; determining position control data of the cross-medium aircraft according to the second difference value and the actual speed data; and generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the attitude control data and the position control data.
According to any of the foregoing embodiments of the first aspect of the present application, before determining a target course path for the cross-medium vehicle to travel to the target location based on the ambient data and the actual location data, the method of controlling the state of motion of the cross-medium vehicle further comprises: acquiring historical navigation data of a cross-medium aircraft and a preset task execution period of the cross-medium aircraft; extracting spatial sequence features and time sequence features in actual motion state data, surrounding environment data and historical navigation data to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data; under the condition that the task execution period is not finished, inputting the characteristic sequence into a pre-trained motion trail prediction model to obtain predicted position data of the cross-medium aircraft at a plurality of moments in a preset time period; calculating a third difference value between the actual position data and each predicted position data; and determining that the cross-medium aircraft meets the preset position maintaining condition when the third difference value is greater than or equal to the preset error distance.
According to any of the foregoing embodiments of the first aspect of the present application, in a case where the task execution cycle has ended, calculating a fourth difference value between the actual position data and the target position data; and under the condition that the fourth difference value is larger than or equal to the preset keeping distance, determining that the cross-medium aircraft meets the preset position keeping condition.
According to any one of the foregoing embodiments of the first aspect of the present application, before extracting the spatial sequence feature and the temporal sequence feature in the actual motion state data, the ambient environment data, and the historical voyage data, the method for controlling the motion state of the cross-medium craft further includes: converting the actual motion state data, the surrounding environment data and the historical voyage data into a time sequence form; and carrying out data preprocessing on the converted actual motion state data, the surrounding environment data and the historical navigation data.
According to any of the foregoing embodiments of the first aspect of the present application, extracting spatial sequence features and temporal sequence features in actual motion state data, surrounding environment data, and historical voyage data to obtain a feature sequence of the actual motion state data, the surrounding environment data, and the historical voyage data includes: and extracting spatial sequence features and time sequence features in the actual motion state data, the surrounding environment data and the historical navigation data after data preprocessing to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data.
According to any of the foregoing embodiments of the first aspect of the present application, extracting spatial sequence features and temporal sequence features in actual motion state data, surrounding environment data, and historical voyage data after data preprocessing, to obtain a feature sequence of the actual motion state data, the surrounding environment data, and the historical voyage data, includes: extracting space sequence features in actual motion state data, surrounding environment data and historical navigation data after data preprocessing based on a convolutional neural network; extracting time sequence characteristics in actual motion state data, surrounding environment data and historical navigation data after data preprocessing based on a time sequence analysis method; and weighting characteristic data at different positions in an input sequence based on a self-attention mechanism to obtain a characteristic sequence of actual motion state data, surrounding environment data and historical navigation data, wherein the input sequence comprises a spatial sequence characteristic and a time sequence characteristic.
According to any of the foregoing embodiments of the first aspect of the present application, the method for controlling the motion state of a cross-medium vehicle further includes, prior to inputting the feature sequence into the pre-trained motion trajectory prediction model: dividing historical navigation data into a training set and a testing set, wherein the training set comprises historical position data of the cross-medium aircraft at a plurality of moments in a historical time period; inputting historical navigation data at a first moment in a historical time period into a motion trail prediction model to obtain predicted position data of a cross-medium aircraft at a second moment in the historical time period; calculating a loss function value of the motion trail prediction model according to the predicted position data at the second moment and the historical position data at the second moment; and under the condition that the loss function value does not meet the preset training stop condition, adjusting the model parameters of the motion trail prediction model until the loss function value meets the preset training stop condition, and obtaining the trained motion trail prediction model.
In a second aspect, an embodiment of the present application provides a control device for a movement state of a cross-medium aircraft, where the control device for a movement state of a cross-medium aircraft includes: the acquisition module is used for acquiring actual motion state data, surrounding environment data and target motion state data of the cross-medium aircraft; the actual motion state data comprises actual gesture data and actual position data of the cross-medium aircraft, and the target motion state data comprises target gesture data and target position data of the cross-medium aircraft; the first determining module is used for determining a target route path for the cross-medium aircraft to travel to a target position according to the surrounding environment data and the actual position data under the condition that the cross-medium aircraft meets the preset position maintaining condition; the generation module is used for generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data; the adjusting module is used for adjusting the motion state of the cross-medium aircraft according to the control instruction; and the second determining module is used for determining that the cross-medium aircraft has traveled to the target position according to the target route path under the condition that the motion state of the cross-medium aircraft is consistent with the target motion state.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the method of controlling the movement state of a cross-medium vehicle as provided in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the method of controlling the motion state of a cross-medium vehicle as provided in the first aspect.
According to the control method, the device, the equipment and the medium for the movement state of the cross-medium aircraft, when the cross-medium aircraft meets the preset position maintaining condition and the movement state of the cross-medium aircraft needs to be adjusted, a target route path of the cross-medium aircraft moving to a target position can be determined according to the acquired surrounding environment data and actual position data of the cross-medium aircraft, and relatively accurate route planning of the cross-medium aircraft is achieved. According to the obtained first difference value of the actual gesture data and the target gesture data of the cross-medium aircraft and the obtained second difference value of the actual position data and the target position data of the cross-medium aircraft, a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state is generated, so that the motion state of the cross-medium aircraft is timely adjusted in the navigation process of the cross-medium aircraft according to the control instruction, and the cross-medium aircraft can travel to the target position according to the determined target route path. Thus, by the embodiment of the application, the precise control of the motion state of the cross-medium aircraft can be realized even in complex and changeable environments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.
Fig. 1 is a schematic flow chart of a method for controlling a movement state of a cross-medium aircraft according to an embodiment of the present application;
FIG. 2 is a flow chart of another method for controlling a motion state of a cross-medium vehicle according to an embodiment of the present application;
FIG. 3 is a flow chart of yet another method for controlling a motion state of a cross-medium vehicle according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a motion trail prediction model provided in an embodiment of the present application;
FIG. 5 is a schematic diagram of a control principle of a movement state of a cross-medium vehicle according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a control device for a movement state of a cross-medium vehicle according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application are described in detail below to make the objects, technical solutions and advantages of the present application more apparent, and to further describe the present application in conjunction with the accompanying drawings and the detailed embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative of the application and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by showing examples of the present application.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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 … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Accordingly, this application is intended to cover such modifications and variations of this application as fall within the scope of the appended claims (the claims) and their equivalents. The embodiments provided in the examples of the present application may be combined with each other without contradiction.
Before describing the technical solution provided by the embodiments of the present application, in order to facilitate understanding of the embodiments of the present application, the present application first specifically describes a problem existing in the prior art:
as previously mentioned, the inventors of the present application have found that a cross-medium vehicle requires fast switching between water and air, and that the complexity and variability of the water-air environment presents a significant challenge for controlling the motion state of the cross-medium vehicle. If the precise control of the motion state of the cross-medium aircraft is to be realized in a complex and changeable environment, the precise positioning navigation of the cross-medium aircraft is not needed.
The existing water surface positioning technology of the cross-medium aircraft mainly depends on technologies such as a satellite system and a radar, but the satellite system is easy to be subjected to reflection interference on the water surface, so that the accuracy of water surface positioning is affected. The air positioning technology of the cross-medium aircraft faces more complex environment and condition than the water surface positioning technology, and the traditional navigation system is easily influenced by factors such as weather, building shielding and the like in the air, so that signals are weakened or even lost, and the accuracy of air positioning is also influenced. Thus, existing positioning navigation techniques cannot flexibly cope with complex environmental changes, and the current need for cross-medium aircraft motion state control.
In order to solve the problems in the prior art, the embodiment of the application provides a method, a device, equipment and a medium for controlling the motion state of a cross-medium aircraft.
The following first describes a method for controlling the motion state of a cross-medium aircraft provided in an embodiment of the present application.
Fig. 1 is a schematic flow chart of a method for controlling a movement state of a cross-medium aircraft according to an embodiment of the present application. As shown in fig. 1, the control method of the movement state of the cross-medium vehicle may include the following steps S101 to S105.
S101, acquiring actual motion state data, surrounding environment data and target motion state data of the cross-medium aircraft.
S102, under the condition that the cross-medium aircraft meets the preset position maintaining condition, determining a target route path for the cross-medium aircraft to travel to a target position according to the surrounding environment data and the actual position data.
S103, generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data.
S104, according to the control instruction, the motion state of the cross-medium aircraft is adjusted.
S105, when the motion state of the medium crossing aircraft is consistent with the target motion state, determining that the medium crossing aircraft has traveled to a target position according to a target route path.
The specific implementation of each of the above steps will be described in detail below.
According to the control method for the movement state of the cross-medium aircraft, when the cross-medium aircraft meets the preset position maintaining condition and the movement state of the cross-medium aircraft needs to be adjusted, a target route path of the cross-medium aircraft moving to the target position can be determined according to the acquired surrounding environment data and actual position data of the cross-medium aircraft, and relatively accurate route planning of the cross-medium aircraft is achieved. According to the obtained first difference value of the actual gesture data and the target gesture data of the cross-medium aircraft and the obtained second difference value of the actual position data and the target position data of the cross-medium aircraft, a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state is generated, so that the motion state of the cross-medium aircraft is timely adjusted in the navigation process of the cross-medium aircraft according to the control instruction, and the cross-medium aircraft can travel to the target position according to the determined target route path. Thus, by the embodiment of the application, the precise control of the motion state of the cross-medium aircraft can be realized even in complex and changeable environments.
A specific implementation of each of the above steps is described below.
In S101, the motion control system of the cross-medium vehicle may acquire actual motion state data and surrounding environment data of the cross-medium vehicle through devices or apparatuses such as a depth sensor, an air pressure altimeter, an inertial measurement unit, a beidou satellite navigation system, and the like. The actual motion state data can comprise actual gesture data and actual position data of the cross-medium aircraft, and can also comprise actual speed data, actual acceleration data, actual angular speed data and actual depth data of the cross-medium aircraft; the ambient data may include data of wind, air temperature, air pressure, precipitation, waves, and seafloor terrain across the medium of the environment in which the aircraft is located. In addition, there is a need to obtain target motion state data of the cross-medium vehicle, which may include attitude data and position data that the cross-medium vehicle is expected to be able to maintain, i.e., target attitude data and target position data.
As another implementation manner of the control method of the movement state of the cross-medium vehicle, as shown in fig. 2, before S102, the control method of the movement state of the cross-medium vehicle may further include the following steps S201 to S207.
S201, historical navigation data of the cross-medium aircraft are obtained, and a preset task execution period of the cross-medium aircraft is obtained.
The motion control system of the cross-medium aircraft can also acquire historical navigation data of the cross-medium aircraft through devices or equipment such as a depth sensor, an air pressure altimeter, an inertial measurement unit, a Beidou satellite navigation system and the like. The historical navigation data may include historical position data of the cross-medium aircraft at a plurality of moments in a historical time period, such as coordinates, a heading change range, a heading angle change amount of the cross-medium aircraft, and the like.
Meanwhile, the motion control system of the cross-medium aircraft also needs to set a task execution period of the cross-medium aircraft through a timer, so that the cross-medium aircraft can realize timing floating and submerging in the task execution period.
S202, extracting spatial sequence features and time sequence features in actual motion state data, surrounding environment data and historical navigation data to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data.
Optionally, before executing step S202, the actual motion state data, the surrounding environment data and the historical voyage data may be converted into a time series form, and then the converted actual motion state data, surrounding environment data and historical voyage data are subjected to data preprocessing, so as to ensure the integrity and accuracy of the data. Illustratively, the process of data preprocessing may include normalization processing, filling in missing values, and the like.
As an implementation manner of S202, S202 may specifically include: and extracting spatial sequence features and time sequence features in the actual motion state data, the surrounding environment data and the historical navigation data after data preprocessing to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data.
As another implementation manner of S202, S202 may specifically include: extracting space sequence features in actual motion state data, surrounding environment data and historical navigation data after data preprocessing based on a convolutional neural network; extracting time sequence characteristics in actual motion state data, surrounding environment data and historical navigation data after data preprocessing based on a time sequence analysis method; and weighting characteristic data at different positions in an input sequence based on a self-attention mechanism to obtain a characteristic sequence of actual motion state data, surrounding environment data and historical navigation data, wherein the input sequence comprises a spatial sequence characteristic and a time sequence characteristic.
The spatial sequence features in the actual motion state data, the surrounding environment data and the historical navigation data after data preprocessing are extracted based on the convolutional neural network (Convolutional Neural Network, CNN), and even in a complex and changeable environment, the feature points can be well classified and matched, so that matching errors caused by environmental changes or noise interference can be avoided, and the accuracy and stability of feature point matching are improved.
For example, convolutional neural networks may be replaced with other network structures in order to better accommodate the characteristics of different media environments. For example, convolutional neural networks may be used for feature extraction of aerial images, and cyclic neural networks may be used for time-series modeling of sensor data in water. The embodiments of the present application are not limited in this regard.
The feature sequence recorded with the key information in the actual motion state data, the surrounding environment data and the historical navigation data can be obtained by extracting the spatial sequence features and the time sequence features in the actual motion state data, the surrounding environment data and the historical navigation data after the data preprocessing and weighting the feature data at different positions in the spatial sequence features and the time sequence features by utilizing a self-attention mechanism, so that the accuracy of a model prediction result is improved when the feature sequence is subsequently input into a motion trail prediction model, and the performance of the model is further improved.
As another implementation manner of the control method of the movement state of the cross-medium vehicle, as shown in fig. 3, before S203, the control method of the movement state of the cross-medium vehicle may further include the following steps S301 to S304.
S301, dividing the historical voyage data into a training set and a testing set.
Illustratively, the following may be applied: the scale of 3 divides the historical voyage data into a training set and a testing set, which is not limited in this embodiment of the present application. Both the training set and the test set may include historical position data for the cross-medium vehicle at a plurality of times over a historical time period.
S302, inputting historical navigation data of a first moment in a historical time period into a motion trail prediction model to obtain predicted position data of a second moment in the historical time period of the cross-medium aircraft.
Alternatively, as shown in fig. 4, the motion trail prediction model in the embodiment of the present application may be a model LSTM-ATT combining Long Short-Term Memory (LSTM) with Attention mechanism (ATT).
The long-term and short-term memory network can model and predict data acquired in a water-air environment, and intelligent motion control of the cross-medium aircraft is achieved. By learning the time series characteristics, the motion trail of the cross-medium craft in a future period of time can be well predicted. Once the deviation of the medium-crossing aircraft from the preset track is predicted, the potential dangerous area can be reached beyond the early warning line, measures can be timely taken to warn, or the position of the medium-crossing aircraft can be adjusted in advance to avoid the obstacle.
In predicting the position and motion trajectory of a cross-medium vehicle, extraction of time series features is critical to the accuracy and precision of the prediction. The long and short term memory network alone may ignore some minutiae points or abnormal data points, resulting in errors. By introducing a self-attention mechanism, key time series features can be accurately extracted from historical navigation data so as to further improve the accuracy of position and motion trail prediction. The self-attention mechanism can accurately focus on key information in the process of feature extraction, and plays a role in supplementing and perfecting motion control of the cross-medium aircraft.
For example, in order to better improve the accuracy and robustness of the motion trail prediction model, the self-attention mechanism may be replaced by other types of attention mechanisms, such as a multi-head attention mechanism, a local attention mechanism, and the like, which is not limited in the embodiments of the present application.
In this way, the historical navigation data of the first moment in the historical time period in the training set is input into the motion trail prediction model provided by the embodiment of the application, and the model is trained, so that the predicted position data and the predicted motion trail of the cross-medium aircraft at the second moment in the historical time period can be obtained. Alternatively, the second time instant may be a plurality of time instants within the historical time period after the first time instant.
S303, calculating a loss function value of the motion trail prediction model according to the predicted position data at the second moment and the historical position data at the second moment.
For example, in the model training process, the mean square error and the cross entropy can be calculated according to the predicted position data at the second moment and the historical position data at the second moment, and then the mean square error and the cross entropy are used as loss function values of the motion trail prediction model.
And S304, under the condition that the loss function value does not meet the preset training stop condition, adjusting the model parameters of the motion trail prediction model until the loss function value meets the preset training stop condition, and obtaining the trained motion trail prediction model.
For example, in the case that the loss function value does not meet the preset training stop condition, a random optimization algorithm (Adaptive momentum, adam) of adaptive momentum may be used to adjust model parameters of the motion trajectory prediction model until the loss function value is minimized, and the preset training stop condition is met, so as to obtain the motion trajectory prediction model after training.
In some embodiments, optionally, after obtaining the trained motion trail prediction model, a test set may be input into the trained motion trail prediction model to test the model training effect, so as to obtain predicted position data and predicted motion trail of the cross-medium craft over a period of time. And evaluating the performance of the model by using the evaluation index, adjusting the super parameters of the model according to the evaluation result, and optimizing the performance of the model, thereby obtaining the trained motion trail prediction model.
Illustratively, the evaluation index may include a root mean square error (Root Mean Square Error, RMSE) and an average absolute error (Mean Absolute Error, MAE), and the hyper-parameters of the model may include the number of neurons and the number of iterations of the hidden layer of the long and short term memory network.
And S203, under the condition that the task execution period is not ended, inputting the characteristic sequence into a pre-trained motion track prediction model to obtain predicted position data of the cross-medium aircraft at a plurality of moments in a preset time period.
And detecting the timing time of the timer, if the timing is not finished, namely the task execution period is not finished, inputting the extracted characteristic sequence into a trained motion track prediction model at the moment to obtain position coordinates and motion tracks of the cross-medium aircraft at each moment before the timing is finished, namely predicted position data and predicted motion tracks at a plurality of moments in a preset time period.
As shown in fig. 5, in order to improve accuracy and stability of positioning navigation, in the embodiment of the present application, a holding circle and an error circle are set, where the radius of the holding circle is R, and the radius of the error circle is R, which are used for assisting the positioning navigation system in performing environment sensing and boundary constraint. By setting the target position point (the origin of the coordinate system in fig. 5) in the water-air medium, additional position information and positioning calibration are provided to further improve the accuracy of positioning. Meanwhile, the navigation area can be defined, the movement range of the cross-medium aircraft is limited, and the problems that errors are continuously accumulated or the cross-medium aircraft is separated from the navigation area are avoided.
For example, when setting the target location point, the process of specifically selecting the target location point may be designed according to factors such as task requirements, environmental conditions, navigation capability of the cross-medium craft, etc., for example, the target is identified by using an image recognition technology, and the coordinates of the target location point are determined by a computer vision algorithm, or the coordinates of the target location point are manually input according to the task requirements. The embodiments of the present application are not limited in this regard.
S204, calculating a third difference value between the actual position data and each predicted position data.
Illustratively, a predicted position coordinate point of the cross-medium vehicle at each moment before the timing is finished is marked, and is marked as i, and a distance L between the i and an actual position coordinate point (x, y) of the cross-medium vehicle is calculated i I.e. the third difference of the actual position data and each predicted position data, respectively.
S205, determining that the cross-medium aircraft meets the preset position maintaining condition when the third difference value is larger than or equal to the preset error distance.
If L is present i The position coordinate point not less than R, i.e. the third difference is greater than or equal to the preset error distance (error circle radius R) Determining that the cross-medium aircraft meets the preset position maintaining condition, changing the timing time of a timer, and adjusting the motion state of the cross-medium aircraft in advance.
S206, calculating a fourth difference value between the actual position data and the target position data when the task execution period is ended.
If the timing is finished, namely the task execution period is finished, judging whether the cross-medium aircraft is positioned under water, on the water surface or in the air according to the information acquired by the sensor. If the aircraft is underwater, the heading of the aircraft needs to be controlled by a vertical rudder of a cross-medium aircraft tail cross rudder, and the aircraft floats to the water surface by a horizontal rudder of the tail cross rudder and a water jet propeller. And calculating the distance d between the actual position coordinate point (x, y) of the cross-medium aircraft and the target position point (0, 0), namely a fourth difference value between the actual position data and the target position data.
S207, determining that the cross-medium aircraft meets the preset position maintaining condition under the condition that the fourth difference value is larger than or equal to the preset maintaining distance.
If d is less than r, indicating that the cross-medium aircraft is positioned in the holding circle, determining that the cross-medium aircraft does not meet the preset position holding condition, and continuously executing the task without adjusting the motion state of the cross-medium aircraft; if R is less than or equal to d < R, indicating that the medium-crossing vehicle is positioned in the error circle outside the holding circle, wherein the fourth difference value is greater than or equal to a preset holding distance (the radius R of the holding circle) and exceeds the boundary of the position holding line, determining that the medium-crossing vehicle meets the preset position holding condition, and adjusting the motion state of the medium-crossing vehicle; if d is more than or equal to R, the cross-medium aircraft is located outside the error circle, exceeds the boundary of the early warning line and deviates too far, the cross-medium aircraft is determined to meet the preset position maintaining condition, an alarm is triggered, the task execution of the cross-medium aircraft is required to be immediately stopped, and the motion state of the cross-medium aircraft is required to be adjusted.
In S102, in the case where it is determined that the cross-medium vehicle satisfies the preset position maintenance condition, a course path, i.e., a target course path, for traveling to the target position by the cross-medium vehicle is determined according to the surrounding environment data and the actual position data, so that the cross-medium vehicle can travel to the target position according to the target course path.
As an implementation manner of S102, S102 may specifically include: constructing an environment model of the cross-medium aircraft according to the surrounding environment data; determining a route path calculation algorithm of the cross-medium aircraft according to the environment model; the ambient data and the actual position data are input to a route path computation algorithm that determines a target route path traveled across the medium craft to a target location.
In some embodiments, optionally, before building the environment model of the cross-medium vehicle according to the ambient environment data, the method for controlling the movement state of the cross-medium vehicle may further include: and carrying out data preprocessing on the surrounding environment data.
For example, the process of data preprocessing may include at least one of data cleaning, denoising, and filtering. By calibrating the surrounding environment data, removing abnormal values and performing smoothing treatment, the accuracy and stability of the data can be improved.
Optionally, the embodiment of the application can also fuse all surrounding environment data in water and in the air based on a multi-sensor information fusion technology, so that an environment model of the cross-medium aircraft can be intuitively and accurately constructed. The underwater and air object position can be accurately determined by fusing the data acquired by the water-air sensor, and the two data are mutually complemented, so that the positioning precision of the cross-medium aircraft can be better improved, and the problem that single air positioning or water positioning is possibly subject to environmental interference or sensor limitation is solved; secondly, the data acquired by the water-air sensors are fused, so that the data acquired by the sensors are compared and verified, the problem that when one system fails and the whole positioning navigation system cannot work normally when the system is positioned only in the air or in water can be avoided, single failure points of the positioning navigation system are reduced, and the reliability of the whole system is improved; thirdly, through the data collected by the fusion water-air sensor, the obstacles in two environments can be sensed simultaneously, the more comprehensive environment sensing capability is provided, the problem that the obstacles in the air can not be sensed when the underwater obstacle is positioned in the water and the underwater obstacle can not be sensed when the underwater obstacle is positioned in the air is solved, and therefore the obstacles can be better avoided, and a better planning path is determined; and fourthly, the fused data can be suitable for more complex environments, for example, in application scenes such as ocean exploration, underwater search and rescue and the like, the actual application requirements cannot be met only by means of single underwater positioning or aerial positioning, and the data acquired by the fused water-air sensor can provide more comprehensive and accurate positioning navigation capability.
Specifically, the environment model of the cross-medium aircraft can be constructed by combining the preprocessed surrounding environment data and the related knowledge of aviation navigation. For example, an aerodynamic model can be constructed according to wind force, air temperature and other data, and the model is used for predicting the flight performance of the cross-medium aircraft under different conditions.
Based on the constructed environmental model and the principle of aviation navigation, determining an air route path calculation algorithm of the cross-medium aircraft, and continuously iterating and optimizing by using reinforcement learning to determine an air route path which is optimal for the cross-medium aircraft to travel to a target position.
In the embodiment of the application, the target route can be adjusted in real time according to the surrounding environment data acquired in real time and the route calculation algorithm. During the process of traveling to the target position by the cross-medium aircraft, new surrounding environment data are collected in real time and input into the route path calculation algorithm, and a new target route can be recalculated. In this way, the target course path can be continuously updated in the course of travel according to the change of the surrounding environment, so as to improve the traveling efficiency and safety of the cross-medium aircraft.
In S103, based on the kalman filtering algorithm of the inertial measurement unit, the obtained actual attitude data, actual acceleration data and actual angular velocity data of the cross-medium aircraft are combined to estimate the actual attitude angle of the cross-medium aircraft. For example, the attitude angles may include pitch angle, roll angle, and yaw angle.
Based on the inertial navigation principle, an extended Kalman filtering algorithm is used, and the acquired actual position data, actual speed data and actual acceleration data of the cross-medium aircraft are combined to estimate the actual position of the cross-medium aircraft.
And generating a control instruction for adjusting the motion state of the medium-crossing aircraft to the target motion state according to the first difference value of the estimated value of the actual attitude angle of the medium-crossing aircraft and the target attitude data and the second difference value of the estimated value of the actual position and the target position data. For example, the first difference and the second difference may be represented as error terms, including angle errors, position errors, and the like.
As an implementation manner of S103, S103 may specifically include: determining attitude control data of the cross-medium aircraft according to the first difference value and the actual angular velocity data; determining position control data of the cross-medium aircraft according to the second difference value and the actual speed data; and generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the attitude control data and the position control data.
Illustratively, a proportional-integral-derivative (Proportional Integral Derivative, PID) control algorithm based on feedback control calculates a control moment or control thrust, i.e., attitude control data, to be applied to the cross-medium vehicle from the first difference and a feedback signal of the actual angular velocity data to correct an attitude error of the cross-medium vehicle; based on a control algorithm of the path planning, a control thrust, i.e. position control data, to be applied to the cross-medium vehicle is calculated from the feedback signal of the second difference and the actual speed data to move the cross-medium vehicle towards the target position.
It should be noted that, the embodiments of the present application are not limited to the estimation and compensation methods of the pose and position of the cross-medium craft, and those skilled in the art may also use the visual sensor to estimate the pose and position, or use the Model predictive control (Model-based Predictive Control, MPC) and the deep learning Model to compensate the pose and position.
In S104, the target course path and the control command are transmitted to the motion control system of the cross-medium aircraft, and the decision unit of the motion control system adjusts the heading, the flying height, the gesture, the position and other motion states of the cross-medium aircraft according to the target course path and the control command, so that the cross-medium aircraft can travel to the target position according to the target course path. Illustratively, the decision unit of the motion control system may include a control host running an embedded real-time operating system, and a motion controller with an ARM Cortex-X4 system chip as a core, which may adjust the position of the cross-medium vehicle by adjusting a timer to control the time interval and single duration of the ascent and descent of the cross-medium vehicle.
In S105, in the process of adjusting the heading and the motion state of the cross-medium aircraft according to the target route path and the control instruction, the motion control system of the cross-medium aircraft also updates the first difference value of the actual attitude data and the target attitude data and the second difference value of the actual position data and the target position data in real time, and regenerates a new control instruction according to the updated first difference value and second difference value, so as to readjust the attitude and the position of the cross-medium aircraft.
If the motion state of the cross-medium aircraft is inconsistent with the target motion state in the adjustment process, returning to the step S101, and continuing to adjust the gesture and the position of the cross-medium aircraft until the motion state of the cross-medium aircraft is consistent with the target motion state, and determining that the cross-medium aircraft has traveled to the target position according to the target route path without any adjustment.
By estimating and compensating the gesture and the position of the cross-medium aircraft in real time, the control precision of the motion state of the cross-medium aircraft can be effectively improved, the continuous accumulation of errors and the influence of unstable factors on the cross-medium aircraft are reduced, and the accuracy of positioning and navigation of the cross-medium aircraft and the reliability and stability of navigation of the cross-medium aircraft are improved. And the gesture and the position of the cross-medium aircraft are estimated in real time, so that more accurate target route planning is realized, and the method has important significance for coping with different medium environments such as water flow, air flow and the like and complex topography and topography.
Based on the control method of the movement state of the cross-medium aircraft provided by the embodiment, correspondingly, the application also provides a specific implementation mode of the control device of the movement state of the cross-medium aircraft. Please refer to the following examples.
As shown in fig. 6, a control device 600 for a movement state of a cross-medium aircraft according to an embodiment of the present application includes the following modules:
an acquisition module 601, configured to acquire actual motion state data, surrounding environment data, and target motion state data of a cross-medium aircraft; the actual motion state data comprises actual gesture data and actual position data of the cross-medium aircraft, and the target motion state data comprises target gesture data and target position data of the cross-medium aircraft;
a first determining module 602, configured to determine, according to the ambient environment data and the actual position data, a target route path for the cross-medium vehicle to travel to the target position if the cross-medium vehicle meets a preset position maintenance condition;
the generating module 603 is configured to generate a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the first difference value between the actual pose data and the target pose data and the second difference value between the actual position data and the target position data;
the adjusting module 604 is configured to adjust a motion state of the cross-medium aircraft according to the control instruction;
a second determination module 605 is configured to determine that the cross-medium vehicle has traveled to the target location according to the target course path if the movement state of the cross-medium vehicle coincides with the target movement state.
According to the control device for the movement state of the cross-medium aircraft, when the cross-medium aircraft meets the preset position maintaining condition and the movement state of the cross-medium aircraft needs to be adjusted, a target route path of the cross-medium aircraft moving to the target position can be determined according to the acquired surrounding environment data and actual position data of the cross-medium aircraft, and relatively accurate route planning of the cross-medium aircraft is achieved. According to the obtained first difference value of the actual gesture data and the target gesture data of the cross-medium aircraft and the obtained second difference value of the actual position data and the target position data of the cross-medium aircraft, a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state is generated, so that the motion state of the cross-medium aircraft is timely adjusted in the navigation process of the cross-medium aircraft according to the control instruction, and the cross-medium aircraft can travel to the target position according to the determined target route path. Thus, by the embodiment of the application, the precise control of the motion state of the cross-medium aircraft can be realized even in complex and changeable environments.
In some embodiments, the second determining module 605 may be further configured to, in a case where the movement state of the across-medium vehicle is inconsistent with the target movement state, return to acquiring the actual movement state data, the ambient environment data, and the target movement state data of the across-medium vehicle until the movement state of the across-medium vehicle is consistent with the target movement state.
In some embodiments, the first determining module 602 is specifically configured to construct an environment model of the cross-medium vehicle according to the ambient environment data; determining a route path calculation algorithm of the cross-medium aircraft according to the environment model; the ambient data and the actual position data are input to a route path computation algorithm that determines a target route path traveled across the medium craft to a target location.
In some embodiments, the control device 600 for the motion state of the cross-medium craft may further include: the data preprocessing module is used for preprocessing surrounding environment data; the data preprocessing includes at least one of data cleaning, denoising, and filtering.
In some embodiments, the first determining module 602 may be further configured to construct an environment model of the cross-medium craft based on the data-preprocessed ambient data.
In some embodiments, the generating module 603 is specifically configured to determine attitude control data of the cross-medium craft according to the first difference value and the actual angular velocity data; determining position control data of the cross-medium aircraft according to the second difference value and the actual speed data; and generating a control instruction for adjusting the motion state of the cross-medium aircraft to the target motion state according to the attitude control data and the position control data.
In some embodiments, the control device 600 for the motion state of the cross-medium craft may further include: the third determining module is used for acquiring historical navigation data of the cross-medium aircraft and a preset task execution period of the cross-medium aircraft; extracting spatial sequence features and time sequence features in actual motion state data, surrounding environment data and historical navigation data to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data; under the condition that the task execution period is not finished, inputting the characteristic sequence into a pre-trained motion trail prediction model to obtain predicted position data of the cross-medium aircraft at a plurality of moments in a preset time period; calculating a third difference value between the actual position data and each predicted position data; and determining that the cross-medium aircraft meets the preset position maintaining condition when the third difference value is greater than or equal to the preset error distance.
In some embodiments, the third determining module may be further configured to calculate a fourth difference between the actual position data and the target position data when the task execution period has ended; and under the condition that the fourth difference value is larger than or equal to the preset keeping distance, determining that the cross-medium aircraft meets the preset position keeping condition.
In some embodiments, the control device 600 for the motion state of the cross-medium craft may further include: the conversion module is used for converting the actual motion state data, the surrounding environment data and the historical navigation data into a time sequence form; and carrying out data preprocessing on the converted actual motion state data, the surrounding environment data and the historical navigation data.
In some embodiments, the third determining module may be further configured to extract spatial sequence features and temporal sequence features in the actual motion state data, the surrounding environment data, and the historical voyage data after the data preprocessing, and obtain a feature sequence of the actual motion state data, the surrounding environment data, and the historical voyage data.
In some embodiments, the third determining module may be further configured to extract spatial sequence features in the data-preprocessed actual motion state data, the surrounding environment data, and the historical voyage data based on a convolutional neural network; extracting time sequence characteristics in actual motion state data, surrounding environment data and historical navigation data after data preprocessing based on a time sequence analysis method; and weighting characteristic data at different positions in an input sequence based on a self-attention mechanism to obtain a characteristic sequence of actual motion state data, surrounding environment data and historical navigation data, wherein the input sequence comprises a spatial sequence characteristic and a time sequence characteristic.
In some embodiments, the control device 600 for the motion state of the cross-medium craft may further include: the model training module is used for dividing the historical navigation data into a training set and a testing set, wherein the training set comprises historical position data of the cross-medium aircraft at a plurality of moments in a historical time period; inputting historical navigation data at a first moment in a historical time period into a motion trail prediction model to obtain predicted position data of a cross-medium aircraft at a second moment in the historical time period; calculating a loss function value of the motion trail prediction model according to the predicted position data at the second moment and the historical position data at the second moment; and under the condition that the loss function value does not meet the preset training stop condition, adjusting the model parameters of the motion trail prediction model until the loss function value meets the preset training stop condition, and obtaining the trained motion trail prediction model.
Each module in the apparatus shown in fig. 6 has a function of implementing each step in fig. 1, and can achieve a corresponding technical effect, which is not described herein for brevity.
Based on the control method of the movement state of the cross-medium aircraft provided by the embodiment, correspondingly, the application also provides a specific implementation mode of the electronic equipment. Please refer to the following examples.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
The electronic device may include a processor 701 and a memory 702 storing computer program instructions.
In particular, the processor 701 described above may include a central processing unit (Central Processing Unit, CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
Memory 702 may include mass storage for data or instructions. By way of example, and not limitation, memory 702 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. In one example, the memory 702 may include removable or non-removable (or fixed) media, or the memory 702 is a non-volatile solid state memory. Memory 702 may be internal or external to the integrated gateway disaster recovery device.
In one example, memory 702 may be Read Only Memory (ROM). In one example, the ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.
Memory 702 may include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described with reference to a method according to an aspect of the present application.
The processor 701 reads and executes the computer program instructions stored in the memory 702 to implement the methods/steps S101 to S105 in the embodiment shown in fig. 1, and achieve the corresponding technical effects achieved by executing the methods/steps in the embodiment shown in fig. 1, which are not described herein for brevity.
In one example, the electronic device may also include a communication interface 703 and a bus 710. As shown in fig. 7, the processor 701, the memory 702, and the communication interface 703 are connected by a bus 710 and perform communication with each other.
The communication interface 703 is mainly used for implementing communication between each module, device, unit and/or apparatus in the embodiments of the present application.
Bus 710 includes hardware, software, or both that couple components of the electronic device to one another. By way of example, and not limitation, the buses may include an accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) Bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (Industry Standard Architecture, ISA) Bus, an infiniband interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (MCa) Bus, a Peripheral Component Interconnect (PCI) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a video electronics standards association local (VLB) Bus, or other suitable Bus, or a combination of two or more of the above. Bus 710 may include one or more buses, where appropriate. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.
In addition, in combination with the method for controlling the motion state of the cross-medium aircraft in the above embodiment, the embodiment of the application may be implemented by providing a computer readable storage medium. The computer readable storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement a method of controlling the motion state of any of the above embodiments of a cross-medium craft. Examples of computer readable storage media include non-transitory computer readable storage media such as electronic circuits, semiconductor memory devices, ROMs, random access memories, flash memories, erasable ROMs (EROM), floppy disks, CD-ROMs, optical disks, hard disks.
It should be clear that the present application is not limited to the particular arrangements and processes described above and illustrated in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps, after appreciating the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be different from the order in the embodiments, or several steps may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations 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, 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, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the foregoing, only the specific embodiments of the present application are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, which are intended to be included in the scope of the present application.
Claims (13)
1. A method of controlling a state of motion of a cross-medium vehicle, the method comprising:
acquiring actual motion state data, surrounding environment data and target motion state data of a cross-medium aircraft; the actual motion state data comprises actual gesture data and actual position data of the cross-medium aircraft, and the target motion state data comprises target gesture data and target position data of the cross-medium aircraft;
acquiring historical navigation data of the cross-medium aircraft and a preset task execution period of the cross-medium aircraft;
Extracting spatial sequence features and time sequence features in the actual motion state data, the surrounding environment data and the historical navigation data to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data;
under the condition that the task execution period is not finished, inputting the characteristic sequence into a pre-trained motion trail prediction model to obtain predicted position data of the cross-medium aircraft at a plurality of moments in a preset time period;
determining whether the cross-medium aircraft meets a preset position maintaining condition according to the actual position data and the predicted position data;
under the condition that the cross-medium aircraft meets a preset position maintaining condition, determining a target route path of the cross-medium aircraft to travel to a target position according to the surrounding environment data and the actual position data;
generating a control instruction for adjusting the motion state of the cross-medium aircraft to a target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data;
According to the control instruction, the motion state of the cross-medium aircraft is adjusted;
and determining that the cross-medium aircraft has traveled to the target position according to the target course path under the condition that the motion state of the cross-medium aircraft is consistent with the target motion state.
2. The method of claim 1, wherein in the event that the movement state of the cross-medium vehicle does not coincide with the target movement state, returning the acquiring actual movement state data, ambient environment data, and target movement state data of the cross-medium vehicle until the movement state of the cross-medium vehicle coincides with the target movement state.
3. The method of claim 1 or 2, wherein the determining a target course path for the cross-medium craft to travel to a target location based on the ambient data and the actual location data comprises:
constructing an environment model of the cross-medium aircraft according to the surrounding environment data;
determining a route path calculation algorithm of the cross-medium aircraft according to the environment model;
inputting the ambient data and the actual position data to the route-path estimation algorithm to determine a target route path for the cross-medium craft to travel to a target location.
4. A method according to claim 3, wherein prior to said constructing an environmental model of the cross-medium craft from the ambient data, the method further comprises:
performing data preprocessing on the surrounding environment data; the data preprocessing comprises at least one of data cleaning, denoising and filtering;
the constructing the environment model of the cross-medium aircraft according to the surrounding environment data comprises the following steps:
and constructing an environment model of the cross-medium aircraft according to the surrounding environment data after data preprocessing.
5. The method of claim 1 or 2, wherein the actual motion state data further comprises actual speed data and actual angular speed data of the cross-medium craft;
the generating a control instruction for adjusting the motion state of the cross-medium aircraft to a target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data comprises the following steps:
determining attitude control data of the cross-medium aircraft according to the first difference value and the actual angular velocity data;
Determining position control data of the cross-medium aircraft according to the second difference value and the actual speed data;
and generating a control instruction for adjusting the motion state of the cross-medium aircraft to a target motion state according to the attitude control data and the position control data.
6. The method of claim 1, wherein determining whether the cross-medium vehicle satisfies a preset position maintenance condition based on the actual position data and the predicted position data comprises:
calculating a third difference value between the actual position data and each predicted position data;
and under the condition that the third difference value is larger than or equal to the preset error distance, determining that the medium-crossing aircraft meets the preset position maintaining condition.
7. The method according to claim 1, characterized in that, in case the task execution cycle has ended, a fourth difference value of the actual position data and the target position data is calculated;
and under the condition that the fourth difference value is larger than or equal to a preset keeping distance, determining that the medium-crossing aircraft meets a preset position keeping condition.
8. The method of claim 1, wherein prior to the extracting spatial and temporal sequence features in the actual motion state data, the ambient environment data, and the historical voyage data, the method further comprises:
Converting the actual motion state data, the ambient environment data and the historical voyage data into a form of a time series;
performing data preprocessing on the converted actual motion state data, the surrounding environment data and the historical navigation data;
the extracting the spatial sequence features and the temporal sequence features in the actual motion state data, the surrounding environment data and the historical navigation data to obtain the feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data comprises the following steps:
and extracting the spatial sequence features and the time sequence features in the actual motion state data, the surrounding environment data and the historical navigation data after data preprocessing to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data.
9. The method of claim 8, wherein the extracting the spatial sequence features and the temporal sequence features in the data-preprocessed actual motion state data, the surrounding data, and the historical voyage data to obtain the feature sequence of the actual motion state data, the surrounding data, and the historical voyage data comprises:
Extracting the spatial sequence characteristics in the actual motion state data, the surrounding environment data and the historical navigation data after data preprocessing based on a convolutional neural network;
extracting time sequence characteristics in the actual motion state data, the surrounding environment data and the historical navigation data after data preprocessing based on a time sequence analysis method;
and weighting characteristic data of different positions in an input sequence based on a self-attention mechanism to obtain a characteristic sequence of the actual motion state data, the surrounding environment data and the historical navigation data, wherein the input sequence comprises the spatial sequence characteristic and the time sequence characteristic.
10. The method of claim 1, wherein prior to said inputting the feature sequence into a pre-trained motion trajectory prediction model, the method further comprises:
dividing the historical navigation data into a training set and a testing set, wherein the training set comprises historical position data of the cross-medium aircraft at a plurality of moments in a historical time period;
inputting historical navigation data at a first moment in a historical time period into a motion trail prediction model to obtain predicted position data of the cross-medium aircraft at a second moment in the historical time period;
Calculating a loss function value of the motion trail prediction model according to the predicted position data at the second moment and the historical position data at the second moment;
and under the condition that the loss function value does not meet the preset training stop condition, adjusting the model parameters of the motion trail prediction model until the loss function value meets the preset training stop condition, and obtaining the trained motion trail prediction model.
11. A control device for the state of motion of a cross-medium vehicle, the device comprising:
the first acquisition module is used for acquiring actual motion state data, surrounding environment data and target motion state data of the cross-medium aircraft; the actual motion state data comprises actual gesture data and actual position data of the cross-medium aircraft, and the target motion state data comprises target gesture data and target position data of the cross-medium aircraft;
the second acquisition module is used for acquiring historical navigation data of the cross-medium aircraft and a preset task execution period of the cross-medium aircraft;
the extraction module is used for extracting the spatial sequence features and the time sequence features in the actual motion state data, the surrounding environment data and the historical navigation data to obtain feature sequences of the actual motion state data, the surrounding environment data and the historical navigation data;
The input module is used for inputting the characteristic sequence into a pre-trained motion trail prediction model under the condition that the task execution period is not ended, so as to obtain predicted position data of the medium-crossing aircraft at a plurality of moments in a preset time period;
the first determining module is used for determining whether the medium-crossing aircraft meets a preset position maintaining condition according to the actual position data and the predicted position data;
the second determining module is used for determining a target route path of the cross-medium aircraft to travel to a target position according to the surrounding environment data and the actual position data under the condition that the cross-medium aircraft meets a preset position maintaining condition;
the generation module is used for generating a control instruction for adjusting the motion state of the medium-crossing aircraft to a target motion state according to the first difference value of the actual gesture data and the target gesture data and the second difference value of the actual position data and the target position data;
the adjusting module is used for adjusting the motion state of the medium-crossing aircraft according to the control instruction;
and a third determining module, configured to determine that the cross-medium aircraft has traveled to the target location according to the target course path, if the motion state of the cross-medium aircraft is consistent with the target motion state.
12. An electronic device, the electronic device comprising: a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of the method of controlling the movement state of a cross-medium craft as claimed in any one of claims 1 to 10.
13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements the steps of the method of controlling the movement state of a cross-medium vehicle according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311581428.5A CN117289723B (en) | 2023-11-24 | 2023-11-24 | Method, device, equipment and medium for controlling movement state of cross-medium aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311581428.5A CN117289723B (en) | 2023-11-24 | 2023-11-24 | Method, device, equipment and medium for controlling movement state of cross-medium aircraft |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117289723A CN117289723A (en) | 2023-12-26 |
| CN117289723B true CN117289723B (en) | 2024-02-20 |
Family
ID=89258976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311581428.5A Active CN117289723B (en) | 2023-11-24 | 2023-11-24 | Method, device, equipment and medium for controlling movement state of cross-medium aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117289723B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117606490A (en) * | 2024-01-23 | 2024-02-27 | 吉林大学 | Collaborative search path planning method for autonomous underwater vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115857521A (en) * | 2022-11-16 | 2023-03-28 | 中国船舶重工集团公司第七一九研究所 | Cross-medium aircraft control method for multi-task profile |
| CN116026324A (en) * | 2023-02-10 | 2023-04-28 | 北京大学 | Cross-domain navigation system and method for water-air cross-medium craft |
| CN116679727A (en) * | 2023-05-19 | 2023-09-01 | 哈尔滨工程大学 | Water outlet control method of folding wing type cross-medium aircraft |
| CN116954137A (en) * | 2023-09-20 | 2023-10-27 | 北京大学 | Method, system, device, equipment and medium for controlling movement of medium-crossing aircraft |
| CN116992577A (en) * | 2023-09-28 | 2023-11-03 | 北京大学 | Simulation method, system, equipment and storage medium of cross-medium aircraft |
-
2023
- 2023-11-24 CN CN202311581428.5A patent/CN117289723B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115857521A (en) * | 2022-11-16 | 2023-03-28 | 中国船舶重工集团公司第七一九研究所 | Cross-medium aircraft control method for multi-task profile |
| CN116026324A (en) * | 2023-02-10 | 2023-04-28 | 北京大学 | Cross-domain navigation system and method for water-air cross-medium craft |
| CN116679727A (en) * | 2023-05-19 | 2023-09-01 | 哈尔滨工程大学 | Water outlet control method of folding wing type cross-medium aircraft |
| CN116954137A (en) * | 2023-09-20 | 2023-10-27 | 北京大学 | Method, system, device, equipment and medium for controlling movement of medium-crossing aircraft |
| CN116992577A (en) * | 2023-09-28 | 2023-11-03 | 北京大学 | Simulation method, system, equipment and storage medium of cross-medium aircraft |
Non-Patent Citations (2)
| Title |
|---|
| Experimental Investigation of High Speed Cross-Domain Vehicles with Hydrofoil;Zeqi Shi.etc;《Journal of Marine Science and Engineering》;第1-18页 * |
| 仿生水-空跨介质航行器控制系统研究;李宏源 等;《舰船科学技术》;第45卷(第20期);第79-82页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117289723A (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110850403B (en) | Multi-sensor decision-level fused intelligent ship water surface target feeling knowledge identification method | |
| CN109885066B (en) | Motion trail prediction method and device | |
| CN105892471B (en) | Automatic driving method and apparatus | |
| Wilthil et al. | Radar-based maritime collision avoidance using dynamic window | |
| CN117289723B (en) | Method, device, equipment and medium for controlling movement state of cross-medium aircraft | |
| CN107577230B (en) | Intelligent collision avoidance system for unmanned ship | |
| CN107942095B (en) | Wave glider actual heading prediction technique | |
| CN108919640B (en) | Method for realizing self-adaptive multi-target tracking of unmanned aerial vehicle | |
| CN109753068A (en) | A kind of more USV multi-agent synergy collision-avoidance planning methods considering signal intelligence | |
| CN108536149A (en) | A kind of automatic driving vehicle avoidance obstacle device and control method based on the paths Dubins | |
| EP3722911B1 (en) | A system and method of planning a path for an autonomous vessel | |
| CN110546459A (en) | Robot tracking navigation with data fusion | |
| CN105302126A (en) | Control method of autonomously descending and landing on warship of unmanned shipboard helicopter | |
| CN113283653B (en) | Ship track prediction method based on machine learning and AIS data | |
| CN110378411B (en) | Method for assisting underwater maneuvering target tracking by support vector machine based on interactive multi-model | |
| KR20160048530A (en) | Method and apparatus for generating pathe of autonomous vehicle | |
| CN106569214A (en) | Method and system for processing vehicle-mounted radar data of adaptive cruise vehicle in conjunction with navigation information | |
| CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
| CN109782760A (en) | A kind of more USV multi-agent synergy collision-avoidance planning methods of the consideration without communication | |
| CN104679008B (en) | A kind of AUV independently seeks bottom control method | |
| CN104180801B (en) | Forecasting Methodology and system based on ADS B system track points | |
| US20230222671A1 (en) | System for predicting near future location of object | |
| CN114815851A (en) | Robot following method, robot following device, electronic device, and storage medium | |
| CN108733042A (en) | The method for tracking target and device of automatic driving vehicle | |
| Perera et al. | Detections of potential collision situations by relative motions of vessels under parameter uncertainties |
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 |