CN116039959A - Evasion maneuver control method and device for spacecraft - Google Patents

Evasion maneuver control method and device for spacecraft Download PDF

Info

Publication number
CN116039959A
CN116039959A CN202310106661.1A CN202310106661A CN116039959A CN 116039959 A CN116039959 A CN 116039959A CN 202310106661 A CN202310106661 A CN 202310106661A CN 116039959 A CN116039959 A CN 116039959A
Authority
CN
China
Prior art keywords
spacecraft
threat
speed
vector
acceleration
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.)
Granted
Application number
CN202310106661.1A
Other languages
Chinese (zh)
Other versions
CN116039959B (en
Inventor
吴健发
魏春岭
张海博
李克行
黄盘兴
董峰
姜甜甜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Control Engineering
Original Assignee
Beijing Institute of Control Engineering
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Control Engineering filed Critical Beijing Institute of Control Engineering
Priority to CN202310106661.1A priority Critical patent/CN116039959B/en
Publication of CN116039959A publication Critical patent/CN116039959A/en
Application granted granted Critical
Publication of CN116039959B publication Critical patent/CN116039959B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64G—COSMONAUTICS; VEHICLES OR EQUIPMENT THEREFOR
    • B64G1/00—Cosmonautic vehicles
    • B64G1/22—Parts of, or equipment specially adapted for fitting in or to, cosmonautic vehicles
    • B64G1/24—Guiding or controlling apparatus, e.g. for attitude control
    • B64G1/242—Orbits and trajectories
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64G—COSMONAUTICS; VEHICLES OR EQUIPMENT THEREFOR
    • B64G1/00—Cosmonautic vehicles
    • B64G1/22—Parts of, or equipment specially adapted for fitting in or to, cosmonautic vehicles
    • B64G1/24—Guiding or controlling apparatus, e.g. for attitude control
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention relates to the technical field of space aircrafts, in particular to a method and a device for controlling evasion maneuver of a space aircrafts. Wherein the method comprises the following steps: determining whether to change a desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat; constructing a disturbance matrix of the spacecraft based on the position of the spacecraft and the threat and the latest speed; correcting the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evading speed of the spacecraft; and obtaining the final orbit control acceleration of the spacecraft based on the expected avoidance speed and a preset orbit motion equation, and taking the final orbit control acceleration as an avoidance maneuver control instruction of the spacecraft. The invention can solve the technical problem of high energy consumption for avoiding maneuver.

Description

Evasion maneuver control method and device for spacecraft
Technical Field
The invention relates to the technical field of space aircrafts, in particular to a method and a device for controlling evasion maneuver of a space aircrafts.
Background
The current frequent occurrence of track conflict events brings serious challenges to the safety of a spacecraft, and a corresponding evasion maneuver control technology is urgently developed.
In the related art, the relative distance between two parties is mostly used as a main optimization control index, and the characteristic that a threat may exist in a detection blind area is not fully utilized for avoiding. Thus, once the threat implements a continuous acceleration tracking strategy on my, it causes the spacecraft to take a synchro-accelerated avoidance maneuver in order to maintain a constant safe distance, thereby forming a "your catch-up" game with the threat at the cost of high energy consumed in avoiding maneuvers.
Based on this, a method and a device for controlling maneuver for avoiding a spacecraft are needed to solve the technical problem of high energy consumption for avoiding maneuver.
Disclosure of Invention
In order to solve the technical problem of high energy consumption for avoiding maneuver, the embodiment of the specification provides a maneuver avoiding control method and device for a spacecraft.
In a first aspect, embodiments of the present disclosure provide a method for controlling maneuver for avoiding a spacecraft, including:
determining whether to change a desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat;
Constructing a disturbance matrix of the spacecraft based on the position of the spacecraft and the threat and the latest speed; the disturbance matrix comprises three adjustable parameters, wherein the adjustable parameters are a radial reaction coefficient, a tangential reaction coefficient and a direction coefficient, the radial reaction coefficient and the tangential reaction coefficient determine an avoidance opportunity, and the direction coefficient determines an avoidance direction;
correcting the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evading speed of the spacecraft;
and obtaining the final orbit control acceleration of the spacecraft based on the expected avoidance speed and a preset orbit motion equation, and taking the final orbit control acceleration as an avoidance maneuver control instruction of the spacecraft.
In a second aspect, embodiments of the present disclosure further provide an evasive maneuver control apparatus for a spacecraft, including:
a determination module for determining whether to change a desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat;
a building module for building a disturbance matrix of the spacecraft based on the position and the latest speed of the spacecraft and the threat; the disturbance matrix comprises an adjustable radial reaction coefficient, a tangential reaction coefficient and a direction coefficient, wherein the radial reaction coefficient and the tangential reaction coefficient determine the evading moment, and the direction coefficient determines the evading direction;
The correction module is used for correcting the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evading speed of the spacecraft;
the output module is used for obtaining the final orbit control acceleration of the spacecraft based on the expected avoidance speed and a preset orbit motion equation, and taking the final orbit control acceleration as an avoidance maneuver control instruction of the spacecraft.
In a third aspect, embodiments of the present specification further provide an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor implements the method described in any embodiment of the present specification when executing the computer program.
In a fourth aspect, the embodiments of the present specification also provide a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method according to any of the embodiments of the present specification.
The embodiment of the specification provides a method and a device for controlling the evasion maneuver of a spacecraft, which are used for constructing a disturbance matrix of the spacecraft based on the positions and the latest speeds of the spacecraft and the threat so as to correct the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evasion speed of the spacecraft, and finally obtaining the final orbital acceleration of the spacecraft based on the expected evasion speed and a preset orbital motion equation so as to take the final orbital acceleration as an evasion maneuver control instruction of the spacecraft. Therefore, the scheme can enable the spacecraft to have the capability of suddenly steering to a proper escape direction when the threat is in the own rear hemisphere area and continuous trailing acceleration tracking is carried out, so that the spacecraft can enter a detection blind area of the threat as soon as possible with smaller energy consumption, and the energy consumption during the avoidance of the spacecraft is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present description, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for maneuver control for avoiding a spacecraft according to an embodiment of the present disclosure;
FIG. 2 is a hardware architecture diagram of an electronic device according to an embodiment of the present disclosure;
FIG. 3 is a block diagram of a maneuver for avoiding control of a spacecraft according to an embodiment of the present disclosure;
FIG. 4 is a flow chart of a method for overall evasion maneuver control for a spacecraft provided in an embodiment of the present disclosure;
FIG. 5 is a schematic illustration of a trigger condition for a desired speed direction change of a spacecraft provided in an embodiment of the present disclosure;
FIG. 6 is a schematic illustration of a virtual target position setting for a spacecraft when a desired speed direction is changed, as provided in an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of an initial training environment for deep reinforcement learning provided by an embodiment of the present disclosure;
FIG. 8 is a schematic illustration of maneuver trajectories of a spacecraft and threat in a simulation test provided by an embodiment of the present disclosure;
FIG. 9 is a schematic diagram of relative distance of a spacecraft and threat in a simulation test provided by an embodiment of the present disclosure;
FIG. 10 is a schematic illustration of energy consumption of a spacecraft and threat in a simulation test provided in an embodiment of the present disclosure;
FIG. 11 is a schematic view of target line of sight angles for threats in a simulation test provided by an embodiment of the present disclosure.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present specification more apparent, the technical solutions of the embodiments of the present specification will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present specification, and it is apparent that the described embodiments are some, but not all, embodiments of the present specification, and all other embodiments obtained by persons of ordinary skill in the art without making any inventive effort based on the embodiments of the present specification are within the scope of protection of the present specification.
Referring to fig. 1, an embodiment of the present disclosure provides a method for controlling maneuver for avoiding a spacecraft, including:
Step 100: determining whether to change the desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat;
step 102: constructing a disturbance matrix of the spacecraft based on the positions and the latest speeds of the spacecraft and the threat; the disturbance matrix comprises three adjustable parameters, wherein the adjustable parameters are a radial reaction coefficient, a tangential reaction coefficient and a direction coefficient, the radial reaction coefficient and the tangential reaction coefficient determine the evading moment, and the direction coefficient determines the evading direction;
step 104: correcting the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evading speed of the spacecraft;
step 106: based on the expected avoidance speed and a preset orbital motion equation, the final orbital acceleration of the spacecraft is obtained, and the final orbital acceleration is used as an avoidance maneuver control instruction of the spacecraft.
In this embodiment, a disturbance matrix of the spacecraft is constructed based on the positions and the latest speeds of the spacecraft and the threat, so that the latest speed of the spacecraft is corrected by using the disturbance matrix to obtain a desired avoidance speed of the spacecraft, and finally, based on the desired avoidance speed and a preset orbital motion equation, the final orbital acceleration of the spacecraft is obtained, so that the final orbital acceleration is used as an avoidance maneuver control instruction of the spacecraft. Therefore, the scheme can enable the spacecraft to have the capability of suddenly steering to a proper escape direction when the threat is in the own rear hemisphere area and continuous trailing acceleration tracking is carried out, so that the spacecraft can enter a detection blind area of the threat as soon as possible with smaller energy consumption, and the energy consumption during the avoidance of the spacecraft is reduced.
The manner in which the individual steps shown in fig. 1 are performed is described below.
For step 100:
in one embodiment of the present disclosure, step 100 may specifically include:
if the positions and speeds of the spacecraft and the threat all meet the preset triggering conditions, changing the expected speed direction of the spacecraft, otherwise, not changing the expected speed direction of the spacecraft;
the triggering conditions include:
the vector included angle between the position vector of the spacecraft pointing threat and the speed vector of the spacecraft is greater than 90 degrees;
the vector angle between the position vector of the threat pointing to the spacecraft and the velocity vector of the threat is less than 90 °;
the relative position difference between the spacecraft and the threat is smaller than a preset warning distance; the warning distance is greater than a preset safety distance, and the safety distance is the minimum distance between the spacecraft and the threat in the avoidance process.
In this embodiment, it is considered that the intersection of the trailing pursuit may occur only when a threat is present in the rear hemisphere area of the spacecraft and continuous trailing acceleration tracking is performed, and thus, in order to avoid this occurrence, it is necessary to change the desired speed direction of the spacecraft under a certain trigger condition.
It should be noted that if the spacecraft and the threat are in an oncoming flight, since the spacecraft can detect the position and the speed of the threat in real time, this is only required to control the spacecraft and the threat to be kept out of a safe distance, i.e. to control the orbital acceleration of the spacecraft without changing the desired speed direction of the spacecraft.
As shown in fig. 5, the environment in which the method of the present invention is applicable is defined as: there is only one non-cooperative threat in space, which can be modeled as a dynamic sphere with an equivalent safety radius of
Figure SMS_1
(i.e. the distance of the spacecraft from the threat during evasion needs to be always greater than +.>
Figure SMS_2
). In addition, the threat has corresponding intersection guidance strategies, and maneuver can be performed according to the evasive actions of the spacecraft.
Based on the geometric relation of the relative motions of the two parties, a triggering condition for changing the expected speed direction of the spacecraft is constructed, wherein the triggering condition is shown in the following formula:
Figure SMS_3
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_4
the positions of the two parties under the LVLH coordinate system arePA threat is indicated and the threat is indicated,Erepresenting an my spacecraft, the speed of both parties is +.>
Figure SMS_5
），/>
Figure SMS_6
Representing the vector included angle>
Figure SMS_7
For the warning distance, its value is greater than +.>
Figure SMS_8
。
Then, the latest speeds in the form of are constructed for the spacecraft
Figure SMS_9
：
Figure SMS_10
In the method, in the process of the invention,
Figure SMS_11
amplitude and->
Figure SMS_12
Identical, the direction is->
Figure SMS_13
Point to->
Figure SMS_14
；/>
Figure SMS_15
And representing a virtual target position to be set, and driving the spacecraft to suddenly turn to avoid so as to get rid of a threat detection range.
In one embodiment of the present specification, let the first plane be a plane formed by a position vector of a threat directed to a spacecraft and a velocity vector of the threat, and let the second plane be a plane formed by a position vector of a threat directed to a spacecraft and a velocity vector of a spacecraft;
the desired speed direction of the spacecraft is changed in at least one of the following ways:
when the vector included angle of the threat pointing to the position vector of the spacecraft and the threat speed vector is not equal to 0, the threat speed vector is located on the left side of the threat pointing to the position vector of the spacecraft in the first plane, and the threat is located on the left side of the speed vector of the spacecraft in the second plane, performing: calculating the symmetrical position of the threat relative to the speed vector of the spacecraft; determining a virtual target position based on the position of the spacecraft and the symmetrical position; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
When the vector included angle of the threat pointing to the position vector of the spacecraft and the threat speed vector is not equal to 0, the threat speed vector is located on the left side of the threat pointing to the position vector of the spacecraft in the first plane, and the threat is located on the right side of the speed vector of the spacecraft in the second plane, performing: determining a virtual target location based on the location of the spacecraft and the threat; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
when the vector included angle of the threat pointing to the position vector of the spacecraft and the threat speed vector is not equal to 0, the threat speed vector is located on the right side of the threat pointing to the position vector of the spacecraft in the first plane, and the threat is located on the left side of the speed vector of the spacecraft in the second plane, performing: determining a virtual target location based on the location of the spacecraft and the threat; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
when the vector included angle between the threat pointing to the position vector of the spacecraft and the threat speed vector is not equal to 0, the threat speed vector is located on the right side of the threat pointing to the position vector of the spacecraft in the first plane, and the threat is located on the right side of the speed vector of the spacecraft in the second plane, performing: calculating the symmetrical position of the threat relative to the speed vector of the spacecraft; determining a virtual target position based on the position of the spacecraft and the symmetrical position; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
When the vector included angle of the position vector of the threat pointing to the spacecraft and the velocity vector of the threat is equal to 0, performing: determining a virtual target location based on the location of the spacecraft and the threat; the desired speed direction of the spacecraft is determined as the direction in which the position of the spacecraft points to the virtual target position.
In this embodiment, by changing the desired speed direction of the space vehicle in the above five manners, not only can the intersection with the threat be avoided, but also the detection blind area of the threat can be entered as soon as possible with less energy consumption.
The setting of the virtual target position is exemplified below with reference to table 1 and fig. 6.
TABLE 1 virtual target position setting logic
Figure SMS_16
Note that:
Figure SMS_17
representing vectorsAAndBa plane is formed.
As can be seen from table 1,
Figure SMS_18
or->
Figure SMS_19
. Of course, the relationship of the virtual target location to the location of the spacecraft, the location of the threat, or the symmetrical location of the threat may take other forms, and is not limited herein.
For step 102:
constructing a disturbance matrix for a spacecraft based on the position and latest speed of the spacecraft and the threat
Figure SMS_20
. The specific implementation process can be seen in literature [ unmanned aerial vehicle three-dimensional route planning based on disturbance fluid dynamic system: method and application unmanned system technology 2018,1 (1): 72-82 ]Here, theAnd will not be described in detail. />
Figure SMS_21
Comprises adjustable parameters->
Figure SMS_22
Wherein->
Figure SMS_23
And->
Figure SMS_24
For the radial/tangential reaction coefficients respectively, determining avoidance timing; />
Figure SMS_25
As the direction coefficient, an avoidance direction is determined.
To ensure that the desired evasion speed is obtained by correcting the evasion speed of the space vehicle, the parameter needs to be
Figure SMS_26
And (5) optimizing.
Because key information such as intersection strategies, maneuverability and the like of non-cooperative track threats are difficult to acquire in advance, most of the existing researches realize avoidance decision and maneuver control by logically reasoning current/historical state information, the control mode is called deliberate control, the control mode is represented as a layered serial control process of 'state-estimation-prediction-modeling-planning-action', the calculation solving process is complex, accumulation calculation time of each link is long, and quick response to high maneuverability threats is not facilitated.
In order to make the calculation solution flow shorter and the calculation efficiency higher, the spacecraft is more beneficial to timely reacting to the non-cooperative orbit threat, and the method is specifically characterized in that: on one hand, compared with the traditional incomplete information track avoidance deliberate control mode based on the process of 'state-estimation-prediction-modeling-planning-action', the method can realize 'state-action' end-to-end and short-flow decision control; on the other hand, the designed maneuvering control algorithm has no complex numerical calculation process.
Specifically, in one embodiment of the present disclosure, after step 102 and before step 104, the method specifically may further include:
training an intelligent agent by using an Actor-Critic deep reinforcement learning algorithm to obtain a target neural network;
three adjustable parameters of the constructed disturbance matrix are input into a target neural network, and the three optimized adjustable parameters are output so as to correct the latest speed of the spacecraft by utilizing the optimized disturbance matrix.
In one embodiment of the present disclosure, the step of training the agent using the Actor-Critic deep reinforcement learning algorithm to obtain the target neural network may specifically include:
setting an initial training environment of deep reinforcement learning; the training environment comprises an initial position of the spacecraft, an initial position and an initial speed of the threat and a meeting guidance strategy of the threat;
the termination condition of the training round is set using the following formula:
Figure SMS_27
in the method, in the process of the invention,Resetin order to terminate the condition of the termination,Cond 1 to avoid failure determination conditions, the approach of both sides to a safe distance is expressed
Figure SMS_28
An inner part;Cond 2 to circumvent the success decision condition, the energy consumption representing a threat exceeds a set threshold +.>
Figure SMS_29
；Cond 3 To circumvent the success decision condition, a probe blind zone is indicated that the spacecraft has entered the threat, +. >
Figure SMS_30
As the target line-of-sight angle magnitude of the threat,t f for the moment at which the training round ends, +.>
Figure SMS_31
A maximum line of sight angle that is effective to ensure that the threat is perceived; when the termination condition is equal to 1, entering the next training round, and simultaneously resetting the initial training environment of the spacecraft;
setting observance quantity, action quantity and rewarding function of the intelligent agent; wherein the observed quantity is related to the position and the speed of the spacecraft and the threat, and the action quantity is three adjustable parameters of a disturbance matrix;
training the intelligent agent by using an Actor-Critic deep reinforcement learning algorithm until the mean curve of the reward function enters a convergence state;
and extracting the target neural network from the intelligent agent obtained by training.
In the embodiment, aiming at the inherent defects of deliberate control, a reactive evasion maneuver control parameter optimization mechanism based on deep reinforcement learning is constructed, the optimal control parameters of the maneuver control strategy are rapidly generated based on the end-to-end control mode of 'state-action' under the condition of incomplete information, and real-time reaction and safe evasion of non-cooperative orbit threats are realized, so that the calculation solution flow is shorter, the calculation efficiency is higher, and timely response of a spacecraft to the non-cooperative orbit threats is facilitated.
The following describes the parameters in detail with reference to FIGS. 4 and 7
Figure SMS_32
Is described.
Step S1, constructing a deep reinforcement learning training environment of reactive evasion maneuver control shown in FIG. 7, and setting the initial position of the spacecraft as the initial position
Figure SMS_33
Threat initial position and speed settings are shown in the following formulas: />
Figure SMS_34
Figure SMS_35
In the method, in the process of the invention,
Figure SMS_36
and->
Figure SMS_37
An angle that threatens to the initial orientation of the spacecraft; />
Figure SMS_38
For the initial relative distance of the two parties, the maximum effective detection distance of the spacecraft is generally available; the initial speed amplitude of threat is +.>
Figure SMS_39
Direction is directed to->
Figure SMS_40
。
The threat engagement strategy may be set as guidance laws commonly used in current engineering, such as proportional guidance, bias proportional guidance, differential countermeasures, etc., and is not limited herein.
Step S2, setting a training round termination conditionResetWhen (when)
Figure SMS_41
When the next training round is entered, the initial training scene is reset according to step S1:
Figure SMS_42
s3, setting observed quantity of deep reinforcement learning intelligent agentoAmount of movementaAnd a bonus functionrThe following formulas are respectively shown:
Figure SMS_43
Figure SMS_44
wherein, the liquid crystal display device comprises a liquid crystal display device,ois set to the current relative position and speed of the two parties,
Figure SMS_45
and->
Figure SMS_46
Respectively representing the relative distance and the speed amplitude of the initial moments of the two parties for makingoIs maintained at approximately the same level; aSetting three parameters of a disturbance matrix;rconsists of four parts:r 1 as a distance index, the larger the distance between the two parties is, the safer the spacecraft is, and the higher the rewarding value is;r 2 the smaller the applied acceleration amplitude is, the smaller the energy consumption is, and the higher the rewarding value is;r 3 as the line of sight angle index, the larger the line of sight angle is, the higher the probability that the spacecraft enters the threat detection blind area is, and the higher the rewarding value is;r end as termination condition index: when (when)
Figure SMS_47
If the avoidance is successful, a positive constant reward value is givenpos_rewardIf the avoidance fails, a negative constant penalty value is givenneg_reward；/>
Figure SMS_48
Weights for the corresponding bonus items. The rewarding value and the punishment value are preset values which are equal tor 1 、r 2 Andr 3 in this regard, the description thereof will not be repeated here. The bonus item weights are preset values and are not limited herein.
Step S4, based on the training environment, the termination condition and the state of the agent set in the steps S1 to S3
Figure SMS_49
Selecting an Actor-Critic depth reinforcement learning algorithm oriented to continuous motion space, e.g. depth deterministic strategy gradient (Deep Deterministic Policy Gradient) algorithm, dual-delay depth deterministic strategy gradient (TwinDelayed Deep Deterministic Policy Gradient) algorithmAnd training corresponding agents by a method, a Soft Actor-Critic algorithm and the like until the mean curve of the reward function enters a convergence state.
And S5, extracting a corresponding deep neural network from the trained intelligent agent, and then realizing on-line evasion maneuver control based on the flow shown in FIG. 4. That is, on the one hand, the neural network based on the current observed quantityoGenerating optimal perturbation matrix coefficients ("State")
Figure SMS_50
And calculates the corresponding disturbance matrix accordingly>
Figure SMS_51
On the other hand, based on the latest speed constructed in step S1, the corresponding +.>
Figure SMS_52
(if not triggered, skipping this step) on the basis of the evasion maneuver control strategy constructed in the step S2, solving the track control acceleration +.>
Figure SMS_53
("action") and finally realizing end-to-end and reactive evasion maneuver control of the "state-action".
For step 104:
in one embodiment of the present disclosure, step 104 may specifically include:
the desired avoidance speed of the spacecraft is obtained using the following set of formulas:
Figure SMS_54
in the method, in the process of the invention,
Figure SMS_56
to expect evasion speed->
Figure SMS_59
For disturbance matrix +.>
Figure SMS_62
Is a radial reaction coefficient>
Figure SMS_58
For the tangential reaction coefficient, +.>
Figure SMS_61
Is the direction coefficient +.>
Figure SMS_65
For the latest speed of the spacecraft, < >>
Figure SMS_66
For the speed when the desired speed direction of the spacecraft is unchanged, < >>
Figure SMS_55
For threat speed, < >>
Figure SMS_60
For the position of a spacecraft >
Figure SMS_63
For threat location, <' > for threat>
Figure SMS_64
For a preset safety distance, +.>
Figure SMS_57
To correct the velocity.
In this embodiment, the latest speed of the spacecraft is corrected by using the disturbance matrix, so that the expected avoidance speed of the spacecraft can be obtained, and preparation is made for obtaining more accurate track-controlled acceleration subsequently.
For step 106:
in one embodiment of the present disclosure, step 106 may specifically include:
the desired acceleration is calculated using the following formula:
Figure SMS_67
in the method, in the process of the invention,
Figure SMS_68
for the desired acceleration, ->
Figure SMS_69
To expect evasion speed->
Figure SMS_70
For the speed when the desired speed direction of the spacecraft is unchanged, < >>
Figure SMS_71
Sampling step length for the controller;
the preset orbital motion equation (i.e., the Clohessy-Wiltshire orbital motion equation) adopts the following formula set:
Figure SMS_72
in the method, in the process of the invention,
Figure SMS_73
for the positions of both parties in the LVLH coordinate system,Pa threat is indicated and the threat is indicated,Erepresenting a spacecraft, the speeds of both parties are +.>
Figure SMS_74
；/>
Figure SMS_75
Is the track angular velocity; />
Figure SMS_76
The rail control acceleration is the rail control acceleration of both sides;
the expected acceleration is brought into the track motion equation to calculate the commanded track acceleration according to the following formula:
Figure SMS_77
in the method, in the process of the invention,
Figure SMS_78
the acceleration is controlled for a command rail;
limiting the command rail control acceleration according to the following formula group to obtain the final rail control acceleration of the spacecraft
Figure SMS_79
：
Figure SMS_80
In the method, in the process of the invention,
Figure SMS_81
is the maximum rail controlled acceleration of the spacecraft.
Simulation testing of threat and spacecraft is described below in connection with fig. 8-11.
Simulation verification is carried out on the situation when the threat is the same as the spacecraft mobility, and simulation parameters are as follows: the threat adopts a proportional guidance law,
Figure SMS_83
，/>
Figure SMS_85
，/>
Figure SMS_87
，/>
Figure SMS_84
，/>
Figure SMS_86
，
Figure SMS_88
，/>
Figure SMS_89
，/>
Figure SMS_82
. The simulation computer is configured to: CPU AMD Ryzen 7-5800 3.40 GHz,RAM 16 GB. Trajectory of both partiesThe relative distance and energy consumption are shown in fig. 8-10, respectively, and the threat's target line of sight angle is shown in fig. 11.
The result shows that in the evading maneuver process, the relative distance between the two parties is always kept outside the safety radius, and the spacecraft finally enters a detection blind area of the threat under the condition that the energy consumption is greatly lower than the threat, so that the successful evasion is realized. In terms of calculation time, the single-step running time of the method is approximately in the range of 3-4 ms, so that the method achieves near real-time and can meet the corresponding rapid reaction requirement. In summary, the method of the invention can rapidly plan proper maneuvering control instructions to enable the spacecraft to realize safe avoidance with lower energy consumption cost in the face of the threat of continuous trailing tracking.
As shown in fig. 2 and 3, the embodiment of the present disclosure provides an evasive maneuver control apparatus for a spacecraft. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. In terms of hardware, as shown in fig. 2, a hardware architecture diagram of an electronic device where a maneuver avoidance control device for a spacecraft provided in the embodiments of the present disclosure is located is shown, where the electronic device where the embodiments are located may include other hardware, such as a forwarding chip responsible for processing a message, besides the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 2. Taking a software implementation as an example, as shown in fig. 3, the device in a logic sense is formed by reading a corresponding computer program in a nonvolatile memory into a memory by a CPU of an electronic device where the device is located and running the computer program.
As shown in fig. 3, the evasion maneuver control apparatus for a spacecraft provided in this embodiment includes:
a determination module 300 for determining whether to change a desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat;
a building module 302 for building a disturbance matrix of the spacecraft based on the position of the spacecraft and the threat and the latest speed; the disturbance matrix comprises an adjustable radial reaction coefficient, a tangential reaction coefficient and a direction coefficient, wherein the radial reaction coefficient and the tangential reaction coefficient determine the evading moment, and the direction coefficient determines the evading direction;
the correction module 304 is configured to correct the latest speed of the spacecraft by using the disturbance matrix, so as to obtain a desired avoidance speed of the spacecraft;
and the output module 306 is configured to obtain a final orbital acceleration of the spacecraft based on the desired avoidance speed and a preset orbital equation, so as to use the final orbital acceleration as an avoidance maneuver control command of the spacecraft.
In the embodiment of the present disclosure, the determining module 300 may be used to perform the step 100 in the embodiment of the method, the constructing module 302 may be used to perform the step 102 in the embodiment of the method, the modifying module 304 may be used to perform the step 104 in the embodiment of the method, and the output module 306 may be used to perform the step 106 in the embodiment of the method.
In one embodiment of the present specification, the determining module is configured to perform the following operations:
if the positions and speeds of the spacecraft and the threat all meet preset trigger conditions, changing the expected speed direction of the spacecraft, otherwise, not changing the expected speed direction of the spacecraft;
the triggering conditions include:
the vector included angle between the position vector of the spacecraft pointing at the threat and the speed vector of the spacecraft is greater than 90 degrees;
the threat is directed to a position vector of the spacecraft and a vector included angle of a velocity vector of the threat is less than 90 °;
the relative position difference between the spacecraft and the threat is smaller than a preset warning distance; the warning distance is larger than a preset safety distance, and the safety distance is the minimum distance between the spacecraft and the threat in the avoidance process.
In one embodiment of the present specification, let a first plane be a plane formed by a position vector of the threat directed to the spacecraft and a velocity vector of the threat, and a second plane be a plane formed by a position vector of the threat directed to the spacecraft and a velocity vector of the spacecraft;
The desired speed direction of the spacecraft is changed in at least one of the following ways:
when the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located in the first plane to the left of the position vector of the threat directed to the spacecraft, and the threat is located in the second plane to the left of the velocity vector of the spacecraft, performing: calculating the symmetrical position of the threat relative to the speed vector of the spacecraft; determining a virtual target position based on the position of the spacecraft and the symmetrical position; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
when the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located in the first plane to the left of the position vector of the threat directed to the spacecraft, and the threat is located in the second plane to the right of the velocity vector of the spacecraft, performing: determining a virtual target location based on the spacecraft and the threat location; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
When the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located on the right side of the position vector of the threat directed to the spacecraft in the first plane, and the threat is located on the left side of the velocity vector of the spacecraft in the second plane, performing: determining a virtual target location based on the spacecraft and the threat location; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
when the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located on the right side of the position vector of the threat directed to the spacecraft in the first plane, and the threat is located on the right side of the velocity vector of the spacecraft in the second plane, performing: calculating the symmetrical position of the threat relative to the speed vector of the spacecraft; determining a virtual target position based on the position of the spacecraft and the symmetrical position; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
When the vector angle between the position vector of the threat pointing to the spacecraft and the velocity vector of the threat is equal to 0, performing: determining a virtual target location based on the spacecraft and the threat location; the desired speed direction of the spacecraft is determined as the direction in which the position of the spacecraft points to the virtual target position.
In one embodiment of the present specification, the correction module is configured to perform the following operations:
the desired avoidance speed of the spacecraft is obtained using the following set of formulas:
Figure SMS_90
in the method, in the process of the invention,
Figure SMS_94
for the desired evasion speed +.>
Figure SMS_96
For the disturbance matrix +.>
Figure SMS_99
For the radial reaction coefficient, < >>
Figure SMS_92
For the tangential reaction coefficient, +.>
Figure SMS_97
For the direction coefficient, +.>
Figure SMS_100
For the latest speed of the spacecraft,/-or->
Figure SMS_102
For the speed when the desired speed direction of the spacecraft is unchanged,/for the speed when the desired speed direction of the spacecraft is unchanged>
Figure SMS_91
For the speed of the threat +.>
Figure SMS_95
For the position of the spacecraft, +.>
Figure SMS_98
For the location of the threat->
Figure SMS_101
For a preset safety distance, +.>
Figure SMS_93
To correct the velocity.
In one embodiment of the present specification, the output module is configured to perform the following operations:
the desired acceleration is calculated using the following formula:
Figure SMS_103
In the method, in the process of the invention,
Figure SMS_104
for the desired acceleration, +.>
Figure SMS_105
For the desired evasion speed +.>
Figure SMS_106
For the speed when the desired speed direction of the spacecraft is unchanged,/for the speed when the desired speed direction of the spacecraft is unchanged>
Figure SMS_107
Sampling step length for the controller;
the preset orbital motion equation adopts the following formula group:
Figure SMS_108
in the method, in the process of the invention,
Figure SMS_109
for the positions of both parties in the LVLH coordinate system,Pthe threat is represented by a set of points in the set,Erepresenting the spacecraft, the speeds of both parties are +.>
Figure SMS_110
；/>
Figure SMS_111
Is the track angular velocity; />
Figure SMS_112
The rail control acceleration is the rail control acceleration of both sides;
bringing the desired acceleration into the orbital motion equation to calculate a commanded orbital acceleration according to the following formula:
Figure SMS_113
/>
in the method, in the process of the invention,
Figure SMS_114
the acceleration is controlled for a command rail;
performing amplitude limiting processing on the command rail control acceleration according to the following formula group to obtain the final rail control acceleration of the spacecraft
Figure SMS_115
：
Figure SMS_116
In the method, in the process of the invention,
Figure SMS_117
is the maximum rail acceleration of the spacecraft.
In one embodiment of the present specification, further comprising:
the training module is used for training the intelligent body by using an Actor-Critic deep reinforcement learning algorithm so as to obtain a target neural network;
the optimizing module is used for inputting three adjustable parameters of the constructed disturbance matrix into the target neural network, and outputting the three optimized adjustable parameters so as to correct the latest speed of the spacecraft by utilizing the optimized disturbance matrix.
In one embodiment of the present specification, the training module is configured to perform the following operations:
setting an initial training environment of deep reinforcement learning; the training environment comprises an initial position of the spacecraft, an initial position and an initial speed of the threat and an intersection guidance strategy of the threat;
the termination condition of the training round is set using the following formula:
Figure SMS_118
in the method, in the process of the invention,Resetin order to provide the termination condition in question,Cond 1 to avoid failure determination conditions, the approach of both sides to a safe distance is expressed
Figure SMS_119
An inner part;Cond 2 to circumvent the success decision condition, the energy consumption representing the threat exceeds a set threshold +.>
Figure SMS_120
；Cond 3 To circumvent the success determination condition, representThe spacecraft has entered the threat detection zone,/-or->
Figure SMS_121
For the target angular amplitude of view of the threat,t f for the moment at which the training round ends, +.>
Figure SMS_122
A maximum line of sight angle to ensure that the threat is effectively perceived; when the termination condition is equal to 1, entering the next training round, and simultaneously resetting the initial training environment of the spacecraft;
setting observance quantity, action quantity and rewarding function of the intelligent agent; wherein the observed quantity relates to the position and speed of the spacecraft and the threat, and the action quantity is three adjustable parameters of a disturbance matrix;
Training an intelligent agent by using an Actor-Critic deep reinforcement learning algorithm until a mean curve of the reward function enters a convergence state;
and extracting the target neural network from the intelligent agent obtained by training.
It will be appreciated that the structure illustrated in the embodiments of the present description does not constitute a particular limitation of a spacecraft evasion maneuver control. In other embodiments of the present description, a evasive maneuver control apparatus for a spacecraft may include more or fewer components than illustrated, or may combine certain components, or split certain components, or may be a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The content of information interaction and execution process between the modules in the above-mentioned device, because the content is based on the same conception as the method embodiment of the present specification, the specific content can be referred to the description in the method embodiment of the present specification, and the description is not repeated here.
The embodiment of the specification also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the evasion maneuver control method of the spacecraft in any embodiment of the specification when executing the computer program.
Embodiments of the present specification also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform a method of maneuver for evasion control of a spacecraft in any of the embodiments of the present specification.
Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present specification.
Examples of the storage medium for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
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.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: various media in which program code may be stored, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present specification, and are not limiting thereof; although the present specification has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present specification.

Claims (10)

1. A method of maneuver control for avoiding a spacecraft, comprising:
determining whether to change a desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat;
Constructing a disturbance matrix of the spacecraft based on the position of the spacecraft and the threat and the latest speed; the disturbance matrix comprises three adjustable parameters, wherein the adjustable parameters are a radial reaction coefficient, a tangential reaction coefficient and a direction coefficient, the radial reaction coefficient and the tangential reaction coefficient determine an avoidance opportunity, and the direction coefficient determines an avoidance direction;
correcting the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evading speed of the spacecraft;
and obtaining the final orbit control acceleration of the spacecraft based on the expected avoidance speed and a preset orbit motion equation, and taking the final orbit control acceleration as an avoidance maneuver control instruction of the spacecraft.
2. The method of claim 1, wherein the determining whether to change the desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat comprises:
if the positions and speeds of the spacecraft and the threat all meet preset trigger conditions, changing the expected speed direction of the spacecraft, otherwise, not changing the expected speed direction of the spacecraft;
The triggering conditions include:
the vector included angle between the position vector of the spacecraft pointing at the threat and the speed vector of the spacecraft is greater than 90 degrees;
the threat is directed to a position vector of the spacecraft and a vector included angle of a velocity vector of the threat is less than 90 °;
the relative position difference between the spacecraft and the threat is smaller than a preset warning distance; the warning distance is larger than a preset safety distance, and the safety distance is the minimum distance between the spacecraft and the threat in the avoidance process.
3. The method of claim 1, wherein a first plane is a plane formed by a position vector of the threat directed to the spacecraft and a velocity vector of the threat, and a second plane is a plane formed by a position vector of the threat directed to the spacecraft and a velocity vector of the spacecraft;
the desired speed direction of the spacecraft is changed in at least one of the following ways:
when the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located in the first plane to the left of the position vector of the threat directed to the spacecraft, and the threat is located in the second plane to the left of the velocity vector of the spacecraft, performing: calculating the symmetrical position of the threat relative to the speed vector of the spacecraft; determining a virtual target position based on the position of the spacecraft and the symmetrical position; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
When the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located in the first plane to the left of the position vector of the threat directed to the spacecraft, and the threat is located in the second plane to the right of the velocity vector of the spacecraft, performing: determining a virtual target location based on the spacecraft and the threat location; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
when the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located on the right side of the position vector of the threat directed to the spacecraft in the first plane, and the threat is located on the left side of the velocity vector of the spacecraft in the second plane, performing: determining a virtual target location based on the spacecraft and the threat location; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
When the vector included angle between the position vector of the threat directed to the spacecraft and the velocity vector of the threat is not equal to 0, the velocity vector of the threat is located on the right side of the position vector of the threat directed to the spacecraft in the first plane, and the threat is located on the right side of the velocity vector of the spacecraft in the second plane, performing: calculating the symmetrical position of the threat relative to the speed vector of the spacecraft; determining a virtual target position based on the position of the spacecraft and the symmetrical position; determining a desired speed direction of the spacecraft as a direction in which the position of the spacecraft points to the virtual target position;
when the vector angle between the position vector of the threat pointing to the spacecraft and the velocity vector of the threat is equal to 0, performing: determining a virtual target location based on the spacecraft and the threat location; the desired speed direction of the spacecraft is determined as the direction in which the position of the spacecraft points to the virtual target position.
4. The method of claim 1, wherein correcting the most recent velocity of the spacecraft using the disturbance matrix to obtain a desired avoidance velocity of the spacecraft comprises:
The desired avoidance speed of the spacecraft is obtained using the following set of formulas:
Figure QLYQS_1
in the method, in the process of the invention,
Figure QLYQS_4
for the desired evasion speed +.>
Figure QLYQS_6
For the disturbance matrix +.>
Figure QLYQS_8
As a function of the radial reaction coefficient in question,
Figure QLYQS_3
for the tangential reaction coefficient, +.>
Figure QLYQS_9
For the direction coefficient, +.>
Figure QLYQS_11
For the latest speed of the spacecraft,/-or->
Figure QLYQS_13
For the speed when the desired speed direction of the spacecraft is unchanged,/for the speed when the desired speed direction of the spacecraft is unchanged>
Figure QLYQS_2
For the speed of the threat +.>
Figure QLYQS_7
For the position of the spacecraft, +.>
Figure QLYQS_10
For the location of the threat->
Figure QLYQS_12
For a preset safety distance, +.>
Figure QLYQS_5
To correct the velocity.
5. The method of claim 4, wherein the deriving a final orbital acceleration of the spacecraft based on the desired avoidance speed and a preset orbital equation of motion comprises:
the desired acceleration is calculated using the following formula:
Figure QLYQS_14
in the method, in the process of the invention,
Figure QLYQS_15
for the desired acceleration, +.>
Figure QLYQS_16
For the desired evasion speed +.>
Figure QLYQS_17
For the speed when the desired speed direction of the spacecraft is unchanged,/for the speed when the desired speed direction of the spacecraft is unchanged>
Figure QLYQS_18
Sampling step length for the controller;
the preset orbital motion equation adopts the following formula group:
Figure QLYQS_19
in the method, in the process of the invention,
Figure QLYQS_20
for the positions of both parties in the LVLH coordinate system,Pthe threat is represented by a set of points in the set,Erepresenting the spacecraft, the speeds of both parties are +. >
Figure QLYQS_21
；/>
Figure QLYQS_22
Is the track angular velocity; />
Figure QLYQS_23
The rail control acceleration is the rail control acceleration of both sides;
bringing the desired acceleration into the orbital motion equation to calculate a commanded orbital acceleration according to the following formula:
Figure QLYQS_24
in the method, in the process of the invention,
Figure QLYQS_25
controlling acceleration for the command track;
performing amplitude limiting processing on the command rail control acceleration according to the following formula group to obtain the final rail control acceleration of the spacecraft
Figure QLYQS_26
：
Figure QLYQS_27
In the method, in the process of the invention,
Figure QLYQS_28
is the maximum rail acceleration of the spacecraft.
6. The method according to any one of claims 1-5, further comprising, after said constructing a disturbance matrix for said spacecraft and before said correcting a most recent velocity of said spacecraft with said disturbance matrix:
training an intelligent agent by using an Actor-Critic deep reinforcement learning algorithm to obtain a target neural network;
three adjustable parameters of the constructed disturbance matrix are input into the target neural network, and the three optimized adjustable parameters are output so as to correct the latest speed of the spacecraft by utilizing the optimized disturbance matrix.
7. The method of claim 6, wherein training the agent using an Actor-Critic deep reinforcement learning algorithm to obtain the target neural network comprises:
Setting an initial training environment of deep reinforcement learning; the training environment comprises an initial position of the spacecraft, an initial position and an initial speed of the threat and an intersection guidance strategy of the threat;
the termination condition of the training round is set using the following formula:
Figure QLYQS_29
in the method, in the process of the invention,Resetin order to provide the termination condition in question,Cond 1 to avoid failure determination conditions, the approach of both sides to a safe distance is expressed
Figure QLYQS_30
An inner part;Cond 2 to circumvent the success decision condition, the energy consumption representing the threat exceeds a set threshold +.>
Figure QLYQS_31
；Cond 3 To circumvent the success determination condition, a detection blind zone indicating that the spacecraft has entered the threat,/->
Figure QLYQS_32
For the target angular amplitude of view of the threat,t f for the moment at which the training round ends, +.>
Figure QLYQS_33
A maximum line of sight angle to ensure that the threat is effectively perceived; when the termination condition is equal to 1, entering the next training round, and simultaneously resetting the initial training environment of the spacecraft;
setting observance quantity, action quantity and rewarding function of the intelligent agent; wherein the observed quantity relates to the position and speed of the spacecraft and the threat, and the action quantity is three adjustable parameters of a disturbance matrix;
Training an intelligent agent by using an Actor-Critic deep reinforcement learning algorithm until a mean curve of the reward function enters a convergence state;
and extracting the target neural network from the intelligent agent obtained by training.
8. An evasion maneuver control apparatus for a spacecraft, comprising:
a determination module for determining whether to change a desired speed direction of the spacecraft based on the position and speed of the spacecraft and a threat;
a building module for building a disturbance matrix of the spacecraft based on the position and the latest speed of the spacecraft and the threat; the disturbance matrix comprises an adjustable radial reaction coefficient, a tangential reaction coefficient and a direction coefficient, wherein the radial reaction coefficient and the tangential reaction coefficient determine the evading moment, and the direction coefficient determines the evading direction;
the correction module is used for correcting the latest speed of the spacecraft by using the disturbance matrix to obtain the expected evading speed of the spacecraft;
the output module is used for obtaining the final orbit control acceleration of the spacecraft based on the expected avoidance speed and a preset orbit motion equation, and taking the final orbit control acceleration as an avoidance maneuver control instruction of the spacecraft.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the method of any of claims 1-7 when the computer program is executed.
10. A computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of any of claims 1-7.
CN202310106661.1A 2023-02-13 2023-02-13 Evasion maneuver control method and device for spacecraft Active CN116039959B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310106661.1A CN116039959B (en) 2023-02-13 2023-02-13 Evasion maneuver control method and device for spacecraft

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310106661.1A CN116039959B (en) 2023-02-13 2023-02-13 Evasion maneuver control method and device for spacecraft

Publications (2)

Publication Number Publication Date
CN116039959A true CN116039959A (en) 2023-05-02
CN116039959B CN116039959B (en) 2023-08-15

Family

ID=86125463

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310106661.1A Active CN116039959B (en) 2023-02-13 2023-02-13 Evasion maneuver control method and device for spacecraft

Country Status (1)

Country Link
CN (1) CN116039959B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040100395A1 (en) * 2002-11-22 2004-05-27 Anderson Christopher M. Airborne microwave/infrared wind shear and clear air turbulence detector
US10059470B1 (en) * 2018-02-09 2018-08-28 Launchspace Technologies Corporation Apparatus and methods for creating artificial geosynchronous orbits
CN109903590A (en) * 2017-12-11 2019-06-18 上海航空电器有限公司 A kind of aircraft automatic maneuver bypassing method based on landform envelope curve
CN114440896A (en) * 2022-04-08 2022-05-06 中国人民解放军96901部队 High-speed aircraft flight pipeline planning method based on dynamic identification of threat scene
CN115416877A (en) * 2022-09-06 2022-12-02 宁波天巡科技有限公司 Satellite collision height avoidance method based on low thrust and intelligent system
CN115657711A (en) * 2022-10-09 2023-01-31 北京航空航天大学 Hypersonic aircraft avoidance guidance method based on deep reinforcement learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040100395A1 (en) * 2002-11-22 2004-05-27 Anderson Christopher M. Airborne microwave/infrared wind shear and clear air turbulence detector
CN109903590A (en) * 2017-12-11 2019-06-18 上海航空电器有限公司 A kind of aircraft automatic maneuver bypassing method based on landform envelope curve
US10059470B1 (en) * 2018-02-09 2018-08-28 Launchspace Technologies Corporation Apparatus and methods for creating artificial geosynchronous orbits
CN114440896A (en) * 2022-04-08 2022-05-06 中国人民解放军96901部队 High-speed aircraft flight pipeline planning method based on dynamic identification of threat scene
CN115416877A (en) * 2022-09-06 2022-12-02 宁波天巡科技有限公司 Satellite collision height avoidance method based on low thrust and intelligent system
CN115657711A (en) * 2022-10-09 2023-01-31 北京航空航天大学 Hypersonic aircraft avoidance guidance method based on deep reinforcement learning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
姚党鼐;王振国;: "航天器在轨防碰撞自主规避策略", 国防科技大学学报, no. 06, pages 1 - 10 *
王宏伦;吴健发;姚鹏;: "基于扰动流体动态系统的无人机三维航路规划:方法与应用", 无人系统技术, no. 01, pages 80 - 90 *

Also Published As

Publication number Publication date
CN116039959B (en) 2023-08-15

Similar Documents

Publication Publication Date Title
Shaobo et al. A collision avoidance decision-making system for autonomous ship based on modified velocity obstacle method
Chen et al. A hybrid path planning algorithm for unmanned surface vehicles in complex environment with dynamic obstacles
Ramirez et al. Integrated Hybrid Planning and Programmed Control for Real Time UAV Maneuvering.
Minne Automatic testing of maritime collision avoidance algorithms
CN110377034B (en) Global robust sliding mode control method for track tracking of surface ship based on dragonfly algorithm optimization
CN114063644B (en) Unmanned fighter plane air combat autonomous decision-making method based on pigeon flock reverse countermeasure learning
Rubí et al. Quadrotor path following and reactive obstacle avoidance with deep reinforcement learning
CN105372653B (en) A kind of efficient turning maneuvering target tracking method towards in bank base air traffic control radar system
Figueiredo et al. Deep reinforcement learning algorithms for ship navigation in restricted waters
Lu et al. A two-stage dynamic collision avoidance algorithm for unmanned surface vehicles based on field theory and COLREGs
Guan et al. Autonomous collision avoidance of unmanned surface vehicles based on improved A-star and dynamic window approach algorithms
Liu et al. COLREGS-based collision avoidance algorithm for unmanned surface vehicles using modified artificial potential fields
Rasib et al. Are self-driving vehicles ready to launch? An insight into steering control in autonomous self-driving vehicles
CN116039959B (en) Evasion maneuver control method and device for spacecraft
Barfield Autonomous collision avoidance: the technical requirements
CN107272736B (en) Unmanned aerial vehicle obstacle avoidance guiding method based on pigeon passive obstacle avoidance flight
Henriksen Automatic testing of maritime collision avoidance methods with sensor fusion
Karelahti et al. Game optimal support time of a medium range air-to-air missile
CN116841298A (en) Finite time tracking control method suitable for four-wheel mobile robot lane change early warning
Jeon et al. Aerial chasing of a dynamic target in complex environments
Jose et al. Navigating the Ocean with DRL: Path following for marine vessels
Wei et al. UCAV formation online collaborative trajectory planning using hp adaptive pseudospectral method
Carr Optimal control methods for missile evasion
Do et al. Design and simulate a Fuzzy autopilot for an Unmanned Surface Vessel
Oshman et al. Enhanced air-to-air missile tracking using target orientation observations

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