EP3407004A1 - Missionsplanung für waffensysteme - Google Patents

Missionsplanung für waffensysteme Download PDF

Info

Publication number
EP3407004A1
EP3407004A1 EP17172972.6A EP17172972A EP3407004A1 EP 3407004 A1 EP3407004 A1 EP 3407004A1 EP 17172972 A EP17172972 A EP 17172972A EP 3407004 A1 EP3407004 A1 EP 3407004A1
Authority
EP
European Patent Office
Prior art keywords
weapon
surrogate model
training data
performance
mission planning
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.)
Ceased
Application number
EP17172972.6A
Other languages
English (en)
French (fr)
Inventor
designation of the inventor has not yet been filed The
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.)
MBDA UK Ltd
Original Assignee
MBDA UK Ltd
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 MBDA UK Ltd filed Critical MBDA UK Ltd
Priority to EP17172972.6A priority Critical patent/EP3407004A1/de
Priority to EP18724986.7A priority patent/EP3631344A1/de
Priority to US16/614,857 priority patent/US11029130B2/en
Priority to IL270798A priority patent/IL270798B2/en
Priority to PCT/GB2018/051338 priority patent/WO2018215738A1/en
Priority to CA3064158A priority patent/CA3064158A1/en
Priority to AU2018273014A priority patent/AU2018273014B2/en
Publication of EP3407004A1 publication Critical patent/EP3407004A1/de
Ceased legal-status Critical Current

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F41—WEAPONS
    • F41G—WEAPON SIGHTS; AIMING
    • F41G7/00—Direction control systems for self-propelled missiles
    • F41G7/006—Guided missiles training or simulation devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F41—WEAPONS
    • F41G—WEAPON SIGHTS; AIMING
    • F41G7/00—Direction control systems for self-propelled missiles
    • F41G7/007—Preparatory measures taken before the launching of the guided missiles
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F41—WEAPONS
    • F41G—WEAPON SIGHTS; AIMING
    • F41G9/00—Systems for controlling missiles or projectiles, not provided for elsewhere
    • F41G9/002—Systems for controlling missiles or projectiles, not provided for elsewhere for guiding a craft to a correct firing position
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F41—WEAPONS
    • F41G—WEAPON SIGHTS; AIMING
    • F41G7/00—Direction control systems for self-propelled missiles
    • F41G7/001—Devices or systems for testing or checking
    • F41G7/002—Devices or systems for testing or checking target simulators

Definitions

  • the present invention seeks to mitigate the above-mentioned problems. Alternatively or additionally, the present invention seeks to provide an improved mission planning method for predicting the capability of a weapon during combat operations.
  • the present invention provides, according to a first aspect, a mission planning method for use with a weapon.
  • the method may comprise a step of obtaining a training data set describing the performance of the weapon.
  • the method may comprise a step of using the training data and a Gaussian Process (GP) or Neural Network to obtain a surrogate model which gives a functional approximation of the performance of the weapon.
  • the method may comprise providing the surrogate model to a weapons system for use in calculating a performance characteristic of the weapon during combat operations.
  • GP Gaussian Process
  • the method may comprise launching a weapon in dependence on the performance characteristic(s) calculated by the surrogate model.
  • the method may comprise launching a weapon when the results of the surrogate model indicate that the weapon is within a LAR, and/or the target is within a LSZ.
  • the method may comprise carrying out a defensive action, for example an evasive action in dependence on the performance characteristic(s) calculated by the surrogate model.
  • the surrogate model is configured to predict the behaviour of an enemy weapon it is not necessary for the surrogate model to be provided to weapons system, it may instead be provided to a friendly asset for use in defence of said asset or another friendly asset.
  • the method may comprise the step of obtaining a plurality of training data sets.
  • Each training data set may be applicable to a pre-defined combination of parameters, hereafter known as an applicability zone.
  • each applicability zone may corresponding to a pre-defined parameter space.
  • the method may comprise running a kinematic model for a plurality of points (i.e. combinations of parameters) located within the applicability zone.
  • the method may comprise running a kinematic model for a plurality of points (i.e. combinations of parameters) located adjacent to, but outside, the applicability zone. Running the model for points immediately outside the applicability zone may improve the accuracy of the surrogate model produced using that data set when predicating performance characteristics at the edges of the zone.
  • the method may comprise identifying the applicability zone corresponding to the current engagement parameters.
  • the method may comprise selecting a surrogate model from the plurality of surrogate models in dependence on the applicability zone so identified.
  • the method may comprise using the surrogate model so selected to calculate a performance characteristic of the weapon. Using the applicability zones to divide the parameter space into different areas may allow for faster calculation of the performance characteristic, as only the induction points relating to the current applicability zone need be considered at any one time.
  • the method may comprise obtaining further training data sets, each further training data set corresponding to another parameter space (or applicability zone).
  • the surrogate model may comprise more than two applicability zones.
  • the method may comprise applying one or more correctors to the output of the surrogate model.
  • the corrector may be a linear multiplier, a bias, an offset, a minimum value or a maximum value.
  • a different corrector, or set of correctors may be applied to each zone. Applying a corrector to the output of the surrogate model may allow for differences in the overall performance of the weapon when it is integrated onto the weapons platform to be taken into account without having to make extensive software changes. Correctors of this kind may also be used to more easily alter the indicated performance of the weapon to suit operational, training or commercial requirements. Thus, the use of correctors, particularly in combination with applicability zones, may provide a more flexible surrogate model.
  • the step of generating the training data and/or obtaining the surrogate model may be carried out by one or more computer processors that are separate from the weapons system.
  • the step of calculating a performance characteristic of the weapon may be carried out by a processor forming part of the weapons system, for example one or more processors mounted on the weapon, for example the missile and/or the launcher.
  • the step of calculating a performance characteristic of the weapon may be carried out by a processor forming part of the control system of the weapons platform.
  • the method may comprise using a first set of one or more processors to run the kinematic model to generate the training data and/or to train the GP or Neural Network to generate the surrogate model.
  • the first set of processors may be located on the ground, for example in a research facility.
  • the method may comprise using a second set of one or more processors to calculate one or more performance characteristic(s) using the surrogate model.
  • the processors of the second set may be located on a mobile weapon system.
  • the step of obtaining the training data, and the step of calculating the performance characteristics may be carried out in physically separate locations and/or by different processors.
  • the method may comprise a step of preparing the training data for use in the GP process or Neural Network. This step may comprise formatting the functional data from the kinematic model into pairs comprising a set of input parameters and the corresponding value of the function (i.e. the performance characteristic) to be approximated.
  • the weapons system may comprise a weapons platform.
  • the weapon system may comprise the weapon.
  • the weapon may be mounted on the weapons platform, for example the weapon may be mounted on a launcher mounted on the weapons platform.
  • the weapons platform may be a mobile weapons platform, for example an aircraft, a ship or a ground vehicle, for example a truck.
  • a missile comprising a processor programmed with software configured to calculate a performance characteristic of a weapon of the weapons system using a functional approximation comprising a surrogate model produced using a GP or Neural Network.
  • a weapons system comprising a processor programmed with software configured to carry out the method of the first, or any other, aspect of the present invention.
  • Figure 1 shows a process for calculating the Launch Acceptability Region (LAR) of a missile in accordance with a first example embodiment of the invention.
  • the process comprises three stages (in order); training data generation 1; determining a surrogate model 2 for calculating LAR ; and an operational step 3, where the surrogate model produced in step 2 is used in deciding whether to launch the weapon at a target.
  • IR-Outer In order to calculate the LAR of a missile it may be necessary to approximate four functions associated with a given engagement situation: IR-Outer, IR-Inner, IZ-Outer and IZ-Inner.
  • IR refers to 'in-range' and denotes the weapon attainability boundary for an engagement with no explicit user specified constraints.
  • IZ refers to 'in-zone' which may further include user specified constrains such as demanded missile impact heading, cruise altitude, specified way-points and run-in distance.
  • ⁇ is the angle of launch position with respect to the target (deg)
  • H is the launch altitude (m)
  • v is the launch speed (m/s)
  • ⁇ is the pitch/dive angle at impact (deg).
  • a range of values for each of the parameters ⁇ , H , v , ⁇ are input to a kinematic model.
  • the kinematic model is then run multiple times 4 with different combinations of parameter values to produce a set of training data 6 and a set of validation data 8 describing the variation of R over the parameter space.
  • This data sets represents noisy and sparse observations of the true continuous underlying LAR function.
  • the training data is input into a FITC algorithm (Fully Independent Training Conditional approximation as described in " A unifying View of Sparse Approximate Gaussian Process Regression" by Quinonero-Candela J. & Rasmussen C.E., Journal of Machine Learning Research, Vol.
  • the pseudo or inducing-points u are treated as hyper-parameters to be optimised.
  • the LAR approximation requires the following hyper-parameters 14 to be generated; ⁇ ⁇ , ⁇ H , ⁇ v , ⁇ ⁇ , ⁇ f , X u , w
  • ⁇ ⁇ , ⁇ H , ⁇ v , ⁇ ⁇ are length-scale parameters learned during training
  • ⁇ f is an overall scale factor determined from training
  • X u represents the induction points determined in training
  • w represents a weighted output value, one per induction point, derived from the covariance function (see below)
  • ⁇ n the noise parameter.
  • These hyper-parameters 14 are calculated 12 using the FITC algorithm and a squared exponential covariance function 15 with Automatic Relevance Detection (ARD). Once calculated 12, the hyper-parameters 14 are passed to an evaluation step 18 which compares the predicted values calculated using a covariance function employing those parameters 14 with the validation data 8 to verify that the resulting surrogate model is sufficiently accurate.
  • the covariance function 15 corresponding to the GP and hyper-parameters 14 are then incorporated 16 into a playback algorithm 19, for use in stage 3. Stages 1 and 2 of the method are carried out 'off-line', and separate from any weapons
  • R * K x u , x * ⁇ w
  • the playback algorithm 19 embodying the covariance function 15 and hyper-parameters 14 is used to calculate 20 the function R at any given instant.
  • the other functions required to calculate the LAR are similarly calculated.
  • the prediction of the LAR is continually updated as engagement conditions change and this information is provided to the pilot who uses that information to decide 22 whether to launch 24 the missile against a given target.
  • FIG. 2 shows part of an aircraft 100 for use with the method of the first embodiment.
  • the aircraft 100 has a fuselage 102 and a wing 104, and a missile 108 mounted on a launcher 106 located on the underside of the wing 104.
  • a processor 110 programmed with the playback algorithm 19 embodying the covariance function 15 and having access to the hyper-parameters 14 is located within the fuselage 102 and forms part of the command and control (C2) system (not shown) of the aircraft 100.
  • C2 command and control
  • data representing the current conditions and location of the aircraft 100 and a target (not shown) is provided to the processor 110 which uses the covariance function 15 and hyper-parameters 14 to calculate the LAR for that target.
  • the LAR is provided to the pilot who then uses that information in deciding whether to launch the missile 108 as discussed above.
  • the missile may be located in a bomb bay, internal to the aircraft.
  • Figure 3 shows a variation of the arrangement of Figure 2 .
  • the processor 110 is located within the missile 108 and provides a LAR to the aircraft command and control (C2) system (not shown) which relays this information to the pilot.
  • C2 aircraft command and control
  • weapons systems in accordance with the present example embodiment may facilitate interoperability and maintenance as there is no need to update on-board software to reflect changes in missile performance; this information is provided as part of the missile itself through the hyper-parameters 14 and covariance function 15.
  • FIG. 4 shows a schematic depiction of a cuboidal parameter space 200, with a first parameter A increasing along the x-axis, a second parameter B increasing along the y-axis and a third parameter C increasing along the z-axis.
  • the parameter space 200 has been divided into four zones 208a, 208b, 208c and 208d. Each of the zones 208a, 208b, 208c occupies a separate volume of the cuboidal space 200, with the fourth zone 208d representing the space not falling within the first three zones 208a, 208b, 208c.
  • the first zone 208a is immediately adjacent to the second zone 208b.
  • the third zone is spaced apart from both the first zone 208a and the second zone 208b.
  • the training data for a given zone is generated using combinations of parameters falling within, and immediately adjacent to, the zone.
  • a set of training data 6a and verification data 8a is obtained for zone 208a and so on for each of zones b to d.
  • Each set of training data is then prepared and the FITC algorithm used to produce a set of hyper-parameters (including inducing points) for each zone. If the behaviour of the missile is different between different zones then the variables describing the LAR may differ leading to different sets of hyper-parameters for each zone.
  • a different covariance function may also be used for each zone.
  • Each covariance function 15 and set of hyper-parameters 14 may then be passed to the aircraft 100 for use in operations 3.
  • the step of predicting the LAR using the covariance function 15 may first comprise identifying which zone the currently observed parameters are located in.
  • the covariance function 15 and hyper-parameters 14 are then used to predict the LAR.
  • Methods in accordance with the present embodiment may further reduce the amount of computation that must be carried out by the weapons system as only the inducing-points u relating to the current zone need be considered during the playback calculation.
  • different correction factors may be applied to each of the different zones 208.
  • the missile performance is found to be different from that predicted in a given zone 208, the results produced by the covariance function 15 corresponding to that zone may be scaled accordingly.
  • the present embodiment allows such scaling to be carried out by varying a single 'correction' parameter. Accordingly, systems using the present embodiment may be more flexible and easier to update than prior art systems.
  • Figure 5 shows a variation of the parameter space 200 and zones 208 of Figure 4 .
  • the same reference numerals denote substantially similar elements. Only those aspects of Figure 5 which differ significantly from Figure 4 will be discussed.
  • each of the four zones 208 occupies a different region of the parameter space 200.
  • three zones 208a to c are shown, and the first zone 208a overlaps with and is contained completely within a second zone 208b.
  • a third zone 208c partially overlaps with zone 208b at a location spaced apart from zone 208a.
  • zones may allow performance of the missile to be limited in a particular region, for example if missile launch in zone 208a posed unacceptable risks, the output of the covariance function 15a could be scaled such that a LAR is rarely achievable within this zone.
  • a list giving the order in which zones are to be investigated in order to identify whether a given parameter combination is located within that zone is passed to the weapon system along with the covariance function 15 and hyper parameters 14. For example, a point in zone 208a is also geometrically in zone 208b, thus the algorithm must check whether a point is in zone 208a before considering if the point is in zone 208b in order for the zone 208a model to be used.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)
EP17172972.6A 2017-05-25 2017-05-25 Missionsplanung für waffensysteme Ceased EP3407004A1 (de)

Priority Applications (7)

Application Number Priority Date Filing Date Title
EP17172972.6A EP3407004A1 (de) 2017-05-25 2017-05-25 Missionsplanung für waffensysteme
EP18724986.7A EP3631344A1 (de) 2017-05-25 2018-05-17 Missionsplanung für waffensysteme
US16/614,857 US11029130B2 (en) 2017-05-25 2018-05-17 Mission planning for weapons systems
IL270798A IL270798B2 (en) 2017-05-25 2018-05-17 Mission planning for weapons systems
PCT/GB2018/051338 WO2018215738A1 (en) 2017-05-25 2018-05-17 Mission planning for weapons systems
CA3064158A CA3064158A1 (en) 2017-05-25 2018-05-17 Mission planning for weapons systems
AU2018273014A AU2018273014B2 (en) 2017-05-25 2018-05-17 Mission planning for weapons systems

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP17172972.6A EP3407004A1 (de) 2017-05-25 2017-05-25 Missionsplanung für waffensysteme

Publications (1)

Publication Number Publication Date
EP3407004A1 true EP3407004A1 (de) 2018-11-28

Family

ID=59014453

Family Applications (1)

Application Number Title Priority Date Filing Date
EP17172972.6A Ceased EP3407004A1 (de) 2017-05-25 2017-05-25 Missionsplanung für waffensysteme

Country Status (1)

Country Link
EP (1) EP3407004A1 (de)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114118758A (zh) * 2021-11-20 2022-03-01 中国人民解放军32181部队 一种基于多视图的武器装备任务剖面建模方法和系统

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000036362A1 (en) * 1998-12-12 2000-06-22 Bae Systems Plc Combat pilot aid system
WO2008129435A2 (en) * 2007-04-18 2008-10-30 Alenia Aeronautica Spa A method and a system for estimating the impact area of a military load launched from an aircraft

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000036362A1 (en) * 1998-12-12 2000-06-22 Bae Systems Plc Combat pilot aid system
WO2008129435A2 (en) * 2007-04-18 2008-10-30 Alenia Aeronautica Spa A method and a system for estimating the impact area of a military load launched from an aircraft

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
BISHOP, C.M.: "Neural Networks for Pattern Recognition", 2005, OXFORD UNIVERSITY PRESS
CARL EDWARD RASMUSSEN ET AL: "Gaussian Processes for Machine Learning (GPML) Toolbox", JOURNAL OF MACHINE LEARNING RESEARCH, MIT PRESS, CAMBRIDGE, MA, US, vol. 11, 1 December 2010 (2010-12-01), pages 3011 - 3015, XP058336466, ISSN: 1532-4435 *
D. NICHOLSON: "Defence Applications of Agent-Based Information Fusion", THE COMPUTER JOURNAL, vol. 54, no. 2, 1 February 2011 (2011-02-01), pages 263 - 273, XP055004119, ISSN: 0010-4620, DOI: 10.1093/comjnl/bxq045 *
QUINONERO-CANDELA J.; RASMUSSEN C.E.: "A unifying View of Sparse Approximate Gaussian Process Regression", JOURNAL OF MACHINE LEARNING RESEARCH, vol. 6, 2005, pages 1939 - 1959, XP058214845
RASMUSSEN C.E; WILLIAMS C.K.I: "Gaussian Process for Machine Learning", 2006, THE MIT PRESS
SHIN, J.Q; CHOI, T.: "Gaussian Process Regression Analysis for Functional Data", 2011, CRC PRESS
SONG KYUNGWOO ET AL: "Data-driven ballistic coefficient learning for future state prediction of high-speed vehicles", 2016 19TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), ISIF, 5 July 2016 (2016-07-05), pages 17 - 24, XP032934988 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114118758A (zh) * 2021-11-20 2022-03-01 中国人民解放军32181部队 一种基于多视图的武器装备任务剖面建模方法和系统
CN114118758B (zh) * 2021-11-20 2023-07-18 中国人民解放军32181部队 一种基于多视图的武器装备任务剖面建模方法和系统

Similar Documents

Publication Publication Date Title
Battistini et al. Differential games missile guidance with bearings-only measurements
Lu et al. Rapid generation of accurate entry landing footprints
Chai et al. Improved gradient-based algorithm for solving aeroassisted vehicle trajectory optimization problems
Hu et al. Maneuver mode analysis and parametric modeling for hypersonic glide vehicles
WO2017014085A1 (ja) 航空機管理装置、航空機、及び航空機の軌道算出方法
US11029130B2 (en) Mission planning for weapons systems
Yun et al. Missile guidance law estimation using modified interactive multiple model filter
US6473747B1 (en) Neural network trajectory command controller
Chai et al. An interactive fuzzy physical programming for solving multiobjective skip entry problem
KR20220113205A (ko) 고기동 표적의 동특성 추정 및 다중경로 억제를 통한 정밀 궤적예측 방법 및 장치
Kim Engagement-scenario-based decoy-effect simulation against an anti-ship missile considering radar cross section and evasive maneuvers of naval ships
Sinclair et al. Optimal and feedback path planning for cooperative attack
EP3407004A1 (de) Missionsplanung für waffensysteme
Shalumov Online launch-time selection using deep learning in a target–missile–defender engagement
US9777995B2 (en) System and method for displaying weapon engagement feasibility
Cervantes et al. Classification and engineering analysis of solid propellant missile telemetry data
EP2876401A1 (de) Systemintegration
Choi et al. Neural network guidance based on pursuit-evasion games with enhanced performance
GB2563011A (en) Mission planning for weapons systems
CN115358098A (zh) 一种远场安全性分析方法、系统、电子设备及存储介质
Yuksek et al. Optimization of Allocation and Launch Conditions of Multiple Missiles for Three‐Dimensional Collaborative Interception of Ballistic Targets
Ross et al. Implementation lessons and pitfalls for real‐time optimal control with stochastic systems
Weintraub et al. An optimal-stochastic aircraft defense strategy for the active target defense scenario
Alpert Normalized analysis of interceptor missiles using the four-state optimal guidance system
Yihan et al. Research on intent recognition method for non-cooperative satellite based on LSTM network

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED

18R Application refused

Effective date: 20181214