System, method and computer program product for interception of vehicular threats

Abstract

Method for defending an area from vehicular threats in the area's vicinity, comprising detection of threat scenarios including vehicular threats in the area's vicinity in real time or near-real time; and / or controlling multiple interceptors to intercept at least some of the vehicular threats as detected; and / or using a machine learning hardware processor, trained on training data which may pair scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors, and / or to feed said mission plans to the interceptor control processor, in real time.

Description

[0001] System, Method And Computer Program Product For Interception Of Vehicular Threats

[0002] FIELD OF THIS DISCLOSURE

[0003] The present invention relates generally to machine learning arts and more particularly to machine learning interception of vehicular threats.

[0004] BACKGROUND FOR THIS DISCLOSURE

[0005] Allocation of targets is a difficult problem. The number of interceptors is necessarily limited. Also, the cost of interception is often extremely high, whereas defensive budgets are necessarily limited.

[0006] Korean patent document KR102223093 Bl describes a method for preventing a hostile drone from entering a prohibited zone in an authorization zone. The method is configured for predicting a flight path of the first drone according to the determination result and calculating at least one collision predicted point for each flight path based on the predicted flight path and speed of the first drone, and transmitting coordinate information for the calculated collision predicted point to at least one response drone.

[0007] Chinese patent document CN114756049A describes target allocation which takes into account combat advantage index parameters of friendly UAVs relative to enemy UAVs, as well as the threat situation index parameters and target value index parameters of the enemy UAVs relative to friendly UAVs. According to the combat advantage index parameters, threat situation index parameters and target value index parameters are used to compute a comprehensive situation function, and a target allocation model is constructed accordingly, solving the problem of unbalanced target allocation using an improved Hungarian algorithm.

[0008] Chinese patent document CN113190041 describes an online target allocation method based on constraint relaxation technology, which belongs to the field of UAV target allocation technology, including:

[0009] Step 1 : Obtaining target UAV data and interceptor data; wherein the target UAV data includes the number, location, speed, and threat level of UAVs; the interceptor data includes the number, location, and speed of interceptors;

[0010] Step 2: Constructing a target allocation model with constraints based on the target UAV data and interceptor data; Step 3 : Calculating and obtaining an optimal solution of the target allocation model that satisfies the constraint conditions, and taking the optimal solution as the UAV target allocation result.

[0011] The disclosures of all publications and patent documents mentioned in the specification, and of the publications and patent documents cited therein directly or indirectly, are hereby incorporated herein by reference in their entirety. If the incorporated material is inconsistent with the express disclosure herein, the interpretation is that the express disclosure herein describes certain embodiments, whereas the incorporated material describes other embodiments. Definition / s within the incorporated material may be regarded as one possible definition for the term / s in question.

[0012] GENERAL SUMMARY

[0013] Certain embodiments seek to provide a system, method, and computer program product for artificially intelligent interception which uses (typically Machine Learning driven) scenario simulation to determine a solution to intercept multiple vehicular threats.

[0014] Certain embodiments of the present invention seek to provide circuitry typically comprising at least one processor in communication with at least one memory, with instructions stored in such memory executed by the processor to provide functionalities which are described herein in detail. Any functionality described herein may be firmware-implemented or processor-implemented, as appropriate.

[0015] Certain embodiments seek to provide a system, method, and computer program product for interception of penetrating typically aerial vehicles.

[0016] Certain embodiments seek to provide a system, method, and computer program product for interception of penetrating typically aerial vehicles with ML functionality, wherein the ML (machine learning) typically learns relationship between scenario characteristics and / or characteristics of a mission plan that was used on that scenario, on the one hand, and outcome (binary or parameterized), on the other hand.

[0017] Certain embodiments seek to provide a system, method, and computer program product for detecting and intercepting threats e.g., aerial drones, where the system, method, or computer program product may include all or any subset of: a. Aircraft detection systems using a radar system that receives returns from sources, or an airborne radar on a manned or unmanned aircraft; and / or b. Any distributed launch group of aircraft for interception, from several locations along the defense areas; and / or c. Any diverse aircraft used for interception, e.g., using bullets, capable of moving at different speeds to and between the threats, and slowing down to the speed of movement for the purpose of completing the interception, through an automatic setup and control system. It is possible to combine interceptors with different propulsion methods, such as piston and jet engines, for different times, and different arrival speeds; and / or d. Any computerized control system linking the detection means, and the launchers, the interception tools, which may provide feedback e.g., interception outcomes to a machine learning module which, once trained, provides scenarios to be executed to the control system; and e. A hardware processor configured as a scenario generator which may generate scenarios to serve as training data for the machine learning module.

[0018] It is appreciated that any reference herein to, or recitation of, an operation being performed is, e.g. if the operation is performed at least partly in software, intended to include both an embodiment where the operation is performed in its entirety by a server A, and also to include any type of “outsourcing” or “cloud” embodiments in which the operation, or portions thereof, is or are performed by a remote processor P (or several such), which may be deployed off-shore or “on a cloud”, and an output of the operation is then communicated to, e.g. over a suitable computer network, and used by, server A. Analogously, the remote processor P may not, itself, perform all of the operations, and, instead, the remote processor P itself may receive output / s of portion / s of the operation from yet another processor / s P', may be deployed off-shore relative to P, or “on a cloud”, and so forth.

[0019] The present invention typically includes at least the following embodiments:

[0020] Embodiment 1. A system for defending an area from vehicular threats in the area’s vicinity, the system comprising all or any subset of: i. at least one detection apparatus for detection of vehicular threats which occur in the area’s vicinity in real time or near-real time; ii. an interceptor control processor for controlling multiple interceptors to intercept at least vehicular threats detected by the detection apparatus; and iii. a (typically machine learning) hardware processor which is trained on training data which pairs threat interception scenarios, each specifying vehicular threats which occurred during the scenario, to their respective outcomes, wherein each outcome specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario were or were not intercepted, wherein the machine learning (e.g.) hardware processor is trained, on the training data, to generate at least one mission plan for controlling at least one of the multiple interceptors, and to feed the mission plans to the interceptor control processor, in real time.

[0021] Embodiment 2. A system according to any of the preceding embodiments and also comprising: iv. a scenario simulator including a hardware processor configured to generate the training data including simulating artificial threat scenarios and / or to generate mission plans for each of the artificial threat scenarios.

[0022] Embodiment 3. A system according to any of the preceding embodiments wherein each scenario has scenarios characteristics including at least one of the number of threats, their incoming trajectory (source, speed, angle), threat characteristics, e.g., min / max speed, interceptor characteristics, e.g., min / max speed, and cloudiness of the vicinity.

[0023] Embodiment 4. A system according to any of the preceding embodiments wherein outcome characteristics may include a weighted combination of intercepted threats.

[0024] Embodiment 5. A system according to any of the preceding embodiments wherein mission plan characteristics may include all or any subset of how many interceptor / s to use and which interceptor / s to use, from among a population of available interceptors; which vehicular threats will be targeted by each interceptor; a duration and velocity to define a duration, during which a higher-than-threat velocity is used to enable interceptor to close in on threat or target, after which the interceptor slows to match the threat’s velocity; for each interceptor assigned to plural vehicular threats, an order in which the vehicular threats are to be intercepted; flight altitude / s for each interceptor, during each of at least one stage of each interceptor’s operation, such as first try, second try, etc. firing angle and / or direction of approach, for each threat; and if-then logic to describe whether or not to turn around and make a second try, and / or whether or not to activate additional interceptors, and / or whether or not to continue firing, as a function of a logical condition. Embodiment 6. A system according to any of the preceding embodiments and also comprising at least one interceptor equipped with at least one gun or at least one machine gun.

[0025] Embodiment 7. A system according to any of the preceding embodiments and also comprising at least one interceptor equipped with a laser target intercepting mechanism.

[0026] Embodiment 8. A system according to any of the preceding embodiments wherein at least one interceptor operates according to the following stages, for at least one threat T: A approach threat T B first attempt to intercept threat T aka 1 st try C turnaround

[0027] D match velocity of threat T

[0028] E second attempt to intercept threat T aka 2nd try and wherein the mission plan includes parameterization of at least one of the above stages.

[0029] Embodiment 9. A system according to any of the preceding embodiments wherein each threat interception scenario in the training data includes a mission plan P for intercepting threats detected within the scenarios.

[0030] Embodiment 10. A system according to any of the preceding embodiments wherein the mission plan P includes at least one if-then decision point comprising a logical condition and at least one alternative carried out by at least one of the interceptors, depending on whether the logical condition is true or false.

[0031] Embodiment 11. A system according to any of the preceding embodiments and wherein the machine learning processor continues to train itself while the system is operational, including receiving feedback on system operation which includes at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario, the scenario including a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by at least one of the multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted. Embodiment 12. A system according to any of the preceding embodiments wherein the outcome comprises an optical Operational Success Indication of whether or not interception was achieved.

[0032] Embodiment 13. A system according to any of the preceding embodiments wherein the outcome comprises a radar-detected Operational Success Indication of whether or not interception was achieved.

[0033] Embodiment 14. A system according to any of the preceding embodiments wherein each scenario has plural parameters, such as how many threats exist and how many interceptors exist, and how many bullets each interceptor has, and wherein each of the plural parameters has an allowed range, and wherein the scenario simulator comprises a Scenario Generator, which generates a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within the individual one parameter’s allowed range.

[0034] Embodiment 15. A system according to any of the preceding embodiments and wherein, during training of the machine learning processor, an Initial Interception Response Generator, using a response model, generates interception responses and / or mission plans by randomly selecting a solution or an interception response, from an approximate parameter domain.

[0035] Embodiment 16. A system according to any of the preceding embodiments and wherein outcomes are saved in a state machine, which updates the response model regarding at least one scenario.

[0036] Embodiment 17. A system according to any of the preceding embodiments wherein at least one ongoing scenario includes at least one “step" in which at least one “major” event occurs during the scenario, where “major” refers to any event which requires an additional ML evaluation, and sending an updated recommended mission plan for approval to a human operator.

[0037] Embodiment 18. A system according to any of the preceding embodiments wherein at least one of the following events is defined as “Major”: detection of at least one additional target in the course of the scenario, successful interception, missed interception pass, number of bullets available to an individual interceptor descends below a level expected to suffice for completion of the interception passes assigned to the individual interceptor.

[0038] Embodiment 19. A system according to any of the preceding embodiments wherein the vicinity is within a field of view of the detection apparatus and wherein the detection detects each vehicular threat as it enters the vicinity.

[0039] Embodiment 20. A system according to any of the preceding embodiments and also comprising at least one interceptor equipped with at least one of: a jet engine; at least one folding wing at least one fixed wing a turbine propulsion system,

[0040] Multi rotor propulsion, and an internal combustion propulsion system.

[0041] Embodiment 21. A system according to any of the preceding embodiments wherein the interceptor control processor stores dynamic and aerodynamic model / s of at least one of the multiple interceptors.

[0042] Embodiment 22. A system according to any of the preceding embodiments wherein the multiple interceptors comprise at least one drone.

[0043] Embodiment 23. A system according to any of the preceding embodiments wherein the at least one detection apparatus is configured for predicting a trajectory of at least one target using at least one of the following:

[0044] Kalman Filter,

[0045] Extended Kalman filter,

[0046] Alpha Beta Gamma Filter,

[0047] Wiener filter,

[0048] Monte Carlo Filter

[0049] H - infinity Filter.

[0050] Embodiment 24. A system according to any of the preceding embodiments wherein the at least one detection apparatus comprises more than one detection apparatus. Embodiment 25. A system according to any of the preceding embodiments and also comprising at least one apparatus for surveillance other than the at least one detection apparatus.

[0051] Embodiment 26. A system according to any of the preceding embodiments wherein the at least one detection apparatus comprises at least one airborne detection apparatus.

[0052] Embodiment 27. A system according to any of the preceding embodiments wherein the at least one interceptor is equipped with at least one bullet or multiple bullets arranged in a barrel.

[0053] Embodiment 28. A system according to any of the preceding embodiments wherein the at least one interceptor is equipped with bullet-counting functionality configured to transmit a number of remaining bullets to the interceptor control processor.

[0054] Embodiment 29. A system according to any of the preceding embodiments wherein the machine learning hardware processor comprises a Deep learning and artificial intelligence processor of one of the following types:

[0055] • GPU (Graphics Processing Unit) or

[0056] • FPGA (Field programmable gate arrays) or

[0057] • ASIC (application-specific integrated circuits).

[0058] Embodiment 30. A method for defending an area from vehicular threats in the area’s vicinity, the method comprising: i. detection of threat scenarios including plural vehicular threats in the area’s vicinity in real time or near-real time; ii. controlling multiple interceptors to intercept at least some of the plural vehicular threats as detected; and iii. using a machine learning hardware processor, trained on training data which pairs scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors, and to feed the mission plans to the interceptor control processor, in real time.

[0059] Embodiment 31. A method according to any of the preceding embodiments and also comprising iv. a scenario simulator including a hardware processor configured to generate the training data including simulating artificial threat scenarios and / or to generate mission plans for each of the artificial threat scenarios.

[0060] Embodiment 32. A method according to any of the preceding embodiments wherein each scenario has plural parameters such as how many threats exist and how many interceptors exist and how many bullets each interceptor has, and wherein each of the plural parameters has an allowed range, and wherein the scenario simulator comprises a Scenario Generator, which generates a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within the individual one parameter’s allowed range.

[0061] Embodiment 33. A method according to any of the preceding embodiments wherein each scenario has scenario characteristics including at least one of the number of threats, their incoming trajectory (source, speed, angle), threat characteristics, e.g., min / max speed, interceptor characteristics, e.g., min / max speed, and cloudiness of the vicinity.

[0062] Embodiment 34. A method according to any of the preceding embodiments wherein outcome characteristics may include a weighted combination of intercepted threats.

[0063] Embodiment 35. A method according to any of the preceding embodiments wherein mission plan characteristics may include all or any subset of how many interceptor / s to use and which interceptor / s to use, from among a population of available interceptors; which vehicular threats will be targeted by each interceptor; a duration and velocity to define a duration, during which a higher-than-threat velocity is used to enable interceptor to close in on threat or target after which the interceptor slows to match the threat’s velocity; for each interceptor assigned to plural vehicular threats, an order in which the vehicular threats are to be intercepted; flight altitude / s for each interceptor, during each of at least one stage of each interceptor’s operation; firing angle and / or direction of approach, for each threat; and if-then logic to describe whether or not to turn around and make a second try and / or whether or not to activate additional interceptors and / or whether or not to continue firing, as a function of a logical condition.

[0064] Embodiment 36. A method according to any of the preceding embodiments wherein at least one interceptor operates according to the following stages, for at least one threat T: A approach threat T B first attempt to intercept threat T aka 1 st try C turnaround

[0065] D match velocity of threat T

[0066] E second attempt to intercept threat T aka 2nd try and wherein the mission plan includes parameterization of at least one of the above stages.

[0067] Embodiment 37. A method according to any of the preceding embodiments wherein each threat interception scenario in the training data includes a mission plan P for intercepting threats detected within the scenarios.

[0068] Embodiment 38. A method according to any of the preceding embodiments wherein the mission plan P includes at least one if-then decision point comprising a logical condition and at least one alternative carried out by at least one of the interceptors depending on whether the logical condition is true or false.

[0069] Embodiment 39. A method according to any of the preceding embodiments and wherein the machine learning processor continues to train itself while the method is operational, including receiving feedback on method operation which includes at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario, the scenario including a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by at least one of the multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted.

[0070] Embodiment 40. A method according to any of the preceding embodiments and also comprising: iv. simulating artificial threat scenarios and generating mission plans for each of the artificial threat scenarios. Embodiment 41. A computer program product, comprising a non- transitory tangible computer readable medium having computer readable program code embodied therein, the computer readable program code adapted to be executed to implement a method for defending an area from vehicular threats in the area’s vicinity, the method comprising: i. detection of threat scenarios including plural vehicular threats in the area’s vicinity in real time or near-real time; ii. controlling multiple interceptors to intercept at least some of the plural vehicular threats as detected; and iii. using a machine learning processor, trained on training data which pairs scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors and to feed the mission plans to the controller, in real time.

[0071] Embodiment 42. A computer program product according to any of the preceding embodiments and also comprising: iv. a scenario simulator including a hardware processor configured to generate the training data including simulating artificial threat scenarios and / or to generate mission plans for each of the artificial threat scenarios.

[0072] Embodiment 43. A computer program product according to any of the preceding embodiments wherein each scenario has plural parameters, such as how many threats exist and how many interceptors exist, and how many bullets each interceptor has, and wherein each of the plural parameters has an allowed range, and wherein the scenario simulator comprises a Scenario Generator, which generates a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within the individual one parameter’s allowed range.

[0073] Embodiment 44. A computer program product according to any of the preceding embodiments wherein each scenario has scenarios characteristics including at least one of: the number of threats, their incoming trajectory (source, speed, angle), threat characteristics e.g., min / max speed, interceptor characteristics, e.g., min / max speed, and cloudiness of the vicinity.

[0074] Embodiment 45. A computer program product according to any of the preceding embodiments wherein outcome characteristics may include a weighted combination of intercepted threats. Embodiment 46. A computer program product according to any of the preceding embodiments wherein mission plan characteristics include all or any subset of: how many interceptor / s to use and which interceptor / s to use, from among a population of available interceptors; which vehicular threats will be targeted by each interceptor; a duration and velocity to define a duration, during which a higher-than-threat velocity is used to enable interceptor to close in on threat or target, after which the interceptor slows to match the threat’s velocity; for each interceptor assigned to plural vehicular threats, an order in which the vehicular threats are to be intercepted; flight altitude / s for each interceptor, during each of at least one stage of each interceptor’s operation such as first try, second try etc.; firing angle and / or direction of approach, for each threat; if-then logic to describe whether or not to turn around and make a second try and / or whether or not to activate additional interceptors and / or whether or not to continue firing, as a function of a logical condition.

[0075] Embodiment 47. A computer program product according to any of the preceding embodiments wherein at least one interceptor operates according to the following stages, for at least one threat T: A approach threat T

[0076] B first attempt to intercept threat T aka 1 st try

[0077] C turnaround

[0078] D match velocity of threat T

[0079] E second attempt to intercept threat T aka 2nd try and wherein the mission plan includes parameterization of at least one of the above stages.

[0080] Embodiment 48. A computer program product according to any of the preceding embodiments wherein each threat interception scenario in the training data includes a mission plan P for intercepting threats detected within the scenarios.

[0081] Embodiment 49. A computer program product according to any of the preceding embodiments wherein the mission plan P includes at least one if-then decision point comprising a logical condition and at least one alternative carried out by at least one of the interceptors, depending on whether the logical condition is true or false.

[0082] Embodiment 50. A computer program product according to any of the preceding embodiments and wherein the machine learning processor continues to train itself while the method is operational, including receiving feedback on method operation which includes at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario, the scenario including a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by at least one of the multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted.

[0083] BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Certain embodiments of the present invention are illustrated in the following drawings; in the block diagrams, arrows between modules may be implemented as APIs and any suitable technology may be used for interconnecting functional components or modules illustrated herein in a suitable sequence or order, e.g., via a suitable API / Interface. For example, state of the art tools may be employed, such as but not limited to Apache Thrift and Avro which provide remote call support. Or, a standard communication protocol may be employed, such as but not limited to HTTP or MQTT, and may be combined with a standard data format, such as but not limited to JSON or XML. According to one embodiment, one of the modules may share a secure API with another. Communication between modules may comply with any customized protocol or customized query language or may comply with any conventional query language or protocol.

[0085] Specifically:

[0086] Fig. 1 is a simplified block diagram illustration of an interception system according to certain embodiments.

[0087] Fig. 2 is an example of a scenario provided in accordance with certain embodiments which may be used in conjunction with all or any subset of the components illustrated in Fig. 1 and / or Fig. 3. Fig. 3 is a simplified flowchart illustration of an interception method according to certain embodiments; the method typically comprises all or any subset of the illustrated operations, suitably ordered, e.g., as shown.

[0088] Methods and systems included in the scope of the present invention may include any subset or all of the functional blocks shown in the specifically illustrated implementations by way of example, in any suitable order, e.g., as shown. Flows may include all or any subset of the illustrated operations, suitably ordered, e.g., as shown. Tables herein may include all or any subset of the fields and / or records and / or cells and / or rows and / or columns described.

[0089] DETAILED DESCRIPTION

[0090] Reference is made to Fig. 1 which illustrates a system for defending an area from vehicular threats in the area’s vicinity, according to certain embodiments. As shown, the system may comprise: i. detection apparatus 10 for detection of vehicular threats which occur in the area’s vicinity in real time or near-real time; and / or ii. a hardware processor 30 (e.g. machine learning driven) which is trained on training data which pairs threat interception scenarios, each specifying vehicular threats which occurred during the scenario, to their respective outcomes, wherein each outcome specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario were or were not intercepted, and / or iii. an interceptor control processor 40 for controlling multiple interceptors to intercept at least vehicular threats detected by the detection apparatus.

[0091] The Machine learning hardware processor may comprise a Deep learning and Artificial intelligence processor such as GPU, FPGA or ASIC. More generally, any suitable deep learning and artificial intelligence processor may be used to implement the hardware processor, such as but not limited to those described online in Habana.ai or Al chips generally.

[0092] Artificial intelligence (Al) chips as referred to herein are intended to include any computer chip designed for use in Al applications e.g. for machine learning and / or image recognition and / or NLP aka natural language processing. Al chips typically include devices configured for Al e.g. graphics processing units (GPUs, used e.g. for training Al algorithms) and / or field-programmable gate arrays (FPGAs, used e.g. for inference tasks) and / or application-specific integrated circuits (ASICs - which may be used inter alia for either training or inference).

[0093] Al chips are typically configured to execute a multiplicity of computations in parallel (rather than in series, as in CPUs). Al chips may compute numbers with precision high enough to complete Al algorithms successfully but low enough to lower, relative to ordinary CPUS, the number of transistors required. Al chips may expedite memory access e.g. by storing an entire Al algorithm on a single Al chip. Al chips may use programming languages designed to translate Al computer code for effective execution on board an Al chip. Al chips may perform more computations per energy unit consumed) by using many smaller transistors, rather than less larger transistors.

[0094] The machine learning processor is trained, on that training data, to generate at least one mission plan for controlling at least one of the multiple interceptors and to feed the mission plans to the interceptor control processor, in real time.

[0095] Each outcome may comprise an optical and / or radar-detected Operational Success Indication of whether or not interception was achieved.

[0096] Any mission plan described herein may then be sent to interceptors for execution, including interception of one or more threats. Typically, each mission plan generated as described herein initially exists as a recommendation, which, once approved by a human operator, turns into a mission plan for execution, which is conveyed to the interceptors, which execute the mission plan accordingly.

[0097] It is appreciated that mission plans, e.g., those incorporated within scenarios in the training data and / or those generated by the machine learning processor once trained, may vary in their length and complexity. For example, some scenarios may require only a few minutes to execute and may include no decision points or only a few decision points and may handle only a few threats, all of which may be known at the mission plan’s onset, and other scenarios may require many hours, days, or weeks to execute, and may include many decision points and may handle many threats, some of which may occur while the mission plan is being executed and may not be known at the mission plan’s onset.

[0098] Some scenarios may terminate once all threats present when the scenario began, have either been intercepted or have successfully, from their viewpoint, passed into the area to be defended due to an interception failure, from the system viewpoint. Some scenarios may include if-then logic (implemented in any suitable programming language) describing how to control interceptors, e.g., if at least one new threat is detected in the area’s vicinity after the scenario began; the command which controls the interceptors may include parameters such as the location along the vicinity’s perimeter at which the new threat was detected and its initial velocity and direction.

[0099] If-then logic may also be used in mission plans, e.g., those incorporated within scenarios in the training data and / or those generated by the machine learning processor once trained, to describe whether or not to turn around and make a second try, whether or not to activate additional interceptors, whether or not to continue firing, as a function of (say) whether or not given threat / s assigned to an interceptor have already been intercepted.

[0100] It is appreciated that training data may include at least one mission plan which was generated by a human expert and / or by a computer, using heuristics or rules of thumb applied to a scenario on which the mission plan is to operate.

[0101] For example, the heuristics might specify that interceptor aerial threats or other high-cost interceptors would be used only for a certain subset of scenarios, and not for scenarios which are not included in this subset.

[0102] It is appreciated that the heuristics may not be correct in the sense that subsequently the machine learning may later yield contradictory insights. For example, heuristics may specify that interceptions should be frontal (head-on) or from the rear and not at an angle, whereas the machine learning may result in interception at an angle, in certain scenarios.

[0103] The detection system e.g., airborne or ground radar or other suitable typically low frequency detection radar, or optical detection system, or other spectrum frequency based detection systems provides, e.g., to the interceptor control processor, indications of positions and / or velocities of detected vehicular threats aka incoming targets, which may enter the target’s detection range and direction to the vicinity of the area to be protected.

[0104] The simulator typically provides scenarios, fortraining purposes, to the machine learning module, which, once trained, generates mission plans for the interceptor control processor. It is appreciated that each such machine-generated or “recommended” mission plan is typically vetted by a human, via a suitable user interface. The user interface may enable the human to simply approve (or not) the machine-generated mission plan and / or the interface may enable the human to modify, e.g., to alter parameters of, the machine-generated version of the plan. Typically, the mission plans executed by the interceptors are only those approved by the human, via the interface.

[0105] Any suitable machine learning module may be employed; the module may, for example, include a Scenario Generator, which generates a multiplicity of scenarios randomly by selecting changeable scenario parameters randomly, from allowed ranges defined for each of the changeable scenario parameters. An Initial Interception Response Generator may operate even before a learning system is in place and may be based on an approximate parameter domain including (human-generated, e.g.,) approximations for each of plural changeable scenario parameters, and random selection of a solution from the approximate domain. Outcome / s or any result measurements may be saved in a state machine, which typically gradually updates the system response model, in relation to each scenario.

[0106] The ML module may generate scenarios periodically and / or or each time a previous scenario has been completed and / or upon demand and / or responsive to having been triggered by an external event and / or continually.

[0107] The ML module may for example stipulate, e.g., in each mission plan generated, how many interceptors should be launched and / or positions, e.g., along the perimeter of the area to be defended, from which each interceptor should be launched, and / or trajectories which each interceptor, once launched, should follow and / or which threats are assigned to each interceptor and / or an order in which threats, assigned to a given interceptor, should be intercepted thereby, and / or a direction from which a given threat is to be intercepted and / or any other mission plan parameter and / or which angular velocity should be used.

[0108] The initial scenarios which may include mission plans, and paired outcomes which may also be generated by the simulator by digitally applying a digital mission plan to threats specified in a given digital scenario, may be provided to the ML module, and may serve as training data. Typically, however, even after the ML module is trained and operational, new training data typically flows back from processor 40 to the ML module during operation, to further improve the ML module’s model accuracy, typically in real time.

[0109] Each outcome may indicate which threats were intercepted and which were not, and may also indicate the total cost of interception of these threats, e.g., the cost of operation of intercepting threats 1, 2 and 3, including failed interceptions occurring as part of the mission plan, using high cost interceptors in a first scenario, vs. the cost of operation of intercepting perhaps the same threats 1, 2 and 3, again included failed interceptions, using low cost interceptors this time, in a second scenario which is the same of the first, but has been paired with a different mission plan which uses different interceptors. Each outcome may also indicate the total effect of interception, e.g., by computing a weighted sum of threats intercepted, where each threat is weighted by its value, e.g., a highly lethal threat may have a larger weight than a low-lethality threat. For example, a weight of 7 may be assigned to each intercepted fast drone, whereas a weight of 2 may be assigned to each intercepted slow drone.

[0110] Outcomes may include any suitable characteristics, including but not limited to all or any subset of: how many drones reached the area without being intercepted, which drones were / were not intercepted, (weighted) combination of all these individual typically binary outcomes, which interceptor / s intercepted each drone and in which stage and at which velocity, upon interception, of target and / or of interceptor.

[0111] Typically, processor 40, which is typically ground-based, provides communications to interceptor launch systems and / or to interceptors. The interceptors, which are typically aerial, may or may not be within the interceptor control processor’s line of sight. For interceptors beyond the line of sight, an indirect transponder (e.g. airborne) may be employed.

[0112] Execution status comprises an indication to processor 40, from systems onboard interceptors, and / or from the detection system, that interception was / was not successful, and / or an indication, e.g., from systems on-board interceptors, of interceptor’s position and / or velocity and / or an indication of how much ammunition and / or fuel has been expended by vs. remains available to, the interceptor. Typically, an interception is considered “successful” if a threat detected in the vicinity of the area to be protected, is intercepted before that vehicular threat can proceed into the area to be protected.

[0113] It is appreciated that interception success may or may not be a binary parameter. While, typically, an interception may be said to have either success or failed, alternatively, degrees of success / failure may be defined, e.g., one or more degrees of partial interception of a threat, intervening between complete success in interception on the one hand, and complete failure to intercept, on the other hand. An ongoing scenario may be said to have a “step" when a “major” event occurs during the scenario, where “major” refers to any event which requires an additional ML evaluation of the situation and an update for the mission recommendation to the operator (human). The recommendation, as usual, typically, once approved, turns into a mission plan, which may then be sent to the interceptors. Any suitable events may be defined as “major” such as all or any subset of the following: detection of an additional target in the course of the scenario, successful interception, missed interception pass, and / or reduction of bullets available to an interceptor below a level expected to suffice for completion of the planned interception passes.

[0114] Certain embodiments seek to provide a system which generates mission plans which include at least one built-in if-then statement. Mission plan characteristics may include at least one condition which may be defined over (typically dynamic) scenario characteristics, e.g., whether or not given threat / s assigned to an interceptor have already been intercepted (e.g. as determined by the interceptor’s firing control system or imaging and image-processing system or radar), or whether or not cloudiness has increased to above a threshold, or whether or not new threats, not present when the mission plan began to be executed, have now emerged in the vicinity, and at least one consequence parameter paired to the condition which define the consequence to be executed by the interceptors, if the condition is true (e.g. that a specific set of interceptors will, at velocity v and from angle a, shoot at non-intercepted threat t, in which case v, a, and t are all consequence parameters).

[0115] In mission plans, consequences may be defined in terms of other systems, e.g., “interceptor 5 on threat 2, using parameters determined by interceptor 5’s firing control system”.

[0116] Each interceptor may be equipped with interception control software and / or a firing control system and / or threat imaging functionality and / or an image-processing system.

[0117] Each interceptor may include a motor whose power suffices to enable the interceptor to achieve a chasing speed high enough to approach within firing distance of a threat, fast enough to enable the threat to be intercepted before the threat reaches the area to be protected, and may comprise means for reducing the power, low enough to enable the interceptor to match the threat’s velocity when chasing the threat.

[0118] Each interceptor, e.g., drone may include an odometer and / or an optical camera which may provide time-stamped visual imagery indicative of whether or not interception was successful, and at which point in time, which enables the system to determine which firing attempt was the successful one, given that firing attempts are also typically recorded, time-stamped, by the system. Interceptors may be equipped with munition cartridges storing any suitable ammunition, such as but not limited to airburst rounds, bullets, shells, or grenades. Any suitable motor may be used for each interceptor, such as but not limited to reciprocating or rotary piston engines, turboshaft engines, turbojet engines, turbofan engines, pulse detonation motors, solid rocket motors, or even battery-driven motors.

[0119] The system may have tables in memory which identify attributes of interceptors such that the system knows that a given type of interceptor has, say, a minimum velocity of v, a maximum velocity or (maximum possible dash speed) of V, R rounds in its munition cartridge / s and certain fuel tank size and fuel requirements and / or batteryoperation parameters, for battery-operated interceptors.

[0120] According to certain embodiments, interception is prohibited in certain regions of the vicinity; this data can be fed to the system which then generates only mission plans which always conduct interception only outside such regions.

[0121] Advantages of embodiments herein include optimizing (reducing) cost of interception, and / or optimizing (increasing) probability of successful interception reflected in less threats reaching the area to be protected, for example, as a result of successful learning of changing patterns of threat penetration. For example, as a reaction to the defending party, the offensive party may have new considerations governing their attacking strategy; however, these new considerations are gradually learned by the system herein. Alternatively, or in addition, due to the many interacting variables, many of them change in real time, which characterize both the scenario and the mission plan, for each of the interceptors. Better optimization is achieved even if the patterns of threat penetration are uniform and do not change over time, given that due to the number of, and rate of change of, the parameters themselves, it is effectively impossible to generate optimal mission plans using known methods. Apart from the inherent advantage of achieving cost effective interception, there is also a defensive advantage, given that the attacking side may later present more sophisticated threats, typically aerial, which require more sophisticated interceptors; thus the system herein which optimizes interception including minimizing cost of interceptors employed, has the effect of conserving such interceptors toward such time in the future, as and when they may be needed. FIG. 2 is a simplified pictorial illustration of an example interception scenario which may be provided in accordance with an embodiment. In this specific scenario, the detection system 10 of Fig. 1 detects and locates two incoming enemy drones c and d. Dashed lines are used to identify trajectories or subsequent positions of a given interceptor, such as each of interceptors A and B in the illustrated example.

[0122] Typically, Fig. 1’s ML system 30 recommends an interception scenario to an operator, which approves interception mission to launch system and to interceptors 50. Interceptor A is launched first, in the example, followed by Interceptor B. At time tl, Interceptor A attempts head-on interception of drone c. After the pass, an outcome, e.g., success or failure in downing drone c, is reported to the ML system 30. The ML 30updates its interception scenario every time a report of success or failure is received. At time t2, Interceptor B either attempts a head-on interception of drone c, if drone c was missed by Interceptor A, or continues to other enemy drones if Interceptor A was successful in downing drone c.

[0123] At time t3, Interceptor A which may itself be a drone, attempts to intercept head-on enemy drone d, then reports success or failure. If outcome = failure, the ML system 30 may replan a follow-up interception attempt. Interceptor A completes a turnaround at time t5, in the example, closes in on drone d in drone d’s new position d2, and makes interception attempts at time t7, until successful, or until Interceptor A runs out of bullet munition. At time 4, Interceptor B attempts to intercept head-on enemy drone e, and reports success or failure. If outcome = failure, the ML system 30 may replan a follow-up interception attempt. Interceptor B completes a turnaround at time t6, in the illustrated example, closing in on drone d at drone d’s new position e2. B makes interception attempt / s at time 8, and typically onward, until successful, or until B runs out of bullet munition. Typically, throughout the scenario, after every report of success or failure, the ML system replans and updates a system interception scenario recommendation. The updates may be received from either the detection system 10 or from the Interceptors 50 such as interceptors A and / or B, e.g., in the form of execution status data generated by interceptors. Typically, systems on the interceptor generate an output which indicates whether or not an interception was successful.

[0124] Fig. 3 is a simplified flowchart illustration of a method for defending an area from vehicular threats, to be intercepted in the area’s vicinity, which may for example be performed using the system of Fig. 1. The method may for example include all or any subset of the following operations, suitably ordered, e.g., as follows:

[0125] Operation 310. Detection of threat scenarios including plural vehicular threats in the area’s vicinity in real time or near-real time;

[0126] Operation 320. Controlling multiple interceptors to intercept at least some of the plural vehicular threats as detected; and

[0127] Operation 330. Using a machine learning processor, trained on training data which pairs scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors and

[0128] Operation 340. To feed the mission plans to the interceptor control processor, in real time.

[0129] Many variations of the method of Fig. 3 are possible. For example, all or any subset of the following functionalities may be provided: a. Detection at a range far enough from the target of the attack to allow a response time long enough to send an aircraft (e.g., drone) and timely complete acquiring and intercepting enemy drones before these reach their own targets which are typically within the area to be defended; b. Decision-making by a learning system, which takes into account locations of launchers, and / or locations of known enemy drones, and / or patterns of arrival of additional enemy drones following them, e.g., based on previous events and / or cloud cover and / or weather disturbance, and / or velocity of threats, and / or maximum and / or minimum speed of interceptors and / or their respective delay times (all or any subset of which, like other parameters and quantities described herein, may be stored in the system, for all available types of interceptors), times of interception, and distances and times required to pass between enemy drones; typically the ML system learns to make decisions to send out plural interceptors, e.g., aircraft to intercept, from positions, at times and on routes, which result in maximum operational benefit; the system may have functionality to define operational benefit quantitatively, e.g., by combining various data into a single scalar. c. Simulating and training the learning system, using a scenario generator that simulates parameters suitable for initial preparation of the system for operation, and learning from real events. d. Monitoring outcome, e.g., success in interception, and completing a maximum number of interceptions, to gradually improve decision-making based on detections effected by detection system / s 10, and / or fire control system / s on the aircraft. e. Planning trajectory / ies (using simulations and / or experiments, and / or actual successes during previous operational sessions) which route interceptors in relation to threats to maximize interception probability. For example, the machine learning functionality will eventually yield matched velocities and matched altitudes (which match interceptors’ velocities and altitudes to those of targets assigned to those interctors respectively, which will enable interceptors to close in on targets successfully and hence to intercept successfully. f. Determining outcome optically and / or using radar, e.g., whether interception succeeded and / or within how many interception attempts, success being operationalized, e.g., in terms of the number of projectiles used, and / or in terms of extent of success of shooting down vehicular threats, e.g., drones.

[0130] Moreover, outcomes may comprise an optical and / or a radar-detected Operational Success Indication of whether or not interception of a given threat or target was achieved by a given interceptor. Outcomes may be saved in a state machine, which updates the response model regarding at least one scenario.

[0131] An ongoing scenario may include at least one “step” in which at least one “major” event occurs during the scenario, where “major” refers to any event which requires an additional ML evaluation, and sending an updated recommended mission plan for approval to a human operator. “Major” events may include all or any subset of the following: detection of at least one additional target in the course of the scenario, successful interception, missed interception pass, and / or number of bullets available to an individual interceptor descends below a level expected to suffice for completion of the interception passes assigned to the individual interceptor.

[0132] Also, scenarios may have plural parameters, such as but not limited to all or any subset of: how many threats exist and how many interceptors exist, and how many bullets each interceptor has. Each of the plural parameters may have an allowed range. The scenario simulator 20 of Fig. 1 may include a Scenario Generator, including a hardware processor configured to generate a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within the individual one parameter’s allowed range.

[0133] During training of the machine learning processor, an Initial Interception Response Generator may be provided, which, typically using a response model, generates interception responses and / or mission plans by selecting a solution or an interception response, from an approximate parameter domain.

[0134] Other possible variations include: a.at least one interceptor handled by the system may be equipped with a jet engine and / or with a laser target intercepting mechanism and / or with at least one folding or fixed wing and / or with a turbine propulsion system, and / or with an internal combustion propulsion system and / or with at least one bullet or multiple bullets arranged in a barrel and / or bullet-counting functionality which may be configured to transmit a number of remaining bullets to the interceptor control processor. b.At least one mission plan P may include if-then decision point / s each comprising a logical condition and altemative / s carried out by interceptor / s, depending on whether the logical condition is true or false.

[0135] For example, the logical condition may be: if all targets assigned to a given interceptor I in a first try defined by a mission plan in a given scenario were intercepted during the first try, end; else turn around and carry out a second try, defined by the mission plan in the given scenario, to intercept targets not intercepted during the first try, in a certain order defined by the second try. Any suitable programming language may be used to represent if-then statements, or even natural language. c.The machine learning processor may continue to train itself while the system is operational, e.g. including receiving feedback on system operation which includes scenarios e.g. at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario. The scenario may include a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by one or more of the multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted.

[0136] Typically, the feedback on system operation is provided to the ml-processor, by the interceptor control processor. It is appreciated that the border between the area’s vicinity which is within the field of view of the detection apparatus, on the one hand, and between the area to be defended, on the other hand, is typically considered a No Pass Line, in which case the outcome typically specifies which threats were intercepted before the threat reached the no-pass line.

[0137] It is appreciated that outcome may also comprise cost indications, e.g., the number of bullets which an interceptor expended in order to intercept threat / s aka targets assigned to that interceptor in a given scenario; typically if outcome is a weighted combination of interceptions and cost indications, interceptions are weighted more heavily than cost indications. Thus, number of interceptions is typically weighted as a primary parameter determining a positive outcome or scenario success, whereas the number of remaining bullets is typically a secondary success parameter, e.g., may be subtracted from the sum (weighted or simple) of interceptions, or interceptions which expended less bullets may be weighted more highly than interceptions which expended more bullets. d. The interceptor control processor may store dynamic and / or aerodynamic model / s of all or any subset of the interceptors. e. The detection apparatus may be configured for predicting a trajectory of at least one target using a (simple or extended) Kalman Filter, Alpha Beta Gamma Filter, Wiener filter, Monte Carlo Filter or H - infinity Filter.

[0138] It is appreciated that specific filters have variations which are also included in the scope of the disclosure. For example, variations on the Kalman filter are described in the following online reference: kuscholarworks.ku.edu / bitstream / handle / 1808 / 14535 / Lindsey_ku_0099M_13455_DA TA_l.pdf?sequence=l%3E (MSc thesis, “On the Kalman Filter and Its Variations” By Theodore S. Lindsey). f. The system may include at least one apparatus for surveillance other than the detection apparatus. g. At least one decision may be made (e.g. may be included as if-then logic in at least one scenario) to send additional interceptors each time a first group of interceptors were in the arena and failed to stop threats before the threats reached a certain typically predefined threshold defense line. h. An investigative mechanism may be provided that records / logs and typically also analyzes all actions taken to date. i. At least one scenario, or all scenarios, may end with one, some or all interceptors returning to home base. And / or, at least one scenario may end with one, some or all interceptors remaining in place.

[0139] Many defense use-cases are possible. For example, the embodiments herein are useful for intercepting various threats that may arrive individually or in groups over a wide and / or even penetration sector, using any suitable group of one or more drones (or other interceptors) which may be carrying, say, explosive projectiles or low-cost aerial threats.

[0140] Also, many variations are possible. Any suitable ground or airborne system may be used for detecting and locating threats, even at a great distance from the target area, which provides elliptical position accuracy and estimated speed accuracy that gradually improves as the threats are tracked. Interceptors, e.g., drones, may be launched into the mission area following the discovery and location of vehicular threats, typically with a first, higher speed when moving towards the threats and / or moving between them, and with a second, lower speed for completing interception. Any suitable computer system may be used to determine interception parameters, such as but not limited to the number of interceptors required to complete the interception mission, and / or the allocation of threats to interceptors, and / or the order of execution of the interception for each interceptor. Any suitable network communication system may be used to update each of the interceptors on their mission, e.g., according to outcomes of mission / s completed by other interceptors, and / or responsive to possible appearance of additional vehicular threats in the sector of operation. Any suitable method of operation may be used, which may include all or any subset of the following operations, suitably ordered: determination of an initial estimated amount of interceptors required, e.g., based on the number of threats and / or on their relative locations and distances, and / or the interception time estimated to be required for each threat; determining an initial solution of a minimum distance problem, for a tree rooted at the launch site, and crossing the locations of all interceptors known to the system. It is appreciated that alternatives for implementation include, but are not limited to, Iterative Computation of a path for each of the interceptors that provides the best response in time and / or in outcome, e.g., in the number of downed threats; and / or carrying out planning for interceptor routes using a learning system fed with penetration simulations of groups of threats of different sizes and various penetration sectors, after typically training the system based, e.g., at least in part, on real situations, e.g., past attacks of a given sector 1 to be protected, by vehicular threats; and / or comparison between computation methods and selection of a best answer by a human operator; the system may learn these operator decisions over time. Any suitable machine learning (ML) technology, supervised or unsupervised, may be employed, such as but not limited to neural networks. According to certain embodiments, adversarial networks are employed in which, say, one network may model interceptors and a second adversarial network may model targets.

[0141] Embodiments herein yield many useful advantages.

[0142] For example, embodiments herein provide a defensive response for detection and interception of a large number of vehicular threats, e.g., drones, with limited interceptor resources, and the interception cost may be as low as possible, to increase operational value per invested resources. And / or, the system according to embodiments herein may adapt itself to the detection systems that will be used in this arena, including several systems at the same time that complement each other, and to various and changing threats during the lifetime of the system, without the need to predict, or to update all the possibilities with constant control and software updates. And / or, the system can handle threats moving at low altitudes. And / or, the system can adapt itself to different arena conditions, in terms of terrain cover (e.g. foliage, buildings) and / or weather and / or threat motion characteristics such as altitude and speed, and / or attack patterns.

[0143] It is appreciated that terminology such as "mandatory", "required", "need" and "must" refer to implementation choices made within the context of a particular implementation or application described herewithin for clarity and are not intended to be limiting, since, in an alternative implementation, the same elements might be defined as not mandatory and not required, or might even be eliminated altogether.

[0144] Components described herein as software may, alternatively, be implemented wholly or partly in hardware and / or firmware, if desired, using conventional techniques, and vice-versa. Each module or component or processor may be centralized in a single physical location or physical device or distributed over several physical locations or physical devices.

[0145] Included in the scope of the present disclosure, inter alia, are electromagnetic signals in accordance with the description herein. These may carry computer-readable instructions for performing any or all of the operations of any of the methods shown and described herein, in any suitable order, including simultaneous performance of suitable groups of operations, as appropriate. Included in the scope of the present disclosure, inter alia, are machine-readable instructions for performing any or all of the operations of any of the methods shown and described herein, in any suitable order; program storage devices readable by machine, tangibly embodying a program of instructions executable by the machine to perform any or all of the operations of any of the methods shown and described herein, in any suitable order, i.e., not necessarily as shown, including performing various operations in parallel or concurrently, rather than sequentially, as shown; a computer program product comprising a computer useable medium having computer readable program code, such as executable code, having embodied therein, and / or including computer readable program code for performing, any or all of the operations of any of the methods shown and described herein, in any suitable order; any technical effects brought about by any or all of the operations of any of the methods shown and described herein, when performed in any suitable order; any suitable apparatus or device or combination of such, programmed to perform, alone or in combination, any or all of the operations of any of the methods shown and described herein, in any suitable order; electronic devices each including at least one processor and / or cooperating input device and / or output device and operative to perform e.g. in software any operations shown and described herein; information storage devices or physical records, such as disks or hard drives, causing at least one computer or other device to be configured so as to carry out any or all of the operations of any of the methods shown and described herein, in any suitable order; at least one program pre-stored, e.g. ,in memory or on an information network such as the Internet, before or after being downloaded, which embodies any or all of the operations of any of the methods shown and described herein, in any suitable order, and the method of uploading or downloading such, and a system including server / s and / or client / s for using such; at least one processor configured to perform any combination of the described operations or to execute any combination of the described modules; and hardware which performs any or all of the operations of any of the methods shown and described herein, in any suitable order, either alone or in conjunction with software. Any computer-readable or machine-readable media described herein is intended to include non-transitory computer- or machine-readable media.

[0146] Any computations or other forms of analysis described herein may be performed by a suitable computerized method. Any operation or functionality described herein may be wholly or partially computer-implemented, e.g., by one or more processors. The invention shown and described herein may include (a) using a computerized method to identify a solution to any of the problems or for any of the objectives described herein, the solution optionally including at least one of a decision, an action, a product, a service, or any other information described herein, that impacts, in a positive manner, a problem or objectives described herein; and (b) outputting the solution.

[0147] The system may, if desired, be implemented as a network- e.g., web-based system employing software, computers, routers, and telecommunications equipment, as appropriate.

[0148] Any suitable deployment may be employed to provide functionalities, e.g., software functionalities shown and described herein. For example, a server may store certain applications, for download to clients, which are executed at the client side, the server side serving only as a storehouse. Any or all functionalities, e.g., software functionalities shown and described herein, may be deployed in a cloud environment. Clients, e.g., mobile communication devices such as smartphones, may be operatively associated with, but external to the cloud.

[0149] The scope of the present invention is not limited to structures and functions specifically described herein, and is also intended to include devices which have the capacity to yield a structure, or perform a function described herein, such that even though users of the device may not use the capacity, they are, if they so desire, able to modify the device to obtain the structure or function.

[0150] Any “if -then” logic described herein is intended to include embodiments in which a processor is programmed to repeatedly determine whether condition x, which is sometimes true and sometimes false, is currently true or false, and to perform y each time x is determined to be true, thereby to yield a processor which performs y at least once, typically on an “if and only if’ basis, e.g., triggered only by determinations that x is true, and never by determinations that x is false.

[0151] Any determination of a state or condition described herein, and / or other data generated herein, may be harnessed for any suitable technical effect. For example, the determination may be transmitted or fed to any suitable hardware, firmware, or software module, which is known or which is described herein to have capabilities to perform a technical operation responsive to the state or condition. The technical operation may, for example, comprise changing the state or condition, or may more generally cause any outcome which is technically advantageous, given the state or condition or data, and / or may prevent at least one outcome which is disadvantageous, given the state or condition or data. Alternatively, or in addition, an alert may be provided to an appropriate human operator or to an appropriate external system.

[0152] Features of the present invention, including operations, which are described in the context of separate embodiments may also be provided in combination in a single embodiment. For example, a system embodiment is intended to include a corresponding process embodiment and vice versa. Also, each system embodiment is intended to include a server-centered “view” or client centered “view”, or “view” from any other node of the system, of the entire functionality of the system, computer-readable medium, apparatus, including only those functionalities performed at that server or client or node. Features may also be combined with features known in the art, and particularly, although not limited, to those described in the Background section or in publications mentioned therein.

[0153] Conversely, features of the invention, including operations, which are described for brevity in the context of a single embodiment or in a certain order, may be provided separately or in any suitable subcombination, including with features known in the art (particularly although not limited to those described in the Background section or in publications mentioned therein) or in a different order, "e.g." is used herein in the sense of a specific example which is not intended to be limiting. Each method may comprise all or any subset of the operations illustrated or described, suitably ordered e.g., as illustrated or described herein.

[0154] Devices, apparatus or systems shown coupled in any of the drawings may in fact be integrated into a single platform in certain embodiments, or may be coupled via any appropriate wired or wireless coupling, such as but not limited to optical fiber, Ethernet, Wireless LAN, HomePNA, power line communication, cell phone, Smart Phone (e.g. iPhone), Tablet, Laptop, PDA, Blackberry GPRS, or other mobile delivery. It is appreciated that in the description and drawings shown and described herein, functionalities described or illustrated as systems and sub-units thereof, can also be provided as methods and operations therewithin, and functionalities described or illustrated as methods and operations therewithin can also be provided as systems and sub-units thereof. The scale used to illustrate various elements in the drawings is merely exemplary and / or appropriate for clarity of presentation, and is not intended to be limiting. Any suitable communication may be employed between separate units herein, e.g., wired data communication and / or in short-range radio communication with sensors, such as cameras, e.g., via WiFi, Bluetooth or Zigbee.

[0155] It is appreciated that implementation via a cellular app as described herein is but an example, and, instead, embodiments of the present invention may be implemented, say, as a smartphone SDK; as a hardware component; as an STK application, or as suitable combinations of any of the above.

[0156] Any processing functionality illustrated (or described herein) may be executed by any device having a processor, such as but not limited to a mobile telephone, set- top-box, TV, remote desktop computer, game console, tablet, mobile e.g. laptop or other computer terminal, embedded remote unit, which may either be networked itself (may itself be a node in a conventional communication network, e.g.,) or may be conventionally tethered to a networked device (to a device which is a node in a conventional communication network or is tethered directly or indirectly / ultimately to such a node).

[0157] Any operation or characteristic described herein may be performed by another actor outside the scope of the patent application and the description is intended to include an apparatus, whether hardware, firmware or software, which is configured to perform, enable, or facilitate that operation or to enable, facilitate, or provide that characteristic.

[0158] The terms processor or controller or module or logic as used herein are intended to include hardware such as computer microprocessors or hardware processors, which typically have digital memory and processing capacity, such as those available from, say Intel and Advanced Micro Devices (AMD). Any operation or functionality or computation or logic described herein may be implemented entirely or in any part on any suitable circuitry including any such computer microprocessor / s, as well as in firmware or in hardware, or any combination thereof.

[0159] It is appreciated that elements illustrated in more than one drawing, and / or elements in the written description, may still be combined into a single embodiment, except if otherwise specifically clarified herein. Any of the systems shown and described herein may be used to implement or may be combined with, any of the operations or methods shown and described herein.

[0160] It is appreciated that any features, properties , logic, modules, blocks, operations, or functionalities described herein, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment, except where the specification or general knowledge specifically indicates that certain teachings are mutually contradictory and cannot be combined. Any of the systems shown and described herein may be used to implement or may be combined with, any of the operations or methods shown and described herein.

[0161] Conversely, any modules, blocks, operations, or functionalities described herein, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable sub-combination, including with features known in the art. Each element, e.g., operation described herein, may have all characteristics and attributes described or illustrated herein, or, according to other embodiments, may have any subset of the characteristics or attributes described herein.

[0162] References herein to “said (or the) element x” having certain (e.g., functional or relational) limitations / characteristics, are not intended to imply that a single instance of element x is necessarily characterized by all the limitations / characteristics. Instead, “said (or the) element x” having certain (e.g. functional or relational) limitations / characteristics is intended to include both (a) an embodiment in which a single instance of element x is characterized by all of the limitations / characteristics and (b) embodiments in which plural instances of element x are provided, and each of the limitations / characteristics is satisfied by at least one instance of element x, but no single instance of element x satisfies all limitations / characteristics. For example, each time L limitations / characteristics are ascribed to “said” or “the” element X in the specification or claims (e.g., to “said processor” or “the processor”), this is intended to include an embodiment in which L instances of element X are provided, which respectively satisfy the L limitations / characteristics, each of the L instances of element X satisfying an individual one of the L limitations / characteristics. The plural instances of element x need not be identical. For example, if element x is a hardware processor, there may be different instances of x, each programmed for different functions and / or having different hardware configurations (e.g., there may be 3 instances of x: two Intel processors of different models, and one AMD processor).

Claims

CLAIMS1. A system for defending an area from vehicular threats in the area’s vicinity, the system comprising: i. at least one detection apparatus for detection of vehicular threats which occur in the area’s vicinity in real time or near-real time; ii. an interceptor control processor for controlling multiple interceptors to intercept at least vehicular threats detected by the detection apparatus; and iii. a machine learning hardware processor which is trained on training data which pairs threat interception scenarios, each specifying vehicular threats which occurred during the scenario, to their respective outcomes, wherein each outcome specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario were or were not intercepted, wherein said machine learning hardware processor is trained, on said training data, to generate at least one mission plan for controlling at least one of said multiple interceptors, and to feed said mission plans to the interceptor control processor, in real time.

2. A system according to claim 1 and also comprising: iv. a scenario simulator including a hardware processor configured to generate said training data including simulating artificial threat scenarios and / or to generate mission plans for each of the artificial threat scenarios.

3. A system according to claim 1 wherein each scenario has scenarios characteristics including at least one of: the number of threats, their incoming trajectory (source, speed, angle), threat characteristics, e.g., min / max speed, interceptor characteristics, e.g., min / max speed, and cloudiness of the vicinity.

4. A system according to claim 1 wherein outcome characteristics may include a weighted combination of intercepted threats.

5. A system according to claim 1 wherein mission plan characteristics may include all or any subset of:how many interceptor / s to use and which interceptor / s to use, from among a population of available interceptors; which vehicular threats will be targeted by each interceptor; a duration and velocity to define a duration, during which a higher-than-threat velocity is used to enable interceptor to close in on threat or target, after which the interceptor slows to match the threat’s velocity; for each interceptor assigned to plural vehicular threats, an order in which the vehicular threats are to be intercepted; flight altitude / s for each interceptor, during each of at least one stage of each interceptor’s operation, such as first try, second try, etc. firing angle and / or direction of approach, for each threat; and if-then logic to describe whether or not to turn around and make a second try, and / or whether or not to activate additional interceptors, and / or whether or not to continue firing, as a function of a logical condition.

6. A system according to claim 1 and also comprising at least one interceptor equipped with at least one gun or at least one machine gun.

7. A system according to claim 1 and also comprising at least one interceptor equipped with a laser target intercepting mechanism.

8. A system according to claim 5 wherein at least one interceptor operates according to the following stages, for at least one threat T:A approach threat TB first attempt to intercept threat T aka 1 st tryC turnaroundD match velocity of threat TE second attempt to intercept threat T aka 2nd try and wherein the mission plan includes parameterization of at least one of the above stages.

9. A system according to claim 1 wherein each threat interception scenario in the training data includes a mission plan P for intercepting threats detected within the scenarios.

10. A system according to claim 9 wherein said mission plan P includes at least one if-then decision point comprising a logical condition and at least one alternative carried out by at least one of the interceptors, depending on whether the logical condition is true or false.

11. A system according to claim 1 and wherein the machine learning processor continues to train itself while the system is operational, including receiving feedback on system operation which includes at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario, the scenario including a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by at least one of said multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted.

12. A system according to claim 11 wherein said outcome comprises an optical Operational Success Indication of whether or not interception was achieved.

13. A system according to claim 11 wherein said outcome comprises a radar- detected Operational Success Indication of whether or not interception was achieved.

14. A system according to claim 2 wherein each scenario has plural parameters, such as how many threats exist and how many interceptors exist, and how many bullets each interceptor has, and wherein each of the plural parameters has an allowed range, and wherein the scenario simulator comprises a Scenario Generator, which generates a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within said individual one parameter’s allowed range.

15. A system according to claim 1 and wherein, during training of the machine learning processor, an Initial Interception Response Generator, using a response model, generates interception responses and / or mission plans by randomly selecting a solution or an interception response, from an approximate parameter domain.

16. A system according to claim 15 and wherein outcomes are saved in a state machine, which updates the response model regarding at least one scenario.

17. A system according to claim 1 wherein at least one ongoing scenario includes at least one “step" in which at least one “major” event occurs during the scenario, where “major” refers to any event which requires an additional ML evaluation, and sending an updated recommended mission plan for approval to a human operator.

18. A system according to claim 17 wherein at least one of the following events is defined as “Major”: detection of at least one additional target in the course of the scenario, successful interception, missed interception pass, number of bullets available to an individual interceptor descends below a level expected to suffice for completion of the interception passes assigned to said individual interceptor.

19. A system according to claim 1 wherein said vicinity is within a field of view of the detection apparatus and wherein said detection detects each vehicular threat as it enters said vicinity.

20. A system according to claim 1 and also comprising at least one interceptor equipped with at least one of: a jet engine; at least one folding wing at least one fixed wing a turbine propulsion system,Multi rotor propulsion, and an internal combustion propulsion system.

21. A system according to claim 1 wherein the interceptor control processor stores dynamic and aerodynamic model / s of at least one of the multiple interceptors.

22. A system according to claim 1 wherein said multiple interceptors comprise at least one drone.

23. A system according to claim 1 wherein said at least one detection apparatus is configured for predicting a trajectory of at least one target using at least one of the following:Kalman Filter,Extended Kalman filter,Alpha Beta Gamma Filter,Wiener filter,Monte Carlo FilterH - infinity Filter.

24. A system according to claim 1 wherein said at least one detection apparatus comprises more than one detection apparatus.

25. A system according to claim 1 and also comprising at least one apparatus for surveillance other than said at least one detection apparatus.

26. A system according to claim 1 wherein said at least one detection apparatus comprises at least one airborne detection apparatus.

27. A system according to claim 6 wherein said at least one interceptor is equipped with at least one bullet or multiple bullets arranged in a barrel.

28. A system according to claim 27 wherein said at least one interceptor is equipped with bullet-counting functionality configured to transmit a number of remaining bullets to said interceptor control processor.

29. A system according to claim 1 wherein said machine learning hardware processor comprises a Deep learning and artificial intelligence processor of one of the following types:• GPU (Graphics Processing Unit) or• FPGA (Field programmable gate arrays) or• ASIC (application-specific integrated circuits).

30. A method for defending an area from vehicular threats in the area’s vicinity, the method comprising: i. detection of threat scenarios including plural vehicular threats in the area’s vicinity in real time or near-real time; ii. controlling multiple interceptors to intercept at least some of the plural vehicular threats as detected; and iii. using a machine learning hardware processor, trained on training data which pairs scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors, and to feed said mission plans to the interceptor control processor, in real time.

31. A method according to claim 30 and also comprising iv. a scenario simulator including a hardware processor configured to generate said training data including simulating artificial threat scenarios and / or to generate mission plans for each of the artificial threat scenarios.

32. A method according to claim 31 wherein each scenario has plural parameters such as how many threats exist and how many interceptors exist and how many bullets each interceptor has, and wherein each of the plural parameters has an allowed range, and wherein the scenario simulator comprises a Scenario Generator, which generates a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within said individual one parameter’s allowed range.

33. A method according to claim 30 wherein each scenario has scenario characteristics including at least one of the number of threats, their incoming trajectory (source, speed, angle), threat characteristics, e.g., min / max speed, interceptor characteristics, e.g., min / max speed, and cloudiness of the vicinity.

34. A method according to claim 30 wherein outcome characteristics may include a weighted combination of intercepted threats.

35. A method according to claim 30 wherein mission plan characteristics may include all or any subset of: how many interceptor / s to use and which interceptor / s to use, from among a population of available interceptors; which vehicular threats will be targeted by each interceptor; a duration and velocity to define a duration, during which a higher-than-threat velocity is used to enable interceptor to close in on threat or target after which the interceptor slows to match the threat’s velocity; for each interceptor assigned to plural vehicular threats, an order in which the vehicular threats are to be intercepted; flight altitude / s for each interceptor, during each of at least one stage of each interceptor’s operation; firing angle and / or direction of approach, for each threat; and if-then logic to describe whether or not to turn around and make a second try and / or whether or not to activate additional interceptors and / or whether or not to continue firing, as a function of a logical condition.

36. A method according to claim 35 wherein at least one interceptor operates according to the following stages, for at least one threat T:A approach threat TB first attempt to intercept threat T aka 1 st tryC turnaroundD match velocity of threat TE second attempt to intercept threat T aka 2nd try and wherein the mission plan includes parameterization of at least one of the above stages.

37. A method according to claim 30 wherein each threat interception scenario in the training data includes a mission plan P for intercepting threats detected within the scenarios.

38. A method according to claim 37 wherein said mission plan P includes at least one if-then decision point comprising a logical condition and at least one alternativecarried out by at least one of the interceptors depending on whether the logical condition is true or false.

39. A method according to claim 30 and wherein the machine learning processor continues to train itself while the method is operational, including receiving feedback on method operation which includes at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario, the scenario including a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by at least one of said multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted.

40. A method according to claim 30 and also comprising: iv. simulating artificial threat scenarios and generating mission plans for each of the artificial threat scenarios.

41. A computer program product, comprising a non-transitory tangible computer readable medium having computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method for defending an area from vehicular threats in the area’s vicinity, the method comprising: i. detection of threat scenarios including plural vehicular threats in the area’s vicinity in real time or near-real time; ii. controlling multiple interceptors to intercept at least some of the plural vehicular threats as detected; and iii. using a machine learning processor, trained on training data which pairs scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors and to feed said mission plans to the controller, in real time.

42. A computer program product according to claim 41 and also comprising: iv. a scenario simulator including a hardware processor configured to generate said training data including simulating artificial threat scenarios and / or to generate mission plans for each of the artificial threat scenarios.

43. A computer program product according to claim 42 wherein each scenario has plural parameters, such as how many threats exist and how many interceptors exist, and how many bullets each interceptor has, and wherein each of the plural parameters has an allowed range, and wherein the scenario simulator comprises a Scenario Generator, which generates a multiplicity of scenarios including defining each scenario from among the multiplicity of scenarios, by assigning each individual one of the plural parameters randomly each from within said individual one parameter’s allowed range.

44. A computer program product according to claim 41 wherein each scenario has scenarios characteristics including at least one of: the number of threats, their incoming trajectory (source, speed, angle), threat characteristics e.g., min / max speed, interceptor characteristics, e.g., min / max speed, and cloudiness of the vicinity.

45. A computer program product according to claim 41 wherein outcome characteristics may include a weighted combination of intercepted threats.

46. A computer program product according to claim 41 wherein mission plan characteristics include all or any subset of: how many interceptor / s to use and which interceptor / s to use, from among a population of available interceptors; which vehicular threats will be targeted by each interceptor; a duration and velocity to define a duration, during which a higher-than-threat velocity is used to enable interceptor to close in on threat or target, after which the interceptor slows to match the threat’s velocity; for each interceptor assigned to plural vehicular threats, an order in which the vehicular threats are to be intercepted; flight altitude / s for each interceptor, during each of at least one stage of each interceptor’s operation such as first try, second try etc.; firing angle and / or direction of approach, for each threat; if-then logic to describe whether or not to turn around and make a second try and / or whether or not to activate additional interceptors and / or whether or not to continue firing, as a function of a logical condition.

47. A computer program product according to claim 46 wherein at least one interceptor operates according to the following stages, for at least one threat T:A approach threat TB first attempt to intercept threat T aka 1 st tryC turnaroundD match velocity of threat TE second attempt to intercept threat T aka 2nd try and wherein the mission plan includes parameterization of at least one of the above stages.

48. A computer program product according to claim 41 wherein each threat interception scenario in the training data includes a mission plan P for intercepting threats detected within the scenarios.

49. A computer program product according to claim 48 wherein said mission plan P includes at least one if-then decision point comprising a logical condition and at least one alternative carried out by at least one of the interceptors, depending on whether the logical condition is true or false.

50. A computer program product according to claim 41 and wherein the machine learning processor continues to train itself while the method is operational, including receiving feedback on method operation which includes at least one threat interception scenario S specifying vehicular threats which were detected by the detection apparatus during the scenario, the scenario including a mission plan generated by the machine learning processor, fed to the interceptor control processor, and executed by at least one of said multiple interceptors as controlled, accordingly, by the interceptor control processor, and, paired therewith, an outcome which specifies which of the vehicular threats which occurred in the area’s vicinity during the scenario S were or were not intercepted.

Images