CA3067580A1 - Threat situation assessment systems and methods for unmanned underwater vehicle - Google Patents
Threat situation assessment systems and methods for unmanned underwater vehicle Download PDFInfo
- Publication number
- CA3067580A1 CA3067580A1 CA3067580A CA3067580A CA3067580A1 CA 3067580 A1 CA3067580 A1 CA 3067580A1 CA 3067580 A CA3067580 A CA 3067580A CA 3067580 A CA3067580 A CA 3067580A CA 3067580 A1 CA3067580 A1 CA 3067580A1
- Authority
- CA
- Canada
- Prior art keywords
- uuv
- threat
- bayesian network
- control system
- threat situation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Systems and methods for unmanned underwater vehicle threat assessment. UUV
carries multiple sensor systems that are composed by a sensing system, a control system, a propulsion system, a payload system, a communication system and a power system. The UUV control system involves the autonomous control system and the motion control system and includes integrated application of intelligent architecture, autonomous navigation, task planning, motion control and other subsystems. The autonomous control system is the core and key system for UUV to autonomously complete operational tasks which is equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information. Through multiple heterogeneous sensors, the autonomous control system receives the real-time data. Based on the model of the invention, UUV can perceive surrounding condition and assess threat situation by constructing integrated threat situation assessment network model and applying static Bayes reason and dynamic Bayes reason to get the results of the task threat situation assessment for UUV. It can not only evaluate the threat situation at the current moment or in a continuous period, but also obtain the threat degree ranking of various current threats through sensitivity analysis.
Input the threat situation assessment results into the task planning system. The priority of the tasks that the UUV plans to perform will be changed based on the data output from the threat situation assessment system. Finally, the movement of the UUV will be changed by the motion control system in term of latest task.
carries multiple sensor systems that are composed by a sensing system, a control system, a propulsion system, a payload system, a communication system and a power system. The UUV control system involves the autonomous control system and the motion control system and includes integrated application of intelligent architecture, autonomous navigation, task planning, motion control and other subsystems. The autonomous control system is the core and key system for UUV to autonomously complete operational tasks which is equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information. Through multiple heterogeneous sensors, the autonomous control system receives the real-time data. Based on the model of the invention, UUV can perceive surrounding condition and assess threat situation by constructing integrated threat situation assessment network model and applying static Bayes reason and dynamic Bayes reason to get the results of the task threat situation assessment for UUV. It can not only evaluate the threat situation at the current moment or in a continuous period, but also obtain the threat degree ranking of various current threats through sensitivity analysis.
Input the threat situation assessment results into the task planning system. The priority of the tasks that the UUV plans to perform will be changed based on the data output from the threat situation assessment system. Finally, the movement of the UUV will be changed by the motion control system in term of latest task.
Description
Threat Situation Assessment Systems and Methods for Unmanned Underwater Vehicle Field of the invention The present invention relates to threat assessment systems' form and methods for UUV (Unmanned Underwater Vehicle).
Description of the prior Art With more and more attention paid to ocean development, the development of marine technology has been improved significantly. UUV intelligence is the key point of underwater technology development. The improvement of UUV intelligence mainly depends on perceiving the underwater environment and making appropriate decision which is based on threat assessment. Due to the complexity of the underwater environment and the limited sensor capability, it is urgent to have systems and methods that can assess the threat status.
The literatures on threat assessment for unmanned vehicle focus on UAV
(Unmanned Aerial Vehicle) mostly. The representative literatures avoid the question of how to get the threat level of obstacles mostly. It needs to set threat level parameter for the whole systems or the obstacles artificially. Those methods are not practical.
Example Literature Documents relevant to the prior art include:
Ivansson B, Johan. Situation Assessment in a Stochastic Environment using Bayesian Networks[J]. Institutionen For Systemteknik, 2002, describes a method to assess the dynamic environment changes for UAV based on fuzzy Bayesian network.
It classifies different objects into non-enemies and enemies according to threat level.
The enemies are also classified according to threat level.
In the underwater circumstance, UUV can only use sonars to detect surroundings.
The ocean noise also has a great adverse effect on the detection sonars. All those factors make UUV perception have highly uncertainty. Above all, the invention which is based on Bayesian network uses information collected by UUV to assess threat situation.
Summary of the Invention The present invention provides systems and methods for UUV threat situation assessment.
The UUV carries multiple sensor systems that are composed by a sensing system, a control system, a propulsion system, a payload system, a communication system and an energy system. The UUV control system involves the autonomous control system and the motion control system and includes integrated application of intelligent architecture, autonomous navigation, task planning, motion control and other subsystems. The autonomous control system is the core and key system for UUV
to autonomously complete operational tasks which is equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information.
The autonomous control system is a kernel key composition as a kind of unmanned systems without human guidance especially for UUV. The sensing system composes by GPS, INS, MRU, DVL, Octans and FLS. The control system composes by autonomous control system and motion control system. The propulsion system composes by left thruster, right thruster, bow horizontal propeller, bow vertical propeller, stern horizontal propeller, stern vertical propeller, rudder and elevator. The payload system composes by CTD, multibeam imaging sonar, side scan sonar, ADCP, imaging sensor, electronic sensor and composite sensor. The communication system composes by Wi-Fi module, radio module and acoustic communication module. The energy system composes by power battery pack and instrument power pack.
Brief Description of the Drawings FIG 1 is the composition of UUV equipment system.
FIG 2 is the system principle block diagram of UUV.
FIG 3 is the integrated network model for UUV threat situation assessment.
FIG 4(a) is the environment level dynamic Bayesian network model.
FIG 4(b) is the platform level dynamic Bayesian network model.
FIG 4(c) is the mission level dynamic Bayesian network model.
FIG 5(a) is the quantitative evaluation result of the environment level dynamic Bayesian network model.
FIG 5(b) is the quantitative evaluation result of the platform level dynamic Bayesian network model.
FIG 5(c) is the quantitative evaluation result of the mission level dynamic Bayesian network model.
FIG 5(d) is the quantitative evaluation result of the threat mode.
FIG 6(a) is the rendering which takes the t=9 moment as the analysis moment.
FIG 6(b) is the quantitative evaluation rendering of threat level which uses color shades to reflect variation.
FIG 6(c) is the quantitative evaluation sequence of threat level.
Detailed Description The present invention provides threat situation assessment systems and methods for UUV.
The processing of threat assessment runs by UUV system includes following steps.
(1) Analyzing the elements of UUV equipment systems and possible threat sources.
Description of the prior Art With more and more attention paid to ocean development, the development of marine technology has been improved significantly. UUV intelligence is the key point of underwater technology development. The improvement of UUV intelligence mainly depends on perceiving the underwater environment and making appropriate decision which is based on threat assessment. Due to the complexity of the underwater environment and the limited sensor capability, it is urgent to have systems and methods that can assess the threat status.
The literatures on threat assessment for unmanned vehicle focus on UAV
(Unmanned Aerial Vehicle) mostly. The representative literatures avoid the question of how to get the threat level of obstacles mostly. It needs to set threat level parameter for the whole systems or the obstacles artificially. Those methods are not practical.
Example Literature Documents relevant to the prior art include:
Ivansson B, Johan. Situation Assessment in a Stochastic Environment using Bayesian Networks[J]. Institutionen For Systemteknik, 2002, describes a method to assess the dynamic environment changes for UAV based on fuzzy Bayesian network.
It classifies different objects into non-enemies and enemies according to threat level.
The enemies are also classified according to threat level.
In the underwater circumstance, UUV can only use sonars to detect surroundings.
The ocean noise also has a great adverse effect on the detection sonars. All those factors make UUV perception have highly uncertainty. Above all, the invention which is based on Bayesian network uses information collected by UUV to assess threat situation.
Summary of the Invention The present invention provides systems and methods for UUV threat situation assessment.
The UUV carries multiple sensor systems that are composed by a sensing system, a control system, a propulsion system, a payload system, a communication system and an energy system. The UUV control system involves the autonomous control system and the motion control system and includes integrated application of intelligent architecture, autonomous navigation, task planning, motion control and other subsystems. The autonomous control system is the core and key system for UUV
to autonomously complete operational tasks which is equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information.
The autonomous control system is a kernel key composition as a kind of unmanned systems without human guidance especially for UUV. The sensing system composes by GPS, INS, MRU, DVL, Octans and FLS. The control system composes by autonomous control system and motion control system. The propulsion system composes by left thruster, right thruster, bow horizontal propeller, bow vertical propeller, stern horizontal propeller, stern vertical propeller, rudder and elevator. The payload system composes by CTD, multibeam imaging sonar, side scan sonar, ADCP, imaging sensor, electronic sensor and composite sensor. The communication system composes by Wi-Fi module, radio module and acoustic communication module. The energy system composes by power battery pack and instrument power pack.
Brief Description of the Drawings FIG 1 is the composition of UUV equipment system.
FIG 2 is the system principle block diagram of UUV.
FIG 3 is the integrated network model for UUV threat situation assessment.
FIG 4(a) is the environment level dynamic Bayesian network model.
FIG 4(b) is the platform level dynamic Bayesian network model.
FIG 4(c) is the mission level dynamic Bayesian network model.
FIG 5(a) is the quantitative evaluation result of the environment level dynamic Bayesian network model.
FIG 5(b) is the quantitative evaluation result of the platform level dynamic Bayesian network model.
FIG 5(c) is the quantitative evaluation result of the mission level dynamic Bayesian network model.
FIG 5(d) is the quantitative evaluation result of the threat mode.
FIG 6(a) is the rendering which takes the t=9 moment as the analysis moment.
FIG 6(b) is the quantitative evaluation rendering of threat level which uses color shades to reflect variation.
FIG 6(c) is the quantitative evaluation sequence of threat level.
Detailed Description The present invention provides threat situation assessment systems and methods for UUV.
The processing of threat assessment runs by UUV system includes following steps.
(1) Analyzing the elements of UUV equipment systems and possible threat sources.
(2) Establishing static Bayesian network based on the result of Step 1.
(3) Establishing dynamic Bayesian network by adding time state transition probability to the static Bayesian network.
(4) Quantifying the threat factors in an actual case.
(5) Computing the data samples by the dynamic Bayesian network.
(6) Computing the data at each moment by the static Bayesian network and taking the sensitivity analysis.
(7) Computing the result of step 6 and 7 for task planning system.
The system of step 1, wherein the invention requires a UUV which has a complete equipment system. The elements of UUV systems include a sensing system, a control system, a propulsion system, a payload system, a communication system and a power system. The UUV control system involves the autonomous control system and the motion control system and includes integrated application of intelligent architecture, autonomous navigation, task planning, motion control and other subsystems. The autonomous control system is the core and key system for UUV to autonomously complete operational tasks which is equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information. The autonomous control system is a kernel key composition as a kind of unmanned systems without human guidance especially for UUV. The sensing system composes by GPS, INS, MRU, DVL, Octans and FLS. The control system composes by autonomous control system and motion control system. The propulsion system composes by left thruster, right thruster, bow horizontal propeller, bow vertical propeller, stern horizontal propeller, stern vertical propeller, rudder and elevator. The payload system composes by CTD, multibeam imaging sonar, side scan sonar, ADCP, imaging sensor, electronic sensor and composite sensor. The communication system composes by Wi-Fi module, radio module and acoustic communication module. The power system composes by power battery pack and instrument power pack. FIG 1 describes the composition as mentioned above. FIG 2 is the system principle block diagram of UUV which describes the information interaction between threat assessment system and other parts of the whole system.
The system of step 2, wherein the prior probability and static Bayesian network structure are set by expert empirical method. FIG 3 is the integrated network model for UUV threat situation assessment which shows the structure of static Bayesian network that described in step 2. The Mathematical principles of the network model which is based on Bayes' formula and independent assumption is showed below.
=
PCI1x) P ()ix) (1) P (X131) P(Y) = P(Yx) p(xi, x2, = = = , xn) = 1-111,1 p(xi Ilr(xi)) (2) Wherein formula (1) and (2), p(xly) means the probability of x happening which supposing that y already happened. p(yx) means the probability of x and y happening together. p(xi, x2, === , xn) is the joint distribution of all nodes in the established evaluation model. ir(xi) is a set of the parent nodes of node X.
For the static Bayesian network model described above, it is assumed that the network has n hidden nodes and m observation nodes. With the formula and hypothesis showed above. The reasoning formula is:
pujincy; fl P(xiln(x,)) P(Xii x2, = xnlYi, Y2, = Yni) ¨ (3) HT, KY j)) P(xiln(xi)) Wherein formula (3), p(ri, x2, == = , xnl))'i, y2, = == ym) stands for the probability that the set of x happens which is influenced by the set of y. xi is a value of the joint Xi, yj is a value of the joint K.
The system of step 3, wherein the structure of dynamic Bayesian network is a three parallel level. They are environment level, platform level and mission level respectively. Prior probability setting and dynamic Bayesian network structure are based on static Bayesian network which is described in step 2. FIG 4(a), FIG
4(b) and FIG 4(c) show the structure of dynamic Bayesian network component correspondingly. We believe that the influence of obstacles bearing is a dynamic influence. The influence of this factor on the threat degree of obstacles at a certain time can be ignored. Therefore, we add obstacle bearing node to the dynamic Bayesian network based on the original static Bayesian network structure.
Adding time state transition probability to the static Bayesian network. Expanding the time line which makes the dynamic network contain T time points. When the observed values only have a certain composite state, the distribution of the hidden variables as follow:
P(xii, xi2, = xin, = " xri, xn, = = = XTn Y12, = = Ylm, ' = = YT1, YT2, = =
= Yrm) =
rik,j P(YkjI7T(Ykj)) nk,ipcxkdircxki (4) Hic,j P(Ykiln(Ykj))llk,i P(Xki lit(Xki)) In formula (4), k = 1,2, === , T ; j = 1,2, ===, m ; i = 1,2, === , n.xki represents the value of the i th hidden node in the k th time slice. yki represents the value the j th observed node in the k th time slice. If the observed value has multiple states, the formula is:
=== Xn, XT2, XTnlY11c,, Yl2o, = = = Ylmo, = , 317'10,3/T2w = Yrnto) =
nic,j13(Y kj'Y kjoliqY kj))nk,iP(x kilff(xki)) m"xii_y12,'..yrixT2.--rTnnkooki=ykiowyki nk,ipc.kiiirc.ki ILJP0,k; = (5) In formula (5), k = 1,2, = == , T ; j = 1,2, = == , m ; i = 1,2, = = = , n.
ykio represents the observed states of the j th observed node yki in the k th time slice. The third subscript o is the number of states.
The system of step 4, wherein the quantized data is preliminarily processed to generate data samples which can be input into the network. We assume that the UUV
is implementing a detection mission. The details of the mission are described below.
The UUV surveys the seabed topography within 0.5 miles of the operation center, collects data and transmit it back to the operation center. The UUV has already been working for 10 hours, the power electric voltage still have 40%; The current is slight;
The density is 1.025g/cm3; From t=4 moment, there is an abnormal deflection of imaging sensor motor; There exist a static, single and known characteristic obstacle which is 100m from the UUV; There is an unknown dynamic characteristic target on the side detected by detection sonar which is 13km from the UUV and move slowly.
After preprocessed, we assume that each condition is in a good condition before t=4. After t=4 moment, the single known characteristic obstacle is 50m to 130m from the UUV; the power electric pack voltage is lack; Lifting antenna motor angle for imaging sensor is lack; the single unknown dynamic characteristic target is 12km to 15km from UUV; other condition is good. The input parameter of three parallel level network is showed below (Form 1-3).
Form 1: Environment level parameter.
Number of Distance from Moment Temperature Salinity Velocity of Current known known (t) ( C) (%0) obstacles obstacles obstacles(m) 0 med med slight single 130+ steady med med slight single 130+ steady 2 med med slight single 130+ steady 3 med med slight single 130+ steady 4 med med slight single 50-130 dynamic med med slight single 50-130 dynamic 6 low med slight single 50-130 dynamic 7 low med slight single 50-130 dynamic
The system of step 1, wherein the invention requires a UUV which has a complete equipment system. The elements of UUV systems include a sensing system, a control system, a propulsion system, a payload system, a communication system and a power system. The UUV control system involves the autonomous control system and the motion control system and includes integrated application of intelligent architecture, autonomous navigation, task planning, motion control and other subsystems. The autonomous control system is the core and key system for UUV to autonomously complete operational tasks which is equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information. The autonomous control system is a kernel key composition as a kind of unmanned systems without human guidance especially for UUV. The sensing system composes by GPS, INS, MRU, DVL, Octans and FLS. The control system composes by autonomous control system and motion control system. The propulsion system composes by left thruster, right thruster, bow horizontal propeller, bow vertical propeller, stern horizontal propeller, stern vertical propeller, rudder and elevator. The payload system composes by CTD, multibeam imaging sonar, side scan sonar, ADCP, imaging sensor, electronic sensor and composite sensor. The communication system composes by Wi-Fi module, radio module and acoustic communication module. The power system composes by power battery pack and instrument power pack. FIG 1 describes the composition as mentioned above. FIG 2 is the system principle block diagram of UUV which describes the information interaction between threat assessment system and other parts of the whole system.
The system of step 2, wherein the prior probability and static Bayesian network structure are set by expert empirical method. FIG 3 is the integrated network model for UUV threat situation assessment which shows the structure of static Bayesian network that described in step 2. The Mathematical principles of the network model which is based on Bayes' formula and independent assumption is showed below.
=
PCI1x) P ()ix) (1) P (X131) P(Y) = P(Yx) p(xi, x2, = = = , xn) = 1-111,1 p(xi Ilr(xi)) (2) Wherein formula (1) and (2), p(xly) means the probability of x happening which supposing that y already happened. p(yx) means the probability of x and y happening together. p(xi, x2, === , xn) is the joint distribution of all nodes in the established evaluation model. ir(xi) is a set of the parent nodes of node X.
For the static Bayesian network model described above, it is assumed that the network has n hidden nodes and m observation nodes. With the formula and hypothesis showed above. The reasoning formula is:
pujincy; fl P(xiln(x,)) P(Xii x2, = xnlYi, Y2, = Yni) ¨ (3) HT, KY j)) P(xiln(xi)) Wherein formula (3), p(ri, x2, == = , xnl))'i, y2, = == ym) stands for the probability that the set of x happens which is influenced by the set of y. xi is a value of the joint Xi, yj is a value of the joint K.
The system of step 3, wherein the structure of dynamic Bayesian network is a three parallel level. They are environment level, platform level and mission level respectively. Prior probability setting and dynamic Bayesian network structure are based on static Bayesian network which is described in step 2. FIG 4(a), FIG
4(b) and FIG 4(c) show the structure of dynamic Bayesian network component correspondingly. We believe that the influence of obstacles bearing is a dynamic influence. The influence of this factor on the threat degree of obstacles at a certain time can be ignored. Therefore, we add obstacle bearing node to the dynamic Bayesian network based on the original static Bayesian network structure.
Adding time state transition probability to the static Bayesian network. Expanding the time line which makes the dynamic network contain T time points. When the observed values only have a certain composite state, the distribution of the hidden variables as follow:
P(xii, xi2, = xin, = " xri, xn, = = = XTn Y12, = = Ylm, ' = = YT1, YT2, = =
= Yrm) =
rik,j P(YkjI7T(Ykj)) nk,ipcxkdircxki (4) Hic,j P(Ykiln(Ykj))llk,i P(Xki lit(Xki)) In formula (4), k = 1,2, === , T ; j = 1,2, ===, m ; i = 1,2, === , n.xki represents the value of the i th hidden node in the k th time slice. yki represents the value the j th observed node in the k th time slice. If the observed value has multiple states, the formula is:
=== Xn, XT2, XTnlY11c,, Yl2o, = = = Ylmo, = , 317'10,3/T2w = Yrnto) =
nic,j13(Y kj'Y kjoliqY kj))nk,iP(x kilff(xki)) m"xii_y12,'..yrixT2.--rTnnkooki=ykiowyki nk,ipc.kiiirc.ki ILJP0,k; = (5) In formula (5), k = 1,2, = == , T ; j = 1,2, = == , m ; i = 1,2, = = = , n.
ykio represents the observed states of the j th observed node yki in the k th time slice. The third subscript o is the number of states.
The system of step 4, wherein the quantized data is preliminarily processed to generate data samples which can be input into the network. We assume that the UUV
is implementing a detection mission. The details of the mission are described below.
The UUV surveys the seabed topography within 0.5 miles of the operation center, collects data and transmit it back to the operation center. The UUV has already been working for 10 hours, the power electric voltage still have 40%; The current is slight;
The density is 1.025g/cm3; From t=4 moment, there is an abnormal deflection of imaging sensor motor; There exist a static, single and known characteristic obstacle which is 100m from the UUV; There is an unknown dynamic characteristic target on the side detected by detection sonar which is 13km from the UUV and move slowly.
After preprocessed, we assume that each condition is in a good condition before t=4. After t=4 moment, the single known characteristic obstacle is 50m to 130m from the UUV; the power electric pack voltage is lack; Lifting antenna motor angle for imaging sensor is lack; the single unknown dynamic characteristic target is 12km to 15km from UUV; other condition is good. The input parameter of three parallel level network is showed below (Form 1-3).
Form 1: Environment level parameter.
Number of Distance from Moment Temperature Salinity Velocity of Current known known (t) ( C) (%0) obstacles obstacles obstacles(m) 0 med med slight single 130+ steady med med slight single 130+ steady 2 med med slight single 130+ steady 3 med med slight single 130+ steady 4 med med slight single 50-130 dynamic med med slight single 50-130 dynamic 6 low med slight single 50-130 dynamic 7 low med slight single 50-130 dynamic
8 low med slight single 50-130 dynamic
9 low med slight single 50-130 dynamic Form 2.1: Platform level parameter (Leakage detection state).
Moment Instrument Propulsion Power battery pack Instrument module (t) power pack system Form 2.2: Platform level parameter (Energy state and Feature region).
Power battery pack Instrument power pack Distance from Moment(t) Voltage(V) Voltage(V) feature region (km) 0 enough enough 15+
1 enough enough 15+
2 enough enough 15+
3 enough enough 15+
4 lack enough 15+
5 lack enough 15+
6 lack enough 15+
7 lack enough 15+
8 lack enough 15+
9 lack enough 15+
Form 2.3: Platform level parameter (Unknown static and dynamic characteristic targets).
Number of Distance from Bearing of Number of Distance from Moment unknown unknown unknown unknown static unknown (t) dynamic dynamic dynamic characteristic static characteristic characteristic characteristic target characteristic target target (km) target target (m) 0 0 15+ above single 130+
1 0 15+ above single 130+
2 0 15+ above single 130+
3 0 15+ above single 130+
4 1 12-15 above single 130+
1 12-15 above single 130+
6 1 12-15 above single 130+
7 1 12-15 horizontal single 130+
8 1 12-15 horizontal single 130+
9 1 12-15 horizontal single 130+
Form 3.1: Mission level parameter (Energy state and State of propulsion system).
Power battery pack Instrument power State of propulsion Moment(t) Voltage (V) pack Voltage(V) system 0 enough enough normal 1 enough enough normal 2 enough enough normal 3 enough enough normal 4 lack enough normal 5 lack enough normal 6 lack enough normal 7 lack enough normal 8 lack enough normal 9 lack enough normal Form 3.2: Mission level parameter (Lifting antenna motor and Platform operating state).
Angle for Angle for Angle for imaging Pitch Moment(t) electronic composite Yaw Angle sensor Angle sensor sensor 0 normal normal normal none none 1 normal normal normal none none 2 normal normal normal none none 3 normal normal normal none none 4 lack normal normal none none 5 lack normal normal none none 6 lack normal normal none none 7 lack normal normal none none 8 lack normal normal none none 9 lack normal normal none none The system of step 5, wherein the result of threat situation assessment and threat mode are obtained by reasoning. FIG 5(a), FIG 5(b) and FIG 5(c) show the result of each network component of three parallel network level after entering the simulation data. FIG 5(d) shows the result of the whole dynamic Bayesian network after entering the simulation data. Through the model speculation, the underwater known obstacle should be a terrain obstacle. The result would be transmitted back to the autonomous control system.
The system of step 6, wherein the result is that ranking of the threat factors at the current moment which is the priority processing basis for the planning decision of the UUV autonomous control system. After entering the parameter at the t=9 moment into the network, the result is showed in FIG 6(a) to 6(c). FIG 6(a) shows the result of the static Bayesian network after entering the simulation data. The value of safety is about 33%. FIG 6(b) and FIG 6(c) show the result of sensitive analysis. As it showed in FIG
6(b), the red joints represent the threat factors. The threat ranking is showed in FIG
6(c). It shows the sensitive analysis of the task threat with the set of Task_threat_level=danger. At the moment showed in the figure, the current value is 0.666108. The reachable range is [0.494927, 1]. We can see from the figure that the most dangerous factor is unknown dynamic characteristic target. Secondary threat is energy state.
The system of step 7, wherein the task planning system is a subsystem of autonomous control system which generates the optimal decision at each moment based on the results of the threat situation assessment. According to the analysis results, it should deal with the threat from unknown dynamic characteristic target firstly. The best solution at that moment is turn back to get a charge while monitor the movement of unknown dynamic characteristic target.
As will be apparent to those skilled in the art in the light of the foregoing disclosure, many alterations and modifications are possible in the practice of this invention. The scope of the claims should not be limited by the preferred embodiments set forth in the examples, but should be given the broadest interpretation consistent with the description as a whole.
Moment Instrument Propulsion Power battery pack Instrument module (t) power pack system Form 2.2: Platform level parameter (Energy state and Feature region).
Power battery pack Instrument power pack Distance from Moment(t) Voltage(V) Voltage(V) feature region (km) 0 enough enough 15+
1 enough enough 15+
2 enough enough 15+
3 enough enough 15+
4 lack enough 15+
5 lack enough 15+
6 lack enough 15+
7 lack enough 15+
8 lack enough 15+
9 lack enough 15+
Form 2.3: Platform level parameter (Unknown static and dynamic characteristic targets).
Number of Distance from Bearing of Number of Distance from Moment unknown unknown unknown unknown static unknown (t) dynamic dynamic dynamic characteristic static characteristic characteristic characteristic target characteristic target target (km) target target (m) 0 0 15+ above single 130+
1 0 15+ above single 130+
2 0 15+ above single 130+
3 0 15+ above single 130+
4 1 12-15 above single 130+
1 12-15 above single 130+
6 1 12-15 above single 130+
7 1 12-15 horizontal single 130+
8 1 12-15 horizontal single 130+
9 1 12-15 horizontal single 130+
Form 3.1: Mission level parameter (Energy state and State of propulsion system).
Power battery pack Instrument power State of propulsion Moment(t) Voltage (V) pack Voltage(V) system 0 enough enough normal 1 enough enough normal 2 enough enough normal 3 enough enough normal 4 lack enough normal 5 lack enough normal 6 lack enough normal 7 lack enough normal 8 lack enough normal 9 lack enough normal Form 3.2: Mission level parameter (Lifting antenna motor and Platform operating state).
Angle for Angle for Angle for imaging Pitch Moment(t) electronic composite Yaw Angle sensor Angle sensor sensor 0 normal normal normal none none 1 normal normal normal none none 2 normal normal normal none none 3 normal normal normal none none 4 lack normal normal none none 5 lack normal normal none none 6 lack normal normal none none 7 lack normal normal none none 8 lack normal normal none none 9 lack normal normal none none The system of step 5, wherein the result of threat situation assessment and threat mode are obtained by reasoning. FIG 5(a), FIG 5(b) and FIG 5(c) show the result of each network component of three parallel network level after entering the simulation data. FIG 5(d) shows the result of the whole dynamic Bayesian network after entering the simulation data. Through the model speculation, the underwater known obstacle should be a terrain obstacle. The result would be transmitted back to the autonomous control system.
The system of step 6, wherein the result is that ranking of the threat factors at the current moment which is the priority processing basis for the planning decision of the UUV autonomous control system. After entering the parameter at the t=9 moment into the network, the result is showed in FIG 6(a) to 6(c). FIG 6(a) shows the result of the static Bayesian network after entering the simulation data. The value of safety is about 33%. FIG 6(b) and FIG 6(c) show the result of sensitive analysis. As it showed in FIG
6(b), the red joints represent the threat factors. The threat ranking is showed in FIG
6(c). It shows the sensitive analysis of the task threat with the set of Task_threat_level=danger. At the moment showed in the figure, the current value is 0.666108. The reachable range is [0.494927, 1]. We can see from the figure that the most dangerous factor is unknown dynamic characteristic target. Secondary threat is energy state.
The system of step 7, wherein the task planning system is a subsystem of autonomous control system which generates the optimal decision at each moment based on the results of the threat situation assessment. According to the analysis results, it should deal with the threat from unknown dynamic characteristic target firstly. The best solution at that moment is turn back to get a charge while monitor the movement of unknown dynamic characteristic target.
As will be apparent to those skilled in the art in the light of the foregoing disclosure, many alterations and modifications are possible in the practice of this invention. The scope of the claims should not be limited by the preferred embodiments set forth in the examples, but should be given the broadest interpretation consistent with the description as a whole.
Claims (15)
- Claim 1: A threat situation assessment system for UUV (Unmanned Underwater Vehicle), comprising a UUV, wherein the UUV comprises multiple systems comprising a sensing system, a control system, a propulsion system, a payload system, a communication system and an energy system, and wherein the UUV control system comprises an autonomous control system and a motion control system, comprising integrated application of intelligent architecture, autonomous navigation, task planning, and motion control subsystems, and wherein the autonomous control system is the core and key system for the UUV to autonomously complete operational tasks being equivalent to human brain playing the function of intelligent planning and decision-making based on sensory information, and wherein the autonomous control system is a kernel key composition being a type of unmanned systems without human guidance especially for UUV, and wherein the UUV comprises a threat assessment system, and wherein the threat assessment system is a part of the autonomous control system, and wherein the autonomous control system is capable of receiving real-time data from multiple heterogeneous sensors, and wherein the UUV can perceive the surrounding oceanic conditions, the operating state, the health state of the platform, the operating state of the payload system and assess potential threat situation, and wherein the UUV is capable of not only evaluating the threat situation at the current moment and in a continuous period, but also obtaining the threat degree ranking of various current threats through sensitivity analysis, and wherein the UUV
comprises a task planning system, wherein the task planning system is a subsystem of the autonomous control system, and wherein the task planning system is responsible for adjusting the priority of UUV tasks based on data output from the threat assessment system. - Claim 2: The threat situation assessment system for UUV according to claim 1, wherein the system can assess the threat factors about environment related factors, UUV platform related factors and mission related factors, and also can analyze and sort the dangerous factors based on the UUV platform.
- Claim 3: The threat situation assessment system for UUV according to claim 1, wherein the processing of threat situation assessment by the system comprises the following steps:
Step (1) Analyzing elements of UUV equipment systems and possible threat sources;
Step (2) Establishing static Bayesian network based on the result of Step 1;
Step (3) Establishing dynamic Bayesian network by adding time state transition probability to the static Bayesian network;
Step (4) Quantifying the threat factors in an actual case;
Step (5) Computing the data samples by the dynamic Bayesian network;
Step (6) Computing the data at each moment by the static Bayesian network and taking the sensitivity analysis;
Step (7) Computing the results of steps 5 and 6 for the task planning system. - Claim 4: The threat situation assessment system for UUV according to claim 3, wherein the sensing system comprises GPS (Global Position System), INS
(Inertial Navigation System), MRU (Motion Reference Unit), DVL (Doppler Velocity Log), Octans, FLS (Forward Looking Sonar), and wherein the propulsion system comprises left thruster, right thruster, bow horizontal propeller, bow vertical propeller, stern horizontal propeller, stern vertical propeller, rudder and elevator, and wherein the payload system comprises CTD (Conductivity-Temperature-Depth System), multibeam imaging sonar, side scan sonar, ADCP (Acoustic Doppler Current Profilers Sensor), imaging sensor, electronic sensor and composite sensor, and wherein the communication system comprises Wi-Fi modules, radio modules and acoustic communication modules, and wherein the energy system comprises power battery packs and instrument power packs. - Claim 5: The threat situation assessment system according to claim 3, wherein in step 2, prior probability and static Bayesian network structure are set by expert empirical method.
- Claim 6: The threat situation assessment system according to claim 3, wherein in step 3, structure of the dynamic Bayesian network comprises three parallel levels, being environment level, platform level and mission level respectively.
- Claim 7: The threat situation assessment system according to claim 3, wherein in step 3, prior probability setting and dynamic Bayesian network structure are based on static Bayesian network which is described in claim 3 step 2.
- Claim 8: The threat situation assessment system according to claim 3, wherein in step 4, the quantified data is preliminarily processed to generate data samples which can be input into the Bayesian network.
- Claim 9: The threat situation assessment system according to claim 3, wherein in step 5, the result of threat assessment and threat mode are obtained by reasoning.
- Claim 10: The threat situation assessment system according to claim 3, wherein in step 6, the result is the ranking of the threat factors at the current moment which is the priority processing basis for the planning decision of the UUV autonomous control system.
- Claim 11: The threat situation assessment system according to claim 3, wherein the task planning system is a subsystem of the autonomous control system which generates the optimal decision at each moment based on the results of the threat situation assessment.
- Claim 12: A UUV (Unmanned Underwater Vehicle), comprising an autonomous control system which comprises a threat assessment subsystem and a task planning subsystem, wherein the UUV is capable of assessing threat situation by performing an operation comprising the following steps:
Step (1) Analyzing elements of possible threat sources;
Step (2) Establishing static Bayesian network based on the results of Step 1;
Step (3) Establishing dynamic Bayesian network by adding time state transition probability to the static Bayesian network;
Step (4) Quantifying the threat factors in an actual case;
Step (5) Computing the data samples by the dynamic Bayesian network;
Step (6) Computing the data at each moment by the static Bayesian network and taking the sensitivity analysis;
Step (7) Computing the results of steps 5 and 6 for the task planning subsystem. - Claim 13: A UUV (Unmanned Underwater Vehicle), wherein the UUV comprises one or more processors and a memory containing computer program code that, when executed by operation of the one or more processors, perform an operation comprising the following steps for analyzing and assessing threat situation:
Step (1) Analyzing elements of possible threat sources;
Step (2) Establishing static Bayesian network based on the results of Step 1;
Step (3) Establishing dynamic Bayesian network by adding time state transition probability to the static Bayesian network;
Step (4) Quantifying the threat factors in an actual case;
Step (5) Computing the data samples by the dynamic Bayesian network;
Step (6) Computing the data at each moment by the static Bayesian network and taking the sensitivity analysis;
Step (7) Computing the results of steps 5 and 6 for a task planning subsystem of the UUV. - Claim 14: A threat situation assessment method for an Unmanned Underwater Vehicle (UUV), wherein the method comprises the following steps:
Step (1) Analyzing elements of possible threat sources;
Step (2) Establishing static Bayesian network based on the results of Step 1;
Step (3) Establishing dynamic Bayesian network by adding time state transition probability to the static Bayesian network;
Step (4) Quantifying the threat factors in an actual case;
Step (5) Computing the data samples by the dynamic Bayesian network;
Step (6) Computing the data at each moment by the static Bayesian network and taking the sensitivity analysis;
Step (7) Computing the results of steps 5 and 6 for a task planning system of the UUV. - Claim 15: A computer readable medium having recorded thereon instructions for execution by an Unmanned Underwater Vehicle (UUV), wherein the instructions are for carrying out a threat situation assessment operation comprising the following steps:
Step (1) Analyzing elements of possible threat sources;
Step (2) Establishing static Bayesian network based on the results of Step 1;
Step (3) Establishing dynamic Bayesian network by adding time state transition probability to the static Bayesian network;
Step (4) Quantifying the threat factors in an actual case;
Step (5) Computing the data samples by the dynamic Bayesian network;
Step (6) Computing the data at each moment by the static Bayesian network and taking the sensitivity analysis;
Step (7) Computing the results of steps 5 and 6 for task planning of the UUV.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910033312.5 | 2019-01-14 | ||
| CN201910033312.5A CN109711087B (en) | 2019-01-14 | 2019-01-14 | UUV dynamic threat situation assessment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA3067580A1 true CA3067580A1 (en) | 2020-07-14 |
Family
ID=66261268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA3067580A Abandoned CA3067580A1 (en) | 2019-01-14 | 2020-01-13 | Threat situation assessment systems and methods for unmanned underwater vehicle |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109711087B (en) |
| CA (1) | CA3067580A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112306076A (en) * | 2020-11-06 | 2021-02-02 | 西北工业大学 | Hybrid drive underwater robot dynamics model establishment method |
| CN112906881A (en) * | 2021-05-06 | 2021-06-04 | 中国科学院自动化研究所 | Man-machine confrontation knowledge data hybrid driving type decision-making method and device and electronic equipment |
| CN113065094A (en) * | 2021-03-24 | 2021-07-02 | 南京航空航天大学 | Situation assessment method and system based on accumulated foreground value and three-branch decision |
| CN116628449A (en) * | 2023-05-29 | 2023-08-22 | 西安航空学院 | Situation assessment method of graph-based adjacency point priority joint tree SAAD-JT algorithm |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110968836B (en) * | 2019-11-18 | 2023-05-02 | 哈尔滨工程大学 | UUV emergency decision method based on threat |
| CN110991647A (en) * | 2019-11-18 | 2020-04-10 | 哈尔滨工程大学 | UUV situation perception inference method based on ontology |
| CN110930024B (en) * | 2019-11-20 | 2024-04-26 | 大连海事大学 | Intelligent analysis system and method for deep sea emergency situation based on Bayesian network |
| CN113377119B (en) * | 2021-04-21 | 2023-05-09 | 北京控制工程研究所 | Spacecraft task deduction method and system based on capability model |
| CN113642237B (en) * | 2021-08-11 | 2024-03-26 | 浙江大学 | Underwater battlefield threat assessment and visual simulation system and method based on Bayesian network |
| CN114051220B (en) * | 2021-10-27 | 2024-04-16 | 上海智能网联汽车技术中心有限公司 | Ontology-based vehicle networking dynamic Bayesian attack graph generation method and system |
| CN114465758A (en) * | 2021-12-14 | 2022-05-10 | 哈尔滨理工大学 | Network situation awareness method based on Bayesian decision network |
| CN115143970B (en) * | 2022-09-01 | 2022-11-29 | 安徽大学 | Obstacle avoidance method and system of underwater vehicle based on threat degree evaluation |
| CN116633685A (en) * | 2023-07-19 | 2023-08-22 | 国家计算机网络与信息安全管理中心江西分中心 | Analysis method based on IPv6 development situation monitoring |
| CN117113216B (en) * | 2023-07-25 | 2024-06-28 | 北京理工大学重庆创新中心 | Heterogeneous multi-unmanned aerial vehicle hit decision method and device based on dynamic Bayesian network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107203493A (en) * | 2017-06-09 | 2017-09-26 | 西北工业大学 | Multiple target battle field situation method based on complicated ratio evaluation method |
| CN108594834B (en) * | 2018-03-23 | 2020-12-22 | 哈尔滨工程大学 | Multi-AUV self-adaptive target searching and obstacle avoiding method oriented to unknown environment |
| CN109146334A (en) * | 2018-10-09 | 2019-01-04 | 中国人民解放军海军航空大学 | A kind of multi-object Threat appraisal procedure suitable for high dynamic environment |
-
2019
- 2019-01-14 CN CN201910033312.5A patent/CN109711087B/en active Active
-
2020
- 2020-01-13 CA CA3067580A patent/CA3067580A1/en not_active Abandoned
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112306076A (en) * | 2020-11-06 | 2021-02-02 | 西北工业大学 | Hybrid drive underwater robot dynamics model establishment method |
| CN112306076B (en) * | 2020-11-06 | 2021-09-14 | 西北工业大学 | Hybrid drive underwater robot dynamics model establishment method |
| CN113065094A (en) * | 2021-03-24 | 2021-07-02 | 南京航空航天大学 | Situation assessment method and system based on accumulated foreground value and three-branch decision |
| CN113065094B (en) * | 2021-03-24 | 2024-07-09 | 南京航空航天大学 | Situation assessment method and system based on accumulated prospect value and three decisions |
| CN112906881A (en) * | 2021-05-06 | 2021-06-04 | 中国科学院自动化研究所 | Man-machine confrontation knowledge data hybrid driving type decision-making method and device and electronic equipment |
| CN116628449A (en) * | 2023-05-29 | 2023-08-22 | 西安航空学院 | Situation assessment method of graph-based adjacency point priority joint tree SAAD-JT algorithm |
| CN116628449B (en) * | 2023-05-29 | 2024-02-13 | 西安航空学院 | Situation assessment method of graph-based adjacency point priority joint tree SAAD-JT algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109711087B (en) | 2022-06-21 |
| CN109711087A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3067580A1 (en) | Threat situation assessment systems and methods for unmanned underwater vehicle | |
| Polvara et al. | Obstacle avoidance approaches for autonomous navigation of unmanned surface vehicles | |
| Tu et al. | Exploiting AIS data for intelligent maritime navigation: A comprehensive survey from data to methodology | |
| Wilthil et al. | Radar-based maritime collision avoidance using dynamic window | |
| Wolf et al. | 360‐degree visual detection and target tracking on an autonomous surface vehicle | |
| Johansen et al. | Ship collision avoidance using scenario-based model predictive control | |
| Johansen et al. | Unmanned aerial surveillance system for hazard collision avoidance in autonomous shipping | |
| US9983581B1 (en) | Artificial intelligence augmented reality command, control and communications system | |
| Iscar et al. | Towards low cost, deep water AUV optical mapping | |
| Benjamin et al. | Obstacle avoidance using multiobjective optimization and a dynamic obstacle manager | |
| EP4239433A1 (en) | High fidelity teammate state estimation for coordinated autonomous operations in communications denied environments | |
| Zhu et al. | A multi-UAV system for exploration and target finding in cluttered and GPS-denied environments | |
| Bremnes et al. | Intelligent risk-based under-ice altitude control for autonomous underwater vehicles | |
| Mohamed et al. | Neutrosophic MCDM methodology for risk assessment of autonomous underwater vehicles | |
| Belbachir et al. | A cooperative architecture for target localization using multiple AUVs | |
| Teacy et al. | Collaborative sensing by unmanned aerial vehicles | |
| Kapetanović et al. | A side-scan sonar data-driven coverage planning and tracking framework | |
| Acosta et al. | Some issues on the design of a low-cost autonomous underwater vehicle with an intelligent dynamic mission planner for pipeline and cable tracking | |
| Ferri et al. | Developing a robotic hybrid network for coastal surveillance: the INFORE experience | |
| Haller et al. | Unmanned underwater vehicle mission systems engineering product reuse return on investment | |
| Kicman et al. | Concept of integrated INS/visual system for autonomous mobile robot operation | |
| Murray | Machine Learning for Enhanced Maritime Situation Awareness: Leveraging Historical AIS Data for Ship Trajectory Prediction | |
| Allison et al. | Towards an AUV swarm based mobile underwater sensor network for invasive species data acquisition | |
| Wilthil | Maritime Target Tracking with Varying Sensor Performance | |
| Goh et al. | AUV Waypoint Re-planning for Optimal Sonar Area Coverage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FZDE | Discontinued |
Effective date: 20230526 |