WO2022241944A1 - 一种海空协同水下目标追踪的路径规划系统及方法 - Google Patents
一种海空协同水下目标追踪的路径规划系统及方法 Download PDFInfo
- Publication number
- WO2022241944A1 WO2022241944A1 PCT/CN2021/108070 CN2021108070W WO2022241944A1 WO 2022241944 A1 WO2022241944 A1 WO 2022241944A1 CN 2021108070 W CN2021108070 W CN 2021108070W WO 2022241944 A1 WO2022241944 A1 WO 2022241944A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- monitoring equipment
- underwater
- path planning
- path
- sea
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 claims abstract description 166
- 238000005457 optimization Methods 0.000 claims abstract description 59
- 238000001514 detection method Methods 0.000 claims abstract description 53
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 39
- 239000002245 particle Substances 0.000 claims description 114
- 230000006870 function Effects 0.000 claims description 44
- 238000004364 calculation method Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000012806 monitoring device Methods 0.000 abstract 8
- 239000003643 water by type Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/04—Control of altitude or depth
- G05D1/06—Rate of change of altitude or depth
- G05D1/0692—Rate of change of altitude or depth specially adapted for under-water vehicles
Definitions
- the invention relates to the technical field of unmanned platform path planning, in particular to a path planning system and method for sea-air collaborative underwater target tracking.
- unmanned surface vehicle When tracking missions in waters with unknown conditions, relying only on surface boats is very inefficient.
- the unmanned surface vehicle sails on the water surface and has a small detection area.
- the process of path planning is complicated, and the ability to identify the optimal channel in the overall sea area is very limited.
- unmanned surface vehicles have poor concealment and weak ability to track underwater targets.
- Sea, air and air monitoring equipment collaboration means that the sea and air monitoring equipment systems cooperate with each other as a whole in the processes of sensing the environment, planning paths, control behaviors, and decision-making, and at the same time independently process and calculate to complete the overall design goals.
- Aerial monitoring equipment navigates in the air and has the characteristics of flexibility, fewer obstacles, and a wide detection field of view, and can efficiently complete the detection task of the surface waterway environment; unmanned submersibles can navigate underwater and have strong concealment, but due to the complex underwater navigation environment, The environmental detection efficiency is low, which is suitable for short-distance channel detection and planning; the unmanned surface vehicle sails on the water surface, and the surface navigation environment is easier to detect than the underwater environment, which is conducive to long-distance path detection planning.
- the unmanned surface vehicle is relatively stable and has a strong load capacity, and can carry other types of unmanned aerial vehicles.
- problems such as low detection efficiency and inaccurate path planning in the cooperation of sea, air and air monitoring equipment. Therefore, how to use the mutual coordination of aerial monitoring equipment, unmanned surface vehicles and unmanned submarine vehicles to carry out accurate target tracking is an urgent problem to be solved.
- the present invention provides a path planning system for sea-air collaborative underwater target tracking, including an air monitoring equipment cluster, a sea surface monitoring equipment cluster, and an underwater monitoring equipment cluster, wherein:
- the aerial monitoring equipment cluster is used to obtain target position information of the detection target, perform first path planning along the channel of the surface monitoring equipment according to the target position information, and construct a route including the target position information and all obstacles in the channel of the sea surface monitoring equipment.
- a map of the surface navigation area of the information and transmitting the map of the surface navigation area to the cluster of sea surface monitoring equipment;
- the sea surface monitoring equipment cluster is used to perform second path planning along the sea surface monitoring equipment channel according to the water surface navigation area map and its own position information, to reach the adjacent area of the detection target, and to plan the second path of the adjacent area. Detecting the underwater environment, constructing an underwater obstacle environment map, and transmitting the underwater obstacle environment map to the underwater monitoring equipment cluster;
- the underwater monitoring equipment cluster is used to perform third path planning according to the underwater obstacle environment map, and track to the position of the detection target, so as to complete the tracking task.
- the present invention also provides a path planning method for sea-air collaborative underwater target tracking, based on the above-mentioned path planning system for sea-air collaborative underwater target tracking, including:
- Obtain the target position information of the detection target carry out the first path planning along the waterway of the surface monitoring equipment according to the target position information, construct a water surface navigation area map including the target position information and all obstacle information in the waterway of the sea surface monitoring equipment, and The water surface navigation area map is transmitted to the sea surface monitoring equipment cluster;
- the second path planning is carried out along the channel of the sea surface monitoring equipment to reach the adjacent area of the detection target, and the underwater environment in the adjacent area is detected to construct an underwater An obstacle environment map, and transmitting the underwater obstacle environment map to the underwater monitoring equipment cluster;
- a third path planning is performed to track to the position of the detection target, so as to complete the tracking task.
- the acquiring target position information of the detection target, and performing the first path planning along the waterway of the surface monitoring equipment according to the target position information include:
- the channel information and the target position information determine the air monitoring equipment channel, wherein the air monitoring equipment channel is a navigable airspace corresponding to the sea surface monitoring equipment channel;
- the first path planning is performed in the airway of the air monitoring equipment, and the path of the navigation detection of the air monitoring equipment cluster is planned, and the navigation is carried out.
- the constructing a water surface navigation area map including the target position information and all obstacle information in the channel of the sea surface monitoring equipment, and transferring the water surface navigation area map to the sea surface monitoring equipment cluster includes:
- the water surface is detected by the detection equipment in the channel of the air monitoring equipment, and the obstacle information along the channel of the sea surface monitoring equipment is collected and stored as coordinate data information;
- the water surface navigation area map is constructed according to the coordinate data information and the target position information, and the water surface navigation area map is transmitted to the sea surface monitoring equipment cluster.
- path planning steps of the first path planning, the second path planning and the third path planning include:
- the waypoint particle swarm includes the air monitoring equipment cluster corresponding to the first path planning, and the sea surface monitoring equipment cluster corresponding to the second path planning
- the initialization parameters include the number of cooperative populations, population size, particle dimension and initial velocity;
- the various iteration parameters include the space range of the channel, inertia factor, individual learning factor and group learning factor;
- the various iteration parameters according to Iteratively updating the coordinate data of path point particles includes:
- the coordinates of the path point particles are updated according to the updated speed and the current coordinate position of the particles.
- t indicates the current iteration number
- ⁇ t indicates the inertia factor corresponding to the current iteration number
- ⁇ t-1 indicates the inertia factor corresponding to the previous iteration number
- ⁇ max indicates the maximum value corresponding to the preset inertia factor
- ⁇ min indicates the preset inertia factor
- the minimum value corresponding to the set inertia factor, g represents the preset constant.
- the calculation process of the independent fitness includes:
- the weighted summation of the collision optimization function value, the turning optimization function value and the time optimization function is performed to determine the independent fitness.
- the calculation process of the turning optimization function value includes:
- the path angle, first distance and limit turning radius are calculated according to every three adjacent waypoints, which are expressed by the following formulas:
- ⁇ represents the described path angle determined by every three adjacent path points
- l represents the first distance
- l 1 represents the distance of the first two path points
- l 2 represents the distance of the latter two path points
- l 3 represents the distance between the first way point and the third way point
- ⁇ represents the limit turning radius, which is the maximum inscribed circle radius of the first distance l;
- tu(p k-1 , p k , p k+1 ) represents the value of the turning optimization function
- P k-1 , P k , P k+1 represent three adjacent path points in turn
- ⁇ represents the The limit turning radius
- R represents the minimum turning radius, for a single path point particle, if at least one of the turning optimization function value tu(p k-1 , p k , p k+1 ) is 0, then The turning optimization function value corresponding to a single path point particle is 0;
- the calculation process of the overall fitness includes:
- the optimal fitness is summed to determine the overall fitness.
- the beneficial effects of the present invention include: firstly, the target position information of the detection target is effectively obtained through the air monitoring equipment cluster, and the first path planning is carried out along the channel of the sea surface monitoring equipment, so as to carry out navigation, Carry out water obstacle detection during navigation, build a water surface navigation area map, and feed back all obstacle information in the sea surface monitoring equipment channel; then, receive the water surface navigation area map transmitted by the air monitoring equipment cluster through the sea surface monitoring equipment cluster, based on the water surface navigation area Obstacle information, target location information, and self-location information in the map, the second path planning is carried out along the channel of the sea surface monitoring equipment until reaching the adjacent area of the detection target, and then the underwater environment in the adjacent area is further detected, and the underwater environment is constructed and transmitted.
- the present invention adopts collaborative optimization of aerial monitoring equipment clusters, sea surface monitoring equipment clusters and underwater monitoring equipment clusters to reduce the number of iterations, improve optimization efficiency, make path planning reasonable, quickly track target positions, and improve autonomous collaborative tracking capabilities.
- FIG. 1 is a schematic flow chart of an embodiment of a path planning method for sea-air cooperative underwater target tracking provided by the present invention
- Fig. 2 is a schematic flow diagram of an embodiment of step S1 in Fig. 1 provided by the present invention
- Fig. 3 is a schematic flow diagram 2 of an embodiment of step S1 in Fig. 1 provided by the present invention
- FIG. 4 is a schematic flowchart of an embodiment of path planning provided by the present invention.
- FIG. 5 is a schematic flowchart of an embodiment of step S04 in FIG. 4 provided by the present invention.
- FIG. 6 is a schematic flow chart of an embodiment of calculating independent fitness provided by the present invention.
- Fig. 7 is a schematic flowchart of an embodiment of calculating the overall fitness provided by the present invention.
- An embodiment of the present invention provides a path planning system for sea-air collaborative underwater target tracking, including an air monitoring equipment cluster, a sea surface monitoring equipment cluster, and an underwater monitoring equipment cluster, wherein:
- the aerial monitoring equipment cluster is used to obtain the target position information of the detection target, perform the first path planning along the channel of the surface monitoring equipment according to the target position information, and construct a surface navigation area map including the target position information and all obstacle information in the channel of the sea surface monitoring equipment , and transmit the surface navigation area map to the sea surface monitoring equipment cluster; it can be understood that the air monitoring equipment cluster is generally a UAV cluster;
- the sea surface monitoring equipment cluster is used to plan the second path along the waterway of the surface monitoring equipment according to the surface navigation area map and its own position information, reach the adjacent area of the detection target, and detect the underwater environment in the adjacent area to build underwater obstacles object environment map, and transmit the underwater obstacle environment map to the underwater monitoring equipment cluster; it can be understood that the sea surface monitoring equipment cluster is generally an unmanned boat cluster;
- the underwater monitoring equipment cluster is used to plan the third path according to the underwater obstacle environment map, and track to the position of the detection target to complete the tracking task; it can be understood that the underwater monitoring equipment cluster is generally a submersible vehicle cluster.
- the target position information of the detection target is effectively acquired through the air monitoring equipment cluster, and the first path planning is carried out along the channel of the sea surface monitoring equipment, so as to carry out navigation, and the water area obstacle detection is carried out during the navigation process , build a surface navigation area map, and feed back all obstacle information in the channel of the sea surface monitoring equipment; receive the water surface navigation area map transmitted by the air monitoring equipment cluster through the sea surface monitoring equipment cluster, based on the obstacle information, target position information and self Position information, carry out the second path planning along the sea surface monitoring equipment channel until reaching the adjacent area of the detection target, and then further detect the underwater environment in the adjacent area, construct and transmit the underwater obstacle environment map; through the underwater monitoring equipment cluster The underwater obstacle environment map is received, and based on the underwater obstacle environment information in the adjacent area in the underwater obstacle environment map, the third path planning is continued to track to the position of the detection target.
- FIG. 1 is a schematic flow chart of an embodiment of the path planning method for sea-air collaborative underwater target tracking provided by the present invention.
- a path planning system based on the above-mentioned sea-air cooperative underwater target tracking, including steps S1 to S3, wherein:
- step S1 the target position information of the detection target is obtained, the first path planning is carried out along the channel of the surface monitoring equipment according to the target position information, and a water surface navigation area map including the target position information and all obstacle information in the channel of the sea surface monitoring equipment is constructed, and Transfer the surface navigation area map to the sea surface monitoring equipment cluster;
- step S2 according to the surface navigation area map and its own position information, the second path planning is carried out along the waterway of the surface monitoring equipment to reach the adjacent area of the detection target, and the underwater environment in the adjacent area is detected to build an underwater obstacle environment map, and transmit the underwater obstacle environment map to the underwater monitoring equipment cluster;
- step S3 a third path planning is performed according to the underwater obstacle environment map, and the location of the detection target is tracked to complete the tracking task.
- the target position information of the detection target is effectively acquired through the air monitoring equipment cluster, and the first path planning is carried out along the channel of the sea surface monitoring equipment, so as to carry out navigation, and the water obstacle Object detection, build a surface navigation area map, and feed back all obstacle information in the channel of the sea surface monitoring equipment; then, receive the water surface navigation area map transmitted by the air monitoring equipment cluster through the sea surface monitoring equipment cluster, based on the obstacle information and target of the water surface navigation area map Position information and its own position information, carry out the second path planning along the channel of the sea surface monitoring equipment until reaching the adjacent area of the detection target, and then further detect the underwater environment in the adjacent area, construct and transmit the underwater obstacle environment map; finally, The underwater obstacle environment map is received by the underwater monitoring equipment cluster, and based on the underwater obstacle environment information in the adjacent area in the underwater obstacle environment map, the third path planning is continued to track to the position of the detection target.
- FIG. 2 is a schematic flow diagram of an embodiment of step S1 in FIG. 1 provided by the present invention.
- Step S1 includes steps S11 to S13, wherein:
- step S11 the starting position of the air monitoring equipment cluster, the channel information and the target position information of the sea surface monitoring equipment channel are obtained;
- step S12 according to the starting position, the channel information and the target position information, the air monitoring equipment channel is determined, wherein the air monitoring equipment channel is the navigable airspace corresponding to the sea surface monitoring equipment channel;
- step S13 the first path planning is performed in the airway of the aerial monitoring equipment, and the path of the navigation detection of the airborne monitoring equipment cluster is planned, and the navigation is performed.
- the embodiment of the present invention obtains the initial position of the aerial monitoring equipment, combines the known basic information of the sea surface monitoring equipment channel, generates the corresponding navigation airspace environment information of the aerial monitoring equipment, and plans the airspace in the navigable airspace of the aerial monitoring equipment. Monitor the path of the navigation probe of the device cluster and conduct navigation.
- FIG. 3 is a schematic flow diagram of an embodiment of step S1 in FIG. 1 provided by the present invention.
- Step S1 includes step S14 to step S15, wherein:
- step S14 during the group navigation process of the air monitoring equipment, the water surface is detected by the detection equipment in the waterway of the air monitoring equipment, and the obstacle information along the waterway of the surface monitoring equipment is collected and stored as coordinate data information;
- step S15 a water surface navigation area map is constructed according to the coordinate data information and the target position information, and the water surface navigation area map is transmitted to the sea surface monitoring equipment cluster.
- the air monitoring equipment cluster collects obstacle information along the road through the detection equipment, stores it as coordinate data information, and transmits the complete obstacle coordinate information to the sea surface monitoring equipment cluster.
- FIG. 4 is a schematic flowchart of an embodiment of path planning provided by the present invention, including steps S01 to S05, wherein:
- step S01 the set initialization parameters are obtained, and the waypoint particle swarm is initialized, wherein the waypoint particle swarm includes the air monitoring equipment cluster corresponding to the first path planning, the sea surface monitoring equipment cluster corresponding to the second path planning, and the third path planning Corresponding subsea monitoring equipment cluster;
- step S02 various iteration parameters and the number of iterations set are obtained.
- step S03 adding the coordinates of the starting position of the particle and the coordinates of the ending position of the particle into the path point particle group, and determining the initial route coordinate matrix
- step S04 the independent fitness and the overall fitness corresponding to the current position of each particle are calculated, and the coordinate data of the path point particles are iteratively updated according to various iteration parameters, wherein the overall fitness is based on the independent adaptation of all the path point particle swarms determined by degree;
- step S05 when the number of iterations is reached, the iteration ends, and the coordinates of the optimal path point are output.
- the embodiment of the present invention first performs effective particle initialization, and then performs collaborative optimization between particle swarms through independent fitness and overall fitness to achieve iterative updating, thereby completing optimal path planning.
- the air monitoring equipment is used to detect the target water area, and the detected obstacle position information is combined with the existing chart channel information to serve as the navigation environment of the unmanned surface vehicle; and then Using the cooperative particle swarm optimization algorithm, the long-distance optimal tracking path planning of the unmanned surface vehicle swarm is carried out. After the sea surface monitoring equipment cluster reaches the preset underwater target near the waters, the underwater area detection is carried out, and the known underwater environment information is integrated as the navigation environment of the submersible; Distance underwater tracking path planning.
- the present invention Compared with homogeneous unmanned equipment cluster tracking targets, the present invention effectively detects unknown navigation waters, and can find the optimal navigation path, and the planning process is more reasonable; the efficiency of long-distance surface navigation and short-distance underwater navigation cooperative tracking is higher. High; at the same time, the present invention uses a method of collaborative optimization of multiple particle swarms, which reduces the mutual interference of particles, avoids the optimization from falling into a local optimal solution, improves the optimization efficiency, and reduces the number of iterations and time.
- the number of coordinated particle swarms is the number of aircraft.
- different cooperative particle swarms are optimized independently according to the category of the vehicle.
- each aircraft path is regarded as an independent optimization target, and different path point populations are iteratively updated independently; at the same time, the penalty function information of each population is shared and included in the calculation of the overall fitness, and the fitness is used as overall optimization goal.
- the initialization parameters include the number of cooperative populations, population size, particle dimension and initial velocity.
- the embodiment of the present invention completes effective particle initialization by setting various initialization parameters.
- the multiple iteration parameters include the space range of the channel, inertia factor, individual learning factor and group learning factor.
- various iteration parameters are set to update the particle velocity and position.
- the first step is to set the cooperative population number nn of the particle swarm, the population size P, the particle dimension dim, and the initial velocity v, and then initialize the path point particle swarm;
- the second step is to set the space range of the channel, the inertia factor ⁇ , the learning factors c1 and c2, and the number of iterations g;
- the third step is to add the start and end position coordinates to the path point particle swarm to form the initial route coordinate matrix
- the fourth step is to calculate the cost function first, then calculate the fitness value, and iteratively update the coordinate data of the path point particles according to the fitness value;
- the fifth step is to reach the maximum number of iterations and end the iteration. Output the optimal path point coordinates to complete the path planning of unmanned equipment.
- FIG. 5 is a schematic flowchart of an embodiment of step S04 in FIG. 4 provided by the present invention.
- Step S04 includes steps S041 to S042, wherein:
- step S041 the velocity of the waypoint particles is updated according to the space range of the channel, the inertia factor, the individual learning factor and the group learning factor.
- step S042 according to the updated velocity and the current coordinate position of the particle, the coordinates of the particle at the waypoint are updated.
- the embodiment of the present invention first updates the speed through the channel space range, inertia factor, individual learning factor and group learning factor, and then updates the corresponding coordinates according to the updated speed and the current coordinate position of the particle.
- update the speed of the waypoint particle (take the speed and position update formula in the x direction as an example), expressed by the following formula:
- vx ⁇ vx+c1 ⁇ rand(0,1) ⁇ (pbest-posx)+c2 ⁇ rand(0,1) ⁇ (gbest-posx);
- vx is the velocity of the particle in the x-axis direction
- posx is the position of the particle in the x-axis direction
- ⁇ is the inertia factor
- c1 is the individual learning factor
- c2 is the group learning factor
- pbest individual optimal particle position in the x-axis direction is a random number between 0 and 1.
- rand(0,1) is a random number between 0 and 1.
- the inertia factor decreases uniformly as the number of iterations increases, expressed by the following formula:
- t indicates the current iteration number
- ⁇ t indicates the inertia factor corresponding to the current iteration number
- ⁇ t-1 indicates the inertia factor corresponding to the previous iteration number
- ⁇ max indicates the maximum value corresponding to the preset inertia factor
- ⁇ min indicates the preset inertia factor
- the minimum value corresponding to the set inertia factor, g represents the preset constant.
- the embodiment of the present invention implements iterative updating of speed and position through gradient descent updating of inertial factors.
- FIG. 6 is a schematic flowchart of an embodiment of calculating independent fitness provided by the present invention, including steps S043 to S044, wherein:
- step S043 for a single waypoint particle, determine the corresponding collision optimization function value, turning optimization function value and time optimization function;
- step S044 the collision optimization function value, the turning optimization function value and the time optimization function are weighted and summed to determine the independent fitness.
- the embodiment of the present invention sets the collision optimization function value, the turning optimization function value and the time optimization function, so as to obtain the independent fitness, and independently optimize a single path point particle, and at the same time, combine the particle swarm Overall fitness, independent optimization of different cooperating particle swarms.
- the calculation process of the turning optimization function value includes:
- the path angle, first distance and limit turning radius are calculated according to every three adjacent waypoints, which are expressed by the following formulas:
- ⁇ represents the path angle determined by every three adjacent path points
- l represents the first distance
- l 1 represents the distance between the first two path points
- l 2 represents the distance between the last two path points
- l 3 represents the first The distance between the first waypoint and the third waypoint
- ⁇ represents the limit turning radius, which is the maximum inscribed circle radius of the first distance l;
- the turning optimization function value is determined, expressed by the following formula:
- tu(p k-1 , p k , p k+1 ) represents the turning optimization function value
- P k-1 , P k , P k+1 represent three adjacent path points in turn
- ⁇ represents the limit turning radius
- R represents the minimum turning radius.
- the embodiment of the present invention performs a corresponding solution to the collision optimization function value, the turning optimization function value and the time optimization function, so as to obtain the corresponding independent fitness, which is convenient for iterative update of particles.
- FIG. 7 is a schematic flowchart of an embodiment of calculating the overall fitness provided by the present invention, including steps S045 to S046, wherein:
- step S045 the independent fitness of each corresponding particle is determined for the air monitoring equipment cluster, the sea surface monitoring equipment cluster and the underwater monitoring equipment cluster respectively;
- step S046 according to the independent fitness, determine the optimal fitness corresponding to different clusters
- step S047 the optimal fitness is summed to determine the overall fitness.
- the embodiment of the present invention utilizes the overall fitness to realize the collaborative optimization of multiple particle swarms, which reduces the mutual interference of particles and prevents the optimization from falling into a local optimal solution.
- the invention discloses a path planning system and method for sea-air cooperative underwater target tracking. Firstly, the target position information of the detection target is effectively acquired through the air monitoring equipment cluster, and the first path planning is performed along the channel of the sea surface monitoring equipment. , use this to navigate, detect obstacles in the water area during the navigation process, construct a surface navigation area map, and feed back all obstacle information in the channel of the sea surface monitoring equipment; then, receive the water surface navigation area transmitted by the air monitoring equipment cluster through the sea surface monitoring equipment cluster Figure, based on the obstacle information, target location information and self-location information of the surface navigation area map, the second path planning is carried out along the channel of the sea surface monitoring equipment until reaching the adjacent area of the detection target, and then the underwater environment in the adjacent area is further detected , build and transmit the underwater obstacle environment map; finally, receive the underwater obstacle environment map through the underwater monitoring equipment cluster, and proceed to the third step based on the underwater obstacle environment information in the adjacent area in the underwater obstacle environment map Path planning, tracking to the location of the detection target.
- the technical solution of the present invention by dividing different aircraft into different particle groups, sharing information with each other, and synchronous iterative evolution, solves the problem of collaborative tracking targets among multiple heterogeneous aircraft, that is, air monitoring equipment, sea surface monitoring equipment, and underwater monitoring equipment clusters path planning problem.
- the technical solution provided by the invention has flexible application scenarios and can effectively adapt to unknown waterways; the collaborative particle swarm algorithm reduces the number of iterations and improves optimization efficiency; the path planning is reasonable and can quickly track the target position; Autonomous collaborative tracking capability of swarms in unknown obstacle waters.
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
一种海空协同水下目标追踪的路径规划系统及方法，该方法包括：空中监测设备集群获取探测目标的目标位置信息，沿海面监测设备航道进行第一路径规划，构建水面航行区域图，并将水面航行区域图传递至海面监测设备集群；海面监测设备集群根据水面航行区域图和自身位置信息，沿海面监测设备航道进行第二路径规划，到达探测目标的临近区域，并对临近区域的水下环境进行探测，构建水下障碍物环境图，并将水下障碍物环境图传递至海下监测设备集群；海下监测设备集群根据水下障碍物环境图，进行第三路径规划，追踪至探测目标的位置。上述方法采用集群协同优化，减少迭代次数，提高优化效率，快速追踪目标位置，提高自主协同追踪能力。
Description
本发明涉及无人平台路径规划技术领域，尤其涉及一种海空协同水下目标追踪的路径规划系统及方法。
在状况不明的水域进行追踪任务时，仅依靠水面艇追踪的效率十分低下。无人水面艇在水面航行，探测区域较小。特别是在复杂水域航行时，十分依赖及时避障，路径规划的过程复杂，识别整体海域最优航道的能力十分有限。同时，无人水面艇隐蔽性差，追踪水下目标能力较弱。
海空空中监测设备协同是指海、空中监测设备系统在感知环境、规划路径、控制行为、决策下达等流程中，整体上相互协同进行，同时也分别独立处理和运算，来完成整体设计目标的过程。空中监测设备在空中航行，具有灵活、障碍少、探测视野开阔等特点，能高效完成水面航道环境探测任务；无人潜航器能在水下航行，隐蔽性强，但由于水下航行环境复杂、环境探测效率低，适合短距离航道探测和规划；无人水面艇在水面航行，水面航行环境较于水下环境更易探测，有利于进行较远距离的路径探测规划。同时无人水面艇较为稳定、负载能力强，可以携带其他类型的无人航行器。但现有技术中，海空空中监测设备协同存在探测效率低、路径规划不准确等问题，这是源于未充分利用、发挥空中监测设备、无人水面艇和无人潜航器的各自优势。因此，如何利用空中监测设备、无人水面艇和无人潜航器的相互协同进行准确的目标追踪是亟待解决的问题。
发明内容
有鉴于此，有必要提供一种海空协同水下目标追踪的路径规划系统及方法， 用以解决现有技术中空中监测设备、无人水面艇和无人潜航器无法协同进行准确的目标追踪的问题。
本发明提供一种海空协同水下目标追踪的路径规划系统，包括空中监测设备集群、海面监测设备集群以及海下监测设备集群，其中：
所述空中监测设备集群，用于获取探测目标的目标位置信息，根据所述目标位置信息沿海面监测设备航道进行第一路径规划，构建包含所述目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将所述水面航行区域图传递至所述海面监测设备集群；
所述海面监测设备集群，用于根据所述水面航行区域图和自身位置信息，沿所述海面监测设备航道进行第二路径规划，到达所述探测目标的临近区域，并对所述临近区域的水下环境进行探测，构建水下障碍物环境图，并将所述水下障碍物环境图传递至所述海下监测设备集群；
所述海下监测设备集群，用于根据所述水下障碍物环境图，进行第三路径规划，追踪至所述探测目标的位置，以完成追踪任务。
本发明还提供一种海空协同水下目标追踪的路径规划方法，基于如上所述的海空协同水下目标追踪的路径规划系统，包括：
获取探测目标的目标位置信息，根据所述目标位置信息沿海面监测设备航道进行第一路径规划，构建包含所述目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将所述水面航行区域图传递至海面监测设备集群；
根据所述水面航行区域图和自身位置信息，沿所述海面监测设备航道进行第二路径规划，到达所述探测目标的临近区域，并对所述临近区域的水下环境进行探测，构建水下障碍物环境图，并将所述水下障碍物环境图传递至海下监测设备集群；
根据所述水下障碍物环境图，进行第三路径规划，追踪至所述探测目标的位置，以完成追踪任务。
进一步地，所述获取探测目标的目标位置信息，根据所述目标位置信息沿海面监测设备航道进行第一路径规划包括：
获取空中监测设备集群的起始位置、海面监测设备航道的航道信息和所述目标位置信息；
根据所述起始位置、所述航道信息和所述目标位置信息，确定空中监测设备航道，其中，所述空中监测设备航道是与所述海面监测设备航道对应的可航行空域；
在所述空中监测设备航道中进行第一路径规划，规划空中监测设备集群的航行探测的路径，并进行航行。
进一步地，所述构建包含所述目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将所述水面航行区域图传递至海面监测设备集群包括：
在所述空中监测设备集群航行的过程中，在所述空中监测设备航道中通过探测设备探测水面，搜集沿所述海面监测设备航道的障碍物信息，储存为坐标数据信息；
根据所述坐标数据信息和所述目标位置信息，构建所述水面航行区域图，并将所述水面航行区域图传递至所述海面监测设备集群。
进一步地，所述第一路径规划、所述第二路径规划以及所述第三路径规划的路径规划步骤包括：
获取设置的初始化参数，初始化路径点粒子群，其中，所述路径点粒子群包括所述第一路径规划对应的所述空中监测设备集群、所述第二路径规划对应的所述海面监测设备集群和所述第三路径规划对应的所述海下监测设备集群；
获取设置的多种迭代参数和迭代次数；
将粒子起始位置坐标和粒子终点位置坐标加入所述路径点粒子群，确定初始航线坐标矩阵；
计算各粒子当前位置对应的独立适应度和整体适应度，根据所述多种迭代 参数迭代更新路径点粒子的坐标数据，其中，所述整体适应度为根据所有所述路径点粒子群中的独立适应度而确定；
当达到所述迭代次数时结束迭代，输出最优路径点坐标。
进一步地，所述初始化参数包括协同种群数目、种群大小、粒子维度和初始速度；所述多种迭代参数包括航道空间范围、惯性因子、个体学习因子和群体学习因子；所述根据多种迭代参数迭代更新路径点粒子的坐标数据包括：
根据所述航道空间范围、所述惯性因子、所述个体学习因子和所述群体学习因子，更新所述路径点粒子的速度；
根据更新后的速度和粒子当前坐标位置，更新所述路径点粒子的坐标。
进一步地，所述惯性因子随着所述迭代次数的增加而均匀减小，通过如下公式表示：
其中，t表示当前迭代次数，ω
t表示当前迭代次数对应的惯性因子，ω
t-1表示上一迭代次数对应的惯性因子，ω
max表示预设的惯性因子对应的最大值，ω
min表示预设的惯性因子对应的最小值，g表示预设常数。
进一步地，所述独立适应度的计算过程包括：
针对单个路径点粒子，确定对应的碰撞优化函数值、转弯优化函数值和时间优化函数；
将所述碰撞优化函数值、所述转弯优化函数值和所述时间优化函数进行加权求和，确定所述独立适应度。
进一步地，所述转弯优化函数值的计算过程包括：
针对单个路径点粒子，根据每三个相邻路径点计算路径夹角、第一距离和极限转弯半径，分别通过如下公式表示：
l＝min(l
1,l
2)
其中，α表示每三个相邻路径点确定的所述路径夹角，l表示所述第一距离，l
1表示前两个路径点的距离，l
2表示后两个路径点的距离，l
3表示第一个路径点和第三个路径点的距离，ρ表示所述极限转弯半径，为所述第一距离l的最大内切圆半径；
根据所述极限转弯半径和海面监测设备的最小转弯半径，确定所述转弯优化函数值，通过如下公式表示：
其中，tu(p
k-1，p
k，p
k+1)表示所述转弯优化函数值，P
k-1，P
k，P
k+1依次表示三个相邻的路径点，ρ表示所述极限转弯半径，R表示所述最小转弯半径，针对单个路径点粒子，若至少有一个所述转弯优化函数值tu(p
k-1，p
k，p
k+1)取值为0，则单个路径点粒子对应的转弯优化函数值取0；
针对单个路径点粒子，对应的时间优化函数通过如下公式表示：
l
i＝min(l
ij)，j＝1,……,P
其中，l
ijk表示第i个粒子种群，第j个粒子，第k组相邻路径点的距离；l
ij表示第i个粒子种群，第j个粒子的路径总长度；l
i表示第i个粒子种群的最小航行距离；t
i表示第i个粒子种群的最小航行时间；tim表示i个协同种群平均最小航行时间；v
i表示第i个粒子种群的航行速度；nn表示粒子群的协同种群 数目。
进一步地，所述整体适应度的计算过程包括：
分别针对空中监测设备集群、所述海面监测设备集群以及所述海下监测设备集群，确定对应的每个粒子的所述独立适应度；
根据所述独立适应度，确定不同集群对应的最优适应度；
将所述最优适应度进行求和，确定所述整体适应度。
与现有技术相比，本发明的有益效果包括：首先，通过空中监测设备集群对探测目标的目标位置信息进行有效的获取，沿着海面监测设备航道进行第一路径规划，以此进行航行，在航行过程中进行水域障碍物探测，构建水面航行区域图，反馈海面监测设备航道中所有障碍物信息；然后，通过海面监测设备集群接收空中监测设备集群传递的水面航行区域图，基于水面航行区域图的障碍物信息、目标位置信息以及自身位置信息，沿着海面监测设备航道进行第二路径规划直到到达探测目标的临近区域，再进一步对临近区域的水下环境进行探测，构建并传递水下障碍物环境图；最后，通过海下监测设备集群接收水下障碍物环境图，基于水下障碍物环境图中的临近区域的水下障碍物环境信息，继续进行第三路径规划，追踪至探测目标的位置。综上，本发明采用空中监测设备集群、海面监测设备集群以及海下监测设备集群协同优化，减少迭代次数，提高优化效率，路径规划合理，快速追踪目标位置，提高自主协同追踪能力。
图1为本发明提供的海空协同水下目标追踪的路径规划方法一实施例的流程示意图；
图2为本发明提供的图1中步骤S1一实施例的流程示意图一；
图3为本发明提供的图1中步骤S1一实施例的流程示意图二；
图4为本发明提供的路径规划一实施例的流程示意图；
图5为本发明提供的图4步骤S04一实施例的流程示意图；
图6为本发明提供的计算独立适应度一实施例的流程示意图；
图7为本发明提供的计算整体适应度一实施例的流程示意图。
下面结合附图来具体描述本发明的优选实施例，其中，附图构成本申请一部分，并与本发明的实施例一起用于阐释本发明的原理，并非用于限定本发明的范围。
本发明实施例提供了一种海空协同水下目标追踪的路径规划系统，包括空中监测设备集群、海面监测设备集群以及海下监测设备集群，其中：
空中监测设备集群，用于获取探测目标的目标位置信息，根据目标位置信息沿海面监测设备航道进行第一路径规划，构建包含目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将水面航行区域图传递至海面监测设备集群；可以理解的是，空中监测设备集群一般为无人机集群；
海面监测设备集群，用于根据水面航行区域图和自身位置信息，沿海面监测设备航道进行第二路径规划，到达探测目标的临近区域，并对临近区域的水下环境进行探测，构建水下障碍物环境图，并将水下障碍物环境图传递至海下监测设备集群；可以理解的是，海面监测设备集群一般为无人艇集群；
海下监测设备集群，用于根据水下障碍物环境图，进行第三路径规划，追踪至探测目标的位置，以完成追踪任务；可以理解的是，海下监测设备集群一般为潜航器集群。
在本发明实施例中，通过空中监测设备集群对探测目标的目标位置信息进行有效的获取，沿着海面监测设备航道进行第一路径规划，以此进行航行，在航行过程中进行水域障碍物探测，构建水面航行区域图，反馈海面监测设备航道中所有障碍物信息；通过海面监测设备集群接收空中监测设备集群传递的水面航行区域图，基于水面航行区域图的障碍物信息、目标位置信息以及自身位置信息，沿着海面监测设备航道进行第二路径规划直到到达探测目标的临近区域，再进一步对临近区域的水下环境进行探测，构建并传递水下障碍物环境图；通过海下监测设备集群接收水下障碍物环境图，基于水下障碍物环境图中的临 近区域的水下障碍物环境信息，继续进行第三路径规划，追踪至探测目标的位置。
本发明实施例提供了一种海空协同水下目标追踪的路径规划方法，结合图1来看，图1为本发明提供的海空协同水下目标追踪的路径规划方法一实施例的流程示意图，基于上述的海空协同水下目标追踪的路径规划系统，包括步骤S1至步骤S3，其中：
在步骤S1中，获取探测目标的目标位置信息，根据目标位置信息沿海面监测设备航道进行第一路径规划，构建包含目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将水面航行区域图传递至海面监测设备集群；
在步骤S2中，根据水面航行区域图和自身位置信息，沿海面监测设备航道进行第二路径规划，到达探测目标的临近区域，并对临近区域的水下环境进行探测，构建水下障碍物环境图，并将水下障碍物环境图传递至海下监测设备集群；
在步骤S3中，根据水下障碍物环境图，进行第三路径规划，追踪至探测目标的位置，以完成追踪任务。
在本发明实施例中，首先，通过空中监测设备集群对探测目标的目标位置信息进行有效的获取，沿着海面监测设备航道进行第一路径规划，以此进行航行，在航行过程中进行水域障碍物探测，构建水面航行区域图，反馈海面监测设备航道中所有障碍物信息；然后，通过海面监测设备集群接收空中监测设备集群传递的水面航行区域图，基于水面航行区域图的障碍物信息、目标位置信息以及自身位置信息，沿着海面监测设备航道进行第二路径规划直到到达探测目标的临近区域，再进一步对临近区域的水下环境进行探测，构建并传递水下障碍物环境图；最后，通过海下监测设备集群接收水下障碍物环境图，基于水下障碍物环境图中的临近区域的水下障碍物环境信息，继续进行第三路径规划，追踪至探测目标的位置。
作为优选的实施例，结合图2来看，图2为本发明提供的图1中步骤S1一实施例的流程示意图一，步骤S1包括步骤S11至步骤S13，其中：
在步骤S11中，获取空中监测设备集群的起始位置、海面监测设备航道的航道信息和目标位置信息；
在步骤S12中，根据起始位置、航道信息和目标位置信息，确定空中监测设备航道，其中，空中监测设备航道是与海面监测设备航道对应的可航行空域；
在步骤S13中，在空中监测设备航道中进行第一路径规划，规划空中监测设备集群的航行探测的路径，并进行航行。
作为具体实施例，本发明实施例获得空中监测设备的起始位置，结合已知的海面监测设备航道的基础信息，生成对应空中监测设备航行空域环境信息，在空中监测设备可航行空域，规划空中监测设备集群的航行探测的路径，并进行航行。
作为优选的实施例，结合图3来看，图3为本发明提供的图1中步骤S1一实施例的流程示意图二，步骤S1包括步骤S14至步骤S15，其中：
在步骤S14中，在空中监测设备集群航行的过程中，在空中监测设备航道中通过探测设备探测水面，搜集沿海面监测设备航道的障碍物信息，储存为坐标数据信息；
在步骤S15中，根据坐标数据信息和目标位置信息，构建水面航行区域图，并将水面航行区域图传递至海面监测设备集群。
作为具体实施例，本发明实施例航行过程中，空中监测设备集群通过探测设备，搜集沿路的障碍物信息，储存为坐标数据信息，将完整的障碍坐标信息传输给海面监测设备集群。
作为优选的实施例，结合图4来看，图4为本发明提供的路径规划一实施例的流程示意图，包括步骤S01至步骤S05，其中：
在步骤S01中，获取设置的初始化参数，初始化路径点粒子群，其中，路径点粒子群包括第一路径规划对应的空中监测设备集群、第二路径规划对应的 海面监测设备集群和第三路径规划对应的海下监测设备集群；
在步骤S02中，获取设置的多种迭代参数和迭代次数；
在步骤S03中，将粒子起始位置坐标和粒子终点位置坐标加入路径点粒子群，确定初始航线坐标矩阵；
在步骤S04中，计算各粒子当前位置对应的独立适应度和整体适应度，根据多种迭代参数迭代更新路径点粒子的坐标数据，其中，整体适应度为根据所有路径点粒子群中的独立适应度而确定；
在步骤S05中，当达到迭代次数时结束迭代，输出最优路径点坐标。
作为具体实施例，本发明实施例首先进行有效的粒子初始化，再通过独立适应度和整体适应度进行粒子群之间的协同优化，实现迭代更新，以此完成最优的路径规划。
需要说明的是，本发明路径规划的算法中，利用空中监测设备探测目标水域，将探测到的障碍物位置信息与已有的海图航道信息相结合，作为无人水面艇的航行环境；然后使用协同的粒子群算法，进行无人水面艇集群的长距离最优的追踪路径规划。海面监测设备集群达到预设的水下目标临近水域后，通过进行水下区域探测，整合已知的水下环境信息，作为潜航器的航行环境；最后利用协同粒子群算法，进行潜航器的短距离水下追踪路径规划。相比于同质无人设备集群追踪目标，本发明有效探测未知的航行水域，并能找到最优航行路径，规划过程更为合理；长距离水面航行、短距离水下航行合作追踪的效率更高；同时本发明使用多个粒子群协同优化的方法，减少了粒子的相互干扰，避免了优化陷入局部最优解，提升了优化效率，减少了迭代次数和时间。
需要说明的是，协同种群数目的设置中，协同的粒子群数量为航行器的数量。在迭代优化过程中，按照航行器的类别，对不同的协同粒子群进行独立优化。协同优化的过程中，把每个航行器路径作为独立的优化目标，对不同的路径点种群进行独立迭代更新；同时，每个种群的惩罚函数信息共享，纳入整体适应度的计算，适应度作为整体的优化目标。
作为优选的实施例，初始化参数包括协同种群数目、种群大小、粒子维度和初始速度。作为具体实施例，本发明实施例通过设置多种初始化参数，完成有效的粒子初始化。
作为优选的实施例，多种迭代参数包括航道空间范围、惯性因子、个体学习因子和群体学习因子。作为具体实施例，本发明实施例设置多种迭代参数，完成粒子速度和位置的更新。
在本发明一个具体的实施例中，路径规划的具体步骤如下：
第一步，设置粒子群的协同种群数目nn，种群大小P、粒子维度dim、初始速度v，然后初始化路径点粒子群；
第二步，设置航道空间范围、惯性因子ω、学习因子c1和c2、迭代次数g；
第三步，把起始和终点位置坐标加入路径点粒子群，形成初始航线坐标矩阵；
第四步，先计算代价函数，然后计算适应度值，根据适应度值迭代更新路径点粒子的坐标数据；
第五步，达到迭代最大次数，结束迭代。输出最优路径点坐标，完成无人设备的路径规划。
作为优选的实施例，结合图5来看，图5为本发明提供的图4步骤S04一实施例的流程示意图，步骤S04包括步骤S041至步骤S042，其中：
在步骤S041中，根据航道空间范围、惯性因子、个体学习因子和群体学习因子，更新路径点粒子的速度。
在步骤S042中，根据更新后的速度和粒子当前坐标位置，更新路径点粒子的坐标。
作为具体实施例，本发明实施例通过航道空间范围、惯性因子、个体学习因子和群体学习因子先更新速度，再根据更新后的速度和粒子当前坐标位置，更新相应的坐标。
在本发明一个具体的实施例中，更新路径点粒子的速度(以x方向的速度 和位置更新公式为例)，通过如下公式表示：
vx＝ω×vx+c1×rand(0,1)×(pbest-posx)+c2×rand(0,1)×(gbest-posx)；
更新路径点粒子的坐标(以x方向的速度和位置更新公式为例)，通过如下公式表示：
posx＝posx+vx；
其中，vx是粒子x轴方向的速度；posx是粒子x轴方向的位置；ω为惯性因子；c1为个体学习因子；c2为群体学习因子；pbest个体x轴方向最优粒子位置；gbest种群x轴方向最优粒子位置；rand(0,1)为0到1的随机数。需要说明的是，空中监测设备群、水面艇群的每个粒子都有两个方向的位置和速度(x、y轴方向)，潜航器群则有三个方向的位置和速度(x、y、z轴方向)，每次迭代每个粒子群的每个粒子都进行速度和位置的更新。
作为优选的实施例，惯性因子随着迭代次数的增加而均匀减小，通过如下公式表示：
其中，t表示当前迭代次数，ω
t表示当前迭代次数对应的惯性因子，ω
t-1表示上一迭代次数对应的惯性因子，ω
max表示预设的惯性因子对应的最大值，ω
min表示预设的惯性因子对应的最小值，g表示预设常数。
作为具体实施例，本发明实施例通过惯性因子的梯度下降更新，实现速度和位置的迭代更新。
作为优选的实施例，结合图6来看，图6为本发明提供的计算独立适应度一实施例的流程示意图，包括步骤S043至步骤S044，其中：
在步骤S043中，针对单个路径点粒子，确定对应的碰撞优化函数值、转弯优化函数值和时间优化函数；
在步骤S044中，将碰撞优化函数值、转弯优化函数值和时间优化函数进行 加权求和，确定独立适应度。
作为具体实施例，本发明实施例设置碰撞优化函数值、转弯优化函数值和时间优化函数，以此求得独立适应度，对单个路径点粒子进行独立的优化，同时，结合粒子群之间的整体适应度，对不同的协同粒子群进行独立优化。
作为优选的实施例，转弯优化函数值的计算过程包括：
针对单个路径点粒子，根据每三个相邻路径点计算路径夹角、第一距离和极限转弯半径，分别通过如下公式表示：
l＝min(l
1,l
2)
其中，α表示每三个相邻路径点确定的路径夹角，l表示第一距离，l
1表示前两个路径点的距离，l
2表示后两个路径点的距离，l
3表示第一个路径点和第三个路径点的距离，ρ表示极限转弯半径，为第一距离l的最大内切圆半径；
根据极限转弯半径和海面监测设备的最小转弯半径，确定转弯优化函数值，通过如下公式表示：
其中，tu(p
k-1，p
k，p
k+1)表示转弯优化函数值，P
k-1，P
k，P
k+1依次表示三个相邻的路径点，ρ表示极限转弯半径，R表示最小转弯半径，针对单个路径点粒子，若至少有一个转弯优化函数值tu(p
k-1，p
k，p
k+1)取值为0，则单个路径点粒子对应的转弯优化函数值取0；
针对单个路径点粒子，对应的时间优化函数通过如下公式表示：
l
i＝min(l
ij)，j＝1,……,P
其中，l
ijk表示第i个粒子种群，第j个粒子，第k组相邻路径点的距离；l
ij表示第i个粒子种群，第j个粒子的路径总长度；l
i表示第i个粒子种群的最小航行距离；t
i表示第i个粒子种群的最小航行时间；tim表示i个协同种群平均最小航行时间；v
i表示第i个粒子种群的航行速度；nn表示粒子群的协同种群数目。
作为具体的实施例，本发明实施例对碰撞优化函数值、转弯优化函数值和时间优化函数进行对应求解，以便求得对应的独立适应度，便于粒子的迭代更新。
作为优选的实施例，结合图7来看，图7为本发明提供的计算整体适应度一实施例的流程示意图，包括步骤S045至步骤S046，其中：
在步骤S045中，分别针对空中监测设备集群、海面监测设备集群以及海下监测设备集群，确定对应的每个粒子的独立适应度；
在步骤S046中，根据独立适应度，确定不同集群对应的最优适应度；
在步骤S047中，将最优适应度进行求和，确定整体适应度。
作为具体实施例，本发明实施例在粒子迭代过程中，利用整体适应度，实现了多个粒子群协同优化，减少了粒子的相互干扰，避免了优化陷入局部最优解。
本发明公开了一种海空协同水下目标追踪的路径规划系统及方法，首先，通过空中监测设备集群对探测目标的目标位置信息进行有效的获取，沿着海面监测设备航道进行第一路径规划，以此进行航行，在航行过程中进行水域障碍物探测，构建水面航行区域图，反馈海面监测设备航道中所有障碍物信息；然后，通过海面监测设备集群接收空中监测设备集群传递的水面航行区域图，基于水面航行区域图的障碍物信息、目标位置信息以及自身位置信息，沿着海面 监测设备航道进行第二路径规划直到到达探测目标的临近区域，再进一步对临近区域的水下环境进行探测，构建并传递水下障碍物环境图；最后，通过海下监测设备集群接收水下障碍物环境图，基于水下障碍物环境图中的临近区域的水下障碍物环境信息，继续进行第三路径规划，追踪至探测目标的位置。
本发明技术方案，通过把不同航行器划分不同粒子群，相互共享信息，同步迭代进化，来解决多个异质航行器，即空中监测设备、海面监测设备、海下监测设备集群间协同追踪目标的路径规划问题。具体包括：使用粒子群算法规划空中监测设备路径，并沿途探测海面监测设备航行区域障碍物，来生成完整的海面监测设备航道障碍分布图；再利用完整的障碍物位置信息，通过协同的粒子群算法，规划海面监测设备集群的协同航行路径；海面监测设备集群达到规划位置后，探测生成水下航行环境图，然后规划潜航器水下路径，并释放潜航器完成追踪目标的任务。本发明提供的技术方案应用场景灵活，能够有效适应未知航道；协同的粒子群算法，减少了迭代次数，提高了优化的效率；路径规划合理，能够快速追踪目标位置；提高了异质无人设备集群在未知障碍水域的自主协同追踪能力。
以上所述，仅为本发明较佳的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本发明的保护范围之内。
Claims (10)
- 一种海空协同水下目标追踪的路径规划系统，其特征在于，包括空中监测设备集群、海面监测设备集群以及海下监测设备集群，其中：所述空中监测设备集群，用于获取探测目标的目标位置信息，根据所述目标位置信息沿海面监测设备航道进行第一路径规划，构建包含所述目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将所述水面航行区域图传递至所述海面监测设备集群；所述海面监测设备集群，用于根据所述水面航行区域图和自身位置信息，沿所述海面监测设备航道进行第二路径规划，到达所述探测目标的临近区域，并对所述临近区域的水下环境进行探测，构建水下障碍物环境图，并将所述水下障碍物环境图传递至所述海下监测设备集群；所述海下监测设备集群，用于根据所述水下障碍物环境图，进行第三路径规划，追踪至所述探测目标的位置，以完成追踪任务。
- 一种海空协同水下目标追踪的路径规划方法，其特征在于，基于根据权利要求1所述的海空协同水下目标追踪的路径规划系统，包括：获取探测目标的目标位置信息，根据所述目标位置信息沿海面监测设备航道进行第一路径规划，构建包含所述目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将所述水面航行区域图传递至海面监测设备集群；根据所述水面航行区域图和自身位置信息，沿所述海面监测设备航道进行第二路径规划，到达所述探测目标的临近区域，并对所述临近区域的水下环境进行探测，构建水下障碍物环境图，并将所述水下障碍物环境图传递至海下监测设备集群；根据所述水下障碍物环境图，进行第三路径规划，追踪至所述探测目标的位置，以完成追踪任务。
- 根据权利要求2所述的海空协同水下目标追踪的路径规划方法，其特征 在于，所述获取探测目标的目标位置信息，根据所述目标位置信息沿海面监测设备航道进行第一路径规划包括：获取空中监测设备集群的起始位置、海面监测设备航道的航道信息和所述目标位置信息；根据所述起始位置、所述航道信息和所述目标位置信息，确定空中监测设备航道，其中，所述空中监测设备航道是与所述海面监测设备航道对应的可航行空域；在所述空中监测设备航道中进行第一路径规划，规划空中监测设备集群的航行探测的路径，并进行航行。
- 根据权利要求3所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述构建包含所述目标位置信息和海面监测设备航道中所有障碍物信息的水面航行区域图，并将所述水面航行区域图传递至海面监测设备集群包括：在所述空中监测设备集群航行的过程中，在所述空中监测设备航道中通过探测设备探测水面，搜集沿所述海面监测设备航道的障碍物信息，储存为坐标数据信息；根据所述坐标数据信息和所述目标位置信息，构建所述水面航行区域图，并将所述水面航行区域图传递至所述海面监测设备集群。
- 根据权利要求2所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述第一路径规划、所述第二路径规划以及所述第三路径规划的路径规划步骤包括：获取设置的初始化参数，初始化路径点粒子群，其中，所述路径点粒子群包括所述第一路径规划对应的所述空中监测设备集群、所述第二路径规划对应的所述海面监测设备集群和所述第三路径规划对应的所述海下监测设备集群；获取设置的多种迭代参数和迭代次数；将粒子起始位置坐标和粒子终点位置坐标加入所述路径点粒子群，确定初始航线坐标矩阵；计算各粒子当前位置对应的独立适应度和整体适应度，根据所述多种迭代参数迭代更新路径点粒子的坐标数据，其中，所述整体适应度为根据所有所述路径点粒子群中的独立适应度而确定；当达到所述迭代次数时结束迭代，输出最优路径点坐标。
- 根据权利要求5所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述初始化参数包括协同种群数目、种群大小、粒子维度和初始速度；所述多种迭代参数包括航道空间范围、惯性因子、个体学习因子和群体学习因子；所述根据多种迭代参数迭代更新路径点粒子的坐标数据包括：根据所述航道空间范围、所述惯性因子、所述个体学习因子和所述群体学习因子，更新所述路径点粒子的速度；根据更新后的速度和粒子当前坐标位置，更新所述路径点粒子的坐标。
- 根据权利要求6所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述惯性因子随着所述迭代次数的增加而均匀减小，通过如下公式表示：
其中，t表示当前迭代次数，ω t表示当前迭代次数对应的惯性因子，ω t-1表示上一迭代次数对应的惯性因子，ω max表示预设的惯性因子对应的最大值，ω min表示预设的惯性因子对应的最小值，g表示预设常数。 - 根据权利要求5所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述独立适应度的计算过程包括：针对单个路径点粒子，确定对应的碰撞优化函数值、转弯优化函数值和时间优化函数；将所述碰撞优化函数值、所述转弯优化函数值和所述时间优化函数进行加权求和，确定所述独立适应度。
- 根据权利要求8所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述转弯优化函数值的计算过程包括：针对单个路径点粒子，根据每三个相邻路径点计算路径夹角、第一距离和极限转弯半径，分别通过如下公式表示：
l＝min(l 1,l 2)
其中，α表示每三个相邻路径点确定的所述路径夹角，l表示所述第一距离，l 1表示前两个路径点的距离，l 2表示后两个路径点的距离，l 3表示第一个路径点和第三个路径点的距离，ρ表示所述极限转弯半径，为所述第一距离l的最大内切圆半径；根据所述极限转弯半径和海面监测设备的最小转弯半径，确定所述转弯优化函数值，通过如下公式表示：
其中，tu(p k-1，p k，p k+1)表示所述转弯优化函数值，P k-1，P k，P k+1依次表示三个相邻的路径点，ρ表示所述极限转弯半径，R表示所述最小转弯半径，针对单个路径点粒子，若至少有一个所述转弯优化函数值tu(p k-1，p k，p k+1)取值为0，则单个路径点粒子对应的转弯优化函数值取0；针对单个路径点粒子，对应的时间优化函数通过如下公式表示：
l i＝min(l ij)，j＝1,……,P
其中，l ijk表示第i个粒子种群，第j个粒子，第k组相邻路径点的距离；l ij表示第i个粒子种群，第j个粒子的路径总长度；l i表示第i个粒子种群的最小 航行距离；t i表示第i个粒子种群的最小航行时间；tim表示i个协同种群平均最小航行时间；v i表示第i个粒子种群的航行速度；nn表示粒子群的协同种群数目。 - 根据权利要求5所述的海空协同水下目标追踪的路径规划方法，其特征在于，所述整体适应度的计算过程包括：分别针对空中监测设备集群、所述海面监测设备集群以及所述海下监测设备集群，确定对应的每个粒子的所述独立适应度；根据所述独立适应度，确定不同集群对应的最优适应度；将所述最优适应度进行求和，确定所述整体适应度。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/732,506 US20220371709A1 (en) | 2021-05-21 | 2022-04-28 | Path planning system and method for sea-aerial cooperative underwater target tracking |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110562485.3 | 2021-05-21 | ||
| CN202110562485.3A CN113342008B (zh) | 2021-05-21 | 2021-05-21 | 一种海空协同水下目标追踪的路径规划系统及方法 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US17/732,506 Continuation US20220371709A1 (en) | 2021-05-21 | 2022-04-28 | Path planning system and method for sea-aerial cooperative underwater target tracking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022241944A1 true WO2022241944A1 (zh) | 2022-11-24 |
Family
ID=77471008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/108070 WO2022241944A1 (zh) | 2021-05-21 | 2021-07-23 | 一种海空协同水下目标追踪的路径规划系统及方法 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113342008B (zh) |
| WO (1) | WO2022241944A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117687416A (zh) * | 2024-01-25 | 2024-03-12 | 水利部交通运输部国家能源局南京水利科学研究院 | 河网水安全检测装置路径规划方法及系统 |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114200929B (zh) * | 2021-11-24 | 2023-10-20 | 中国科学院沈阳自动化研究所 | 多水下机器人最大探测覆盖率的快速梳型路径规划方法 |
| CN114167880A (zh) * | 2021-12-02 | 2022-03-11 | 大连海事大学 | 一种基于时间最优的多水下滑翔机路径规划系统 |
| CN114415697A (zh) * | 2022-03-29 | 2022-04-29 | 武汉理工大学 | 一种多无人海洋运载器协同编队的任务分配方法及系统 |
| CN116700315B (zh) * | 2023-07-03 | 2024-02-06 | 苏州优世达智能科技有限公司 | 一种无人艇的航迹跟踪控制方法及系统 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170059333A1 (en) * | 2015-09-02 | 2017-03-02 | The United States Of America As Represented By The Secretary Of The Navy | Decision support and control systems including various graphical user interfaces configured for displaying multiple transit options for a platform with respect to hazard and objects and related methods |
| CN108318039A (zh) * | 2018-02-02 | 2018-07-24 | 哈尔滨工业大学 | 异介质无人驾驶航行器协同轨迹规划方法 |
| CN109917817A (zh) * | 2019-05-06 | 2019-06-21 | 中国海洋大学 | 多水下机器人协同路径规划方法 |
| CN111045453A (zh) * | 2019-12-25 | 2020-04-21 | 南京工程学院 | 一种基于无人艇与多水下机器人的协同控制系统及方法 |
| CN111381605A (zh) * | 2020-05-11 | 2020-07-07 | 杭州电子科技大学 | 一种应用于多无人机大范围海域水下多目标协同搜索方法 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175245B (zh) * | 2011-01-28 | 2012-07-11 | 哈尔滨工程大学 | 一种基于海流历史统计信息的水下潜器路径规划方法 |
| CN108693849A (zh) * | 2018-05-30 | 2018-10-23 | 佛山市神风航空科技有限公司 | 一种自动远海侦测系统 |
| CN109238291B (zh) * | 2018-10-26 | 2019-07-12 | 河海大学 | 一种水面无人船导引缆回收自主水下航行器的规划方法 |
| CN109579843B (zh) * | 2018-11-29 | 2020-10-27 | 浙江工业大学 | 一种空地多视角下的多机器人协同定位及融合建图方法 |
| CN112327923B (zh) * | 2020-11-19 | 2022-04-01 | 中国地质大学（武汉） | 一种多无人机协同路径规划方法 |
-
2021
- 2021-05-21 CN CN202110562485.3A patent/CN113342008B/zh active Active
- 2021-07-23 WO PCT/CN2021/108070 patent/WO2022241944A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170059333A1 (en) * | 2015-09-02 | 2017-03-02 | The United States Of America As Represented By The Secretary Of The Navy | Decision support and control systems including various graphical user interfaces configured for displaying multiple transit options for a platform with respect to hazard and objects and related methods |
| CN108318039A (zh) * | 2018-02-02 | 2018-07-24 | 哈尔滨工业大学 | 异介质无人驾驶航行器协同轨迹规划方法 |
| CN109917817A (zh) * | 2019-05-06 | 2019-06-21 | 中国海洋大学 | 多水下机器人协同路径规划方法 |
| CN111045453A (zh) * | 2019-12-25 | 2020-04-21 | 南京工程学院 | 一种基于无人艇与多水下机器人的协同控制系统及方法 |
| CN111381605A (zh) * | 2020-05-11 | 2020-07-07 | 杭州电子科技大学 | 一种应用于多无人机大范围海域水下多目标协同搜索方法 |
Non-Patent Citations (1)
| Title |
|---|
| HOU, YUEQI ET AL.: "Cooperative path planning of USV and UAV swarms under multiple constraints", CHINESE JOURNAL OF SHIP RESEARCH, vol. 16, no. 1, 28 February 2021 (2021-02-28), pages 74 - 82, XP093007586, DOI: 10.19693/j.issn.1673-3185 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117687416A (zh) * | 2024-01-25 | 2024-03-12 | 水利部交通运输部国家能源局南京水利科学研究院 | 河网水安全检测装置路径规划方法及系统 |
| CN117687416B (zh) * | 2024-01-25 | 2024-04-12 | 水利部交通运输部国家能源局南京水利科学研究院 | 河网水安全检测装置路径规划方法及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113342008B (zh) | 2023-12-26 |
| CN113342008A (zh) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022241944A1 (zh) | 一种海空协同水下目标追踪的路径规划系统及方法 | |
| US11727812B2 (en) | Airplane flight path planning method and device based on the pigeon-inspired optimization | |
| Kumar et al. | Recent developments on target tracking problems: A review | |
| CN109923492A (zh) | 飞行路径确定 | |
| CN111045453A (zh) | 一种基于无人艇与多水下机器人的协同控制系统及方法 | |
| Yao et al. | A hierarchical architecture using biased min-consensus for USV path planning | |
| Montenegro et al. | A review on distributed control of cooperating mini UAVs | |
| Yao et al. | Gaussian mixture model and self-organizing map neural-network-based coverage for target search in curve-shape area | |
| CN108896957A (zh) | 一种无人机操控信号源的定位系统及方法 | |
| Lan et al. | Improved RRT algorithms to solve path planning of multi-glider in time-varying ocean currents | |
| CN110196425A (zh) | 一种移动平台对水下目标的被动声定位方法 | |
| Jin et al. | Cooperative path planning with priority target assignment and collision avoidance guidance for rescue unmanned surface vehicles in a complex ocean environment | |
| EP3989034B1 (en) | Automatic safe-landing-site selection for unmanned aerial systems | |
| Teng et al. | A dynamic path planning method for terrain-aided navigation of autonomous underwater vehicles | |
| CN113325856B (zh) | 基于逆流逼近策略的uuv最优作业路径规划方法 | |
| Zeng et al. | Path planning for rendezvous of multiple AUVs operating in a variable ocean | |
| Yang et al. | Cooperative UAV navigation using inter-vehicle ranging and magnetic anomaly measurements | |
| Ennong et al. | Design and experiment of a sea-air heterogeneous unmanned collaborative system for rapid inspection tasks at sea | |
| Zhang et al. | A MILP model on coordinated coverage path planning system for UAV-ship hybrid team scheduling software | |
| Kim et al. | Development of a vision-based recognition and position measurement system for cooperative missions of multiple heterogeneous unmanned vehicles | |
| CN116280270A (zh) | 一种遥感星座对空中动目标的智能协同跟踪方法 | |
| US20220371709A1 (en) | Path planning system and method for sea-aerial cooperative underwater target tracking | |
| Yu et al. | Vision-based local multi-resolution mapping and path planning for miniature air vehicles | |
| Hirsch et al. | Decentralized cooperative urban tracking of multiple ground targets by a team of autonomous UAVs | |
| CN114791735A (zh) | 无人船纠偏方法及系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21940393 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21940393 Country of ref document: EP Kind code of ref document: A1 |