CN113419522B - Simulation method and system for unmanned ship path planning algorithm - Google Patents
Simulation method and system for unmanned ship path planning algorithm Download PDFInfo
- Publication number
- CN113419522B CN113419522B CN202110559862.8A CN202110559862A CN113419522B CN 113419522 B CN113419522 B CN 113419522B CN 202110559862 A CN202110559862 A CN 202110559862A CN 113419522 B CN113419522 B CN 113419522B
- Authority
- CN
- China
- Prior art keywords
- target
- simulation
- ith
- list
- time
- 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.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 145
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 45
- 229920000535 Tan II Polymers 0.000 claims description 6
- OIGNJSKKLXVSLS-VWUMJDOOSA-N prednisolone Chemical compound O=C1C=C[C@]2(C)[C@H]3[C@@H](O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 OIGNJSKKLXVSLS-VWUMJDOOSA-N 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 230000009286 beneficial 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
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
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
The invention provides a simulation method and a simulation system for an unmanned ship path planning algorithm, which have the functions of recording a simulation process, displaying a simulation moving target path, displaying a planning path of an autonomous obstacle avoidance algorithm and displaying a real ship kinematics model of an unmanned ship. The unmanned ship can be simulated in the scenes that other ships need to avoid, such as crossing, meeting, overtaking, confrontation and the like. And after the simulation is finished, the playback can be carried out through the simulation recording. The simulation system changing method has the characteristics of freely editable scenes, visualized simulation process, human intervention in the simulation process and the like.
Description
Technical Field
The invention relates to a simulation method and a simulation system for a path planning algorithm of an unmanned ship, and belongs to the field of unmanned ship intelligence.
Background
In recent years, the field of unmanned intelligence is rapidly developed, and the value of unmanned boats is gradually emphasized by military and civil markets. At present, the unmanned boat autonomous driving technology breaks through autonomous operation capability under specific scenes, but the mature solution of operation problems in complex and variable environments is still actively explored. An important difficulty is the ability of the unmanned boat to sense the surrounding environment.
The unmanned ship autonomous obstacle avoidance algorithm carries out dynamic path planning according to a task path after the situation of multi-target complex terrain is constructed through multi-sensor combination. At present, main test methods are a real boat test method and a virtual simulation method, but the real boat test has the defects of large consumption of manpower and material resources and low development efficiency, few schemes developed for unmanned boats are available in the current virtual simulation method, and the influence of a real boat model and human factors is not added. Therefore, a simulation system method for unmanned ship autonomous path obstacle avoidance planning algorithm, which can take the self motion characteristics of the unmanned ship, artificial india and multi-target calculation into consideration, is needed
Disclosure of Invention
The technical problem solved by the invention is as follows: the defects of the prior art are overcome, the simulation method of the autonomous path obstacle avoidance planning algorithm of the unmanned ship can simulate scenes that the unmanned ship needs to avoid when crossing, meeting, pursuing, confrontation and the like occur to other ships, and the simulation effect is better and close to reality.
The technical scheme adopted by the invention is as follows: a simulation method of an unmanned ship path planning algorithm comprises the following steps:
(1) initializing a simulation target list, determining state information of each target in the simulation target list, wherein the state information comprises target type, size, initial position and speed, and defining the current moment as t n At time, n is 0 in the initial state;
(2) record t n State information of each target in the simulation target list corresponding to the moment;
(3) adopting a path planning algorithm, and according to the input task path and t of each target in the simulation target list n Calculating a planning path according to the time state information;
(4) by using a motion simulation method, according to the planned path and t of each target in the simulation target list n The state information of the moment is used for calculating the t of each target in the simulation target list n+1 Status information of the time;
(5) let n be n + 1;
if the ending instruction is not received, jumping to the step (2) for continuous execution after delaying delta t time;
if receiving the end command, recording t n And the state information of each target in the simulation list target list corresponding to the moment is obtained, and the method is ended.
In the step (1):
the simulation target list is in the form of S ═ S 1 ,s 2 ,s 3 ,…,s m }，
Wherein s is i Representing the state information of the ith simulation target in the simulation target list, wherein m represents the total number of the simulation targets; 1,2,3, …, m;
wherein s is i Is of the component form:
wherein v is n Is the north velocity, v, of the target e Is the target east velocity, p n Is the north coordinate, p, of the object e Is the target east coordinate, s a Is the target major axis distance, s b Is the target short axis distance, k is the target type;
the object types include: a simulation program control target, a path planning algorithm control target and a manned control target;
the target number m in a simulation process target simulation list is more than or equal to 2, and at least one path planning algorithm controls the target of the target.
In the step (4), each target t in the simulation target list is calculated by using a motion simulation method n+1 The method of the time state is as follows:
(4.1) setting the initial value of i to be 1;
(4.2) updating the state information of the ith target in the simulation target list;
(4.3) if i +1 is less than or equal to m, i ═ i +1, repeating step (4.2);
and if i +1 is larger than m, finishing updating.
In the step (4.2), the method for updating the shape information of the ith target in the simulation target list comprises the following steps:
according to different types of each target in the simulation target list, different updating methods are adopted, and the method specifically comprises the following steps:
the target long-axis distance, the target short-axis distance and the type of each target are not changed;
the state information update equation of the simulation program control target is as follows:
wherein,
represents t n+1 The ith target state information at the moment;
represents t n+1 The north velocity of the ith target at time;
represents t n+1 East speed of the ith target at time;
represents t n+1 The north coordinate of the ith target at the moment;
for the path planning algorithm control target, the planned path of the step (3) and t of the ith target n Status information of time of day
Inputting the unmanned ship motion model and calculating t n+1 Status information of the ith target at time:
for the manned control target, the north direction speed and the east direction speed of the manned control target are changed through the manned control signal, and the specific method comprises the following steps:
a＝tan2(v n ,v e )+ΔR-ΔL
wherein v and a respectively represent the changed target closing speed and the changed movement direction;
respectively representing the changed north-oriented speed and east-oriented speed of the target; delta F and delta B respectively correspond to the speed increment of the front and the back of the target; the delta R and the delta L respectively correspond to angular velocity increment of the left direction and the right direction of the target; the increment value is equal to the increment size input by the external equipment;
wherein, the formula of the ReLU function is as follows:
x is an independent variable;
t n+1 status information of the ith target of time
Comprises the following steps:
wherein,
represents t n The changed north-facing speed of the ith target at the moment;
denotes t n The east-wise velocity after the ith target change at time.
A simulation system of an unmanned ship path planning algorithm comprises:
a first module, configured to initialize a simulation target list, determine state information of each target in the simulation target list, where the state information includes a target type, a size, an initial position, and a speed, and define a current time as t n At time, n is 0 in the initial state;
a second module for recording t n State information of each target in the simulation target list corresponding to the moment; adopting a path planning algorithm, and according to the input task path and t of each target in the simulation target list n Calculating a planning path according to the time state information;
a third module for simulating t of each target in the target list according to the planned path and the simulation by using a motion simulation method n The state information of the moment is used for calculating the t of each target in the simulation target list n+1 Status information of the time;
let n be n + 1; if the ending instruction is not received, returning to call the second module for continuous execution after delaying the time delta t; if receiving the end command, recording t n And the state information of each target in the simulation list target list corresponding to the moment.
The simulation target list is in the form of S ═ S 1 ,s 2 ,s 3 ,…,s m }，
Wherein s is i Representing the state information of the ith simulation target in the simulation target list, wherein m represents the total number of the simulation targets; 1,2,3, …, m;
wherein s is i Is of the component form:
wherein v is n Is the north velocity, v, of the target e Is the target east velocity, p n Is the north coordinate, p, of the object e Is the east direction of the targetCoordinate, s a Is the target major axis distance, s b The target short axis distance is defined, and k is the target type;
the object types include: a simulation program control target, a path planning algorithm control target and a manned control target;
the target number m in a simulation process target simulation list is more than or equal to 2, and at least one path planning algorithm controls the target of the target.
In the third module, each target t in the simulation target list is calculated by using a motion simulation method n+1 The method of the time state is as follows:
(4.1) setting the initial value of i to be 1;
(4.2) updating the state information of the ith target in the simulation target list;
(4.3) if i +1 is less than or equal to m, i ═ i +1, repeating step (4.2);
and if i +1 is larger than m, finishing updating.
In the step (4.2), the method for updating the shape information of the ith target in the simulation target list comprises the following steps:
according to different types of each target in the simulation target list, different updating methods are adopted, and the method specifically comprises the following steps:
the target long-axis distance, the target short-axis distance and the type of each target are not changed;
the state information update equation of the simulation program control target is as follows:
wherein,
represents t n+1 The ith target state information at the moment;
represents t n+1 The north velocity of the ith target at time;
represents t n+1 East speed of the ith target at time;
represents t n+1 The north coordinate of the ith target at the moment;
for the path planning algorithm control target, the planned path of the step (3) and t of the ith target n Status information of time of day
Inputting a model of the unmanned ship motion and calculating t n+1 Status information of the ith target at time:
for the manned control target, the north direction speed and the east direction speed of the manned control target are changed through the manned control signal, and the specific method comprises the following steps:
a＝tan2(v n ,v e )+ΔR-ΔL
wherein v and a respectively represent the changed target closing speed and the changed movement direction;
respectively representing the changed target north-oriented speed and east-oriented speed; delta F and delta B respectively correspond to the speed increment of the front and the back of the target; the delta R and the delta L respectively correspond to angular velocity increment of the left direction and the right direction of the target; the increment value is equal to the increment size input by the external equipment;
wherein, the formula of the ReLU function is as follows:
x is an independent variable;
t n+1 status information of the ith target of time
Comprises the following steps:
wherein,
represents t n The changed north-facing speed of the ith target at the moment;
represents t n The east-wise velocity after the ith target change at time.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a simulation system method for an unmanned ship autonomous path obstacle avoidance planning algorithm, which has a simulation process recording function, a simulation moving target path display function, an autonomous obstacle avoidance algorithm planning path display function and an unmanned ship real ship kinematics model. The unmanned ship can simulate the scenes that the unmanned ship needs to avoid in the situations of crossing, meeting, overtaking, confrontation and the like of other ships by considering the self motion characteristics, human factors and multi-target calculation of the unmanned ship, and the simulation effect is better and close to the reality. And after the simulation is finished, the playback can be carried out through the simulation recording. The simulation system changing method has the advantages that the scene can be freely edited, the simulation process is visualized, and the artificial intervention can be performed in the simulation process.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1, a simulation method of an unmanned ship path planning algorithm includes the following specific steps:
(1) initializing a simulation target list, determining the type, size, initial position and speed of each target in the simulation target list, and defining the current time as t n And (n ═ 0) time.
The simulation target list is in the form of S ═ S 1 ,s 2 ,s 3 ,…,s m In which s is i And the state information of the ith simulation target in the list is shown, m represents the total number of the simulation targets, and i is 1,2,3, … and m.
Wherein s is i Is of the component form:
wherein v is n Is the target north component velocity v e Is the target east component velocity, p n Is a north coordinate, p e As east coordinate, s a Is the target major axis distance, s b For target minor axis distance, k is the target type. The simulation system abstracts the object into an elliptical shape, so the values of its major and minor axes need to be well defined.
The target types are: a simulation program control target (k is 0), a path planning algorithm control target (k is 1), and an attended control target (k is 2).
The number m of targets in a simulation process simulation list is more than or equal to 2, and at least one path planning algorithm controls the targets of the target (k is 1).
(2) Note the bookRecord t n And simulating the state information of each target in the target list at the moment.
(3) The path planning algorithm is based on the input task path and t of each target in the simulation target list n And calculating a planned path according to the time state information.
(4) By using a motion simulation method, according to the planned path and t of each target in the simulation target list n The state information of the moment is used for calculating the t of each target in the simulation target list n+1 The method of the state of the time is as follows.
1) Setting the initial value of i as 1;
2) updating the state of the ith target in the simulation target list;
3) and (5) if the i +1 is less than or equal to m, repeating the step (2) if the i +1 is less than or equal to m, otherwise, finishing updating.
In step 2), different algorithms are adopted according to different types of each target in the simulation target list, and the following specific algorithms are adopted: wherein the target major axis distance, target minor axis distance and type of each target do not change.
1) Simulation program control target
Since the simulation program controls the north-oriented speed and the east-oriented speed of the target, the state information of the target does not change after initialization, and the state information updating equation is as follows:
where the part of the subscript following the comma indicates the time at which the condition is.
Wherein,
represents t n+1 The ith target state information at the moment;
represents t n+1 The north velocity of the ith target at time;
represents t n+1 East speed of the ith target at time;
represents t n+1 The north coordinate of the ith target at the moment;
represents t n+1 East coordinate of the ith target at time;
2) path planning algorithm control objective
The path planning algorithm controls the target, plans the path according to step (3), and t of the target n Inputting the state of the moment into the unmanned ship motion model, and calculating t n+1 The state of the moment.
The unmanned ship motion model comprises the modeling of a controlled object and the design of a controller in the field of automatic control, and can be constructed according to related knowledge in the field.
3) Someone controlling an object
The manned control target changes the speed state of movement of the target in response to the manned control signal. In the simulation process, an operator can change the north speed and the east speed of the manned control target through external equipment (a keyboard, a rocker and the like), and the specific method comprises the following steps:
a＝tan2(v n ,v e )+ΔR-ΔL
wherein v and a respectively represent the resultant velocity and the movement direction after being changed (the north direction is 0, and the north is positive when the north is deviated from the east);
respectively representing the changed northbound speed and eastern speed; delta F and delta B respectively correspond to the speed increment of the front and the back of the target; Δ R, Δ L correspond to angular velocity increments of the target left and right directions, respectively. The increment value size is equal to the device input size.
Wherein the formula of the ReLU function is:
the state at the next moment is:
wherein,
represents t n The changed north-facing speed of the ith target at the moment;
represents t n East speed after the ith target is changed;
(5)n＝n+1；
(6) if the ending instruction is not received, jumping to the step (2) for continuous execution after delaying delta t time, and if the ending instruction is received, recording t n And at the moment, simulating the state information of each target in the list of targets, and ending.
A simulation system of an unmanned ship path planning algorithm comprises:
a first module for initializing the simulation target list and determining the state information of each target in the simulation target list, wherein the state information includes the targetMark type, size, initial position and speed, and defining current time as t n At time, n is 0 in the initial state;
a second module for recording t n State information of each target in the simulation target list corresponding to the moment; adopting a path planning algorithm, and according to the input task path and t of each target in the simulation target list n Calculating a planning path according to the time state information;
a third module for simulating t of each target in the target list according to the planned path and the simulation target by using a motion simulation method n The state information of the moment is used for calculating the t of each target in the simulation target list n+1 Status information of the time;
let n be n + 1; if the ending instruction is not received, returning to call the second module for continuous execution after delaying the time delta t; if receiving the end command, recording t n And the state information of each target in the simulation list target list corresponding to the moment.
The simulation target list is in the form of S ═ S 1 ,s 2 ,s 3 ,…,s m }，
Wherein s is i Representing the state information of the ith simulation target in the simulation target list, wherein m represents the total number of the simulation targets; 1,2,3, …, m;
wherein s is i Is of the component form:
wherein v is n Is the north velocity, v, of the target e Is the target east velocity, p n Is the target north coordinate, p e Is the target east coordinate, s a Is the target major axis distance, s b The target short axis distance is defined, and k is the target type;
the object types include: a simulation program control target, a path planning algorithm control target and a manned control target;
the target number m in a simulation process target simulation list is more than or equal to 2, and at least one path planning algorithm controls the target of the target.
In the third module, each target t in the simulation target list is calculated by using a motion simulation method n+1 The method of the time state is as follows:
(4.1) setting the initial value of i to be 1;
(4.2) updating the state information of the ith target in the simulation target list;
(4.3) if i +1 is less than or equal to m, i ═ i +1, repeating step (4.2);
and if i +1 is larger than m, finishing updating.
In the step (4.2), the method for updating the shape information of the ith target in the simulation target list comprises the following steps:
according to different types of each target in the simulation target list, different updating methods are adopted, and the method specifically comprises the following steps:
the target long-axis distance, the target short-axis distance and the type of each target are not changed;
the state information update equation of the simulation program control target is as follows:
wherein,
represents t n+1 The ith target state information at the moment;
represents t n+1 The north velocity of the ith target at time;
represents t n+1 East speed of the ith target at time;
represents t n+1 The north coordinate of the ith target at the moment;
for the path planning algorithm control target, the planned path of the step (3) and t of the ith target n Status information of time of day
Inputting the unmanned ship motion model and calculating t n+1 Status information of the ith target at time:
for the manned control target, the north direction speed and the east direction speed of the manned control target are changed through the manned control signal, and the specific method comprises the following steps:
a＝tan2(v n ,v e )+ΔR-ΔL
wherein v and a respectively represent the changed target closing speed and the changed movement direction;
respectively representing the changed north-oriented speed and east-oriented speed of the target; delta F and delta B respectively correspond to the speed increment of the front and the back of the target; the delta R and the delta L respectively correspond to angular velocity increment of the left direction and the right direction of the target; the increment value is equal to the increment size input by the external equipment;
wherein, the formula of the ReLU function is as follows:
x is an independent variable;
t n+1 status information of the ith target of time
Comprises the following steps:
wherein,
denotes t n The changed north-facing speed of the ith target at the moment;
represents t n The east-wise velocity after the ith target change at time.
Claims (4)
1. A simulation method of an unmanned ship path planning algorithm is characterized by comprising the following steps:
(1) initializing a simulation target list, determining state information of each target in the simulation target list, wherein the state information comprises target type, size, initial position and speed, and defining the current moment as t n At time, n is 0 in the initial state;
(2) record t n State information of each target in the simulation target list corresponding to the moment;
(3) adopting a path planning algorithm, and according to the input task path and t of each target in the simulation target list n Calculating a planning path according to the time state information;
(4) by using a motion simulation method, according to the planned path and t of each target in the simulation target list n Time of dayThe state information of (2) is calculated, and each target in the simulation target list is at t n+1 Status information of the time;
(5) let n be n + 1;
if the ending instruction is not received, jumping to the step (2) for continuous execution after delaying delta t time;
if receiving the end command, recording t n The state information of each target in the simulation column target list corresponding to the moment is obtained, and the method is finished;
in the step (4), each target t in the simulation target list is calculated by utilizing a motion simulation method n+1 The method of the time state is as follows:
(4.1) setting the initial value of i to be 1;
(4.2) updating the state information of the ith target in the simulation target list;
(4.3) if i +1 is less than or equal to m, i ═ i +1, repeating step (4.2);
if i +1 is larger than m, the updating is finished;
in the step (4.2), the method for updating the state information of the ith target in the simulation target list is as follows:
according to different types of each target in the simulation target list, different updating methods are adopted, and the method specifically comprises the following steps:
the target long-axis distance, the target short-axis distance and the type of each target are not changed;
the state information update equation of the simulation program control target is as follows:
wherein,
represents t n+1 The ith target state information at the moment;
represents t n+1 The north velocity of the ith target at time;
represents t n+1 East speed of the ith target at time;
represents t n+1 The north coordinate of the ith target at the moment;
for the path planning algorithm control target, the planned path of the step (3) and t of the ith target n Status information of time of day
Inputting the unmanned ship motion model and calculating t n+1 Status information of the ith target at time:
for the manned control target, the north direction speed and the east direction speed of the manned control target are changed through the manned control signal, and the specific method comprises the following steps:
a＝tan2(v n ，v e )+ΔR-ΔL
wherein v is n Is the north velocity, v, of the target e Is the target east speed; v and a respectively represent the changed target closing speed and the movement direction;
respectively representing the changed north-oriented speed and east-oriented speed of the target; delta F and delta B respectively correspond to the speed increment of the front and the back of the target; the delta R and the delta L respectively correspond to angular velocity increment of a target in the left direction and the right direction; the increment value is equal to the increment size input by the external equipment;
wherein, the formula of the ReLU function is as follows:
x is an independent variable;
t n+1 status information of the ith target of time
Comprises the following steps:
wherein,
represents t n The changed north-facing speed of the ith target at the moment;
represents t n The east-wise velocity after the ith target change at time.
2. The simulation method of the unmanned ship path planning algorithm according to claim 1, wherein: in the step (1):
the simulation target list is in the form of S ═ S 1 ，s 2 ，s 3 ，...，s m }，
Wherein s is i Representing the state information of the ith simulation target in the simulation target list, wherein m represents the total number of the simulation targets; 1,2,3, …, m;
wherein s is i Is of the component form:
Wherein v is n Is the north velocity, v, of the target e Is the target east velocity, p n Is the north coordinate, p, of the object e Is the target east coordinate, s a Is the target major axis distance, s b The target short axis distance is defined, and k is the target type;
the object types include: a simulation program control target, a path planning algorithm control target and a manned control target;
the total number m of simulation targets in a simulation process target simulation list is more than or equal to 2, and at least one path planning algorithm controls the targets of the targets.
3. A simulation system of a path planning algorithm of an unmanned ship is characterized by comprising the following components:
a first module, configured to initialize a simulation target list, determine state information of each target in the simulation target list, where the state information includes a target type, a size, an initial position, and a speed, and define a current time as t n At time, n is 0 in the initial state;
a second module for recording t n State information of each target in the simulation target list corresponding to the moment; adopting a path planning algorithm, and according to the input task path and t of each target in the simulation target list n The planning path is calculated according to the time state information;
a third module for simulating t of each target in the target list according to the planned path and the simulation target by using a motion simulation method n The state information of the moment is used for calculating the t of each target in the simulation target list n+1 Status information of the time;
let n be n + 1; if the ending instruction is not received, returning to call the second module for continuous execution after delaying the time delta t; if receiving the end command, recording t n State information of each target in the simulation list target list corresponding to the moment;
in the third module, each target t in the simulation target list is calculated by using a motion simulation method n+1 The method of the time state is as follows:
(4.1) setting the initial value of i to be 1;
(4.2) updating the state information of the ith target in the simulation target list;
(4.3) if i +1 is less than or equal to m, i ═ i +1, repeating step (4.2);
if i +1 is larger than m, the updating is finished;
in the step (4.2), the method for updating the state information of the ith target in the simulation target list is as follows:
according to different types of each target in the simulation target list, different updating methods are adopted, and the method specifically comprises the following steps:
the target long-axis distance, the target short-axis distance and the type of each target are not changed;
the state information update equation of the simulation program control target is as follows:
wherein,
represents t n+1 The ith target state information at the moment;
represents t n+1 The north velocity of the ith target at time;
represents t n+1 East speed of the ith target at time;
represents t n+1 The north coordinate of the ith target at the moment;
for the path planning algorithm control target, the planned path of the step (3) and t of the ith target n Status information of time of day
Inputting the unmanned ship motion model and calculating t n+1 Status information of the ith target at time:
for the manned control target, the north direction speed and the east direction speed of the manned control target are changed through the manned control signal, and the specific method comprises the following steps:
a＝tan2(v n ，v e )+ΔR-ΔL
wherein v is n Is the north velocity, v, of the target e Is the target east speed; v and a respectively represent the changed target closing speed and the movement direction;
respectively representing the changed north-oriented speed and east-oriented speed of the target; delta F and delta B respectively correspond to the speed increment of the front and the back of the target; the delta R and the delta L respectively correspond to angular velocity increment of a target in the left direction and the right direction; the increment value is equal to the increment size input by the external equipment;
wherein, the formula of the ReLU function is as follows:
x is an independent variable;
t n+1 status information of the ith target of time
Comprises the following steps:
wherein,
represents t n The changed north-facing speed of the ith target at the moment;
represents t n The east-wise velocity after the ith target change at time.
4. The unmanned boat path gauge of claim 3The simulation system of the algorithm planning is characterized in that: the simulation target list is in the form of S ═ S 1 ，s 2 ，s 3 ，...，s m }，
Wherein s is i Representing the state information of the ith simulation target in the simulation target list, wherein m represents the total number of the simulation targets; i is 1,2,3, …, m;
wherein s is i Is of the component form:
Wherein v is n Is the north velocity, v, of the target e Is the target east velocity, p n Is the north coordinate, p, of the object e Is the target east coordinate, s a Is the target major axis distance, s b The target short axis distance is defined, and k is the target type;
the object types include: a simulation program control target, a path planning algorithm control target and a manned control target;
the total number m of simulation targets in a simulation process target simulation list is more than or equal to 2, and at least one path planning algorithm controls the targets of the targets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110559862.8A CN113419522B (en) | 2021-05-21 | 2021-05-21 | Simulation method and system for unmanned ship path planning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110559862.8A CN113419522B (en) | 2021-05-21 | 2021-05-21 | Simulation method and system for unmanned ship path planning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113419522A CN113419522A (en) | 2021-09-21 |
| CN113419522B true CN113419522B (en) | 2022-08-12 |
Family
ID=77712766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110559862.8A Active CN113419522B (en) | 2021-05-21 | 2021-05-21 | Simulation method and system for unmanned ship path planning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113419522B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676871A (en) * | 2016-01-19 | 2016-06-15 | 武汉理工大学 | Model ship based autonomous navigation control simulation system and method of under-actuated unmanned ship |
| CN108664020A (en) * | 2018-04-11 | 2018-10-16 | 上海大学 | A kind of unmanned boat dynamic obstacle avoidance algorithm based on Speed Obstacles method and dynamic window method |
| KR20190040558A (en) * | 2017-10-11 | 2019-04-19 | 주식회사 날다테크 | Method for controlling a aerial vehicle using artificial intelligence and physical simulation |
| CN109933067A (en) * | 2019-03-12 | 2019-06-25 | 哈尔滨工程大学 | A kind of unmanned boat collision prevention method based on genetic algorithm and particle swarm algorithm |
| CN110262492A (en) * | 2019-06-25 | 2019-09-20 | 北京航天控制仪器研究所 | A kind of Realtime collision free and method for tracking target of unmanned boat |
| CN111256694A (en) * | 2019-12-16 | 2020-06-09 | 中国船舶工业系统工程研究院 | Method for determining path of unmanned surface vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2669630A1 (en) * | 2012-06-01 | 2013-12-04 | ABB Technology AG | Method and system for determination of a route for a ship |
-
2021
- 2021-05-21 CN CN202110559862.8A patent/CN113419522B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676871A (en) * | 2016-01-19 | 2016-06-15 | 武汉理工大学 | Model ship based autonomous navigation control simulation system and method of under-actuated unmanned ship |
| KR20190040558A (en) * | 2017-10-11 | 2019-04-19 | 주식회사 날다테크 | Method for controlling a aerial vehicle using artificial intelligence and physical simulation |
| CN108664020A (en) * | 2018-04-11 | 2018-10-16 | 上海大学 | A kind of unmanned boat dynamic obstacle avoidance algorithm based on Speed Obstacles method and dynamic window method |
| CN109933067A (en) * | 2019-03-12 | 2019-06-25 | 哈尔滨工程大学 | A kind of unmanned boat collision prevention method based on genetic algorithm and particle swarm algorithm |
| CN110262492A (en) * | 2019-06-25 | 2019-09-20 | 北京航天控制仪器研究所 | A kind of Realtime collision free and method for tracking target of unmanned boat |
| CN111256694A (en) * | 2019-12-16 | 2020-06-09 | 中国船舶工业系统工程研究院 | Method for determining path of unmanned surface vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113419522A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Song et al. | Flightmare: A flexible quadrotor simulator | |
| CN107479368B (en) | Method and system for training unmanned aerial vehicle control model based on artificial intelligence | |
| Cao et al. | Target search control of AUV in underwater environment with deep reinforcement learning | |
| US20230419113A1 (en) | Attention-based deep reinforcement learning for autonomous agents | |
| EP3593294A1 (en) | Training action selection neural networks using apprenticeship | |
| Zhang et al. | AUV path tracking with real-time obstacle avoidance via reinforcement learning under adaptive constraints | |
| CN113848974B (en) | Aircraft trajectory planning method and system based on deep reinforcement learning | |
| Stevšić et al. | Sample efficient learning of path following and obstacle avoidance behavior for quadrotors | |
| CN111487992A (en) | Unmanned aerial vehicle sensing and obstacle avoidance integrated method and device based on deep reinforcement learning | |
| Wang et al. | Learning interactive driving policies via data-driven simulation | |
| CN116627157B (en) | Carrier rocket operation control method, device and equipment | |
| CN113419522B (en) | Simulation method and system for unmanned ship path planning algorithm | |
| Yang et al. | Research on autonomous navigation control of unmanned ship based on unity3d | |
| Niu et al. | Building a Flexible Mobile Robotics Teaching Toolkit by Extending MATLAB/Simulink with ROS and Gazebo | |
| Calvo et al. | Waves in isotropic totalistic cellular automata: Application to real-time robot navigation | |
| Huang et al. | Immersive virtual simulation system design for the guidance, navigation and control of unmanned surface vehicles | |
| Regier et al. | Improving navigation with the social force model by learning a neural network controller in pedestrian crowds | |
| CN117387635A (en) | Unmanned aerial vehicle navigation method based on deep reinforcement learning and PID controller | |
| Helble et al. | 3-d path planning and target trajectory prediction for the oxford aerial tracking system | |
| CN114840928B (en) | Underwater vehicle cluster motion simulation method based on deep learning | |
| KR102455003B1 (en) | Simulation method and apparatus for reinforcement learning of unmanned systems | |
| Dang et al. | Imitation learning-based algorithm for drone cinematography system | |
| CN116009583A (en) | Pure vision-based distributed unmanned aerial vehicle cooperative motion control method and device | |
| Sola et al. | Evaluation of a deep-reinforcement-learning-based controller for the control of an autonomous underwater vehicle | |
| CN102332175A (en) | Flock animation method based on shape constraints |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220414 Address after: 266200 aoshanwei sub district office, Jimo District, Qingdao City, Shandong Province Applicant after: Aerospace Times (Qingdao) marine equipment technology development Co.,Ltd. Address before: 142 box 403, box 100854, Beijing, Beijing, Haidian District Applicant before: BEIJIGN INSTITUTE OF AEROSPACE CONTROL DEVICES |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |