CN113359773A - Unmanned ship navigation path decision method and system - Google Patents
Unmanned ship navigation path decision method and system Download PDFInfo
- Publication number
- CN113359773A CN113359773A CN202110766456.9A CN202110766456A CN113359773A CN 113359773 A CN113359773 A CN 113359773A CN 202110766456 A CN202110766456 A CN 202110766456A CN 113359773 A CN113359773 A CN 113359773A
- Authority
- CN
- China
- Prior art keywords
- unmanned ship
- speed
- navigation
- current
- navigation path
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000005070 sampling Methods 0.000 claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 230000001133 acceleration Effects 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 38
- 230000005484 gravity Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 7
- 230000004888 barrier function Effects 0.000 claims description 4
- 230000002787 reinforcement Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
Abstract
The invention relates to a method and a system for deciding a navigation path of an unmanned ship, wherein the method comprises the following steps: acquiring the current speed of the unmanned ship; constraining the current time speed of the unmanned ship and generating a speed sampling space of a next time window of the unmanned ship; generating a navigation path according to the speed sampling space; constructing an evaluation function according to the global gravitational field; screening an optimal navigation path of the unmanned ship by using the evaluation function; and controlling the unmanned ship to sail according to the optimal sailing path. By adding the gravitational field, gravitational constraint of the target point on the unmanned ship is generated, so that the problem that the traditional DWA algorithm is easy to fall into local optimization is solved, the decision precision of the navigation path of the unmanned ship is improved, and the optimal navigation path of the unmanned ship is obtained; meanwhile, the unmanned ship can keep the optimal speed navigation by combining with the speed constraint.
Description
Technical Field
The invention relates to the technical field of unmanned ships, in particular to a navigation path decision method and system for an unmanned ship.
Background
The autonomous navigation is one of the most important core technologies of the unmanned ship, and the solution of the autonomous navigation problem of the unmanned ship not only needs to solve the global path planning problem, but also needs to have a real-time behavior decision function, that is, not only needs to consider collision prevention between the ship and a static obstacle, but also needs to consider collision prevention between the ship and the ship in the movement process.
The traditional DWA (dynamic window approach) behavior decision method is a very excellent real-time obstacle avoidance behavior decision method, and can perform expansion processing on obstacles according to the operating characteristics and the set safe distance of an unmanned ship, establish a dynamic window based on the current motion state of the unmanned ship, and obtain the optimal motion track of the next moment through an evaluation function. However, in the traditional DWA behavior decision method, local optimization is easy to be caused in the process of optimizing the navigation path of the unmanned ship, the accuracy of the decision result is low, and the obtained final navigation path of the unmanned ship may not be optimal.
Therefore, a method and a system for determining a navigation path of an unmanned ship are needed to solve the above problems.
Disclosure of Invention
The invention aims to provide a method and a system for deciding a navigation path of an unmanned ship, so as to improve the decision precision of the navigation path of the unmanned ship and obtain the optimal navigation path of the unmanned ship.
In order to achieve the purpose, the invention provides the following scheme:
a unmanned ship navigation path decision method comprises the following steps:
acquiring the current speed of the unmanned ship;
constraining the current time speed of the unmanned ship and generating a speed sampling space of a next time window of the unmanned ship;
generating a navigation path according to the speed sampling space;
constructing an evaluation function according to the global gravitational field;
screening an optimal navigation path of the unmanned ship by using the evaluation function;
controlling the unmanned ship to sail according to the optimal sailing path;
judging whether the unmanned ship reaches a target point;
if the unmanned ship does not reach the target point, returning to the step of collecting the current speed of the unmanned ship; otherwise, the unmanned ship completes the navigation of the target point.
Optionally, the constraining the speed of the unmanned ship at the current time, and generating a speed sampling space of a next time window of the unmanned ship specifically include:
constraining the current speed of the unmanned ship according to the maximum navigation speed and the minimum navigation speed of the unmanned ship to generate a navigation speed constraint set;
constraining the current speed of the unmanned ship according to the maximum acceleration and the minimum acceleration of the unmanned ship, and generating an acceleration constraint set;
according to the distance between the unmanned ship and the nearest barrier, the speed of the unmanned ship at the current moment is constrained to generate a distance constraint set;
and taking the intersection of the sailing speed constraint set, the acceleration constraint set and the distance constraint set as a speed sampling space of a window at the next moment of the unmanned ship.
Optionally, the set of sailing speed constraints is represented as:
Vm＝{(v,ω)|v∈[vmin,vmax],ω∈[ωmin,ωmax]}
wherein, VmRepresenting the set of voyage speed constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofminRepresenting the minimum navigation speed of the unmanned ship; v. ofmaxRepresenting the maximum navigation speed of the unmanned ship; omegaminRepresenting the minimum turning bow angular velocity of the unmanned ship; omegaminIndicating the maximum yaw rate of the unmanned ship.
Optionally, the set of acceleration constraints is represented as:
Vd＝{(v,ω)|v∈[vc-vbΔt,vc+vaΔt],ω∈[ωc-ωbΔt,ωc+ωaΔt]}
wherein, VdRepresenting the set of acceleration constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofcRepresenting the current navigation speed of the unmanned ship; omegacRepresenting the current turning angular speed of the unmanned ship; v. ofbRepresenting the minimum sailing acceleration of the unmanned ship; Δ t represents the time interval of adjacent windows; v. ofaRepresenting the maximum sailing acceleration of the unmanned ship; omegabRepresenting the minimum turning bow angular acceleration of the unmanned ship; omegaaIndicating the maximum yaw angular acceleration of the unmanned ship.
Optionally, the distance constraint set is represented as:
Va＝{(v,ω)|v≤(2d(v,ω)vb)1/2,ω≤(2d(v,ω)ωb)1/2}
wherein, VaRepresenting the set of distance constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofbRepresenting the minimum sailing acceleration of the unmanned ship; omegabRepresenting the minimum turning bow angular acceleration of the unmanned ship; d (v, ω) represents the distance of the unmanned ship with velocity (v, ω) from the nearest obstacle.
Optionally, the process of establishing the global gravitational field includes:
calculating an attractive force potential field according to the relative distance between the unmanned ship and a target point;
and calculating the gravity of the target point on the unmanned ship according to the gravity potential field.
Optionally, the evaluation function is represented as:
G(ν,ω)＝σ(αheading(ν,ω)+βdist(ν,ω)+γvelocity(ν,ω)+μgravition(ν,ω))
wherein G (v, ω) represents the merit function; σ represents a smoothing function; the heading (v, omega) is used for evaluating an angle between a course and a target point when the unmanned ship reaches the tail end of the simulated track at the current sampling speed; dist (v, ω) represents the distance of the unmanned ship from the nearest obstacle on the voyage path; the velocity (v, omega) is used for evaluating the velocity of the unmanned ship in the current navigation path; the gravity (v, omega) is used for evaluating the gravity of the unmanned ship on a target point in the current navigation path; α, β, γ, and μ denote weight coefficients of four terms.
Optionally, the optimal sailing path of the unmanned ship is screened through the evaluation function and the international maritime collision rule.
Optionally, the weight coefficient in the evaluation function is obtained by training using a deep reinforcement learning algorithm.
An unmanned ship navigation path decision system comprising:
the acquisition module is used for acquiring the current speed of the unmanned ship;
the speed sampling space generation module is used for constraining the speed of the unmanned ship at the current moment and generating a speed sampling space of a window at the next moment of the unmanned ship;
the navigation path generating module is used for generating a navigation path according to the speed sampling space;
the evaluation function constructing module is used for constructing an evaluation function according to the global gravitational field;
the screening module is used for screening the optimal navigation path of the unmanned ship by using the evaluation function;
the control module is used for controlling the unmanned ship to sail according to the optimal sailing path;
the judging module is used for judging whether the unmanned ship reaches a target point; if the unmanned ship does not reach the target point, returning to the step of collecting the current speed of the unmanned ship; otherwise, the unmanned ship completes the navigation of the target point.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a decision-making method and a decision-making system for a navigation path of an unmanned ship.A gravitational force constraint of a target point to the unmanned ship is generated by adding a gravitational field, so that the problem that the traditional DWA algorithm is easy to fall into local optimum is solved, the decision-making precision of the navigation path of the unmanned ship is improved, and the optimal navigation path of the unmanned ship is obtained; meanwhile, the unmanned ship can keep the optimal speed navigation by combining with the speed constraint.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a method for determining a navigation path of an unmanned ship according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a path screened by a conventional DWA behavior decision method and an improved DWA behavior decision method incorporating the international maritime collision avoidance rule provided in embodiment 1 of the present invention;
fig. 3 is a block diagram of a navigation path decision system for an unmanned ship according to embodiment 1 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for deciding a navigation path of an unmanned ship, so as to improve the decision precision of the navigation path of the unmanned ship and obtain the optimal navigation path of the unmanned ship
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example 1:
DWA (dynamic window method): the algorithm can calculate the maximum and minimum speed and angular velocity of the current robot according to the current state of the robot (i.e. the current speed, the heading angle) and a robot motion model (the maximum speed, the maximum angular velocity, the acceleration and the rotation acceleration which can be reached by the robot), and the maximum and minimum speed and angular velocity of the current robot are used as a limited range (the range is a window), and the position which can be reached at each speed and angular velocity is calculated in the range, and each position is evaluated (the evaluation content comprises the distance from an obstacle, the angle towards an end point and the like), so that the current best position is selected, and then the optimal position is continuously repeated to establish a new window, so that the window moves, namely a dynamic window.
In the traditional DWA behavior decision method, local optimization is easy to be caused in the process of optimizing the navigation path of the unmanned ship, the accuracy of a decision result is low, and the obtained final navigation path of the unmanned ship is possibly not optimal. To solve the technical problem, referring to fig. 1, the present invention provides a method for determining a navigation path of an unmanned ship, including:
s1: acquiring the speed of the unmanned ship at the current moment, and simultaneously acquiring the distance between the unmanned ship and the nearest barrier in the navigation path at the next moment;
infinite groups (v, ω) of unmanned ships can be generated in the process of sailing, but the sampling speed of the unmanned ship needs to be defined and limited according to the self-motion characteristics and the surrounding sailing environment as constraint conditions, namely:
s2: constraining the current time speed of the unmanned ship, and generating a speed sampling space of a next time window of the unmanned ship, wherein the speed sampling space specifically comprises the following steps:
the method comprises the following steps of constraining the current speed of the unmanned ship according to the maximum navigation speed and the minimum navigation speed of the unmanned ship, and generating a navigation speed constraint set, wherein the expression is as follows:
Vm＝{(v,ω)|v∈[vmin,vmax],ω∈[ωmin,ωmax]}
wherein, VmRepresenting the set of voyage speed constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofminRepresenting the minimum navigation speed of the unmanned ship; v. ofmaxRepresenting the maximum navigation speed of the unmanned ship; omegaminRepresenting the minimum turning bow angular velocity of the unmanned ship; omegaminRepresenting the maximum turning bow angular velocity of the unmanned ship;
the unmanned ship is influenced by the performance of the motor: because the motor moment of the unmanned ship is limited, the maximum acceleration and deceleration limitation exists, a dynamic window exists in the simulation period based on the unmanned ship track, and the speed in the window is the actual speed which can be reached by the unmanned ship, namely:
constraining the current speed of the unmanned ship according to the maximum acceleration and the minimum acceleration of the unmanned ship, and generating an acceleration constraint set, wherein the expression is as follows:
Vd＝{(v,ω)|v∈[vc-vbΔt,vc+vaΔt],ω∈[ωc-ωbΔt,ωc+ωaΔt]}
wherein, VdRepresenting the set of acceleration constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofcRepresenting the current navigation speed of the unmanned ship; omegacRepresenting the current turning angular speed of the unmanned ship; v. ofbRepresenting the minimum sailing acceleration of the unmanned ship; Δ t represents the time interval of adjacent windows; v. ofaRepresenting the maximum sailing acceleration of the unmanned ship; omegabRepresenting the minimum turning bow angular acceleration of the unmanned ship; omegaaIndicating the maximum yaw angular acceleration of the unmanned ship.
Based on unmanned ship safety considerations: in order to be able to stop before an obstacle or other vessel is hit, the unmanned vessel speed is therefore constrained under maximum deceleration conditions, namely:
according to the distance between the unmanned ship and the nearest barrier, the speed of the unmanned ship at the current moment is constrained to generate a distance constraint set, and the expression is as follows:
Va＝{(v,ω)|v≤(2d(v,ω)vb)1/2,ω≤(2d(v,ω)ωb)1/2}
wherein, VaRepresenting the set of distance constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofbRepresenting the minimum sailing acceleration of the unmanned ship; omegabRepresenting the minimum turning bow angular acceleration of the unmanned ship; d (v, ω) represents the distance of the unmanned ship with velocity (v, ω) from the nearest obstacle.
Taking the intersection of the navigation speed constraint set, the acceleration constraint set and the distance constraint set as a speed sampling space of a window at the next moment of the unmanned ship, wherein the expression is
Where V represents the velocity sample space.
S3: generating a navigation path according to the speed sampling space;
s4: constructing an evaluation function according to the global gravitational field;
s5: screening an optimal navigation path of the unmanned ship by using the evaluation function;
s6: controlling the unmanned ship to sail according to the optimal sailing path;
s7: judging whether the unmanned ship reaches a target point; if the unmanned ship does not reach the target point, returning to the step of collecting the current speed of the unmanned ship;
s8: otherwise, the unmanned ship completes the navigation of the target point.
As an optional implementation, the establishing process of the global gravitational field includes:
calculating an attractive force potential field according to the relative distance between the unmanned ship and a target point, wherein the expression is as follows:
wherein, Uatt(v, ω) is represented as an attractive potential field; ζ is expressed as the gravity gain; d (v, omega) is the relative distance between the unmanned ship and the target point at the current moment of speed.
Calculating the gravitation of the unmanned ship to the target point according to the gravitation potential field, specifically calculating the gravitation potential field Uatt(v, ω) obtaining a corresponding gravity with respect to a negative gradient of the current state of the unmanned ship, wherein the expression is as follows:
the unmanned ship can generate countless navigation tracks of the unmanned ship at the next moment according to the speed sampling space, and the optimal track is screened out through the evaluation function to realize the decision of the path planning behavior of the unmanned ship. The merit function is expressed as:
G(ν,ω)＝σ(αheading(ν,ω)+βdist(ν,ω)+γvelocity(ν,ω)+μgravitation(ν,ω))
wherein G (v, ω) represents the merit function; σ represents a smoothing function; the heading (v, omega) is used for evaluating an angle between a course and a target point when the unmanned ship reaches the tail end of the simulated track at the current sampling speed; dist (v, ω) represents the distance of the unmanned ship from the nearest obstacle on the voyage path; the velocity (v, omega) is used for evaluating the velocity of the unmanned ship in the current navigation path; the gravity (v, omega) is used for evaluating the gravity of the unmanned ship on a target point in the current navigation path; α, β, γ, and μ denote weight coefficients of four terms.
Before the evaluation function is used for calculation, 4 input parameters of header (v, omega), dist (v, omega), velocity (v, omega) and visibility (v, omega) in the formula need to be normalized respectively.
The weight coefficient of the evaluation function in the traditional DWA behavior decision method is difficult to select. In contrast, the present invention trains 4 weight coefficients in the evaluation function using a deep reinforcement learning algorithm, and determines 4 appropriate values of the weight coefficients, that is, α ═ 0.09, β ═ 0.12, γ ═ 0.16, and μ ═ 0.03.
The traditional DWA behavior decision method has the defect that the path tracks needing to be evaluated are too many, so that the efficiency of the algorithm for deciding the optimal path is reduced. Therefore, the invention also provides an optimal navigation path screening method for the unmanned ship, which utilizes the evaluation function G (v, omega) and the international maritime collision rule to carry out screening.
International maritime collision avoidance rules: the marine traffic rules are set by international maritime organization IMO to prevent and avoid collision between marine vessels.
After a part of sailing tracks of the unmanned ship are screened out by introducing international maritime collision avoidance rules, screening can be performed again through an improved evaluation function, and the efficiency of the unmanned ship in behavior decision making by using a DWA method is improved.
As shown in fig. 2, the trajectories generated by the conventional DWA behavior decision method after speed sampling are all trajectories (including a solid-line trajectory and a dotted-line trajectory), and after the international maritime collision avoidance rule is introduced, only the trajectories of the solid-line part need to be evaluated, and the optimal trajectory is selected from the trajectories, so that the ship navigation rule is followed, the decision time is shortened, and the decision efficiency is improved, wherein a graph a represents encounter; FIG. b shows a chase; the diagram c shows an intersection.
According to the invention, (1) on the basis of the traditional DWA behavior decision method, a global gravitational field is added, so that the problem that the traditional DWA algorithm is easy to fall into local optimum is solved, the decision precision of the navigation path of the unmanned ship is improved, the optimal navigation path of the unmanned ship is obtained, the navigation path of the unmanned ship is more reasonable, and the unmanned ship can reach a target point; meanwhile, the unmanned ship can keep the optimal speed navigation by combining the speed constraint;
(2) the international maritime collision avoidance rule is introduced into the screening of the sailing tracks of countless unmanned ships predicted based on the traditional DWA behavior decision method, so that the efficiency of the unmanned ships in behavior decision by using the DWA method is improved;
(3) the weight coefficients in the evaluation function are trained by using a deep reinforcement learning algorithm, so that the problem that the coefficient selection of the evaluation function is difficult in the traditional DWA behavior decision method is solved.
Example 2:
referring to fig. 3, the present invention also provides a decision making system for a navigation path of an unmanned ship, comprising:
the acquisition module M1 is used for acquiring the speed of the unmanned ship at the current moment;
the speed sampling space generation module M2 is used for constraining the current time speed of the unmanned ship and generating a speed sampling space of a next time window of the unmanned ship;
a navigation path generating module M3, configured to generate a navigation path according to the speed sampling space;
an evaluation function constructing module M4, configured to construct an evaluation function according to the global gravitational field;
the screening module M5 is used for screening the optimal navigation path of the unmanned ship by using the evaluation function;
the control module M6 is used for controlling the unmanned ship to sail according to the optimal sailing path;
the judging module M7 is used for judging whether the unmanned ship reaches a target point; if the unmanned ship does not reach the target point, returning to the step of collecting the current speed of the unmanned ship; otherwise, the unmanned ship completes the navigation of the target point.
The emphasis of each embodiment in the present specification is on the difference from the other embodiments, and the same and similar parts among the various embodiments may be referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A unmanned ship navigation path decision method is characterized by comprising the following steps:
acquiring the current speed of the unmanned ship;
constraining the current time speed of the unmanned ship and generating a speed sampling space of a next time window of the unmanned ship;
generating a navigation path according to the speed sampling space;
constructing an evaluation function according to the global gravitational field;
screening an optimal navigation path of the unmanned ship by using the evaluation function;
controlling the unmanned ship to sail according to the optimal sailing path;
judging whether the unmanned ship reaches a target point;
if the unmanned ship does not reach the target point, returning to the step of collecting the current speed of the unmanned ship; otherwise, the unmanned ship completes the navigation of the target point.
2. The unmanned ship navigation path decision method according to claim 1, wherein the constraining the speed of the unmanned ship at the current moment and generating a speed sampling space of a next moment window of the unmanned ship specifically comprises:
constraining the current speed of the unmanned ship according to the maximum navigation speed and the minimum navigation speed of the unmanned ship to generate a navigation speed constraint set;
constraining the current speed of the unmanned ship according to the maximum acceleration and the minimum acceleration of the unmanned ship, and generating an acceleration constraint set;
according to the distance between the unmanned ship and the nearest barrier, the speed of the unmanned ship at the current moment is constrained to generate a distance constraint set;
and taking the intersection of the sailing speed constraint set, the acceleration constraint set and the distance constraint set as a speed sampling space of a window at the next moment of the unmanned ship.
3. The unmanned ship voyage path decision method according to claim 2, wherein the voyage speed constraint set is expressed as:
Vm＝{(v,ω)|v∈[vmin,vmax],ω∈[ωmin,ωmax]}
wherein, VmRepresenting the set of voyage speed constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofminRepresenting the minimum navigation speed of the unmanned ship; v. ofmaxRepresenting the maximum navigation speed of the unmanned ship; omegaminRepresenting the minimum turning bow angular velocity of the unmanned ship; omegaminIndicating the maximum yaw rate of the unmanned ship.
4. The unmanned ship voyage path decision method according to claim 2, wherein the set of acceleration constraints is expressed as:
Vd＝{(v,ω)|v∈[vc-vbΔt,vc+vaΔt],ω∈[ωc-ωbΔt,ωc+ωaΔt]}
wherein, VdRepresenting the set of acceleration constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofcRepresenting the current navigation speed of the unmanned ship; omegacRepresenting the current turning angular speed of the unmanned ship; v. ofbRepresenting the minimum sailing acceleration of the unmanned ship; Δ t represents the time interval of adjacent windows; v. ofaRepresenting the maximum sailing acceleration of the unmanned ship; omegabRepresenting the minimum turning bow angular acceleration of the unmanned ship; omegaaIndicating the maximum yaw angular acceleration of the unmanned ship.
5. The unmanned ship voyage path decision method according to claim 2, wherein the distance constraint set is expressed as:
Va＝{(v,ω)|v≤(2d(v,ω)vb)1/2,ω≤(2d(v,ω)ωb)1/2}
wherein, VaRepresenting the set of distance constraints; (v, ω) represents the velocity of the unmanned ship, v represents the navigation velocity of the unmanned ship, and ω represents the angular velocity of the unmanned ship; v. ofbRepresenting the minimum sailing acceleration of the unmanned ship; omegabRepresenting the minimum turning bow angular acceleration of the unmanned ship; d (v, ω) represents the distance of the unmanned ship with velocity (v, ω) from the nearest obstacle.
6. The unmanned ship navigation path decision method according to claim 1, wherein the global gravitational field establishment process comprises:
calculating an attractive force potential field according to the relative distance between the unmanned ship and a target point;
and calculating the gravitation suffered by the unmanned ship according to the gravitation potential field.
7. The unmanned ship voyage path decision method according to claim 1, wherein the merit function is expressed as:
G(ν,ω)＝σ(αheading(ν,ω)+βdist(ν,ω)+γvelocity(ν,ω)+μgravitation(ν,ω))
wherein G (v, ω) represents the merit function; σ represents a smoothing function; the heading (v, omega) is used for evaluating an angle between a course and a target point when the unmanned ship reaches the tail end of the simulated track at the current sampling speed; dist (v, ω) represents the distance of the unmanned ship from the nearest obstacle on the voyage path; the velocity (v, omega) is used for evaluating the velocity of the unmanned ship in the current navigation path; the gravity (v, omega) is used for evaluating the gravity of the unmanned ship in the current navigation path; α, β, γ, and μ denote weight coefficients of four terms.
8. The unmanned ship navigation path decision method according to claim 1, wherein the optimal navigation path of the unmanned ship is screened by the evaluation function and international maritime collision rules.
9. The unmanned ship navigation path decision method according to claim 1, wherein the weight coefficients in the evaluation function are obtained by training with a deep reinforcement learning algorithm.
10. An unmanned ship navigation path decision system, comprising:
the acquisition module is used for acquiring the current speed of the unmanned ship;
the speed sampling space generation module is used for constraining the speed of the unmanned ship at the current moment and generating a speed sampling space of a window at the next moment of the unmanned ship;
the navigation path generating module is used for generating a navigation path according to the speed sampling space;
the evaluation function constructing module is used for constructing an evaluation function according to the global gravitational field;
the screening module is used for screening the optimal navigation path of the unmanned ship by using the evaluation function;
the control module is used for controlling the unmanned ship to sail according to the optimal sailing path;
the judging module is used for judging whether the unmanned ship reaches a target point; if the unmanned ship does not reach the target point, returning to the step of collecting the current speed of the unmanned ship; otherwise, the unmanned ship completes the navigation of the target point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110766456.9A CN113359773A (en) | 2021-07-07 | 2021-07-07 | Unmanned ship navigation path decision method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110766456.9A CN113359773A (en) | 2021-07-07 | 2021-07-07 | Unmanned ship navigation path decision method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113359773A true CN113359773A (en) | 2021-09-07 |
Family
ID=77538711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110766456.9A Pending CN113359773A (en) | 2021-07-07 | 2021-07-07 | Unmanned ship navigation path decision method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113359773A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114407054A (en) * | 2022-03-30 | 2022-04-29 | 北京大成国测科技有限公司 | Total powerstation robot based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109144102A (en) * | 2018-09-19 | 2019-01-04 | 沈阳航空航天大学 | A kind of Path Planning for UAV based on improvement bat algorithm |
| CN110850873A (en) * | 2019-10-31 | 2020-02-28 | 五邑大学 | Unmanned ship path planning method, device, equipment and storage medium |
| CN111273670A (en) * | 2020-03-03 | 2020-06-12 | 大连海事大学 | Unmanned ship collision avoidance method for fast moving barrier |
| CN112327885A (en) * | 2020-12-01 | 2021-02-05 | 大连海事大学 | Unmanned ship self-adaptive global-local hybrid path planning method |
| CN112486183A (en) * | 2020-12-09 | 2021-03-12 | 上海机器人产业技术研究院有限公司 | Path planning algorithm of indoor mobile robot |
| CN112507520A (en) * | 2020-11-12 | 2021-03-16 | 深圳慧拓无限科技有限公司 | Path planning method and device based on reinforcement learning |
-
2021
- 2021-07-07 CN CN202110766456.9A patent/CN113359773A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109144102A (en) * | 2018-09-19 | 2019-01-04 | 沈阳航空航天大学 | A kind of Path Planning for UAV based on improvement bat algorithm |
| CN110850873A (en) * | 2019-10-31 | 2020-02-28 | 五邑大学 | Unmanned ship path planning method, device, equipment and storage medium |
| CN111273670A (en) * | 2020-03-03 | 2020-06-12 | 大连海事大学 | Unmanned ship collision avoidance method for fast moving barrier |
| CN112507520A (en) * | 2020-11-12 | 2021-03-16 | 深圳慧拓无限科技有限公司 | Path planning method and device based on reinforcement learning |
| CN112327885A (en) * | 2020-12-01 | 2021-02-05 | 大连海事大学 | Unmanned ship self-adaptive global-local hybrid path planning method |
| CN112486183A (en) * | 2020-12-09 | 2021-03-12 | 上海机器人产业技术研究院有限公司 | Path planning algorithm of indoor mobile robot |
Non-Patent Citations (3)
| Title |
|---|
| LU CHANG 等: "Reinforcement based mobile robot path planning with improved dynamic window approach in unknown environment", AUTONOMOUS ROBOTS, vol. 45, no. 1, pages 51 - 76, XP037353858, DOI: 10.1007/s10514-020-09947-4 * |
| 刘渐道 等: "基于改进动态窗口法的无人水面艇自主避碰算法", 上海海事大学学报, vol. 42, no. 2, pages 1 - 7 * |
| 文元桥 等: "水面无人艇的体系结构与运动控制", 31 July 2019, 武汉理工大学出版社, pages: 175 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114407054A (en) * | 2022-03-30 | 2022-04-29 | 北京大成国测科技有限公司 | Total powerstation robot based on artificial intelligence |
| CN114407054B (en) * | 2022-03-30 | 2022-07-29 | 北京大成国测科技有限公司 | Total powerstation robot based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956853B (en) | Multi-ship collision prediction method, system and storage medium | |
| CN111273670B (en) | Unmanned ship collision prevention method for fast moving obstacle | |
| JP4495703B2 (en) | Operation control method, apparatus and program for underwater robot | |
| CN113156947B (en) | Method for planning path of ship in dynamic environment | |
| CN109814392A (en) | A kind of drive lacking underwater robot actuator failures robust Fault-Tolerant Control method | |
| CN113189984B (en) | Unmanned ship path planning method based on improved artificial potential field method | |
| CN111123923A (en) | Unmanned ship local path dynamic optimization method | |
| CN114442640A (en) | Track tracking control method for unmanned surface vehicle | |
| CN113359773A (en) | Unmanned ship navigation path decision method and system | |
| CN113538973B (en) | Automatic ship collision avoidance method based on improved particle swarm optimization | |
| Kim et al. | A numerical and experimental study on the obstacle collision avoidance system using a 2D LiDAR sensor for an autonomous surface vehicle | |
| Li et al. | Integrating dynamic event-triggered and sensor-tolerant control: Application to USV-UAVs cooperative formation system for maritime parallel search | |
| CN117369441A (en) | Self-adaptive intelligent ship path planning method considering ship kinematics and COLLEGs | |
| CN113467483A (en) | Local path planning method and device based on space-time grid map in dynamic environment | |
| Zhao et al. | Robust control of neutral system with time-delay for dynamic positioning ships | |
| CN117311142A (en) | DP ship motion control and thrust distribution cooperative control method integrating particle swarm optimization and neural network predictive control | |
| CN114609925B (en) | Training method of underwater exploration strategy model and underwater exploration method of bionic machine fish | |
| Liang et al. | Economic MPC-based planning for marine vehicles: Tuning safety and energy efficiency | |
| Jose et al. | Navigating the Ocean with DRL: Path following for marine vessels | |
| Sivaraj et al. | Heading control of a ship based on deep reinforcement learning (RL) | |
| CN114879694A (en) | Unmanned ship automatic collision avoidance method based on probability game theory framework | |
| Miotto et al. | UUV on-board path planning in a dynamic environment for the Manta test vehicle | |
| Yuan et al. | EMPMR berthing scheme: A novel event-triggered motion planning and motion replanning scheme for unmanned surface vessels | |
| Malecki | Fuzzy track-keeping steering design for a precise control of the ship | |
| Higo et al. | Development of trajectory-tracking maneuvering system for automatic berthing/unberthing based on double deep Q-network and experimental validation with an actual large ferry |
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 |