CN111580518B - Unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method - Google Patents
Unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method Download PDFInfo
- Publication number
- CN111580518B CN111580518B CN202010396241.8A CN202010396241A CN111580518B CN 111580518 B CN111580518 B CN 111580518B CN 202010396241 A CN202010396241 A CN 202010396241A CN 111580518 B CN111580518 B CN 111580518B
- Authority
- CN
- China
- Prior art keywords
- ship
- unmanned
- unmanned ship
- obstacle avoidance
- obstacle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005457 optimization Methods 0.000 title claims abstract description 29
- 241000255581 Drosophila <fruit fly, genus> Species 0.000 title claims abstract description 17
- 230000004888 barrier function Effects 0.000 claims abstract description 21
- 230000003068 static effect Effects 0.000 claims abstract description 7
- 241000255588 Tephritidae Species 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 25
- 230000000007 visual effect Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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 relates to the field of autonomous navigation of unmanned boats, in particular to an unmanned boat layered obstacle avoidance method based on improved drosophila optimization and dynamic window methods. The invention comprises the following steps: step S1: establishing an unmanned ship marine navigation geographical environment model based on an electronic chart; step S2: an improved drosophila optimization algorithm is adopted to complete global optimal path planning; step S3: establishing an environment model of a dynamic barrier; step S4: an improved dynamic window method is adopted to avoid the ship moving the obstacles. The invention provides an obstacle avoidance method for switching between dynamic and static obstacle avoidance modes based on judgment conditions, which can effectively avoid obstacles during navigation, avoid the algorithm from falling into a local optimal solution, dynamically control the weight parameters of an optimal track by adopting a fuzzy control method, and improve the precision and efficiency of track prediction.
Description
Technical Field
The invention relates to the field of autonomous navigation of unmanned boats, in particular to an unmanned boat layered obstacle avoidance method based on improved drosophila optimization and dynamic window methods.
Background
With the increasing importance of the ocean in the development process of China, higher requirements are put forward on the development of ocean intelligent equipment. The unmanned ship plays a vital role in the civil fields of resource exploration, water area monitoring, meteorology monitoring and the like and the military fields of offshore unmanned combat, enemy target searching and the like. At present, unmanned ships are used as intelligent equipment for autonomous sailing at sea, and due to the uncertainty of marine environment and the complexity of marine traffic sailing, static islands and moving ships threaten the safety of the unmanned ships during marine sailing, so that a great number of ship collision accidents occur. In order to reduce the occurrence of accidents and enable the unmanned ship to smoothly avoid dynamic obstacles and static obstacles such as passing ships when the unmanned ship executes tasks, a mode of switching between global path planning and local dynamic path planning is adopted, so that the unmanned ship can safely reach a terminal point.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a layered obstacle avoidance method of an unmanned ship based on improved fruit fly optimization and a dynamic window method.
Step S1: establishing an unmanned ship marine navigation geographical environment model based on an electronic chart;
the method comprises the steps of obtaining geographic environment information of a navigation sea area of the unmanned ship from an electronic chart, using islands and the like as static obstacles, carrying out expansion processing on the obstacles by a visual chart method to obtain map information, and storing coordinates of visual points and data of visual edges. The position information of the unmanned ship is obtained by using inertial sensors such as a marine accelerometer, a gyroscope, a magnetic compass and the like through a dead reckoning algorithm, and the starting point and the ending point of the navigation are specified.
Step S2: adopting an improved drosophila optimization algorithm to complete global optimal path planning;
in the obstacle environment model established by the visual graph method, a data set containing visual point coordinates and visual edges is established. The problem of planning the global optimal path is converted into the problem of searching the shortest path from the starting point of the unmanned ship to the terminal of the navigation through the visible edge by an improved drosophila optimization algorithm.
Step S3: establishing an environment model of a dynamic barrier;
the obstacle moving on the sea is mainly a passing ship, and the motion information of the obstacle ship moving on the sea is obtained through equipment such as a radar and the like, and comprises the moving position, the moving direction, the moving speed, the moving acceleration and the like of the obstacle ship. The moving barrier vessel is "inflated" into a circle. The current navigation information of the unmanned ship is obtained from the shipborne sensor and the positioning equipment, and the navigation position, navigation speed, direction, acceleration and the like of the ship are read after filtering processing. And setting judgment conditions for avoiding obstacles, and when the obstacle avoiding conditions are met between the unmanned ship and the movement obstacle ships, switching the unmanned ship to an active local obstacle avoiding mode.
Step S4: adopting an improved dynamic window method to avoid the ship moving the barrier;
under an active local obstacle avoidance mode, the optimal speed and the optimal course of unmanned ship navigation at the next moment are selected from an unmanned ship feasible speed window and a rotation speed window by an improved dynamic window method according to a track prediction track evaluation function, so that an obstacle-avoiding ship is avoided, and when the obstacle-avoiding ship is avoided, the unmanned ship is switched to a global optimal path and navigates to a terminal point.
Aiming at the condition of poor overall search performance of the algorithm, the fruit fly optimization algorithm sets the fixed step length of the individual fruit fly movement in the fruit fly optimization algorithm as the variable step length so as to improve the overall search capability. I.e. S ═ S 0 *e r . Where S is the real-time step size, S 0 For the purpose of the initial step size,
t is the current number of iterations, T max Is the maximum number of iterations.
The flight position information of the ith fruit fly individual in the fruit fly optimization algorithm is
Wherein the position of the random initial fruit fly colony in the X, Y coordinate system is X 0 、Y 0 And rand () is [0,1 ]]The random number of (2);
establishing a relative coordinate system V by taking a geometric center O point of the unmanned ship as an original point usv For unmanned boat speed, V obs For moving the speed of the obstacle-carrying vessel, V usv-obs ＝V usv -V obs Indicating the vector difference between the two. Extension V usv-obs If the intersection point exists between the navigation device and the expansion circle, the navigation device needs to be switched to an obstacle avoidance mode, and if the intersection point does not exist, the navigation device navigates along the optimal global path.
And in the obstacle avoidance mode, the position of the obstacle-avoiding ship is monitored in real time by using a shipborne radar of the unmanned ship, and the obstacle avoidance is finished when the stern of the unmanned ship is parallel to or in advance of the obstacle-avoiding ship. And after obstacle avoidance is finished, switching to the global optimal path and continuing navigating to the terminal.
In the track model of the dynamic window algorithm, according to the motion mathematical model of the unmanned ship, the track model of the traditional dynamic window method is improved to obtain the following positions of the unmanned ship in a northeast coordinate system:
wherein x t+1 ，y t+1 North and east positions, x, in the north-east coordinate system at the next moment of time, respectively, of the unmanned surface vehicle t 、y t U is north and east position of unmanned boat at present usv-t The longitudinal speed v of the unmanned ship at the current moment usv-t The lateral speed r of the unmanned ship at the current moment t Is the rotation speed psi of the unmanned ship at the current moment t Is an included angle between the direction of the bow of the unmanned ship at the current moment and the north direction of a northeast coordinate system,
ψ t+1 is the included angle between the direction of the bow of the unmanned ship at the next moment and the north direction of the northeast coordinate system.
Dynamically adjusting weight parameters in a track evaluation function by adopting a fuzzy control method, wherein the track evaluation function is as follows: g (v, ω) ═ σ (a · normal (heading (v, r)) + b · normal (dist (v, r)) + c · normal (velocity (v, r))), heading (v, r), dist (v, r), velocity (v, r), among others) The azimuth evaluation function, the distance evaluation function and the speed evaluation function in the unmanned ship preset track are respectively represented, a, b and c are weight factors of the three evaluation functions, sigma is a set constant value, and normalize represents that the three evaluation functions are subjected to normalization processing. Distances d and V between unmanned ship and barrier ship usv-obs And an included angle beta of 0A is used as an input, wherein the point A is the geometric center of the expanded circle of the obstacle ship, a, b and c are used as outputs to establish a fuzzy controller, and the values of a, b and c are dynamically adjusted.
Compared with the prior art, the invention has the beneficial effects that:
(1) the obstacle avoidance method based on the switching of the dynamic obstacle avoidance mode and the static obstacle avoidance mode under the judgment condition is provided, and the obstacle can be effectively avoided during navigation.
(2) A variable step length method is provided to improve the fruit fly optimization algorithm, and the algorithm is prevented from falling into a local optimal solution.
(3) An improved dynamic window algorithm is provided, the weight parameters of the optimal track are dynamically controlled by adopting a fuzzy control method, and the precision and the efficiency of track prediction are improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification:
FIG. 1 is a flow chart of the overall scheme of the present invention;
FIG. 2 is a schematic view of a visualization method;
FIG. 3 is a flow chart of a global optimal path based on an improved drosophila optimization algorithm;
FIG. 4 is a diagram of the coordinate relationship between the established ship and the obstacle;
FIG. 5 is a system diagram of a fuzzy controller;
FIG. 6 is a flow chart of an improved dynamic windowing method.
Detailed Description
In order to more clearly illustrate the technical solution of the present invention, the present invention will be briefly described below with reference to the embodiments. Referring now to FIG. 1, specific steps of implementation are illustrated.
Step S1: establishing an unmanned ship marine navigation geographical environment model based on an electronic chart;
the geographical environment information of the navigation sea area of the unmanned ship is obtained from the electronic chart, islands and the like are used as static obstacles, the obstacles are subjected to expansion processing through a visual chart method to obtain map information, and the map information is shown in figure 2 and the coordinate of a visual point and the data of a visual side are stored. The position information of the unmanned ship is obtained by using inertial sensors such as a marine accelerometer, a gyroscope, a magnetic compass and the like through a dead reckoning algorithm, and the starting point and the ending point of the navigation are specified.
Step S2: an improved drosophila optimization algorithm is adopted to complete global optimal path planning;
the obstacle environment model established by the visual graph method comprises two data sets of a visual edge and a visual point. The problem of planning a global optimal path is converted into a problem of searching for a shortest path from the starting point of the unmanned ship voyage to the terminal point of the voyage through the visible edge by using an improved drosophila optimization algorithm.
In the fruit fly optimization algorithm, aiming at the condition of poor global search performance of the algorithm, the fixed step length of the individual fruit fly movement in the fruit fly optimization algorithm is changed into the nonlinear decreasing step length so as to improve the global search capability. I.e. S ═ S 0 *e r . Where S is the real-time step size, S 0 For the purpose of the initial step size,
t is the current number of iterations, T max Is the maximum number of iterations.
With reference to fig. 3, the implementation steps of the improved drosophila optimization algorithm are as follows:
initializing parameters of a population, setting the maximum number of individuals in the population to be N, and setting the maximum iteration times t max Random initial Drosophila population position X 0 、Y 0 ；
Secondly, updating the step length S and the flight position information of the ith fruit fly individual
Wherein rand () is [0,1 ]]The random number of (2);
estimating the distance from the ith fruit fly to the origin
Food taste concentration value
Fourthly, calculating the taste concentration value smell of the individual fruit flies according to the fitness function i ＝fit(S i ) (ii) a fit represents a fitness function;
finding out the best individual in each generation;
recording the minimum value of the odor concentration and the position of the fruit fly;
seventhly, iterating the algorithm, repeating the steps from the fourth step to the fifth step, entering into the sixth step when the taste concentration value of the fruit flies is smaller than the result of the previous iteration, and stopping calculation when the iteration times reach the maximum iteration times. And finishing the optimal path planning.
Step S3: and establishing an environment model of the dynamic barrier.
The obstacle moving on the sea is mainly a passing ship, and the motion information of the obstacle ship moving on the sea is obtained through equipment such as a radar and the like, and comprises the moving position, the moving direction, the moving speed, the moving acceleration and the like of the obstacle ship. The moving barrier vessel is "inflated" into a circle. The current navigation information of the unmanned ship is obtained from the shipborne sensor and the Beidou positioning equipment, and the navigation position, the navigation speed, the navigation direction, the acceleration and the like of the ship are read after filtering processing. And setting judgment conditions for avoiding obstacles, and when the obstacle avoiding conditions are met between the unmanned ship and the movement obstacle ships, switching the unmanned ship to an active local obstacle avoiding mode.
Obstacle avoidance switching conditions: establishing a relative coordinate system V by taking a geometric center 0 point of the unmanned ship as an origin usv For unmanned boat speed, V obs For moving the speed of the obstacle-carrying vessel, V usv-obs ＝V usv -V obs Indicating the vector difference between the two. Extension V usv-obs If the intersection point exists between the navigation device and the expansion circle, the navigation device needs to be switched to an obstacle avoidance mode, and if the intersection point does not exist, the navigation device navigates along the optimal global path. In the obstacle avoidance mode, the position of the obstacle-avoiding ship is monitored in real time by using an unmanned ship-borne radarAnd when the stern of the unmanned boat is parallel to or in advance of the barrier boat, obstacle avoidance is finished. After obstacle avoidance is finished, the navigation system is switched to the global optimal path to continue navigating to the terminal point
Description step S4: adopting an improved dynamic window method to avoid the ship moving the barrier;
under an active local obstacle avoidance mode, the optimal speed and the optimal course of unmanned ship navigation at the next moment are selected from an unmanned ship feasible speed window and a rotation speed window by an improved dynamic window method according to a track prediction track evaluation function, so that an obstacle-avoiding ship is avoided, and when the obstacle-avoiding ship is avoided, the unmanned ship is switched to a global optimal path and navigates to a terminal point. According to a motion mathematical model of the unmanned ship, firstly, a track model of a traditional dynamic window method is improved to obtain the following positions of the unmanned ship in a northeast coordinate system:
wherein x t+1 ，y t+1 North and east positions, x, in the north-east coordinate system at the next moment of time, respectively, of the unmanned surface vehicle t 、y t U is the north and east positions of the unmanned boat at the current moment usv-t The longitudinal speed v of the unmanned ship at the current moment usv-t The transverse speed r of the unmanned ship at the current moment t Is the rotation speed psi of the unmanned ship at the current moment t Is the included angle psi between the direction of the bow of the unmanned boat at the current moment and the north direction of the northeast coordinate system t+1 Is the included angle between the direction of the bow of the unmanned ship at the next moment and the north direction of the northeast coordinate system.
Now, with reference to fig. 5, the dynamic adjustment of the weighting parameters in the trajectory evaluation function will be described. The evaluation function of the trace is as follows: g (v, ω) ═ σ (a · normal (v, r)) + b · normal (dist (v, r)) + c · normal (velocity (v, r))), wherein the head (v, r), dist (v, r), velocity (v, r) respectively represent the azimuth evaluation function, the distance evaluation function, the velocity evaluation function in the preset trajectory of the unmanned boat, a, b, c are the weighting factors of the three evaluation functions, σ is a set constant value, and normal represents the three evaluation functions as the set constant valueAnd (6) normalization processing. Distances d and V between unmanned ship and barrier ship usv-obs And an included angle beta with OA is used as an input, wherein the point A is the geometric center of the expanded circle of the obstacle ship, a, b and c are used as outputs to establish a fuzzy controller, and the values of a, b and c are dynamically adjusted. d has a discourse field of [0, 20]Output beta has a discourse field of [0, gamma ]]Gamma is V usv-obs Angle to the circle boundary. d and V usv-obs The value range of (1) is { PS PM PB }, which represents { positive small, middle, positive large }. Discourse domain of a, b and c is [0,1 ]]Their values are { PS PM PB PZ }, which means { positive small, positive big }. And establishing the following fuzzy rule table:
fuzzy rule table of tables 1 a, b, c
With reference to fig. 6, the specific steps of the improved dynamic window algorithm are as follows:
initializing parameters, acquiring information such as position, speed, course and the like of a dynamic barrier, and establishing an environment model of the dynamic barrier;
acquiring motion information of the current navigation position, speed, acceleration, heading and the like of the unmanned ship;
generating a preset track window according to an improved dynamic window method;
eliminating the set of collision speed and rotation speed with the obstacle in the preset track window;
generating an executable speed and a rotation speed window for the unmanned ship to avoid the barrier to sail;
selecting the optimal speed and the rotation speed for executing the obstacle avoidance task according to the improved track preset performance evaluation function;
and seventhly, judging whether obstacle avoidance is finished, if yes, switching to the global planned path for navigation after execution is finished, and if not, continuing to execute the steps from the step two to the step seven.
The invention discloses an unmanned ship layered obstacle avoidance method based on improved drosophila optimization and a dynamic window method. And (3) monitoring dynamic obstacles such as a moving ship and the like through equipment such as a radar and the like, and establishing a dynamic obstacle environment model. The method comprises the steps of obtaining motion information of the unmanned ship and a moving barrier, judging whether collision is possible, and if the collision is possible, switching to a local dynamic obstacle avoidance mode based on a dynamic window method. And when obstacle avoidance is finished, switching to the global optimal path to navigate to the terminal. The invention aims to provide an efficient and safe obstacle avoidance method for autonomous navigation of an unmanned ship at sea.
Claims (5)
1. An unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method is characterized by comprising the following steps:
step S1: establishing an unmanned ship marine navigation geographical environment model based on an electronic chart;
acquiring geographical environment information of a navigation sea area of the unmanned ship from the electronic chart, taking islands and the like as static obstacles, performing expansion processing on the obstacles by a visual graph method to obtain map information, and storing data of a visual point and a visual side; acquiring current navigation information of the unmanned ship from a shipborne sensor and a Beidou positioning system, and after filtering, reading the navigation position, navigation speed, direction and acceleration of the ship and specifying the starting point and the terminal point of navigation;
step S2: an improved drosophila optimization algorithm is adopted to complete global optimal path planning;
in an obstacle environment model established by a visual graph method, a data set comprising visual point coordinates and visual edges; the problem of planning the global optimal path is converted into the problem of searching the shortest path from the starting point of the unmanned ship navigation to the navigation target point through the visual edge by the improved drosophila optimization algorithm;
step S3: establishing an environment model of a dynamic barrier;
the method comprises the following steps that the sea moving barrier is a passing ship, and motion information of the sea moving barrier ship is obtained through equipment such as a radar and the like, wherein the motion information comprises the moving position, direction, speed and acceleration of the moving barrier ship; "inflate" the moving barrier vessel into a circle; acquiring current navigation information of the unmanned ship from a shipborne sensor and a Beidou positioning system, after filtering processing, reading the navigation position, the navigation speed, the heading and the acceleration of the ship, setting judgment conditions needing to adopt obstacle avoidance, and when the obstacle avoidance conditions are met between the unmanned ship and a movement obstacle ship, switching the unmanned ship to an active local obstacle avoidance mode;
step S4: adopting an improved dynamic window method to avoid the ship moving the barrier;
under an active local obstacle avoidance mode, selecting the optimal speed and the rotation speed of the unmanned ship sailing at the next moment from an unmanned ship feasible speed window and a rotation speed window by an improved dynamic window method according to a track prediction track evaluation function so as to avoid an obstacle ship, switching to a global optimal path when avoiding moving the obstacle ship, and sailing towards a terminal point;
aiming at the condition of poor overall search performance of the algorithm, the fruit fly optimization algorithm sets the fixed step length of the movement of the fruit fly in the fruit fly optimization algorithm as the variable step length so as to improve the overall search capability; i.e. S ═ S 0 *e r (ii) a Where S is the real-time step size, S 0 For the purpose of the initial step size,
t is the current number of iterations, T max Is the maximum number of iterations;
in the track model of the dynamic window method, according to the motion mathematical model of the unmanned ship, the track model of the traditional dynamic window method is improved to obtain the following positions of the unmanned ship in a northeast coordinate system:
wherein x t+1 ，y t+1 North and east positions, x, in the north-east coordinate system at the next moment of time, respectively, of the unmanned surface vehicle t 、y t U is north and east position of unmanned boat at present usv-t As the current timeLongitudinal speed, v, of unmanned surface vehicle usv-t The transverse speed r of the unmanned ship at the current moment t Is the rotation speed psi of the unmanned ship at the current moment t The included angle psi between the direction of the bow of the unmanned ship at the current moment and the north direction of the northeast coordinate system t+1 Is the included angle between the direction of the bow of the unmanned ship at the next moment and the north direction of the northeast coordinate system.
2. The layered obstacle avoidance method for the unmanned ship based on the improved fruit fly optimization and dynamic window method as claimed in claim 1, wherein: the flight position information of the ith fruit fly individual in the fruit fly optimization algorithm is
Wherein the position of the random initial fruit fly colony in the X, Y coordinate system is X 0 、Y 0 And rand () is [0,1 ]]The random number of (2).
3. The layered obstacle avoidance method for the unmanned ship based on the improved fruit fly optimization and dynamic window method as claimed in claim 1, wherein: establishing a relative coordinate system V by taking a geometric center O point of the unmanned ship as an origin usv For unmanned boat speed, V obs For moving the speed of the obstacle-carrying vessel, V usv-obs ＝V usv -V obs Representing the vector difference of the two; extension V usv-obs If the intersection point exists between the navigation device and the expansion circle, the navigation device needs to be switched to an obstacle avoidance mode, and if the intersection point does not exist, the navigation device navigates along the optimal global path.
4. The layered obstacle avoidance method for the unmanned ship based on the improved fruit fly optimization and dynamic window method as claimed in claim 1, wherein: in an obstacle avoidance mode, using an unmanned boat shipborne radar to monitor the position of an obstacle ship in real time, and finishing obstacle avoidance when the stern of the unmanned boat is parallel to or in advance of the obstacle ship; and after obstacle avoidance is finished, switching to the global optimal path and continuing navigating to the terminal.
5. The method of claim 1 based on improved drosophila optimization and dynamicsThe layered obstacle avoidance method of the unmanned ship by the window method is characterized by comprising the following steps: dynamically adjusting weight parameters in a track evaluation function by adopting a fuzzy method, wherein the track evaluation function is as follows: g (v, ω) ═ σ (a · normalized (v, r)) + b · normalized (dist (v, r)) + c · normalized (velocity (v, r))), wherein the head (v, r), dist (v, r), and velocity (v, r) respectively represent the azimuth evaluation function, the distance evaluation function, and the velocity evaluation function in the preset trajectory of the unmanned boat, a, b, c are the weighting factors of the three evaluation functions, σ is a set constant value, and the normalized (velocity) represents that the three evaluation functions are subjected to normalization processing; distances d and V between unmanned ship and barrier ship usv-obs And an included angle beta between the obstacle ship and the OA is used as an input, wherein the point A is the geometric center of the expanded circle of the obstacle ship, a, b and c are used as outputs to establish a fuzzy controller, and the values of the a, b and c are dynamically adjusted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010396241.8A CN111580518B (en) | 2020-05-12 | 2020-05-12 | Unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010396241.8A CN111580518B (en) | 2020-05-12 | 2020-05-12 | Unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111580518A CN111580518A (en) | 2020-08-25 |
| CN111580518B true CN111580518B (en) | 2022-08-02 |
Family
ID=72113488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010396241.8A Active CN111580518B (en) | 2020-05-12 | 2020-05-12 | Unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111580518B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112462766B (en) * | 2020-11-23 | 2022-09-09 | 江苏科技大学 | Device and method for autonomous obstacle avoidance of unmanned ship |
| CN112462786B (en) * | 2020-12-03 | 2024-01-19 | 大连海事大学 | Unmanned ship collision prevention method based on fuzzy control strategy double-window algorithm |
| CN112731944B (en) * | 2021-01-15 | 2022-02-18 | 同济大学 | Autonomous obstacle avoidance method for unmanned road roller |
| CN113110424A (en) * | 2021-03-26 | 2021-07-13 | 大连海事大学 | Unmanned ship collision avoidance method based on chart information |
| CN113625720B (en) * | 2021-08-19 | 2024-05-10 | 中国舰船研究设计中心 | Unmanned ship autonomous navigation control algorithm simulation evaluation system |
| CN114281083B (en) * | 2021-12-28 | 2024-05-14 | 江苏大学 | Unmanned ship water quality monitoring Internet of things control system and method based on hybrid path planning autonomous navigation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416152A (en) * | 2018-03-18 | 2018-08-17 | 哈尔滨工程大学 | The optimal global path planning method of unmanned boat ant colony energy consumption based on electronic chart |
| 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 |
| CN110032184A (en) * | 2019-03-12 | 2019-07-19 | 哈尔滨工程大学 | A kind of unmanned boat collision prevention method waterborne based on heredity with slip window sampling |
| CN110609559A (en) * | 2019-10-25 | 2019-12-24 | 江苏恒澄交科信息科技股份有限公司 | Improved DWA dynamic window method for unmanned ship path following and obstacle avoidance |
| CN110802601A (en) * | 2019-11-29 | 2020-02-18 | 北京理工大学 | Robot path planning method based on fruit fly optimization algorithm |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10429847B2 (en) * | 2017-09-22 | 2019-10-01 | Locus Robotics Corp. | Dynamic window approach using optimal reciprocal collision avoidance cost-critic |
| CN110083159B (en) * | 2019-05-14 | 2022-03-08 | 江苏科技大学 | Unmanned ship autonomous dynamic collision avoidance method based on SBG and dynamic window constraint |
-
2020
- 2020-05-12 CN CN202010396241.8A patent/CN111580518B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416152A (en) * | 2018-03-18 | 2018-08-17 | 哈尔滨工程大学 | The optimal global path planning method of unmanned boat ant colony energy consumption based on electronic chart |
| 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 |
| CN110032184A (en) * | 2019-03-12 | 2019-07-19 | 哈尔滨工程大学 | A kind of unmanned boat collision prevention method waterborne based on heredity with slip window sampling |
| CN110609559A (en) * | 2019-10-25 | 2019-12-24 | 江苏恒澄交科信息科技股份有限公司 | Improved DWA dynamic window method for unmanned ship path following and obstacle avoidance |
| CN110802601A (en) * | 2019-11-29 | 2020-02-18 | 北京理工大学 | Robot path planning method based on fruit fly optimization algorithm |
Non-Patent Citations (6)
| Title |
|---|
| Energy-efficient Path Planning and Control;Fuguang Ding等;《OCEANS 2018 MTS/IEEE Charleston》;20190110;全文 * |
| 基于操纵运动特性的海事无人艇自主避碰算法研究;吴博;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》;20150315(第03（21015）期);第C036-197页 * |
| 基于改进果蝇算法的多机器人路径规划;袁盼盼;《中国优秀硕士学位论文全文数据库 信息科技辑》;20190315(第03（2019）期);第I140-27页 * |
| 基于萤火虫算法和动态窗口法的移动机器人混合路径规划;银长伟;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20190415(第04（2019）期);第I140-75页 * |
| 基于速度障碍法和动态窗口法的无人水面艇动态避障;张洋洋等;《上海大学学报（自然科学版）》;20170228;第23卷(第1期);全文 * |
| 小型USV高速运动条件下避碰规划方法研究;郭峰;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20190815(第08（2019）期);第C036-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111580518A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111580518B (en) | Unmanned ship layered obstacle avoidance method based on improved drosophila optimization and dynamic window method | |
| Singh et al. | A constrained A* approach towards optimal path planning for an unmanned surface vehicle in a maritime environment containing dynamic obstacles and ocean currents | |
| CN108564202B (en) | Unmanned ship route optimization method based on environment forecast information | |
| CN108445879A (en) | A kind of unmanned boat barrier-avoiding method based on prediction collision risk region | |
| CN109737970B (en) | Water surface unmanned ship path planning method based on improved RRT algorithm | |
| CN109765929B (en) | UUV real-time obstacle avoidance planning method based on improved RNN | |
| CN109960262B (en) | Unmanned ship dynamic obstacle avoidance method and system based on geometric method | |
| CN108803313A (en) | A kind of paths planning method based on ocean current prediction model | |
| CN110837255B (en) | Autonomous danger avoiding method suitable for high-speed water surface unmanned ship | |
| CN113885534B (en) | Intelligent predictive control-based water surface unmanned ship path tracking method | |
| CN106643723B (en) | A kind of unmanned boat safe navigation dead reckoning method | |
| JP2021181301A (en) | Automatic guidance method for vessel, automatic guidance program for vessel, automatic guidance system for vessel, and vessel | |
| CN109579850B (en) | Deepwater intelligent navigation method based on auxiliary inertial navigation to water velocity | |
| CN112650257B (en) | Unmanned ship area maintenance control method and device | |
| JP6882243B2 (en) | Avoidance support device | |
| Song et al. | Method of emergency collision avoidance for unmanned surface vehicle (USV) based on motion ability database | |
| CN111412918B (en) | Unmanned ship global safety path planning method | |
| Wu et al. | Multi-vessels collision avoidance strategy for autonomous surface vehicles based on genetic algorithm in congested port environment | |
| CN105549589A (en) | Foresight radar based collision avoidance method of unmanned ship | |
| CN114088094A (en) | Intelligent route planning method and system for unmanned ship | |
| CN114061565A (en) | Unmanned ship SLAM and application method thereof | |
| Hinostroza et al. | Experimental and numerical simulations of zig-zag manoeuvres of a self-running ship model | |
| Ennong et al. | Design and experiment of a sea-air heterogeneous unmanned collaborative system for rapid inspection tasks at sea | |
| CN115793639A (en) | Unmanned ship complex path planning method and device based on reinforcement learning algorithm | |
| Bykova et al. | Safe navigation algorithm for autonomous underwater vehicles |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |