CN111487977A - Ship dynamic obstacle avoidance optimization method and system under uncertain environment - Google Patents
Ship dynamic obstacle avoidance optimization method and system under uncertain environment Download PDFInfo
- Publication number
- CN111487977A CN111487977A CN202010394101.7A CN202010394101A CN111487977A CN 111487977 A CN111487977 A CN 111487977A CN 202010394101 A CN202010394101 A CN 202010394101A CN 111487977 A CN111487977 A CN 111487977A
- Authority
- CN
- China
- Prior art keywords
- ship
- target point
- temporary target
- obstacle avoidance
- minimum value
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005457 optimization Methods 0.000 title claims abstract description 22
- 230000004888 barrier function Effects 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000011161 development Methods 0.000 claims 1
- 230000018109 developmental process Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005381 potential energy Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a dynamic obstacle avoidance optimization method and system for a ship in an uncertain environment, wherein the method comprises the steps of judging whether the current position of the ship falls into a local minimum value; after determining that the current position of the ship sinks into a local minimum value, updating an original target point into a temporary target point, and guiding the ship to advance, wherein the temporary target point is obtained according to two barrier positions which are closest to the position of the ship; and after the ship runs to a new position, canceling the temporary target point, recovering the original target point and guiding the ship to advance. The invention can consider real-time dynamic uncertain environmental influence in the ship driving process, and update the potential field by acquiring real-time data, thereby achieving the effect of real-time obstacle avoidance. The method is adopted to carry out dynamic obstacle avoidance on the ship, so that the running safety of the ship can be improved, and the probability of collision accidents between the ship and the obstacle on the sea is reduced.
Description
Technical Field
The invention relates to the field of dynamic obstacle avoidance of ships, in particular to a dynamic obstacle avoidance optimization method and system for ships in an uncertain environment.
Background
The global trade is developed vigorously nowadays, and a transportation mode taking marine transportation as a leading part is gradually formed. The navigation range is enlarged, new routes are increased, and ship navigation safety accidents caused by uncertain marine navigation environments are frequent. A large number of accident cases show that the main reason of the marine navigation safety accident of the ship is the collision between the ship and an obstacle. On the one hand, the sudden obstacle is not detected in the process of the ship going. On the other hand, even if a sudden obstacle is detected, the direction and speed of its movement are constantly changing, thus causing an increase in environmental uncertainty.
The ship dynamic obstacle avoidance under the uncertain environment is realized, namely when the ship detects a sudden obstacle through a sensor, the process of avoiding the sudden obstacle can be quickly responded and completed, and the ship can be rewound to the original route after the obstacle avoidance is successful.
Although the artificial potential field method is suitable for ship obstacle avoidance scenes, with the wide application of the algorithm, a plurality of defects are more prominent when the problem of ship dynamic obstacle avoidance is solved. The most typical problem is that the algorithm is easy to fall into a local minimum value in the calculation implementation process, so that the final dynamic obstacle avoidance fails. For a dynamic obstacle avoidance algorithm of a ship, sudden obstacle information must be processed in real time, the problem of falling into a local minimum value is solved, and a new air route is generated.
At present, in the traditional artificial potential field method, only large static obstacles are considered to be avoided in the process of avoiding the obstacles of the ship, only the global path is optimized, the scene that sudden obstacles appear in the safe sailing range of the ship is not considered, the real-time dynamic obstacle avoidance cannot be realized, and the defects exist in the practical application.
In order to solve the problems, scholars at home and abroad carry out a great deal of research and improvement on the artificial potential field algorithm, including modification of a function model related to the algorithm, optimization of a gain factor related to the function model, improvement of the action direction of force and the like. However, these improvements are overly complex, resulting in algorithms that operate less efficiently. Meanwhile, the obstacle avoidance of the static obstacle is still taken as a target, and a complex dynamic scene of actual navigation of the ship in an uncertain environment is not considered. In addition, whether the modification of the function model in the improved algorithm is optimal or not cannot be measured, and the problem that the algorithm falls into a local minimum value is not solved.
Disclosure of Invention
According to the technical problem that the obstacle avoidance fails due to the fact that the traditional artificial potential field method falls into a local minimum value in the dynamic obstacle avoidance process of the ship in the uncertain environment, the dynamic obstacle avoidance optimization method of the ship in the uncertain environment is provided. When the artificial potential field algorithm falls into a local minimum value, a reverse semicircle is generated based on two obstacles closest to the ship, a temporary target point is randomly generated on the semicircle, and the ship is guided to continue to advance.
The technical means adopted by the invention are as follows:
a dynamic obstacle avoidance optimization method for a ship in an uncertain environment comprises the following steps: judging whether the current position of the ship falls into a local minimum value; after determining that the current position of the ship sinks into a local minimum value, updating an original target point into a temporary target point, and guiding the ship to advance, wherein the temporary target point is obtained according to two barrier positions which are closest to the position of the ship; and after the ship runs to a new position, canceling the temporary target point, recovering the original target point and guiding the ship to advance.
Further, the acquiring of the temporary target point includes: taking the midpoint of two barriers closest to the position of the ship as the circle center, and taking the distance from the ship to the closest barrier as the radius to obtain a reverse semicircle; and randomly selecting a point on the reverse semicircle as a temporary target point.
And further, after the temporary target point is withdrawn, judging whether the current position of the ship falls into a local minimum value at least once.
Further, after the temporary target point is cancelled, if the current position of the ship is judged to be trapped in the local minimum value, the temporary target point is obtained again by taking the original initial position as a reference.
And further, when the current position of the ship is judged not to be trapped into the local minimum value, the ship is guided to advance according to an artificial potential field algorithm.
The invention also provides a dynamic obstacle avoidance optimization system for the ship under the uncertain environment, which comprises the following steps: the judging unit is used for judging whether the current position of the ship falls into a local minimum value; the temporary guiding unit is used for updating the original target point into a temporary target point after determining that the current position of the ship falls into a local minimum value, guiding the ship to advance, canceling the temporary target point after the ship runs to a new position, and recovering the original target point, wherein the temporary target point is obtained according to two barrier positions closest to the position of the ship; and a guide unit for guiding the ship to advance.
Further, the step of the temporary guidance unit acquiring a temporary target point includes: taking the midpoint of two barriers closest to the position of the ship as the circle center, and taking the distance from the ship to the closest barrier as the radius to obtain a reverse semicircle; and randomly selecting a point on the reverse semicircle as a temporary target point.
Further, after the temporary guiding unit withdraws the temporary target point, the judging unit is called to judge whether the current position of the ship falls into the local minimum value at least once.
Further, after the temporary guiding unit cancels the temporary target point, if the judging unit judges that the current position of the ship falls into the local minimum value, the temporary target point is obtained again by taking the original initial position as a reference.
Further, when the judging unit judges that the current position of the ship does not fall into the local minimum value, the guiding unit guides the ship to advance according to the artificial potential field algorithm.
Compared with the prior art, the invention has the following advantages:
1. the invention provides a dynamic obstacle avoidance optimization method for a ship in an uncertain environment, which solves the problem of obstacle avoidance failure caused by the fact that an artificial potential field algorithm falls into a local minimum value in the uncertain environment, and realizes real-time dynamic obstacle avoidance of the ship.
2. The temporary target point generated by the reverse arc is certainly in front of the ship and cannot intersect with two nearest barriers at the moment, and the temporary target point cannot collide with any barrier even if the ship runs forwards and runs to the generated temporary target point, so that the absolute safety of navigation in the dynamic obstacle avoidance process of the ship is ensured.
3. After the method is executed for one step, the detected data are updated again, and the real-time dynamic obstacle avoidance of the ship is realized.
Based on the reason, the invention can be widely popularized in the field of ship obstacle avoidance.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of temporary target point acquisition according to the present invention.
Fig. 3 is a flow chart of dynamic obstacle avoidance of a ship in the embodiment.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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.
As shown in fig. 1, the invention provides a dynamic obstacle avoidance optimization method for a ship in an uncertain environment. Firstly, judging whether the current position of the ship is trapped in a local minimum value, and if not, guiding the ship to advance according to an artificial potential field algorithm. And secondly, after determining that the current position of the ship falls into a local minimum value, updating the original target point into a temporary target point, and guiding the ship to advance, wherein the temporary target point is obtained according to two obstacle positions which are closest to the position of the ship. And finally, after the ship runs to a new position, canceling the temporary target point, recovering the original target point and guiding the ship to advance.
As a further embodiment, as shown in fig. 2, the acquiring of the temporary target point includes: taking the midpoint of two barriers closest to the position of the ship as the circle center, and taking the distance from the ship to the closest barrier as the radius to obtain a reverse semicircle; and randomly selecting a point on the reverse semicircle as a temporary target point.
As a further embodiment, after the temporary target point is cancelled, at least one time of judging whether the current position of the ship falls into the local minimum value is carried out.
As a further embodiment, after the temporary target point is cancelled, if it is determined that the current position of the ship falls into the local minimum value, the temporary target point is acquired again with the original initial position as a reference.
The scheme and effect of the invention are further illustrated by specific application examples.
Example 1
As shown in fig. 3, the embodiment provides a dynamic obstacle avoidance method for a ship in an uncertain environment, and the scheme mainly includes the following parts:
(1) collecting data
Firstly, various data required by obstacle avoidance in the ship navigation process are acquired in real time through various sensing devices, and the acquired various data are stored in a database. The data to be collected mainly include: 1) the information of various obstacles (including sudden obstacles) sensed in the navigation of the ship comprises the longitude and latitude information, the range size, the track and the like of the obstacles; 2) real-time dynamic data such as longitude and latitude, speed and course of the ship. And storing the collected various data in a database.
(2) Determining coordinate interval range
Used for determining the safe sailing area range of the ship. And (4) analyzing and converting the data of the ship, the target point and the plurality of obstacles at the current moment, and determining the range of the coordinate interval.
(3) Constructing a potential field
After the coordinate interval range is determined, ship, target point and obstacle information are filled into the coordinate system, and the distance between the ship and each obstacle and the distance between the ship and the target point are determined. And calculating the potential energy at each point under the coordinate system according to the traditional gravitational field and repulsive field functions to construct a potential field. After the potential field is built, the ship moves, and meanwhile, the obstacle avoidance function is started, and the movement direction of the ship is defaulted to be the minimum potential energy direction of the point where the ship is located, namely the steepest gradient descending direction.
(4) Judging whether the current position of the ship falls into a local minimum value
And (3) the ship moves according to the constructed potential field, and constantly judges whether the current position is sunk into a local minimum value, if the current position is sunk into the local minimum value, the method of the invention is adopted, and a reverse semicircle is generated based on the two nearest obstacles and a temporary target point is randomly generated. And if the current position does not fall into the local minimum value, continuing to drive forwards. And performing reciprocating operation until the target point is reached, and drawing a final ship optimization path.
In the embodiment, a method of generating reverse semicircles based on two nearest obstacles and randomly generating temporary target points is adopted, so that the ship can still continuously realize dynamic obstacle avoidance when a traditional artificial potential field method falls into a local minimum value, and an optimal route is continuously selected to reach the target points.
As shown in fig. 3, if the ship falls into a local minimum value due to the occurrence of static obstacles and sudden obstacles during the process of driving towards the target, the ship periodically oscillates, so that the ship cannot continue to advance towards the target point. The reason for this is that the attraction and repulsion forces at this point are balanced, and the use of the conventional artificial potential field method will result in the ship not knowing where to go next. The invention is provided in view of the above problems, and comprises the following specific steps:
step 1: selecting two closest obstacles (including burst obstacles) in the environment, connecting the centers of the two closest obstacles, selecting a midpoint on the connecting line, and drawing a reverse semicircle by making a radius according to the distance from the ship to the closest obstacle. As can be seen from fig. 3, since the ship is closest to the obstacle 2, a semicircle is drawn according to the distance.
Step 2: and (4) cancelling the original target point, randomly selecting a point in the semicircular arc as a temporary target point, and guiding the ship to advance.
And 3, step 3: when the ship runs to a new position, the temporary target point is immediately cancelled, the original target point is recovered, and the invariance of the environment is ensured.
And 4, step 4: judging whether the new position still has the phenomenon of falling into a local minimum value according to the original potential field, and if not, solving the problem; if the local minimum value exists, the initial starting position is recovered, the step 1 is turned to, and the following operations are repeated until the local minimum value problem is solved. And when the ship reaches the target point, drawing a ship obstacle avoidance path.
The method can solve the problem that the traditional potential field method falls into a local minimum value, and the temporary target point generated by the circular arc in the step 1 is certainly in front of the ship and cannot intersect with two nearest barriers, so that the temporary target point cannot collide with any barrier even if the ship runs forwards and runs to the generated temporary target point, and the absolute safety of navigation in the dynamic barrier avoiding process of the ship is ensured. And in addition, the selected temporary target point guides the ship to move forwards so as to enable the ship to escape from the position where the ship is currently trapped in the local minimum value. And after the step is executed, the detected data is updated again, so that the real-time dynamic obstacle avoidance of the ship is realized. And meanwhile, judging whether the ship reaches a target point, and stopping the operation of the corresponding obstacle avoidance algorithm when the ship reaches the target point.
Example 2
On the other hand, the embodiment of the invention also provides a dynamic obstacle avoidance optimization system for a ship in an uncertain environment, which comprises a judgment unit, a temporary guide unit and a guide unit.
The judging unit is mainly used for judging whether the current position of the ship falls into a local minimum value.
The temporary guiding unit is mainly used for updating the original target point into a temporary target point after determining that the current position of the ship falls into a local minimum value, guiding the ship to advance, and canceling the temporary target point to restore the original target point after the ship runs to a new position. The temporary target point is obtained according to the positions of two obstacles closest to the position of the ship. Specifically, the step of acquiring the temporary target point by the temporary guidance unit includes: taking the midpoint of two barriers closest to the position of the ship as the circle center, and taking the distance from the ship to the closest barrier as the radius to obtain a reverse semicircle; and randomly selecting a point on the reverse semicircle as a temporary target point. In addition, after the temporary guiding unit cancels the temporary target point, the judging unit is called to judge whether the current position of the ship falls into the local minimum value at least once. And if the judging unit judges that the current position of the ship falls into the local minimum value, the temporary target point is obtained again by taking the original initial position as the reference.
The guiding unit is mainly used for guiding the ship to advance. And when the judging unit judges that the current position of the ship does not fall into the local minimum value, the guiding unit guides the ship to advance according to the artificial potential field algorithm.
The invention can consider real-time dynamic uncertain environmental influence in the ship driving process, and update the potential field by acquiring real-time data, thereby achieving the effect of real-time obstacle avoidance. By adopting the scheme of the invention, the running safety of the ship can be improved, and the probability of collision accidents of the ship on the sea and the barrier can be reduced.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A dynamic obstacle avoidance optimization method for a ship in an uncertain environment is characterized by comprising the following steps:
judging whether the current position of the ship falls into a local minimum value;
after determining that the current position of the ship sinks into a local minimum value, updating an original target point into a temporary target point, and guiding the ship to advance, wherein the temporary target point is obtained according to two barrier positions which are closest to the position of the ship;
and after the ship runs to a new position, canceling the temporary target point, recovering the original target point and guiding the ship to advance.
2. The dynamic obstacle avoidance optimization method for the ship according to claim 1, wherein the obtaining of the temporary target point comprises:
taking the midpoint of two barriers closest to the position of the ship as the circle center, and taking the distance from the ship to the closest barrier as the radius to obtain a reverse semicircle;
and randomly selecting a point on the reverse semicircle as a temporary target point.
3. The dynamic obstacle avoidance optimization method for the ship according to claim 1 or 2, wherein after the temporary target point is cancelled, at least one judgment is made as to whether the current position of the ship falls into a local minimum value.
4. The dynamic obstacle avoidance optimization method for the ship according to claim 3, wherein after the temporary target point is cancelled, if the current position of the ship is judged to fall into the local minimum value, the temporary target point is obtained again by taking the original initial position as a reference.
5. The dynamic obstacle avoidance optimization method for the ship according to claim 1, wherein when the current position of the ship is judged not to fall into a local minimum value, the ship is guided to advance according to an artificial potential field algorithm.
6. The utility model provides a boats and ships developments under uncertain environment keep away barrier optimization system which characterized in that includes:
the judging unit is used for judging whether the current position of the ship falls into a local minimum value;
the temporary guiding unit is used for updating the original target point into a temporary target point after determining that the current position of the ship falls into a local minimum value, guiding the ship to advance, canceling the temporary target point after the ship runs to a new position, and recovering the original target point, wherein the temporary target point is obtained according to two barrier positions closest to the position of the ship;
and a guide unit for guiding the ship to advance.
7. The dynamic obstacle avoidance optimization system for ships according to claim 6, wherein the step of acquiring the temporary target point by the temporary guidance unit comprises:
taking the midpoint of two barriers closest to the position of the ship as the circle center, and taking the distance from the ship to the closest barrier as the radius to obtain a reverse semicircle;
and randomly selecting a point on the reverse semicircle as a temporary target point.
8. The dynamic obstacle avoidance optimization system for the ship according to claim 6 or 7, wherein after the temporary guiding unit cancels the temporary target point, the judging unit is invoked to judge whether the current position of the ship falls into the local minimum value at least once.
9. The dynamic obstacle avoidance and optimization system for ships according to claim 8, wherein after the temporary guiding unit cancels the temporary target point, if the judging unit judges that the current position of the ship falls into the local minimum value, the temporary target point is obtained again with the original starting position as a reference.
10. The dynamic obstacle avoidance optimization system for the ship according to claim 6, wherein when the judging unit judges that the current position of the ship does not fall into the local minimum value, the guiding unit guides the ship to advance according to an artificial potential field algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010394101.7A CN111487977B (en) | 2020-05-11 | 2020-05-11 | Ship dynamic obstacle avoidance optimization method and system under uncertain environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010394101.7A CN111487977B (en) | 2020-05-11 | 2020-05-11 | Ship dynamic obstacle avoidance optimization method and system under uncertain environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111487977A true CN111487977A (en) | 2020-08-04 |
| CN111487977B CN111487977B (en) | 2023-06-23 |
Family
ID=71795302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010394101.7A Active CN111487977B (en) | 2020-05-11 | 2020-05-11 | Ship dynamic obstacle avoidance optimization method and system under uncertain environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111487977B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880549A (en) * | 2020-09-14 | 2020-11-03 | 大连海事大学 | Unmanned ship path planning-oriented deep reinforcement learning reward function optimization method |
| CN113108799B (en) * | 2021-05-25 | 2023-04-28 | 上海海事大学 | Ship path optimization method based on field theory |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61204518A (en) * | 1985-03-07 | 1986-09-10 | Shipbuild Res Assoc Japan | Obstacle avoiding sailing method for ship |
| JPH09257918A (en) * | 1996-03-22 | 1997-10-03 | Oki Electric Ind Co Ltd | Navigation safety supporting device |
| CN105022270A (en) * | 2015-03-20 | 2015-11-04 | 武汉理工大学 | Automatic ship collision avoidance method based on velocity vector coordinate system |
| CN108445879A (en) * | 2018-03-12 | 2018-08-24 | 上海大学 | A kind of unmanned boat barrier-avoiding method based on prediction collision risk region |
| CN110470299A (en) * | 2019-07-30 | 2019-11-19 | 南京理工大学 | A kind of seaway planning algorithm evaded based on round roadblock |
| CN111123903A (en) * | 2018-10-30 | 2020-05-08 | 武汉理工大学 | Unmanned ship obstacle avoidance method based on circular track unit |
-
2020
- 2020-05-11 CN CN202010394101.7A patent/CN111487977B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61204518A (en) * | 1985-03-07 | 1986-09-10 | Shipbuild Res Assoc Japan | Obstacle avoiding sailing method for ship |
| JPH09257918A (en) * | 1996-03-22 | 1997-10-03 | Oki Electric Ind Co Ltd | Navigation safety supporting device |
| CN105022270A (en) * | 2015-03-20 | 2015-11-04 | 武汉理工大学 | Automatic ship collision avoidance method based on velocity vector coordinate system |
| CN108445879A (en) * | 2018-03-12 | 2018-08-24 | 上海大学 | A kind of unmanned boat barrier-avoiding method based on prediction collision risk region |
| CN111123903A (en) * | 2018-10-30 | 2020-05-08 | 武汉理工大学 | Unmanned ship obstacle avoidance method based on circular track unit |
| CN110470299A (en) * | 2019-07-30 | 2019-11-19 | 南京理工大学 | A kind of seaway planning algorithm evaded based on round roadblock |
Non-Patent Citations (1)
| Title |
|---|
| ***;史国友;李伟峰;陈作桓;江健;: "基于最短避碰距离和碰撞危险度的避碰决策支持" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880549A (en) * | 2020-09-14 | 2020-11-03 | 大连海事大学 | Unmanned ship path planning-oriented deep reinforcement learning reward function optimization method |
| CN111880549B (en) * | 2020-09-14 | 2024-06-04 | 大连海事大学 | Deep reinforcement learning rewarding function optimization method for unmanned ship path planning |
| CN113108799B (en) * | 2021-05-25 | 2023-04-28 | 上海海事大学 | Ship path optimization method based on field theory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111487977B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019124001A1 (en) | Moving body behavior prediction device and moving body behavior prediction method | |
| CN111487977A (en) | Ship dynamic obstacle avoidance optimization method and system under uncertain environment | |
| US20180100743A1 (en) | Computer-Implemented Method and a System for Guiding a Vehicle Within a Scenario with Obstacles | |
| WO2012132950A1 (en) | Information processing device, information processing method, and program | |
| CN110956853B (en) | Multi-ship collision prediction method, system and storage medium | |
| CN110126817A (en) | A kind of method and system parked or recalled between adaptive arbitrary point and fixed point | |
| US20110213513A1 (en) | Method for automatic avoidance of collisions between a craft and further objects | |
| CN116300973B (en) | Autonomous obstacle avoidance method for unmanned mine car in complex weather | |
| CN111208835B (en) | Ship formation switching control method based on topology reconstruction | |
| CN111469127B (en) | Cost map updating method and device, robot and storage medium | |
| CN115131393A (en) | Trajectory prediction method, collision detection method, apparatus, electronic device, and medium | |
| CN115230719B (en) | Driving track planning method and device | |
| CN110687919A (en) | Unmanned aerial vehicle autonomous flight control method for hydropower station water pipeline inspection | |
| CN116448115B (en) | Unmanned ship probability distance map construction method based on navigation radar and photoelectricity | |
| EP3957122A1 (en) | Marine data collection for marine artificial intelligence systems | |
| CN113359808A (en) | Multi-stage path planning method for power inspection of unmanned aerial vehicle and related device | |
| CN111881580A (en) | Movement planning method for unmanned ship to avoid obstacles | |
| CN112880678A (en) | Unmanned ship navigation planning method in complex water area environment | |
| CN114387822B (en) | Ship collision prevention method | |
| WO2020115893A1 (en) | Movement detection device and movement detection method | |
| JP5664398B2 (en) | Information processing apparatus, information processing method, and program | |
| CN116974282A (en) | Unmanned ship-based marine search area coverage path planning method | |
| CN114995377A (en) | Ship-shore cooperative inland river ship auxiliary driving system | |
| CN113359773A (en) | Unmanned ship navigation path decision method and system | |
| JP7086475B2 (en) | Ship maneuvering support device |
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 |