CN105867383A - Automatic collision preventing control method of USV - Google Patents

Abstract

A method for autonomous collision avoidance control of a USV relates to the technical field of marine search and rescue and survey, in particular to a method for autonomous collision avoidance control of a USV. The purpose of the present invention is to provide a method for USV autonomous collision avoidance control. Through the mutual cooperation and cooperation between the subsystems of the entire collision avoidance system, the unmanned vehicle can autonomously search for obstacles when performing tasks such as search and rescue and survey. The distribution of obstacles implements a collision avoidance strategy. This method is carried out according to the following steps: one, environmental image information collection; two, measure the distance between the obstacle and the unmanned boat; three, the GPS positioning system measures the relative position information of the unmanned boat and other unmanned boats, and Measure the movement speed of the unmanned boat and other unmanned boats; 4. The obstacle judgment system processes the received information; 5. Send the sea surface interference to the genetic algorithm controller; 6. The genetic algorithm controller formulates a collision avoidance strategy . The method of the invention is applicable to the technical field of marine search and rescue and survey.

Description

A method for autonomous collision avoidance control of USV

technical field

The invention relates to the technical field of marine search and rescue and survey, in particular to a method for autonomous collision avoidance control of a USV.

Background technique

An unmanned vehicle (USV) is a small surface platform that integrates autonomous planning, autonomous navigation, and autonomous completion of tasks such as environmental perception and target detection. The marine environment is complex and changeable. If you want to maintain the intelligent navigation of the unmanned vessel, you need to rely on the integration and interaction of its internal information and the external environment. An important prerequisite for this kind of integration and interaction is that the unmanned vehicle can perform autonomous collision avoidance, and can complete the designated mission in a complex marine environment. As an important symbol of the intelligence of unmanned boats, the autonomous collision avoidance technology of unmanned boats not only reflects the level of intelligence of maritime unmanned boats to a certain extent, but also an important research content in the key technical fields of unmanned boats. At present, most of the researches on collision avoidance of unmanned vehicles focus on the algorithm of collision avoidance, but seldom involve the cooperation among subsystems of the whole collision avoidance system.

Contents of the invention

The purpose of the present invention is to provide a method for USV autonomous collision avoidance control. Through the mutual cooperation and cooperation between the subsystems of the entire collision avoidance system, the unmanned vehicle can autonomously search for obstacles when performing tasks such as search and rescue and survey. The distribution of obstacles implements a collision avoidance strategy to ensure the safety of the unmanned boat's autonomous navigation.

In order to realize a method for USV autonomous collision avoidance control, a USV autonomous collision avoidance control device is required, including: an obstacle detection device, a positioning system and a genetic algorithm controller, wherein the obstacle detection device includes a camera, an image recognition system, Rangefinder, speedometer and obstacle judgment system; positioning system includes GPS positioning system and communication system; genetic algorithm controller includes wind, wave and current detection system, controller and actuator.

Usually the main factor affecting the collision avoidance effect of the unmanned boat is: the course of the unmanned boat Velocity v ₀ ; heading of obstacle Velocity v _T ; the distance between the unmanned boat and the obstacle D _T ; the heading angle between the unmanned boat and the obstacle is The true orientation of the obstacle relative to the unmanned boat is θ _T ; the relative speed of the two ships is v _R ; the relative course of the two ships is The minimum passing distance when the unmanned boat and the obstacle meet is DCPA; the time when the unmanned boat and the obstacle reach the closest meeting point is TCPA.

A method for USV autonomous collision avoidance control is carried out in the following steps:

1. The camera will take pictures of the environment within a 360° range centered on the unmanned boat, and transmit the image information to the image recognition system;

2. The image recognition system processes the image information and transmits the suspected obstacle information to the obstacle judgment system. At the same time, the rangefinder measures the distance between the obstacle and the unmanned boat within 500 meters of the unmanned boat, and transmits the information to the Obstacle judgment system;

3. The GPS positioning system locates the current position of the unmanned boat in real time, the communication system establishes contact with other unmanned boats, and obtains the relative position information of the boat and other unmanned boats, and the speedometer measures the unmanned boat and other unmanned boats The movement speed of other unmanned ships is equivalent to obstacles, and then the above information is passed to the obstacle judgment system;

4. The obstacle judgment system processes all the received information and then transmits the obstacle data to the genetic algorithm controller;

5. The wind, wave and current monitoring system monitors the sea surface interference in the sea area where the unmanned boat is located, and transmits the data to the genetic algorithm controller;

6. The genetic algorithm controller formulates a collision avoidance strategy based on the obstacle data and performs safe collision avoidance through the actuator.

The present invention comprises following beneficial effect:

1. The present invention realizes that the unmanned boat can autonomously search for obstacles when performing tasks such as search and rescue and survey through the mutual cooperation and cooperation between the subsystems of the entire collision avoidance system, and implements collision avoidance strategies according to the distribution of obstacles to ensure that no The safety of the manned boat when it sails autonomously;

2. The present invention rationally combines the various collision avoidance subsystems of the unmanned boat, and completes the process of the unmanned boat from searching the nearby navigation environment, collecting and analyzing obstacle information, formulating collision avoidance countermeasures, and completing the avoidance of obstacles. A series of processes have effectively improved the intelligence of the unmanned boat and reduced the workload of the operator;

3. When the unmanned boat is performing tasks such as search and rescue, surveying, etc., it can safely avoid collisions with static and dynamic obstacles in the process of traveling according to the method described in the present invention.

Description of drawings

Figure 1 is a structural block diagram of the USV autonomous collision avoidance control device;

Figure 2 is a schematic diagram of the relative parameters of USV and obstacles;

Fig. 3 is a flowchart for calculating the USV obstacle collision risk;

Fig. 4 is a flow chart of genetic algorithm;

Fig. 5 is a schematic diagram of the unmanned boat avoiding obstacles.

detailed description

In order to make the above-mentioned purpose, features and advantages of the present invention more obvious and easy to understand, the present invention will be further described in detail below in conjunction with FIGS. It is a schematic diagram of the relative parameters of USV and obstacles, and Fig. 3 is a flow chart of calculating the collision risk of USV obstacles.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT 1. A method for USV autonomous collision avoidance control described in this embodiment is carried out according to the following steps:

1. The camera will take pictures of the environment within a 360° range centered on the unmanned boat, and transmit the image information to the image recognition system;

2. The image recognition system processes the image information and transmits the suspected obstacle information to the obstacle judgment system. At the same time, the rangefinder measures the distance between the obstacle and the unmanned boat within 500 meters of the unmanned boat, and transmits the information to the Obstacle judgment system;

3. The GPS positioning system locates the current position of the unmanned boat in real time, the communication system establishes contact with other unmanned boats, and obtains the relative position information of the own boat and other unmanned boats, and the speedometer measures the unmanned boat and other unmanned boats The movement speed of other unmanned ships is equivalent to obstacles, and then the above information is passed to the obstacle judgment system;

4. The obstacle judgment system processes all the received information and then transmits the obstacle data to the genetic algorithm controller;

5. The wind, wave and current monitoring system monitors the sea surface interference in the sea area where the unmanned boat is located, and transmits the data to the genetic algorithm controller;

6. The genetic algorithm controller formulates a collision avoidance strategy based on the obstacle data and performs safe collision avoidance through the actuator.

This embodiment includes the following beneficial effects:

1. In this embodiment, through the mutual cooperation and cooperation between the subsystems of the entire collision avoidance system, the unmanned boat can autonomously search for obstacles when performing tasks such as search and rescue and survey, and implement collision avoidance strategies according to the distribution of obstacles to ensure The safety of unmanned boats when they sail autonomously;

2. In this embodiment, the various collision avoidance subsystems of the unmanned boat are reasonably combined, and the unmanned boat searches the surrounding navigation environment, collects and analyzes obstacle information, and formulates collision avoidance countermeasures to complete the avoidance of obstacles. A series of processes have effectively improved the intelligence of the unmanned boat and reduced the workload of the operator;

3. When the unmanned boat is performing tasks such as search and rescue, surveying, etc., it can safely avoid collisions with static and dynamic obstacles in the process of traveling according to the method described in this embodiment.

Specific Embodiment 2. This embodiment is a further description of the USV autonomous collision avoidance control method described in Specific Embodiment 1. The acquisition period of the shooting environment image described in step 1 is 0.05s, and 10 images are collected each time. cycle, taking a total of 0.5s.

Embodiment 3. This embodiment is a further description of the USV autonomous collision avoidance control method described in Embodiment 1 or 2. The measurement period of the rangefinder in step 2 is 0.5s.

Embodiment 4. This embodiment is a further description of the USV autonomous collision avoidance control method described in Embodiments 1 to 3. The communication cycle of the communication system described in step 3 is 0.5s.

Embodiment 5. This embodiment is a further description of the method for USV autonomous collision avoidance control described in Embodiment 1 to Embodiment 4. The location information obtained by the GPS positioning system and the communication system in step 3 is: The geographic coordinates of the unmanned boat measured by the GPS positioning system are O(x _O ,y _O ), and the geographic coordinates of obstacles obtained by the communication system are T(x _T ,y _T ), where the x-axis is the north-south direction and the y-axis is the east-west direction .

Specific Embodiment 6. This embodiment is a further description of the method for USV autonomous collision avoidance control described in one of specific embodiments 1 to 5. The speed measured by the speedometer in step 3 is: The motion speed vector is v(v _Ox , v _Oy ), and the obstacle motion speed vector is v(v _Tx , v _Ty ).

Specific Embodiment 7. This embodiment is a further description of the USV autonomous collision avoidance control method described in one of specific embodiments 1 to 6. The specific process of information processing described in step 4 is: according to the first three steps The obtained information is used to calculate the course of the unmanned boat and obstacles:

Unmanned boat heading:

in:

According to the geographic coordinate solution of the unmanned boat and the obstacle, the relative distance between the unmanned boat and the obstacle is calculated as:

${\mathrm{<span\; class="notranslate">\; D.</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; =</span>\sqrt{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$

The true orientation of the obstacle relative to the UAV is θ _T :

${\mathrm{<span\; class="notranslate">\; \&theta;</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; no</span>}\frac{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}}}{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}$

The true orientation of the UAV relative to the obstacle is θ ₀ :

${\mathrm{<span\; class="notranslate">\; \&theta;</span>}}_{\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; no</span>}\frac{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}}{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}$

in,

The phase orientation of the obstacle is α _T :

The relative velocity components of the obstacle relative to the UAV on the x and y axes are:

$\left\{\begin{array}{c}{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; x</span>}}\\ {\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; the\; y</span>}}\end{array}\right.$

The relative heading of the obstacle relative to the UAV:

in:

Calculate the closest encounter distance DCPA between the UAV and the target ship:

Calculate the time to the closest point of encounter TCPA:

Among them, v _R is the relative speed of the two ships;

The calculated space collision risk u _dt is:

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}\mathrm{<span\; class="notranslate">\; 1</span>}& <span\; class="notranslate">\; |</span>\mathrm{<span\; class="notranslate">\; D.</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; <</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}\\ \frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; 2</span>}}\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; \&lsqb;</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; D.</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; \&rsqb;</span>& {\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; <</span><span\; class="notranslate">\; |</span>\mathrm{<span\; class="notranslate">\; D.</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; \&le;</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}\\ \mathrm{<span\; class="notranslate">\; 0</span>}& {\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; <</span><span\; class="notranslate">\; |</span>\mathrm{<span\; class="notranslate">\; D.</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; |</span>\end{array}\right.$

In the formula, d ₁ =1.5ρ(θ _T ), d ₂ =2d ₁ ;

ρ(θ _T ) is obtained by the following formula

The calculation time collision risk u _tT is:

When TCPA>0:

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}\mathrm{<span\; class="notranslate">\; 1</span>}& \mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; 1</span>}\\ {<span\; class="notranslate">\; (</span>\frac{{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}}{{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}& {\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; \&le;</span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}\\ \mathrm{<span\; class="notranslate">\; 0</span>}& \mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; ></span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}\end{array}\right.$

When TCPA≤0

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; T</span>}}<span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}\mathrm{<span\; class="notranslate">\; 1</span>}& \mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; 1</span>}\\ {<span\; class="notranslate">\; (</span>\frac{{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}}{{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}& {\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; \&le;</span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}\\ \mathrm{<span\; class="notranslate">\; 0</span>}& \mathrm{<span\; class="notranslate">\; T</span>}\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; ></span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}\end{array}\right.$

in

According to the time collision risk and space collision risk, the comprehensive collision risk of the unmanned vehicle and the obstacle is u _t :

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; \&CirclePlus;</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; T</span>}}$

The value of u _t is divided into three situations, among which, if u _dt =0, u _t =0;

If u _dt ≠0, when u _tT =0, u _t =0;

If u _dt ≠0, u t T ≠0, u _t =max(u _{dt , u tT )} .

Embodiment 8. This embodiment is a further description of the USV autonomous collision avoidance control method described in one of Embodiments 1 to 7. The genetic algorithm controller described in step 5 formulates the collision avoidance method according to the obstacle data. The process of the strategy is: as shown in Figure 4,

1. Encode the population:

Each chromosome represents an initial path of the unmanned vehicle. In the process of population initialization, according to the initial position and target position of the unmanned vehicle, a population with n individuals is automatically generated, and all the unmanned vehicles from the starting point to the destination are automatically generated. Feasible paths are encoded, and each path is an individual in the population;

2. Solve the fitness function:

The calculation of the fitness function should consider the length of the path, the smoothness of the path, and the safety of the path; when converting the objective function into a fitness function, the following two principles are generally followed:

(1) The fitness value is non-negative;

(2) The change direction of the objective function in the optimization process should be consistent with the change direction of the fitness function in the population evolution process.

For the problem of collision avoidance path selection for unmanned vehicles, the fitness function that has a mapping relationship with the objective function can be established by the following formula:

F _(x) = Cf(x)

In the formula, F _(x) is the fitness function; C is an adjustable parameter whose value should make the fitness function F _(x) always greater than or equal to 0; f(x) is the objective function of the optimization problem.

In order to ensure that F _(x) is not less than 0, therefore, the fitness function is established as follows:

${\mathrm{<span\; class="notranslate">\; f</span>}}_{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span>& \mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; <</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; x</span>}}\\ \mathrm{<span\; class="notranslate">\; 0</span>}& \mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&Greater\; Equal;</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; x</span>}}\end{array}\right.$

In the formula, C _max is an adjustable parameter, and C _max can take the theoretically possible maximum value of the objective function f(x); the length of the path, the smoothness of the path and the smoothness of the path should be considered in the selection of the objective function f(x). safety.

3. Basic genetic manipulation

Basic genetic operations include selection, crossover, and mutation. The specific steps are as follows:

(1) Select operation

The selection operation is to select individuals with high fitness from the population and eliminate individuals with low fitness; the probability P _i of individual i being selected is proportional to its fitness value; using the roulette model, the steps are as follows:

1) Calculate the fitness F _i of each chromosome, 1≤i≤n;

2) Accumulate the fitness values of all chromosomes, and record the intermediate accumulated value S _i : S _i S ₁ = F ₁ , S _i = S _i-1 + F _i ;

3) Generate a random number x, 0≤x≤S _n ;

4) Select chromosomes, if S _i-1 <x≤S _i , 1≤i≤n, then the i-th chromosome is selected to enter the next generation population;

5) Repeat step 3) and step 4) until enough chromosomes are obtained.

(2) Cross operation

cross operation

According to the crossover probability, two paired chromosomes exchange some of their genes in a certain way to form two new individuals, and the crossover rate is between 0.5 and 0.95.

(3) Mutation operation

mutation operation

According to the mutation probability, some gene values in the individual code are replaced with other gene values to form a new individual. The mutation rate is generally set between 0 and 0.5, and the gene mutation is performed with a small probability.

For verifying the beneficial effect of the present invention, do following simulation experiment:

As shown in Figure 5, a total of 5 obstacles are set up in this experiment, and the position coordinates are (40,30), (80,80), (90,130), (120,120), (150,160), and the obstacle radius is 11,11, 6, 11, 11. The starting point of the unmanned boat is (10,10), and the end coordinates are (190,190).

The steps of the basic genetic operation:

1. Initialization: mainly set the evolution parameters, set the maximum evolution algebra and randomly generate n individuals as the initial population P(0);

2. Individual evaluation: Calculate the fitness of each individual in the population P(t) through a certain method, and t represents the algebra;

3. Selection: apply the selection operator to the group;

4. Crossover: apply the crossover operator to the group;

5. Mutation: apply the mutation operator to the group;

6. Algorithm termination conditions: two types can be set, one is that if the evolution algebra has reached the maximum value, the individual with the maximum fitness obtained during the evolution process will be output as the optimal solution, and the calculation will be terminated; the other is Set an error, if the error of an individual in the population has reached the requirement, the individual with the best fitness will be output as the optimal approximate solution, and the calculation will be terminated.

This experiment achieved the effect of the invention. During the process of driving the unmanned boat to the target point, through the cooperation between the modules, the unmanned boat can safely and autonomously avoid collisions when encountering obstacles during navigation, and successfully reach the preset target point.

Claims (8)

1. A method for controlling autonomous collision avoidance of a USV (Universal Serial bus) is realized by adopting an autonomous collision avoidance control device of the USV, and the autonomous collision avoidance control device of the USV comprises the following steps: the system comprises an obstacle detection device, a positioning system and a genetic algorithm controller, wherein the obstacle detection device comprises a camera, an image identification system, a distance meter, a velocimeter and an obstacle judgment system; the positioning system comprises a GPS positioning system and a communication system; the genetic algorithm controller comprises a wind, wave and water flow detection system, a controller and an execution mechanism;

the method is characterized by comprising the following steps of:

the camera shoots an environment image within a 360-degree range taking an unmanned boat as a center, and transmits image information to an image recognition system;

secondly, the image recognition system processes the image information and then transmits the suspected obstacle information to the obstacle judgment system, and meanwhile, the range finder measures the distance between the unmanned ship and an obstacle within 500 meters of the unmanned ship and transmits the information to the obstacle judgment system;

thirdly, a GPS positioning system positions the current position of the unmanned ship in real time, a communication system establishes contact with other unmanned ships to obtain relative position information of the unmanned ship and other unmanned ships, a velocimeter measures the movement speed of the unmanned ship and other unmanned ships, the unmanned ships are equivalent to obstacles, and the information is transmitted to an obstacle judgment system;

fourthly, the barrier judgment system processes all the received information and then transmits the barrier data to the genetic algorithm controller;

fifthly, monitoring the sea surface interference condition of the sea area where the unmanned ship is located by a wind, wave and water flow monitoring system in real time, and transmitting data to a genetic algorithm controller;

and sixthly, the genetic algorithm controller works out a collision prevention strategy according to the barrier data and carries out safe collision prevention through an execution mechanism.

2. The method for autonomous collision avoidance control of an USV according to claim 1, wherein in the first step, the capturing period of the captured environment image is 0.05s, and each capturing period is 10 periods, which takes 0.5 s.

3. The method for autonomous collision avoidance control of an USV according to claim 1 or 2, wherein in step two, the measuring period of the distance meter is 0.5 s.

4. The method as claimed in claim 3, wherein the communication period of the communication system in step three is 0.5 s.

5. The method for autonomous collision avoidance control of an USV according to claim 4, wherein the position information obtained by the GPS positioning system and the communication system in step three is: the geographic coordinate of the unmanned ship is O (x) measured by a GPS positioning system_O,y_O) The communication system obtains the geographic coordinate of the obstacle as T (x)_T,y_T) Wherein the x-axis is north-south and the y-axis is east-west.

6. The method for autonomous collision avoidance control of a USV according to claim 5, wherein the moving speed measured by the speedometer in step three is: the motion velocity vector of the unmanned ship is v (v)_Ox,v_Oy) The obstacle motion velocity vector is v (v)_Tx,v_Ty)。

7. The method for autonomous collision avoidance control of an USV according to claim 6, wherein the specific process of the information processing in step four is as follows: and (3) solving the course of the unmanned ship and the barrier according to the information obtained in the previous three steps:

course of the unmanned ship:

wherein:

the relative distance between the unmanned boat and the obstacle is calculated according to the geographic coordinates of the unmanned boat and the obstacle as follows:

$D_T=\sqrt{{(x_T-x_O)}^2+{(y_T-y_O)}^2}$

the true orientation of the obstacle relative to the unmanned surface is θ_T：

${\mathrm{\&theta;}}_T=\arctan \frac{x_T-x_O}{y_T-y_O}+{\mathrm{\&alpha;}}_2$

The true orientation of the unmanned vehicle relative to the obstacle is theta₀：

${\mathrm{\&theta;}}_0=\arctan \frac{x_O-x_T}{y_O-y_T}+{\mathrm{\&alpha;}}_2$

Wherein,

the phase orientation of the obstacle is α_T：

The relative velocity components of the obstacle relative to the unmanned vehicle in the x, y axes are:

$\left\{\begin{array}{c}{v}_{Rx}=v_{Tx}-v_{Ox}\\ v_{Ry}=v_{Ty}-v_{Oy}\end{array}\right.$

relative heading of the obstacle with respect to the unmanned boat:

wherein:

calculating the nearest meeting distance DCPA between the unmanned ship and the target ship:

calculate the time to reach the meeting closest point TCPA:

wherein v is_RThe relative speed of the two ships is large or small;

resolving the space collision risk u_dtComprises the following steps:

$u_{dt}=\left\{\begin{array}{cc}1& \left|DCPA\right|<d_1\\ \frac{1}{2}-\frac{1}{2}sin\&lsqb;\frac{\mathrm{\&pi;}}{d_2-d_1}-\frac{DCPA(d_2+d_1)}{2}\&rsqb;& d_1<\left|DCPA\right|\&le;d_2\\ 0& d_2<\left|DCPA\right|\end{array}\right.$

in the formula d₁＝1.5ρ(θ_T)，d₂＝2d₁；

ρ(θ_T) Obtained from the following formula

Solving the time collision risk u_tTComprises the following steps:

when TCPA > 0:

$u_{tT}=\left\{\begin{array}{cc}1& TCPA\&le;1\\ {\left(\frac{t_2-TCPA}{t_2-t_1}\right)}^2& t_1\&le;TCPA\&le;t_2\\ 0& TCPA>t_2\end{array}\right.$

when TCPA is less than or equal to 0

$u_{tT}=\left\{\begin{array}{cc}1& TCPA\&le;1\\ {\left(\frac{t_2+TCPA}{t_2-t_1}\right)}^2& t_1\&le;TCPA\&le;t_2\\ 0& TCPA>t_2\end{array}\right.$

Wherein

Obtaining the comprehensive collision risk degree u of the unmanned ship and the barrier according to the time collision risk degree and the space collision risk degree_t：

$u_t=u_{dt}\&CirclePlus;u_{tT}$

u_tThe value is divided into three cases,wherein, if u_dtWhen equal to 0, u_t＝0；

If u_dt≠0，u_tTWhen equal to 0, u_t＝0；

If u_dt≠0，u_tTWhen not equal to 0, u_t＝max(u_dt，u_tT)。

8. The method for autonomous collision avoidance control of an USV according to claim 7, wherein the process of the genetic algorithm controller to make a collision avoidance strategy according to the obstacle data in the fifth step is:

1. encoding the population:

each chromosome represents an initial path of the unmanned ship, in the population initialization process, a population with the number of individuals of n is automatically generated according to the initial position and the target position of the unmanned ship, all feasible paths from the starting point to the end point of the unmanned ship are coded, and each path is an individual in the population;

2. solving a fitness function:

the calculation of the fitness function considers the length of the path, the smoothness of the path and the safety of the path; the following two principles are followed when converting the objective function into the fitness function:

(1) the fitness value is non-negative;

(2) the change direction of the target function in the optimization process is consistent with the change direction of the fitness function in the population evolution process;

for the problem of selecting the collision avoidance path of the unmanned ship, a fitness function with a mapping relation with a target function is established through the following formula:

F_(x)＝C-f(x)

in the formula, F_(x)Is a fitness function; c is an adjustable parameter whose value is such that the fitness function F_(x)Constantly greater than or equal to 0; (x) is an objective function of the optimization problem;

to ensure F_(x)Not less than 0, the fitness function is established as follows:

$F_{\left(x\right)}=\left\{\begin{array}{cc}{C}_{max}-f\left(x\right)& f\left(x\right)<C_{max}\\ 0& f\left(x\right)\&GreaterEqual;C_{max}\end{array}\right.$

in the formula C_maxIs an adjustable parameter, C_maxTaking the maximum value theoretically possible for the objective function f (x); the length of the path, the smoothness of the path and the safety of the path are considered in the selection of the target function f (x);

3. basic genetic manipulation

The basic genetic operation comprises selection, crossing and mutation, and comprises the following specific operation steps:

(1) selection operation

Selecting individuals with high fitness from the population, and eliminating individuals with low fitness; probability P of individual i being selected_iProportional to its fitness value; adopting a roulette model, comprising the following steps:

1) calculating fitness of each chromosome F_i，1≤i≤n；

2) Integrating fitness values of all chromosomes, and recording intermediate integrated values S_i：S_iS₁＝F₁，S_i＝S_i-1+F_i；

3) Generating a random number x, 0 ≦ x ≦ S_n；

4) Selecting chromosomes if S_i-1＜x≤S_iIf i is more than or equal to 1 and less than or equal to n, the ith chromosome is selected to enter the next generation population;

5) repeating steps 3) and 4) until enough chromosomes are obtained;

(2) crossover operation

Crossover operation

Exchanging partial genes of two paired chromosomes according to a certain mode according to the cross probability so as to form two new individuals, wherein the cross rate is 0.5-0.95;

(3) mutation operation

Mutation operation

And replacing some gene values in the individual codes with other gene values according to the mutation probability so as to form a new individual, wherein the mutation rate is set to be between 0 and 0.5, and the gene mutation is carried out with small probability.