Underwater robot cable beacon long-distance optical navigation system and method

Abstract

The present invention discloses an underwater cable-tethered beacon long-distance optical navigation system and method, comprising: a blue-green beacon array connected to a power control in a control cabin to form a cable-tethered optical navigation node; the control cabin and the optical navigation node are mounted on a cable-tethered branch to form a map navigation landmark; a submarine cable is connected to onshore and underwater base stations; an underwater camera and a visual recognition module in an underwater robot cabin form an underwater visual recognition system, which receives camera video signals and outputs navigation information to the underwater robot controller; and an optical long-distance navigation algorithm based on the optical navigation node, which obtains navigation information for SLAM positioning through node light source feature extraction, heading calculation, and data fusion. The present invention meets the large-scale, long-distance navigation requirements of underwater robots, has strong adaptability and good stability, and is suitable for long-term navigation and positioning of underwater robots in cable-tethered systems.

Description

Technical Field

[0001] The invention discloses a long-distance optical navigation method of an underwater robot cable-tethered beacon based on a neural network, which is suitable for the long-term mobile navigation of the underwater robot in a cable-tethered environment. Technical Background

[0002] Cables and pipelines are crucial infrastructure in marine engineering construction, primarily used to transport electricity, natural gas, oil, and other materials. With the continuous development of marine engineering, the number of cables and pipelines is also increasing, necessitating regular inspection and maintenance. However, due to the complexity and harshness of the seabed environment, traditional inspection methods (such as manual diving) have certain risks and limitations.

[0003] AUV inspection technology can effectively address these issues. It utilizes AUVs as inspection platforms, using pre-programmed tracks and sensor systems. It can quickly, accurately, and safely perform inspection tasks in underwater environments, and can precisely locate and navigate complex seabed terrain. The emergence of this technology has brought significant breakthroughs in marine engineering, as it provides a safe, efficient, and economical inspection method. With technological advancements, the application scope of AUVs for inspecting cables and pipelines is also expanding. Currently, AUV inspection technology has become the preferred method for inspecting submarine infrastructure and is widely used in marine engineering, marine energy development, and marine environmental monitoring.

[0004] In AUV cable and pipeline detection technology, multiple sensor systems are usually carried, including acoustic sensors, electromagnetic sensors, and visual sensors. However, when sailing underwater, the route deviation may occur due to the influence of water currents and waves, which places high demands on the navigation system. The main purpose of AUV navigation research is to develop an effective navigation system that can operate autonomously in an underwater environment. The underwater environment has complex optical properties and signal transmission limitations, and the kinematic and dynamic characteristics of underwater robots are also relatively complex, which requires solving many technical problems, such as underwater beacon positioning, submersible attitude measurement, and underwater map construction.

[0005] Developing underwater long-distance, large-scale navigation technology can achieve high-precision positioning of AUVs by combining information from multiple sensors, thereby improving their navigation capabilities. However, methods for large-scale, long-distance positioning using cable-tethered beacon nodes and matching neural network navigation algorithms have not yet been reported. Summary of the Invention

[0006] The present invention discloses a long-distance optical navigation system and method for underwater cable-tethered beacons, designs a blue-green beacon array for underwater cable-tethered beacons, and proposes a long-distance cable-tethered node navigation technology based on a neural network.

[0007] In order to achieve the above objectives, the technical solution of the present invention is as follows: an underwater robot cable beacon long-distance optical navigation system, comprising:

[0008] The optical navigation node includes multiple light sources of different colors and is located on the outer surface of the cable.

[0009] A camera, used to collect light spot images of the optical navigation node;

[0010] The visual recognition module is used to identify the light spot image and obtain the relative heading of the underwater robot;

[0011] The robot control module is used to control the forward direction of the underwater robot according to the identified relative heading.

[0012] The optical navigation node includes two light sources, and the line connecting the centers of the two light sources is in the horizontal direction.

[0013] The wavelength of light emitted by the first light source is 450nm, and the wavelength of light emitted by the second light source is 510nm-550nm; the second light source and the first light source are arranged in sequence along the forward direction of the underwater robot.

[0014] The first light source is a blue light source, and the second light source is a green light source; the green light source and the blue light source are arranged in sequence along the forward direction of the underwater robot.

[0015] A long-distance optical navigation method for an underwater robot using a cable-tethered beacon comprises the following steps:

[0016] Collect the light spot image of the optical navigation node through the camera;

[0017] The visual recognition module recognizes the light spot image and obtains the relative heading of the underwater robot;

[0018] The robot control module controls the forward direction of the underwater robot according to the identified relative heading.

[0019] The visual recognition module recognizes the light spot image to obtain the relative heading of the underwater robot, including the following steps:

[0020] The BLOB algorithm is used to extract the outline and center of the navigation node light spot, and the outline of each light spot is identified to obtain the color attribute of each light spot;

[0021] When the number and color attributes of the light spots meet the preset conditions, the rays formed by the centers of the two light spots are fitted, and the node direction is obtained according to the rays and color attributes, and the relative heading is calculated by the angular deviation from the axis of the aircraft.

[0022] The robot control module controls the forward direction of the underwater robot according to the identified relative heading, including the following steps:

[0023] The calculated relative heading is integrated with the navigation trajectory of the underwater robot itself to obtain the heading trajectory error. According to the relative distance of the navigation node in the cable system and the current navigation trajectory error, the relative direction of the next navigation node is obtained to control the underwater robot to move to the next navigation node.

[0024] The preset conditions are: the number of light spots is two, and the color attributes are blue and green respectively.

[0025] The ray formed by fitting the two spot centers is used to obtain the node direction according to the ray and color attributes, as follows:

[0026] The ray formed by the center of the green light spot is used as the starting point and passes through the center of the blue light spot as the direction of the current navigation node.

[0027] The calculated relative heading and the navigation track of the underwater robot are integrated to obtain the heading track error. Specifically, the navigation track of the underwater robot is corrected according to the calculated relative heading to obtain the heading track error.

[0028] The present invention has the following advantages:

[0029] 1. The present invention can perform large-scale, high-precision, and precise navigation operations in a cable-based environment with high performance;

[0030] 2. The present invention can flexibly modify the array configuration according to actual use requirements, and has strong practicality and scalability;

[0031] 3. The navigation accuracy of the present invention is high, and the navigation data can be combined with other navigation and detection equipment of the underwater robot for combined navigation to form an underwater navigation map;

[0032] 4. This invention utilizes the propagation characteristics of blue-green light underwater and uses wavelength differentiation to achieve directional guidance under less lighting conditions, with high reliability;

[0033] 5. The system structure of the present invention is clear and simple, and a flexible underwater topology can be formed by combining multiple nodes;

[0034] 6. The algorithm of the present invention utilizes visual equipment, which has low cost and low algorithm complexity. It can be flexibly deployed in various types of aircraft. For common aircraft that are already equipped with visual equipment, there is no need to change the equipment form status. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a structural diagram of the present invention;

[0036] Figure 2a A side view schematic diagram of the beacon array light path distribution;

[0037] Figure 2bThis is a top view schematic diagram of the beacon array light path distribution diagram;

[0038] Figure 3 Flowchart of the control program adopted for the control method. DETAILED DESCRIPTION

[0039] The present invention is further described in detail below with reference to the embodiments and accompanying drawings.

[0040] The underwater vision positioning system device includes:

[0041] The underwater cable system connects the shore-based and underwater base stations, serving as the main underwater tracking target;

[0042] The underwater optical navigation node is connected to the positioning control cabin by a blue-green beacon array through a watertight connecting cable. The node is mounted as a branch of the cable system at a fixed distance from the node position;

[0043] The underwater camera is connected to the visual recognition module through a network to form an underwater visual recognition system;

[0044] The visual recognition module receives the camera video signal and outputs the positioning information to the underwater robot controller. The visual recognition method of the present invention is as follows:

[0045] First, start the system and initialize the embedded computing platform; the system initializes communication, waits for receiving network video signal data, and performs data processing;

[0046] Timed data transmission: Regularly judge whether there is new data in the sending buffer. If there is new data in the sending buffer, write the sending data, start sending, and send the data to the host computer for processing; if there is no new data in the sending buffer, report an error and perform exception processing;

[0047] A real-time positioning algorithm for cable-tethered beacons based on neural networks: First, a neural network is used to detect and identify the color image transmitted by the camera to obtain the position and size of the target in the image. The image is then cropped and features are extracted at that position to locate the center of each beacon light. Each light is then tracked and the relative heading of the camera and the positioning beacon is given through a position calculation algorithm. Finally, the data is processed to determine its validity. If the data is invalid, the data is processed for exception processing and then re-circulated. If the data is valid, the data is entered into the cache to be sent. Since the feature extraction positioning algorithm is faster than the neural network detection, reprojection is used for target tracking self-loop, and the recognition correction is performed after the neural network module is solved.

[0048] The underwater navigation system structure of the present invention is as follows: Figure 1As shown, the shore-based and underwater base stations are connected via cable beacons. The blue and green beacon arrays on the cable beacon branches are electrically connected to the positioning control cabin via watertight connecting cables to form an optical navigation node.

[0049] The underwater camera is connected to the visual computing module through the network to transmit video signals; the visual recognition module is connected to the robot control cabin through the network to transmit positioning signals;

[0050] The blue and green beacons are connected to the power control in the control cabin, forming a cable-based optical navigation node. The control cabin and the optical navigation node are mounted on the cable branches, forming a map navigation signpost. The submarine cable is connected to the onshore and underwater base stations.

[0051] The two beacons of each navigation node use light sources of different wavelengths to identify the direction. According to the underwater blue-green wavelength transmission window, 450nm blue and 530nm green wavelength LED light sources are used.

[0052] Node beacons form differentiated wavelength light sources underwater.

[0053] The underwater camera is connected to the visual recognition module through the network to transmit video data; the visual recognition module is connected to the robot control cabin through the network to transmit underwater navigation signals.

[0054] After being laid, the cable is laid flat on the bottom of the water, and the optical nodes are separated by a certain distance from the main cable trunk. The blue and green beacons of the same optical node form different light sources underwater, and the light sources are emitted vertically upward from the bottom of the water, such as Figure 2a As shown in the side view, 1 is a blue light source and 2 is a green light source. The horizontal distribution of optical node beacons is as follows Figure 2b As shown in the top view, the blue-green light source differentiates the directionality of the blue-green guidance array, which aligns with the cable's orientation. The optical node's positioning direction is the line formed by the two light sources, which is used to correct underwater robot navigation errors and serve as a landmark for constructing underwater maps.

[0055] The underwater positioning method of the present invention uses a long-distance visual navigation algorithm stored in the visual module. For the specific process, see Figure 3 .

[0056] First, start the system and initialize the embedded computing platform; the system initializes communication, waits for receiving network video signal data, and performs data processing;

[0057] Timed data transmission: Regularly judge whether there is new data in the sending buffer. If there is new data in the sending buffer, write the sending data, start sending, and send the data to the host computer for processing; if there is no new data in the sending buffer, report an error and perform exception processing;

[0058] Long-distance visual navigation algorithm:

[0059] Heading calculation: First, the BLOB algorithm is used to extract the outline and center of the navigation node light source. The statistical features of the outline range are taken in the RGB color domain for identification to obtain the color attributes of each area. The system then determines whether the preset physical conditions of the base station node are met. If not, the system is sent to exception processing. In terms of physical design, the minimum lighting principle is adopted to improve system reliability. Each node contains a blue light and a green light, and the direction is identified by the blue and green light sequence. The node direction is obtained by the center and color information of the two circles. The relative heading is calculated by fitting the angle deviation between the ray formed by the center of the two light sources and the physical center line of the spacecraft. The current heading is compared with the historical heading solution data. If the error is greater than 10%, a processing step is entered. If the error is small, the current data is considered reliable and the next step is entered.

[0060] Data fusion: The calculated relative heading is integrated with the navigation trajectory of the vehicle itself. The current navigation trajectory error is corrected using prior knowledge such as the relative distance of the nodes in the cable system and high-precision heading. The relative direction of the next beacon is given and the result is input into SLAM as a landmark.

[0061] This algorithm utilizes the directional information of differentiated beacons and the propagation advantages of blue-green light in water to realize a simple, fast, and robust underwater cable-tethered beacon long-distance navigation system. The output of the relevant algorithm can effectively compensate for the navigation error caused by the combined navigation track and meet the navigation requirements of the resident cable-tethered vehicle system.

Claims

1. A long-distance optical navigation method for underwater robots using cable-tethered beacons, characterized in that: The following steps are involved: Collect the light spot image of the optical navigation node through the camera; The visual recognition module recognizes the light spot image and obtains the relative heading of the underwater robot; The robot control module controls the forward direction of the underwater robot according to the identified relative heading; The visual recognition module recognizes the light spot image to obtain the relative heading of the underwater robot, including the following steps: The BLOB algorithm is used to extract the outline and center of the navigation node light spot, and the outline of each light spot is identified to obtain the color attribute of each light spot; When the number and color attributes of the light spots meet the preset conditions, the rays formed by the centers of the two light spots are fitted, and the node direction is obtained according to the rays and color attributes, and the relative heading is calculated by the angular deviation from the axis of the aircraft.

2. The underwater robot cable beacon long-distance optical navigation method according to claim 1, characterized in that: The robot control module controls the forward direction of the underwater robot according to the identified relative heading, including the following steps: The calculated relative heading is integrated with the navigation trajectory of the underwater robot itself to obtain the heading trajectory error. According to the relative distance of the navigation node in the cable system and the current navigation trajectory error, the relative direction of the next navigation node is obtained to control the underwater robot to move to the next navigation node.

3. The underwater robot cable beacon long-distance optical navigation method according to claim 1, characterized in that: The preset conditions are: the number of light spots is two, and the color attributes are blue and green respectively.

4. The underwater robot cable beacon long-distance optical navigation method according to claim 1, characterized in that: The ray formed by fitting the two spot centers is used to obtain the node direction according to the ray and color attributes, as follows: The ray formed by the center of the green light spot is used as the starting point and passes through the center of the blue light spot as the direction of the current navigation node.

5. The underwater robot cable beacon long-distance optical navigation method according to claim 2, characterized in that: The calculated relative heading is integrated with the navigation trajectory of the underwater robot to obtain the heading trajectory error, which is as follows: According to the calculated relative heading, the navigation trajectory of the underwater robot itself is corrected to obtain the heading trajectory error.

Images