Movatterモバイル変換


[0]ホーム

URL:


CN119573686A - An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robots - Google Patents

An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robots
Download PDF

Info

Publication number
CN119573686A
CN119573686ACN202411983401.3ACN202411983401ACN119573686ACN 119573686 ACN119573686 ACN 119573686ACN 202411983401 ACN202411983401 ACN 202411983401ACN 119573686 ACN119573686 ACN 119573686A
Authority
CN
China
Prior art keywords
navigation
data
mapping
robot
unit
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.)
Withdrawn
Application number
CN202411983401.3A
Other languages
Chinese (zh)
Inventor
陈永涛
李文奇
吕玲
林武震
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National Marine Environmental Monitoring Center
Original Assignee
National Marine Environmental Monitoring Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by National Marine Environmental Monitoring CenterfiledCriticalNational Marine Environmental Monitoring Center
Priority to CN202411983401.3ApriorityCriticalpatent/CN119573686A/en
Publication of CN119573686ApublicationCriticalpatent/CN119573686A/en
Withdrawnlegal-statusCriticalCurrent

Links

Classifications

Landscapes

Abstract

The application discloses an ocean mapping system based on intelligent navigation of a deepwater detection robot, and belongs to the technical field of ocean mapping. The system comprises a data acquisition module, a navigation fusion module, a quality control module, a path planning module, a fault tolerance control module and a topography mapping module, wherein the data acquisition module acquires navigation positioning data and submarine topography data synchronously with submarine measurement equipment through multi-source navigation equipment carried by a deepwater detection robot, the navigation fusion module is used for realizing self-adaptive fusion of the multi-source data and outputting initial pose estimation, the quality control module is used for carrying out quality estimation and anomaly identification on real-time mapping data, the path planning module is used for planning an optimal mapping path in real time and carrying out on-line adjustment according to retest requirements of the quality control module, the fault tolerance control module is used for realizing multi-level navigation source fault diagnosis, starting a degradation navigation strategy when navigation is abnormal or invalid, and guaranteeing that basic navigation and mapping functions can be maintained, and the topography mapping module is used for carrying out real-time compensation and splicing on the submarine topography data by using pose information provided by the navigation fusion module.

Description

Ocean mapping system based on intelligent navigation of deepwater detection robot
Technical Field
The application relates to the technical field of ocean mapping, in particular to an ocean mapping system based on intelligent navigation of a deepwater detection robot.
Background
Marine surveying and mapping is used as an important means for acquiring marine geographic information, and is widely applied to the fields of submarine resource exploration, marine environment monitoring, channel planning and the like. With the continuous development of ocean scientific research and engineering technology, the mapping requirement of deep water areas is gradually increased. The traditional ocean mapping method mainly depends on manual operation or simple automatic equipment, faces the problems of low mapping efficiency, insufficient precision, poor adaptability and the like, and particularly in a deep water area, navigation positioning difficulty and unstable data quality are caused by complex submarine topography and various environmental changes.
In order to solve these problems, in recent years, deep water exploration robot technology has been developed. The deepwater detection robot can perform autonomous navigation and mapping in a complex submarine environment by integrating various sensors and navigation equipment. However, since the deepwater exploration robot needs to face real-time changes of the marine environment, errors of sensors, inconsistency of data and other challenges when performing tasks, how to realize high-precision and high-efficiency deepwater mapping is still a technical problem to be solved.
At present, although the existing marine surveying and mapping system can provide an automatic surveying and mapping function to a certain extent, the problems of low precision of navigation source data fusion, lack of flexibility of path planning algorithm, insufficient surveying and mapping quality control and the like still exist, and particularly in a deepwater exploration environment, the fault tolerance capability of the system to navigation source failure, submarine topography change and environmental interference is weak, so that the precision in the surveying and mapping process is reduced, and even tasks fail.
In summary, how to realize high-precision and high-reliability navigation and mapping in a complex deepwater environment, how to effectively fuse multi-source navigation data, optimize path planning and ensure fault tolerance of a system has become a technical problem to be solved.
Disclosure of Invention
In order to overcome a series of defects existing in the prior art, the application aims at providing an ocean mapping system based on intelligent navigation of a deepwater detection robot, which comprises the following modules:
the data acquisition module synchronously acquires navigation positioning data and submarine topography data through a multi-source navigation device and a submarine measurement device carried by the deepwater detection robot;
The navigation fusion module is used for realizing self-adaptive fusion of the multi-source data and outputting initial pose estimation;
The quality control module is used for carrying out quality evaluation and anomaly identification on the real-time mapping data, generating local retest requirements according to the evaluation result and ensuring that the mapping precision meets the requirements;
The path planning module is used for planning an optimal mapping path in real time based on the current pose, task requirements and local terrain characteristics of the robot and carrying out online adjustment according to the retest requirements of the quality control module;
The fault-tolerant control module is used for realizing multi-level navigation source fault diagnosis, and starting a degradation navigation strategy when navigation is abnormal or invalid so as to ensure that basic navigation and mapping functions can be maintained;
And the terrain mapping module is used for compensating and splicing submarine terrain data in real time by using the pose information provided by the navigation fusion module.
Further, the data acquisition module comprises the following components:
the navigation positioning unit is used for acquiring original navigation data of the deepwater detection robot through an integrated GPS, an inertial navigation system and sonar positioning equipment;
The submarine topography detection unit is used for acquiring submarine topography data in real time by utilizing multi-beam sonar and side-scan sonar technologies, wherein the submarine topography data comprises the depth, the shape and the characteristics of a seabed;
the environment sensing unit acquires marine environment parameters through an environment sensor and provides real-time data support of environment change during mapping;
The attitude monitoring unit is used for acquiring attitude data of the robot in real time by using the gyroscope and the accelerometer;
And the data preprocessing unit is used for carrying out preliminary processing and formatting on the collected original data and providing standardized data input for a subsequent module.
Further, the navigation fusion module comprises the following components:
The credibility evaluation unit is used for evaluating the data reliability of each navigation source in real time based on a deep learning algorithm and outputting a credibility score of each navigation source;
the weight adjusting unit dynamically adjusts the weight of each navigation source in the fusion calculation according to the reliability score;
an error modeling unit modeling error characteristics of each navigation source using an improved kalman filter algorithm;
The data synchronization fusion unit is used for carrying out time synchronization and integration on navigation data from different sources and calculating a preliminary pose estimation result according to the dynamic weight and the error model;
And the pose output unit outputs the fused preliminary pose estimation result and provides high-precision navigation information for subsequent path planning and mapping compensation.
Further, the reliability score of the navigation source is formulated as: Wherein,Reliability scoring for the ith navigation source, wherein the value is between 0 and 1 to represent the reliability of the navigation source, Wi is a weight matrix corresponding to the ith navigation source, xi is a feature vector of the ith navigation source, and bi is a bias term;
the weight of each navigation source in the fusion calculation is dynamically adjusted by the following formula: wi is the weight of the ith navigation source, corresponding to the confidence scoreProportional to the ratio; the sum of the reliability scores of all navigation sources is ensured to be 1, and normalization processing is carried out.
Further, the preliminary pose estimation result is expressed as: Wherein,Pi(ti) represents navigation data of the ith navigation source at the time ti; Is the change rate of the ith navigation source at the time ti, ti represents the timestamp of the ith navigation source, tsync represents the target synchronization time, ei(tsync) represents the error estimation value of the error model of the ith navigation source at the synchronization time tsync, and ei represents the error model of the ith navigation source.
Further, the path planning module includes the following components:
The task demand analysis unit analyzes task demands according to the targets and constraints of the mapping task and provides task-oriented constraint conditions for path planning;
the environment constraint analysis unit is used for analyzing local topographic features based on real-time submarine topography data and providing environment constraint information for path planning by combining environment perception data;
the path generation unit is used for learning and generating an optimal mapping path in real time based on the current pose, task requirements and terrain characteristics through a reinforcement learning algorithm;
the path optimizing unit dynamically adjusts the current path planning according to the retest demand or feedback information generated by the quality control module, and ensures that the path meets the mapping precision and task requirements;
The safety monitoring unit is used for adjusting the path in real time according to the terrain analysis result and the real-time environment perception, avoiding collision or entering a dangerous area and ensuring the safety of the robot;
and the path output unit converts the optimized path into a control instruction sequence and controls the robot to execute.
Further, the optimal mapping path is generated gradually through a reinforcement learning strategy pi*(sT), and is expressed as follows:,
Wherein aT is an action at the current time T, namely a path planning decision selected by the robot, w1、w2、w3 is a weight coefficient of task demand, terrain adaptability and progress optimization respectively, sT is a state of the robot at the time T, Rtask(sT,aT) is a task reward after taking action aT and used for evaluating the completion degree of the current task demand in the state sT, Rterrain(sT,aT) is a terrain adaptability reward after taking action aT and used for evaluating the adaptation condition of the current path planning on the seabed terrain in the state sT, Rprogress(sT,aT) is a progress reward after taking action aT and used for evaluating the contribution of the current path planning to the task progress in the state sT, gamma is a discount factor and used for balancing the relation between the current reward and future rewards, and V (sT+1) is a value function after the robot takes the optimal strategy in the state sT+1 and represents the maximum long-term reward obtained from the state sT+1.
Further, the fault tolerant control module includes the following components:
the navigation state monitoring unit monitors stability, accuracy and consistency of each navigation source data in real time and captures potential abnormal signals or failure signs;
the fault diagnosis unit is used for analyzing the type and severity of the abnormality of the navigation source based on a multi-level diagnosis algorithm and determining the cause and the influence range of the fault;
the redundant strategy management unit is used for managing the standby navigation source and the redundant strategy library, and rapidly switching to the suboptimal navigation source when the main navigation source fails so as to maintain the navigation function;
The degraded navigation execution unit starts a standby navigation scheme under the condition that a navigation source fails or is abnormal, and maintains a basic navigation function;
The abnormal data processing unit is used for uniformly processing abnormal data from each module and comprises data rejection, abnormal correction and interference suppression;
And the navigation performance evaluation unit evaluates the performance in the degraded navigation mode in real time, ensures that the performance meets the minimum task requirement, and tries to recover the normal navigation mode when the condition allows.
Further, the topographic mapping module includes the following components:
The topographic data compensation unit is used for compensating the collected submarine topographic data in real time according to the current pose information of the robot and correcting data deviation caused by positioning errors or sensor deviation;
The data splicing unit splices submarine topography data acquired in different positions and time periods to form a continuous topography map, so that seamless connection between the data is ensured;
the SLAM algorithm implementation unit optimizes the relation between the pose of the robot and the topographic data in real time based on the SLAM algorithm, and establishes and updates an accurate map of the submarine topography;
The closed-loop optimization unit optimizes the accumulated error of the robot position through closed-loop detection and correction of the SLAM algorithm, and ensures continuous improvement of the map and positioning accuracy;
the topographic feature analysis unit is used for extracting and analyzing features of the submarine topographic data and providing topographic feature information for other modules;
And the precision evaluation and output unit is used for performing precision evaluation on the spliced topographic data, outputting a final submarine topography map and providing a positioning optimization result to other modules.
Further, the data bias due to the positioning error or sensor bias is corrected by the following formula: Wherein Dfinal is corrected submarine topography data, (xraw,yraw) is the coordinate of original submarine topography data, which represents the initial coordinate of submarine topography in the measured data, and is not corrected, ex,ey is a positioning error, which represents the horizontal positioning error and the vertical positioning error of the robot respectively, eθ is an attitude error, which represents the orientation error of the robot, θ is the robot orientation, R (eθ) is a rotation matrix for correcting topography data deviation caused by the attitude error eθ, sx,sy is a sensor deviation, which represents systematic deviation or error of the sensor itself in the horizontal direction and the vertical direction respectively.
Compared with the prior art, the application has the following beneficial effects:
According to the application, through the integration of the multi-source navigation equipment and the submarine measurement equipment carried by the deepwater detection robot, high-efficiency and accurate submarine topography mapping is realized, and through intelligent navigation, path planning and fault-tolerant control, the continuity and reliability of mapping tasks are ensured, and meanwhile, the accuracy and the integrity of mapping data are improved.
Drawings
Fig. 1 is a schematic structural diagram of an ocean mapping system based on intelligent navigation of a deepwater detection robot according to an embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention become more apparent, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, embodiments of the invention.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiments described below, together with the words of orientation, are exemplary and intended to explain the invention and should not be taken as limiting the invention.
As shown in fig. 1, an ocean mapping system based on intelligent navigation of a deepwater detection robot comprises the following modules:
the data acquisition module synchronously acquires navigation positioning data and submarine topography data through a multi-source navigation device and a submarine measurement device carried by the deepwater detection robot;
The navigation fusion module is used for realizing self-adaptive fusion of the multi-source data and outputting initial pose estimation;
The quality control module is used for carrying out quality evaluation and anomaly identification on the real-time mapping data, generating local retest requirements according to the evaluation result and ensuring that the mapping precision meets the requirements;
The path planning module is used for planning an optimal mapping path in real time based on the current pose, task requirements and local terrain characteristics of the robot and carrying out online adjustment according to the retest requirements of the quality control module;
The fault-tolerant control module is used for realizing multi-level navigation source fault diagnosis, and starting a degradation navigation strategy when navigation is abnormal or invalid so as to ensure that basic navigation and mapping functions can be maintained;
And the terrain mapping module is used for compensating and splicing submarine terrain data in real time by using the pose information provided by the navigation fusion module.
The data acquisition module is a basic part of the system and is responsible for synchronously collecting various sensor data on the deepwater exploration robot. The robot performs real-time data acquisition by mounting multi-source navigation devices such as an Inertial Navigation System (INS), a sonar positioning system (SSBL), a depth gauge, and the like, and submarine measurement devices such as a sonar imaging system, a laser scanner, and the like. These devices are capable of providing important information including navigational positioning data (e.g., position, attitude, etc. of the robot) and seafloor topography data (e.g., seafloor topography, obstructions, etc.). The parallel acquisition of the multi-source data not only improves the integrity and the precision of the data, but also can effectively overcome the problems of errors and blind areas possibly caused by single equipment, and provides high-quality original data for subsequent navigation and mapping.
The navigation fusion module is one of core technologies in the system, and has the task of effectively fusing navigation data from different sensors and outputting initial pose estimation of the robot. The data of various sensors usually have certain errors, and how to comprehensively utilize the data through an intelligent algorithm and improve the positioning accuracy are key of the module. Common methods include Kalman filtering, particle filtering and the like, and the positioning accuracy after fusion is ensured by dynamically adjusting the weights of different sensors. The module not only can provide the position information of the robot in real time, but also can carry out self-adaptive adjustment on the weight of the sensor according to different environmental conditions, so that the robot can still be accurately positioned in a complex underwater environment, and an accurate basis is provided for subsequent path planning and topographic mapping.
The main function of the quality control module is to evaluate the quality of mapping data acquired in real time and identify abnormal data. Due to the complex submarine mapping environment, the acquired data may have errors or incomplete conditions under the influence of various factors such as water flow, robot motion state, sensor faults and the like. The module performs accuracy analysis and anomaly detection on each frame of data by designing a data quality evaluation algorithm, and can timely discover and mark potential error data. Meanwhile, the module generates local retest demands according to quality evaluation results, and when certain area mapping precision is found to be substandard, the robot is triggered to re-map the areas, so that the precision of final data is ensured. The technology effectively ensures the overall mapping precision of the system, and particularly ensures the reliability and safety of tasks in a deepwater environment.
The path planning module is responsible for planning an optimal mapping path in real time according to the current pose, task requirements and local terrain features of the robot. The module aims to ensure that the robot performs mapping in a complex submarine environment in an optimal path, so that task requirements can be met, obstacles can be avoided, and mapping time can be reduced. Meanwhile, the path planning module can dynamically adjust according to the local retest demand provided by the quality control module. For example, when mapping accuracy of a certain area is problematic, the path planning module automatically plans a retest path passing through the area, so as to improve accuracy and integrity of data. The design of the module can greatly improve the operation efficiency of the robot, reduce unnecessary path repetition and improve the overall benefit of mapping operation.
The fault-tolerant control module is a key guarantee module of the system and mainly realizes multi-level navigation source fault diagnosis and emergency response. When any navigation equipment has faults or anomalies, the fault-tolerant control module can detect and start corresponding fault emergency mechanisms in real time. For example, when the sonar positioning system fails, the module can automatically switch to the inertial navigation system, and the position of the robot is corrected through a complementary algorithm so as to maintain the navigation continuity. The module is designed through multi-level redundancy, so that the robot can maintain basic navigation and mapping functions even in a complex environment, the task interruption risk caused by equipment faults is reduced, and the high availability of the system is ensured.
The topographic mapping module compensates and splices the submarine topography data in real time by utilizing the pose information provided by the navigation fusion module. Due to the complexity of the subsea environment, the robot may be affected by water currents or obstacles during the movement, resulting in displacements or deviations during the data acquisition. Therefore, after the module collects the topographic data, the module can carry out space compensation according to the real-time pose of the robot, so that the collected topographic data can accurately reflect the real situation of the seabed. Meanwhile, the splicing algorithm can seamlessly splice the measurement data from different positions to generate a complete submarine topography. The high efficiency of the module ensures the continuity and accuracy of the submarine topography map, and provides a reliable basis for subsequent data analysis and decision making.
In a comprehensive view, the ocean mapping system based on intelligent navigation of the deepwater detection robot can realize high-precision and high-efficiency submarine topography mapping in a complex submarine environment through cooperative work of a plurality of technical modules. The data acquisition module provides rich original data, the navigation fusion module ensures accurate positioning information, the quality control module improves the reliability of the data, the path planning module optimizes the efficiency of mapping operation, the fault-tolerant control module ensures the stability of the system, and the topography mapping module finally generates an accurate submarine topography. The organic combination of the technical modules enables the system to show strong adaptability and reliability in deepwater exploration tasks, and has important significance for marine mapping operation.
Further, the data acquisition module comprises the following components:
the navigation positioning unit is used for acquiring original navigation data of the deepwater detection robot through an integrated GPS, an inertial navigation system and sonar positioning equipment;
The submarine topography detection unit is used for acquiring submarine topography data in real time by utilizing multi-beam sonar and side-scan sonar technologies, wherein the submarine topography data comprises the depth, the shape and the characteristics of a seabed;
the environment sensing unit acquires marine environment parameters through an environment sensor and provides real-time data support of environment change during mapping;
The attitude monitoring unit is used for acquiring attitude data of the robot in real time by using the gyroscope and the accelerometer;
And the data preprocessing unit is used for carrying out preliminary processing and formatting on the collected original data and providing standardized data input for a subsequent module.
In summary, through analysis of each component in the data acquisition module, it can be seen that the technical effect of each component plays a critical role in intelligent navigation of the deepwater detection robot. From the accurate position information provided by the navigation positioning unit, to the high-precision terrain data provided by the submarine topography detection unit, and to the real-time monitoring of the environment sensing unit and the attitude monitoring unit, all components together ensure that tasks can be efficiently and stably executed in complex and changeable marine environments. The data preprocessing unit provides optimized data input for the subsequent modules, and ensures the data fluency and accuracy of the whole system. The organic cooperation of each component ensures that the data acquisition module can provide comprehensive and reliable data support for the deepwater exploration robot, ensures the high efficiency and accuracy of the system and promotes the smooth completion of the submarine surveying and mapping task.
Further, the navigation fusion module comprises the following components:
The credibility evaluation unit is used for evaluating the data reliability of each navigation source in real time based on a deep learning algorithm and outputting a credibility score of each navigation source;
the weight adjusting unit dynamically adjusts the weight of each navigation source in the fusion calculation according to the reliability score;
an error modeling unit modeling error characteristics of each navigation source using an improved kalman filter algorithm;
The data synchronization fusion unit is used for carrying out time synchronization and integration on navigation data from different sources and calculating a preliminary pose estimation result according to the dynamic weight and the error model;
And the pose output unit outputs the fused preliminary pose estimation result and provides high-precision navigation information for subsequent path planning and mapping compensation.
The navigation fusion module realizes the efficient fusion of different navigation source data through the cooperative work of a plurality of key components such as reliability assessment, weight adjustment, error modeling, data synchronous fusion, pose output and the like, and provides accurate pose estimation for the deepwater exploration robot. By dynamically adjusting the weight of each navigation source, evaluating its reliability in real time, and accurately modeling the error characteristics of the sensor, the module is able to maintain high-precision, high-reliability navigation in complex and diverse marine environments. The module not only improves the adaptability of the robot in a complex submarine environment, but also provides powerful data support for subsequent path planning and topographic mapping.
Further, the reliability score of the navigation source is formulated as: Wherein,Reliability scoring for the ith navigation source, wherein the value is between 0 and 1 to represent the reliability of the navigation source, Wi is a weight matrix corresponding to the ith navigation source, xi is a feature vector of the ith navigation source, and bi is a bias term;
the weight of each navigation source in the fusion calculation is dynamically adjusted by the following formula: wi is the weight of the ith navigation source, corresponding to the confidence scoreProportional to the ratio; the sum of the reliability scores of all navigation sources is ensured to be 1, and normalization processing is carried out.
The core idea of the above formula is to dynamically evaluate the credibility of each navigation source and adjust its weight in the fusion calculation according to its reliability. The strategy based on credibility scoring and weight adjustment can flexibly cope with the changes of navigation sources under different environments and conditions, and ensures that the fused pose estimation is more accurate and reliable. By means of the method, the navigation fusion module can maintain high-precision navigation in a complex marine environment, and overall operation efficiency and precision of the deepwater detection robot are greatly improved.
Further, the preliminary pose estimation result is expressed as: Wherein,Pi(ti) represents navigation data of the ith navigation source at the time ti; Is the change rate of the ith navigation source at the time ti, ti represents the timestamp of the ith navigation source, tsync represents the target synchronization time, ei(tsync) represents the error estimation value of the error model of the ith navigation source at the synchronization time tsync, and ei represents the error model of the ith navigation source.
The calculation of the initial pose estimation result is realized by fusing the data of a plurality of navigation sources, and factors such as time deviation, change rate, error model and the like of each navigation source are considered. According to the method, the weight of each navigation source is dynamically adjusted, and the error is corrected, so that a high-precision pose estimation result can be provided for the deepwater exploration robot in a complex marine environment. The estimation result provides reliable navigation support for subsequent path planning and submarine mapping tasks, and improves the working efficiency and mapping accuracy of the whole system.
Further, the path planning module includes the following components:
The task demand analysis unit analyzes task demands according to the targets and constraints of the mapping task and provides task-oriented constraint conditions for path planning;
the environment constraint analysis unit is used for analyzing local topographic features based on real-time submarine topography data and providing environment constraint information for path planning by combining environment perception data;
the path generation unit is used for learning and generating an optimal mapping path in real time based on the current pose, task requirements and terrain characteristics through a reinforcement learning algorithm;
the path optimizing unit dynamically adjusts the current path planning according to the retest demand or feedback information generated by the quality control module, and ensures that the path meets the mapping precision and task requirements;
The safety monitoring unit is used for adjusting the path in real time according to the terrain analysis result and the real-time environment perception, avoiding collision or entering a dangerous area and ensuring the safety of the robot;
and the path output unit converts the optimized path into a control instruction sequence and controls the robot to execute.
The path planning module ensures that the deepwater detection robot can efficiently and safely execute mapping tasks in a complex submarine environment through cooperation of a plurality of components such as task demand analysis, environment constraint analysis, path generation, path optimization, safety monitoring, path output and the like. The task demand analysis unit provides constraint conditions for task guidance for path planning, the environment constraint analysis unit provides necessary environment constraints in combination with terrain and environment data, the path generation unit generates an optimal path by using a reinforcement learning algorithm, the path optimization unit carries out dynamic adjustment according to quality control feedback, the safety monitoring unit ensures the safety of the robot, and the path output unit ensures that the path is accurately executed. Through the coordination work of the modules, the path planning module can maximally improve the working efficiency and the task completion degree of the robot while guaranteeing the mapping precision and the task requirements.
Further, the optimal mapping path is generated gradually through a reinforcement learning strategy pi*(sT), and is expressed as follows:,
Wherein aT is an action at the current time T, namely a path planning decision selected by the robot, w1、w2、w3 is a weight coefficient of task demand, terrain adaptability and progress optimization respectively, sT is a state of the robot at the time T, Rtask(sT,aT) is a task reward after taking action aT and used for evaluating the completion degree of the current task demand in the state sT, Rterrain(sT,aT) is a terrain adaptability reward after taking action aT and used for evaluating the adaptation condition of the current path planning on the seabed terrain in the state sT, Rprogress(sT,aT) is a progress reward after taking action aT and used for evaluating the contribution of the current path planning to the task progress in the state sT, gamma is a discount factor and used for balancing the relation between the current reward and future rewards, and V (sT+1) is a value function after the robot takes the optimal strategy in the state sT+1 and represents the maximum long-term reward obtained from the state sT+1.
The generation of the optimal mapping path is realized step by step through a reinforcement learning strategy, and path selection is performed under each state according to a plurality of factors such as task requirements, terrain adaptability, progress and the like. By setting reasonable reward functions and weight coefficients and combining dynamic adjustment of discount factors, the reinforcement learning algorithm can help the robot to generate an optimal path meeting task requirements. The method not only can process complex submarine topography environment, but also can flexibly adjust the path according to real-time task demands and progress demands, and ensures that the mapping task can be efficiently and safely completed.
Further, the fault tolerant control module includes the following components:
the navigation state monitoring unit monitors stability, accuracy and consistency of each navigation source data in real time and captures potential abnormal signals or failure signs;
the fault diagnosis unit is used for analyzing the type and severity of the abnormality of the navigation source based on a multi-level diagnosis algorithm and determining the cause and the influence range of the fault;
the redundant strategy management unit is used for managing the standby navigation source and the redundant strategy library, and rapidly switching to the suboptimal navigation source when the main navigation source fails so as to maintain the navigation function;
The degraded navigation execution unit starts a standby navigation scheme under the condition that a navigation source fails or is abnormal, and maintains a basic navigation function;
The abnormal data processing unit is used for uniformly processing abnormal data from each module and comprises data rejection, abnormal correction and interference suppression;
And the navigation performance evaluation unit evaluates the performance in the degraded navigation mode in real time, ensures that the performance meets the minimum task requirement, and tries to recover the normal navigation mode when the condition allows.
The fault-tolerant control module ensures that the deepwater detection robot can continue to perform tasks and maintain basic functions when encountering navigation source faults or anomalies through multi-level monitoring, diagnosis, redundant switching and data processing. The navigation state monitoring unit captures abnormal signals of the navigation source in real time, the fault diagnosis unit provides accurate fault analysis, and the redundancy strategy management unit and the degradation navigation execution unit ensure that the system can be quickly switched to the standby navigation source and maintain task execution. The abnormal data processing unit and the navigation performance evaluation unit ensure the validity of the data and the stability of the system performance. Through cooperation of the components, the fault-tolerant control module enhances the robustness of the system, so that the robot can always maintain high-efficiency navigation capability in complex and variable environments, and smooth performance of submarine mapping tasks is ensured.
Further, the topographic mapping module includes the following components:
The topographic data compensation unit is used for compensating the collected submarine topographic data in real time according to the current pose information of the robot and correcting data deviation caused by positioning errors or sensor deviation;
The data splicing unit splices submarine topography data acquired in different positions and time periods to form a continuous topography map, so that seamless connection between the data is ensured;
the SLAM algorithm implementation unit optimizes the relation between the pose of the robot and the topographic data in real time based on the SLAM algorithm, and establishes and updates an accurate map of the submarine topography;
The closed-loop optimization unit optimizes the accumulated error of the robot position through closed-loop detection and correction of the SLAM algorithm, and ensures continuous improvement of the map and positioning accuracy;
the topographic feature analysis unit is used for extracting and analyzing features of the submarine topographic data and providing topographic feature information for other modules;
And the precision evaluation and output unit is used for performing precision evaluation on the spliced topographic data, outputting a final submarine topography map and providing a positioning optimization result to other modules.
The SLAM (Simultaneous Localization AND MAPPING) algorithm is a technique that builds maps in real time by sensors and simultaneously self-locates in an unknown environment. It is widely used in the field of robot navigation, autopilot, unmanned aerial vehicle flight, and other applications where tasks need to be performed in an unknown or dynamic environment. The core task of SLAM is to enable the robot to locate its own position and build a map of the surrounding environment without external positioning support (such as GPS).
The topography mapping module cooperates through a plurality of precision components, so that high-precision submarine topography mapping is realized. The terrain data compensation unit and the data splicing unit ensure the accuracy and seamless connection of data, and the SLAM algorithm realization unit and the closed-loop optimization unit ensure the continuous accuracy of the map by optimizing the pose and the map in real time. The topographic feature analysis unit provides valuable environmental information for the system, and the precision evaluation and output unit ensures that the mapping result meets the task requirement. By the technical means, the topography mapping module can provide a high-quality and real-time updated submarine topography map in a complex submarine environment, and a firm guarantee is provided for the deepwater exploration robot to finish an accurate submarine mapping task.
Further, the data bias due to the positioning error or sensor bias is corrected by the following formula: Wherein Dfinal is corrected submarine topography data, (xraw,yraw) is the coordinate of original submarine topography data, which represents the initial coordinate of submarine topography in the measured data, and is not corrected, ex,ey is a positioning error, which represents the horizontal positioning error and the vertical positioning error of the robot respectively, eθ is an attitude error, which represents the orientation error of the robot, θ is the robot orientation, R (eθ) is a rotation matrix for correcting topography data deviation caused by the attitude error eθ, sx,sy is a sensor deviation, which represents systematic deviation or error of the sensor itself in the horizontal direction and the vertical direction respectively.
Through the correction formula and the flow, the deepwater detection robot can effectively correct submarine topography data deviation caused by positioning errors, attitude errors and sensor deviation. The correction measures ensure the accuracy of the acquired submarine topography data, and provide a reliable basis for subsequent path planning, map construction and accuracy evaluation, so that the performance and operability of the whole ocean mapping system are improved.
Finally, it should be pointed out that the above embodiments are only intended to illustrate the technical solution of the invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that modifications may be made to the technical solutions described in the foregoing embodiments or equivalents may be substituted for some of the technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention in essence of the corresponding technical solutions.

Claims (10)

Translated fromChinese
1.一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,包括以下模块:1. An ocean surveying and mapping system based on intelligent navigation of a deep-water exploration robot, characterized in that it includes the following modules:数据采集模块,通过深水探测机器人搭载的多源导航设备与海底测量设备同步采集导航定位数据和海底地形数据;The data acquisition module collects navigation positioning data and seabed topography data synchronously through the multi-source navigation equipment and seabed measurement equipment carried by the deep-water exploration robot;导航融合模块,实现多源数据的自适应融合,输出初始位姿估计;Navigation fusion module, which realizes adaptive fusion of multi-source data and outputs initial pose estimation;质量控制模块,对实时测绘数据进行质量评估与异常识别,并根据评估结果生成局部重测需求,确保测绘精度满足要求;The quality control module conducts quality assessment and anomaly identification on real-time surveying and mapping data, and generates local re-survey requirements based on the assessment results to ensure that the surveying and mapping accuracy meets the requirements;路径规划模块,基于机器人当前位姿、任务需求和局部地形特征,实时规划最优测绘路径,并根据质量控制模块的重测需求进行在线调整;The path planning module plans the optimal mapping path in real time based on the robot's current posture, task requirements, and local terrain features, and makes online adjustments based on the re-measurement requirements of the quality control module;容错控制模块,实现多层次的导航源故障诊断,在导航异常或失效时启动降级导航策略,确保仍能维持基本的导航与测绘功能;Fault-tolerant control module, which implements multi-level navigation source fault diagnosis and initiates degraded navigation strategy when navigation is abnormal or fails, ensuring that basic navigation and mapping functions can still be maintained;地形测绘模块,利用导航融合模块提供的位姿信息对海底地形数据进行实时补偿和拼接。The terrain mapping module uses the posture information provided by the navigation fusion module to perform real-time compensation and splicing of seabed terrain data.2.根据权利要求1所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,数据采集模块包括以下组件:2. According to claim 1, a marine surveying and mapping system based on intelligent navigation of a deep-water exploration robot is characterized in that the data acquisition module includes the following components:导航定位单元,通过集成的GPS、惯性导航系统和声呐定位设备,采集深水探测机器人的原始导航数据;The navigation and positioning unit collects the original navigation data of the deep-water exploration robot through integrated GPS, inertial navigation system and sonar positioning equipment;海底地形探测单元,利用多波束声呐和侧扫声呐技术,实时采集海底地形数据,包括海床的深度、形状和特征;The seafloor topography detection unit uses multi-beam sonar and side-scan sonar technology to collect real-time seafloor topography data, including the depth, shape and characteristics of the seabed;环境感知单元,通过环境传感器获取海洋环境参数,提供测绘时环境变化的实时数据支持;The environmental perception unit obtains marine environmental parameters through environmental sensors and provides real-time data support for environmental changes during surveying and mapping;姿态监测单元,利用陀螺仪和加速度计实时采集机器人的姿态数据;The posture monitoring unit uses a gyroscope and an accelerometer to collect the robot's posture data in real time;数据预处理单元,对采集的原始数据进行初步处理和格式化,为后续模块提供标准化的数据输入。The data preprocessing unit performs preliminary processing and formatting on the collected raw data to provide standardized data input for subsequent modules.3.根据权利要求1所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,导航融合模块包括以下组件:3. According to claim 1, the ocean surveying and mapping system based on intelligent navigation of a deep-water exploration robot is characterized in that the navigation fusion module includes the following components:可信度评估单元,基于深度学习算法,实时评估各个导航源的数据可靠性,输出每个导航源的可信度评分;The credibility assessment unit, based on a deep learning algorithm, evaluates the data reliability of each navigation source in real time and outputs a credibility score for each navigation source;权重调整单元,根据可信度评分,动态调整各导航源在融合计算中的权重;The weight adjustment unit dynamically adjusts the weight of each navigation source in the fusion calculation according to the credibility score;误差建模单元,利用改进的卡尔曼滤波算法,对每个导航源的误差特性进行建模;The error modeling unit uses an improved Kalman filter algorithm to model the error characteristics of each navigation source;数据同步融合单元,对不同来源的导航数据进行时间同步并整合,根据动态权重和误差模型计算初步的位姿估计结果;The data synchronization and fusion unit synchronizes and integrates navigation data from different sources, and calculates the preliminary pose estimation results based on the dynamic weight and error model;位姿输出单元,将融合后的初步位姿估计结果输出,为后续路径规划和测绘补偿提供高精度导航信息。The pose output unit outputs the fused preliminary pose estimation results to provide high-precision navigation information for subsequent path planning and surveying compensation.4.根据权利要求3所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,导航源的可信度评分用公式表示为:其中,为第i个导航源的可信度评分,值在[0,1]之间,表示该导航源的可靠性;Wi是第i个导航源对应的权重矩阵;xi为第i个导航源的特征向量;bi是偏置项;4. According to claim 3, a marine surveying and mapping system based on intelligent navigation of a deep-water exploration robot is characterized in that the credibility score of the navigation source is expressed by the formula: in, is the credibility score of the ith navigation source, with a value between [0, 1], indicating the reliability of the navigation source;Wi is the weight matrix corresponding to the ith navigation source;xi is the eigenvector of the ith navigation source;bi is the bias term;各导航源在融合计算中的权重通过以下公式进行动态调整:wi是第i个导航源的权重,与其对应的可信度评分成正比;是所有导航源可信度评分的总和,确保所有权重的和为1,进行归一化处理。The weight of each navigation source in the fusion calculation is dynamically adjusted by the following formula: wi is the weight of the i-th navigation source and its corresponding credibility score is proportional to; It is the sum of the credibility scores of all navigation sources. It is normalized to ensure that the sum of all weights is 1.5.根据权利要求4所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,初步的位姿估计结果用公式表示为:其中,表示融合后的初步位姿估计结果;pi(ti)表示第i个导航源在时间ti时刻的导航数据;是第i个导航源在ti时刻的变化率;ti表示第i个导航源的时间戳;tsync表示目标同步时间;ei(tsync)表示第i个导航源的误差模型在同步时间tsync下的误差估计值;ei表示第i个导航源的误差模型。5. According to claim 4, a marine surveying and mapping system based on intelligent navigation of a deep-water exploration robot is characterized in that the preliminary pose estimation result is expressed by the formula: in, represents the preliminary pose estimation result after fusion; pi (ti ) represents the navigation data of the i-th navigation source at time ti ; is the rate of change of the i-th navigation source at timeti ;ti represents the timestamp of the i-th navigation source; tsync represents the target synchronization time; ei (tsync ) represents the error estimate of the error model of the i-th navigation source at the synchronization time tsync ; ei represents the error model of the i-th navigation source.6.根据权利要求1所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,路径规划模块包括以下组件:6. According to the ocean surveying and mapping system based on intelligent navigation of deep-water exploration robot in claim 1, it is characterized in that the path planning module comprises the following components:任务需求分析单元,根据测绘任务的目标和约束解析任务需求,为路径规划提供任务导向的约束条件;The task requirement analysis unit analyzes the task requirements according to the objectives and constraints of the surveying and mapping task, and provides task-oriented constraints for path planning;环境约束分析单元,基于实时的海底地形数据分析局部地形特征,结合环境感知数据,为路径规划提供环境约束信息;The environmental constraint analysis unit analyzes local terrain features based on real-time seabed terrain data and combines it with environmental perception data to provide environmental constraint information for path planning;路径生成单元,通过强化学习算法,基于当前位姿、任务需求和地形特征,实时学习并生成最优测绘路径;The path generation unit uses a reinforcement learning algorithm to learn and generate the optimal mapping path in real time based on the current position, task requirements and terrain characteristics;路径优化单元,根据质量控制模块生成的重测需求或反馈信息,动态调整当前路径规划,确保路径满足测绘精度和任务要求;The path optimization unit dynamically adjusts the current path planning according to the re-survey requirements or feedback information generated by the quality control module to ensure that the path meets the surveying and mapping accuracy and task requirements;安全监控单元,根据地形分析结果和实时环境感知,实时调整路径,避免碰撞或进入危险区域,确保机器人安全;The safety monitoring unit adjusts the path in real time based on terrain analysis results and real-time environmental perception to avoid collisions or entering dangerous areas, ensuring the safety of the robot;路径输出单元,将优化后的路径转换为控制指令序列,控制机器人执行。The path output unit converts the optimized path into a control instruction sequence to control the robot execution.7.根据权利要求6所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,最优测绘路径通过强化学习的策略π*(sT)逐步生成,用公式表示为:,其中,aT为当前时刻T下的动作,即机器人选择的路径规划决策;w1、w2、w3分别为任务需求、地形适应性及进度优化的权重系数;sT表示机器人在时刻T的状态;Rtask(sT,aT)表示在状态sT下,采取动作aT后的任务奖励,用于评估当前任务需求的完成度;Rterrain(sT,aT)表示在状态sT下,采取动作aT后的地形适应性奖励,用于评估当前路径规划在海底地形上的适应情况;Rprogress(sT,aT)表示在状态sT下,采取动作aT后的进度奖励,用于评估当前路径规划对任务进度的贡献;γ为折扣因子,用于平衡当前奖励与未来奖励之间的关系;V(sT+1)在状态sT+1下,机器人采取最优策略后的值函数,表示从状态sT+1出发所能获得的最大长期奖励。7. The ocean surveying and mapping system based on intelligent navigation of a deep-water exploration robot according to claim 6, characterized in that the optimal surveying and mapping path is gradually generated by a reinforcement learning strategy π* (sT ), which is expressed by the formula: , where aT is the action at the current time T, that is, the path planning decision selected by the robot; w1 , w2 , and w3 are the weight coefficients of task requirements, terrain adaptability, and progress optimization, respectively; sT represents the state of the robot at time T; Rtask (sT , aT ) represents the task reward after taking action aT in state sT , which is used to evaluate the completion of the current task requirements; Rterrain (sT , aT ) represents the terrain adaptability reward after taking action aT in state sT , which is used to evaluate the adaptability of the current path planning on the seabed terrain; Rprogress (sT , aT ) represents the progress reward after taking action aT in state sT , which is used to evaluate the contribution of the current path planning to the task progress; γ is the discount factor, which is used to balance the relationship between current rewards and future rewards; V (sT+1 ) is the value function of the robot after taking the optimal strategy in state sT+1 , which represents the maximum long-term reward that can be obtained starting from state sT+1 .8.根据权利要求1所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,容错控制模块包括以下组件:8. The ocean surveying and mapping system based on intelligent navigation of a deep-water exploration robot according to claim 1, characterized in that the fault-tolerant control module comprises the following components:导航状态监测单元,实时监测各导航源数据的稳定性、准确性和一致性,捕捉潜在的异常信号或失效迹象;The navigation status monitoring unit monitors the stability, accuracy and consistency of each navigation source data in real time and captures potential abnormal signals or failure signs;故障诊断单元,基于多层次诊断算法分析导航源异常的类型和严重性,确定故障原因和影响范围;The fault diagnosis unit analyzes the type and severity of navigation source anomalies based on a multi-level diagnostic algorithm to determine the cause of the fault and the scope of impact;冗余策略管理单元,管理备用导航源和冗余策略库,在主导航源故障时快速切换至次优导航源以维持导航功能;Redundant strategy management unit, which manages backup navigation sources and redundant strategy libraries, and quickly switches to the suboptimal navigation source to maintain navigation function when the primary navigation source fails;降级导航执行单元,在导航源失效或异常情况下,启动备用导航方案,维持基本导航功能;Degraded navigation execution unit, in case of navigation source failure or abnormality, activates backup navigation scheme to maintain basic navigation function;异常数据处理单元,统一处理来自各模块的异常数据,包括数据剔除、异常修正和干扰抑制;Abnormal data processing unit, which uniformly processes abnormal data from each module, including data elimination, abnormal correction and interference suppression;导航性能评估单元,对降级导航模式下的性能进行实时评估,确保其满足最低任务需求,并在条件允许时尝试恢复正常导航模式。The Navigation Performance Evaluation Unit evaluates the performance in the degraded navigation mode in real time to ensure that it meets the minimum mission requirements and attempts to restore the normal navigation mode when conditions permit.9.根据权利要求1所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,地形测绘模块包括以下组件:9. The ocean surveying and mapping system based on intelligent navigation of a deep-water exploration robot according to claim 1, characterized in that the terrain surveying and mapping module comprises the following components:地形数据补偿单元,根据机器人当前位姿信息,对采集的海底地形数据进行实时补偿,修正由于定位误差或传感器偏差带来的数据偏差;The terrain data compensation unit compensates the collected seabed terrain data in real time according to the current posture information of the robot, and corrects the data deviation caused by positioning error or sensor deviation;数据拼接单元,将不同位置和时间段采集的海底地形数据进行拼接,形成一个连续的地形图,确保数据之间的无缝衔接;The data splicing unit splices the seabed topographic data collected at different locations and time periods to form a continuous topographic map, ensuring seamless connection between data;SLAM算法实现单元,基于SLAM算法实时优化机器人位姿与地形数据的关系,建立和更新海底地形的准确地图;SLAM algorithm implementation unit, which optimizes the relationship between the robot's position and terrain data in real time based on the SLAM algorithm, and establishes and updates an accurate map of the seabed terrain;闭环优化单元,通过SLAM算法的闭环检测和修正,对机器人位置的累计误差进行优化,确保地图和定位精度的持续提升;The closed-loop optimization unit optimizes the accumulated error of the robot's position through closed-loop detection and correction of the SLAM algorithm, ensuring continuous improvement of map and positioning accuracy;地形特征分析单元,对海底地形数据进行特征提取和分析,为其他模块提供地形特征信息;The terrain feature analysis unit extracts and analyzes the features of the seabed terrain data and provides terrain feature information for other modules;精度评估与输出单元,对拼接后的地形数据进行精度评估,输出最终的海底地形图,并将定位优化结果提供给其他模块。The accuracy assessment and output unit performs accuracy assessment on the spliced terrain data, outputs the final seabed topographic map, and provides the positioning optimization results to other modules.10.根据权利要求9所述的一种基于深水探测机器人智能导航的海洋测绘系统,其特征在于,通过下述公式来修正由于定位误差或传感器偏差带来的数据偏差:其中,Dfinal为修正后的海底地形数据;(xraw,yraw)为原始海底地形数据的坐标,表示测量数据中海底地形的初始坐标,未经修正;ex,ey为定位误差,分别表示机器人的水平定位误差和垂直定位误差;eθ为姿态误差,表示机器人的朝向误差;θ为机器人朝向;R(eθ)为旋转矩阵,用于修正由于姿态误差eθ导致的地形数据偏差;sx,sy为传感器偏差,分别表示在水平方向和垂直方向上,传感器本身的系统性偏差或误差。10. The ocean surveying and mapping system based on intelligent navigation of a deep-water exploration robot according to claim 9 is characterized in that the data deviation caused by positioning error or sensor deviation is corrected by the following formula: Among them, Dfinal is the corrected seabed topography data; (xraw , yraw ) are the coordinates of the original seabed topography data, which represent the initial coordinates of the seabed topography in the measured data without correction; ex , ey are positioning errors, which represent the horizontal positioning error and vertical positioning error of the robot, respectively; eθ is the attitude error, which represents the orientation error of the robot; θ is the orientation of the robot; R(eθ ) is the rotation matrix, which is used to correct the terrain data deviation caused by the attitude error eθ ; sx ,sy are sensor deviations, which represent the systematic deviation or error of the sensor itself in the horizontal and vertical directions, respectively.
CN202411983401.3A2024-12-312024-12-31 An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robotsWithdrawnCN119573686A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202411983401.3ACN119573686A (en)2024-12-312024-12-31 An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robots

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202411983401.3ACN119573686A (en)2024-12-312024-12-31 An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robots

Publications (1)

Publication NumberPublication Date
CN119573686Atrue CN119573686A (en)2025-03-07

Family

ID=94797927

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202411983401.3AWithdrawnCN119573686A (en)2024-12-312024-12-31 An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robots

Country Status (1)

CountryLink
CN (1)CN119573686A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN119879880A (en)*2025-03-202025-04-25福建省冶金工业设计院有限公司High-precision investigation lofting intelligent positioning system and method based on multi-source data fusion
CN120523050A (en)*2025-07-242025-08-22自然资源部第一海洋研究所 A control method for deploying and recovering deep-sea bottom-touching DC electrical detection cables based on an intelligent detection platform

Citations (9)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN101900558B (en)*2010-06-042012-11-28浙江大学Combined navigation method of integrated sonar micro navigation autonomous underwater robot
CN106896361A (en)*2015-12-172017-06-27中国科学院沈阳自动化研究所A kind of deep water robot multi-model EKF combined navigation devices and method
CN111486845B (en)*2020-04-272022-02-11中国海洋大学AUV multi-strategy navigation method based on submarine topography matching
CN110320520B (en)*2019-06-262022-08-02哈尔滨工程大学 A robust back-end map optimization method for simultaneous positioning and mapping of sounding information
CN116295386A (en)*2023-04-042023-06-23天津慧洋智能装备有限公司Multi-sensor fusion-based underwater vehicle navigation control system and method
CN117232497A (en)*2023-08-252023-12-15哈尔滨工程大学Combined navigation and positioning system and method for dam underwater defect detection robot
CN117606491B (en)*2024-01-242024-04-26中国海洋大学 A combined positioning and navigation method and device for an autonomous underwater vehicle
CN114488164B (en)*2022-01-172024-05-10清华大学深圳国际研究生院Synchronous positioning and mapping method for underwater vehicle and underwater vehicle
CN118225083A (en)*2024-03-282024-06-21苏州明泰智能装备有限公司Robot navigation positioning method based on multi-sensor fusion

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN101900558B (en)*2010-06-042012-11-28浙江大学Combined navigation method of integrated sonar micro navigation autonomous underwater robot
CN106896361A (en)*2015-12-172017-06-27中国科学院沈阳自动化研究所A kind of deep water robot multi-model EKF combined navigation devices and method
CN110320520B (en)*2019-06-262022-08-02哈尔滨工程大学 A robust back-end map optimization method for simultaneous positioning and mapping of sounding information
CN111486845B (en)*2020-04-272022-02-11中国海洋大学AUV multi-strategy navigation method based on submarine topography matching
CN114488164B (en)*2022-01-172024-05-10清华大学深圳国际研究生院Synchronous positioning and mapping method for underwater vehicle and underwater vehicle
CN116295386A (en)*2023-04-042023-06-23天津慧洋智能装备有限公司Multi-sensor fusion-based underwater vehicle navigation control system and method
CN117232497A (en)*2023-08-252023-12-15哈尔滨工程大学Combined navigation and positioning system and method for dam underwater defect detection robot
CN117606491B (en)*2024-01-242024-04-26中国海洋大学 A combined positioning and navigation method and device for an autonomous underwater vehicle
CN118225083A (en)*2024-03-282024-06-21苏州明泰智能装备有限公司Robot navigation positioning method based on multi-sensor fusion

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
常列 等: "基于多传感器信息融合的海底测绘机器人导航系统设计", 《自动化与仪表》, vol. 38, no. 3, 22 March 2023 (2023-03-22), pages 35 - 39*

Cited By (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN119879880A (en)*2025-03-202025-04-25福建省冶金工业设计院有限公司High-precision investigation lofting intelligent positioning system and method based on multi-source data fusion
CN119879880B (en)*2025-03-202025-06-24福建省冶金工业设计院有限公司 High-precision survey and layout intelligent positioning system and method based on multi-source data fusion
CN120523050A (en)*2025-07-242025-08-22自然资源部第一海洋研究所 A control method for deploying and recovering deep-sea bottom-touching DC electrical detection cables based on an intelligent detection platform

Similar Documents

PublicationPublication DateTitle
CN111045068B (en)Low-orbit satellite autonomous orbit and attitude determination method based on non-navigation satellite signals
CN113375666B (en)Sensor fusion positioning system and method
CN119573686A (en) An ocean surveying and mapping system based on intelligent navigation of deep-water exploration robots
CN109471146B (en)Self-adaptive fault-tolerant GPS/INS integrated navigation method based on LS-SVM
CN108168560B (en)Composite navigation control method for omnidirectional AGV
CN109633664A (en)Joint positioning method based on RGB-D Yu laser odometer
CN119618211B (en)Method and system for detecting faults of mining unmanned vehicle
CN111679680A (en) A method and system for autonomous drone landing
CN114166221A (en) Auxiliary transportation robot positioning method and system in dynamic complex mine environment
CN103434610A (en)Docking positioning guiding method for offshore oil drilling platform
CN119472690B (en)Unmanned ship positioning method and system for automatic oiling robot
CN119336043A (en) Multi-source data fusion and dynamic adjustment algorithm and system for complex flight environment
CN120143854B (en)Underwater propeller control method and system based on water environment analysis
CN119879880B (en) High-precision survey and layout intelligent positioning system and method based on multi-source data fusion
CN119987412A (en) An autonomous flight and inspection system for unmanned aerial vehicles based on multi-sensor fusion technology
CN119758412A (en) A distribution line drone autonomous inspection method and system based on GNSS positioning
CN119509531A (en) A spatial positioning method for construction robots based on BIM model
Yan et al.An extrinsic calibration method between LiDAR and GNSS/INS for autonomous driving
CN116300982B (en)Underwater vehicle and path tracking control method and device thereof
CN119245625B (en) Method and system for constructing point cloud map of electric power operation based on inspection robot
Dergachov et al.ANALYSIS OF SYSTEMATIC AND RANDOM COORDINATE ERRORS OF VISUAL LANDMARKS AND THEIR EFFECT ON POSITIONING ALGORITHM ACCURACY
CN120521603A (en)Unmanned aerial vehicle autonomous positioning method under satellite positioning refusing environment
CN120480901A (en) A robot system overall calibration method and system based on multi-sensor collaboration
CN120552077A (en) A robot control method and system for industrial pipelines
CN119901284A (en) A positioning and navigation device for pipe jacking construction

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
WW01Invention patent application withdrawn after publication

Application publication date:20250307

WW01Invention patent application withdrawn after publication

[8]ページ先頭

©2009-2025 Movatter.jp