CN-122005098-A - Mechanical arm positioning method and system suitable for small-cavity tract operation
Abstract
The invention discloses a mechanical arm positioning method and a mechanical arm positioning system suitable for small-cavity surgery, which relate to the technical field of mechanical intelligent control and comprise the steps of acquiring data to perform three-dimensional structure modeling on cavity tissues, constructing a tactile sensing map of the inner wall of the cavity by combining the three-dimensional structure modeling through a circumferential sliding positioning probe, generating a path cost map based on the three-dimensional structure modeling and the tactile sensing map, generating a mechanical arm control scheme according to tissue physiological characteristics by combining an intelligent compliance adjusting function, monitoring deviation of a mechanical arm positioning track in real time and correcting the deviation. By constructing a multidimensional sensing system integrating a structure and tactile information, combining a path control scheme driven by physiological characteristics and a dynamic learning mechanism based on experience feedback, the method for precisely positioning and controlling the manipulator in the small-cavity surgical scene is formed, and the environmental adaptability, path precision and operation safety of the manipulator are improved.
Inventors
- LIU YOUPING
- CHEN MINGYUAN
- XIA CHONGKUN
- WU WENBIN
- YANG JINGRUI
Assignees
- 中山大学附属第五医院
- 中山大学
Dates
- Publication Date
- 20260512
- Application Date
- 20260203
Claims (10)
- 1.A mechanical arm positioning method suitable for small cavity surgery is characterized by comprising the following steps, Collecting data to perform three-dimensional structure modeling on the cavity tissue, and constructing a tactile perception map of the inner wall of the cavity by combining the three-dimensional structure modeling with the annular sliding positioning probe; generating a path cost map based on three-dimensional structure modeling and a tactile perception map, and generating a mechanical arm control scheme according to tissue physiological characteristics by combining an intelligent compliance adjusting function; And (3) monitoring deviation of the positioning track of the mechanical arm in real time, correcting, and driving the model to learn and update by using experience data generated in the operation process.
- 2. The mechanical arm positioning method suitable for small cavity surgery as set forth in claim 1, wherein the acquiring data is used for performing three-dimensional structural modeling on cavity tissues by using a structural light sparse point cloud reconstruction method, a structural scanning module is arranged at the front end of the mechanical arm, a sparse structural light projection mode is adopted for scanning the inner wall surface of the small cavity, and a section of local point cloud is obtained by scanning each time to obtain a section of local point cloud at the ith section of the cavity ; Forming a continuous and complete three-dimensional point cloud model of the inner wall of the cavity by point cloud coordinate registration 。
- 3. The method for positioning the mechanical arm suitable for small-cavity surgery as claimed in claim 2, wherein the step of constructing the cavity inner wall tactile sensation map by combining the annular sliding positioning probe with the three-dimensional structure modeling is characterized in that a tactile probe with a flexible suspension system and annular sliding capacity is arranged at the front end of the mechanical arm, and annular sliding contact is carried out in the cavity to obtain annular tactile data ; Modeling three-dimensional point cloud Voxelization treatment is carried out to generate a structural voxel network V; Each circumferential haptic data Mapping to a corresponding voxel node Calculating an average contact stiffness value for each voxel node ; Finally, the tactile sensation and perception map is obtained 。
- 4. The method for positioning a mechanical arm suitable for small cavity surgery as set forth in claim 3, wherein generating a path cost map based on three-dimensional structure modeling and haptic sensation map means calculating a path cost value of each voxel node ; And obtaining a path cost map C based on the path cost value of the voxel nodes.
- 5. The method for positioning a manipulator for small-cavity surgery as set forth in claim 4, wherein said generating a manipulator control scheme based on tissue physiological characteristics by combining said intelligent compliance adjustment function means constructing a compliance factor for each voxel node by said intelligent compliance adjustment function ; Calculating a new path cost value of each voxel node based on the path cost spectrogram and the soft factor ; Obtaining new path cost map based on new path cost value of voxel node ; According to the new path cost map Obtaining the lowest cost path ; Outputting the lowest cost path Is a mechanical arm control scheme.
- 6. The method for positioning a manipulator for small-cavity surgery as set forth in claim 5, wherein said real-time monitoring of the deviation of the positioning trajectory of the manipulator and correcting means obtaining the position of the distal end of the actuator at the current time in real time by optical tracking Judging the current position in the control scheme The closest waypoint Based on the waypoints And the current position Calculating error vectors ; Setting an error threshold : If it is Greater than or equal to Calculate the correction direction and will As a correction control increment to the actuator; If it is Less than And if not, continuing to push according to the scheme.
- 7. The method for positioning a manipulator for small-cavity surgery according to claim 6, wherein the learning and updating of the model driven by the empirical data generated in the operation process refers to the collection of error data and execution state information of the manipulator in the execution process in real time as an empirical data uploading database, and the model is learned and updated by using the empirical data to establish closed-loop feedback.
- 8. A mechanical arm positioning system suitable for small cavity surgery is characterized by comprising the mechanical arm positioning method suitable for small cavity surgery based on any one of claims 1-7, The data acquisition module is used for acquiring cavity tissue data; the three-dimensional modeling module is used for processing the acquired cavity tissue data and generating a space model for path planning; The positioning probe module is used for acquiring tactile feedback data of the inner wall of the cavity through annular sliding operation; the tactile spectrum construction module is used for combining the tactile information acquired by the probe with the three-dimensional structure model to generate a tactile perception spectrum of the inner wall of the cavity; the path cost map generation module is used for constructing a path cost map by using the three-dimensional structure model and the tactile perception map; the control scheme generation module is used for combining the path cost map and the tissue physiological characteristics and generating a specific mechanical arm track scheme through a flexible adjustment function; And the model learning and updating module is used for learning and parameter updating the control model by utilizing the empirical data accumulated in the operation process.
- 9. A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is characterized in that the processor realizes the steps of the mechanical arm positioning method suitable for small cavity surgery according to any one of claims 1-7 when executing the computer program.
- 10. A computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the steps of a method for positioning a robotic arm suitable for small-cavity surgery as claimed in any one of claims 1 to 7.
Description
Mechanical arm positioning method and system suitable for small-cavity tract operation Technical Field The invention relates to the technical field of mechanical intelligent control, in particular to a mechanical arm positioning method and system suitable for small-cavity surgery. Background With the continuous progress of minimally invasive surgery technology, mechanical arms are increasingly widely used in the medical field, and particularly show remarkable advantages in cavity-type surgery. The mechanical arm has high-precision positioning and repeated operation capability, and can effectively replace complex operation which is difficult to be finished by a human hand in the traditional operation. In recent years, with the development of technologies such as image guidance, sensor fusion, artificial intelligence and the like, key links such as three-dimensional modeling, path planning, multi-modal sensing and the like are remarkably optimized. For example, some systems have been able to reconstruct the luminal environment from endoscopic images and assist the physician in path planning. However, most of the conventional approaches are based on static image data, and the three-dimensional model lacks real-time property and data support highly associated with tissue contact characteristics, resulting in insufficient positioning response capability of the mechanical arm in a flexible tissue or deformed tissue environment. In addition, in the aspect of control strategies, the bottleneck of low intelligent degree and lack of dynamic adjustment still exists, and the adaptability and the precision of the mechanical arm in a complex cavity environment are limited. The prior art still has a plurality of key links to be improved. Firstly, the structure of the cavity tissue is complex and has a certain dynamic variability, the existing modeling method is difficult to realize three-dimensional reconstruction which is highly matched with the actual tissue state, and the comprehensive data support cannot be provided for path planning. Secondly, the inner wall of the cavity is generally provided with stronger physiological differences and tactile response characteristics, but most of the current systems cannot effectively fuse the tactile information and geometric modeling, so that the response capability of path planning to tissue properties is insufficient. In addition, the existing path planning method mostly generates a fixed track based on a static model, and lacks a monitoring and feedback adjustment mechanism for real-time errors in the execution process. Even if part of the system has a deviation correction function, the control model also often depends on manual parameter adjustment, and the capability of autonomous learning and updating by using operation experience is lacking. Therefore, how to realize dynamic modeling of the cavity tissue, construct a path cost map integrating the tactile sensation, and adjust the control strategy by combining with the physiological characteristics, so as to realize real-time error correction and model learning update in the execution process becomes an important problem to be solved in the technical field. Disclosure of Invention The present invention has been made in view of the above-described problems occurring in the prior art. Therefore, the invention provides a mechanical arm positioning method and a mechanical arm positioning system suitable for small-cavity surgery, which solve the problem that the path planning and accurate positioning of the mechanical arm in the small-cavity surgery are limited by insufficient structural modeling and tactile perception coupling. In order to solve the technical problems, the invention provides the following technical scheme: In a first aspect, the invention provides a mechanical arm positioning method suitable for small-cavity surgery, which comprises the steps of acquiring data to perform three-dimensional structure modeling on cavity tissues, and constructing a tactile perception map of the inner wall of a cavity by combining a circumferential sliding positioning probe with the three-dimensional structure modeling; generating a path cost map based on three-dimensional structure modeling and a tactile perception map, and generating a mechanical arm control scheme according to tissue physiological characteristics by combining an intelligent compliance adjusting function; And (3) monitoring deviation of the positioning track of the mechanical arm in real time, correcting, and driving the model to learn and update by using experience data generated in the operation process. The mechanical arm positioning method suitable for small cavity surgery is characterized in that the acquisition data is used for carrying out three-dimensional structure modeling on cavity tissues by using a structured light sparse point cloud reconstruction method, a structure scanning module is arranged at the front end of the mechanical arm, a sparse structu