An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection
Autonomous intravitreal injection in ophthalmology is a challenging surgical task as accurate depth measurement is difficult due to the individual differences in the patient’s eye and the intricate light reflection or refraction of the eyeball, often requiring the surgeon to first preposition the en...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/24/4184 |
| _version_ | 1797460014197112832 |
|---|---|
| author | Xiangdong He Hua Luo Yuliang Feng Xiaodong Wu Yan Diao |
| author_facet | Xiangdong He Hua Luo Yuliang Feng Xiaodong Wu Yan Diao |
| author_sort | Xiangdong He |
| collection | DOAJ |
| description | Autonomous intravitreal injection in ophthalmology is a challenging surgical task as accurate depth measurement is difficult due to the individual differences in the patient’s eye and the intricate light reflection or refraction of the eyeball, often requiring the surgeon to first preposition the end-effector accurately. Image-based visual servo (IBVS) control does not rely on depth information, exhibiting potential for addressing the issues mentioned above. Here we describe an enhanced IBVS strategy to achieve high performance and robust autonomous injection navigation. The radial basis function (RBF) kernel with strong learning capability and fast convergence is used to globally map the uncertain nonlinear strong coupling relationship in complex uncalibrated IBVS control. The Siamese neural network (SNN) is then used to compare and analyze the characteristic differences between the current and target poses, thus making an approximation of the mapping relationships between the image feature changes and the end-effector motion. Finally, a robust sliding mode controller (SMC) based on min–max robust optimization is designed to implement effective surgical navigation. Data from the simulation and the physical model experiments indicate that the maximum localization and attitude errors of the proposed method are 0.4 mm and 0.18°, exhibiting desirable accuracy with the actual surgery and robustness to disturbances. These results demonstrate that the enhanced strategy can provide a promising approach that can achieve a high level of autonomous intravitreal injection without a surgeon. |
| first_indexed | 2024-03-09T16:59:50Z |
| format | Article |
| id | doaj.art-fc3670f991124a6fa051c3f9f97d49e7 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T16:59:50Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-fc3670f991124a6fa051c3f9f97d49e72023-11-24T14:31:48ZengMDPI AGElectronics2079-92922022-12-011124418410.3390/electronics11244184An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal InjectionXiangdong He0Hua Luo1Yuliang Feng2Xiaodong Wu3Yan Diao4School of Mechanical Engineering, Sichuan University, Chengdu 610065, ChinaSchool of Mechanical Engineering, Sichuan University, Chengdu 610065, ChinaAier School of Ophthalmology, Central South University, Changsha 410000, ChinaSchool of Mechanical Engineering, Sichuan University, Chengdu 610065, ChinaSchool of Mechanical Engineering, Sichuan University, Chengdu 610065, ChinaAutonomous intravitreal injection in ophthalmology is a challenging surgical task as accurate depth measurement is difficult due to the individual differences in the patient’s eye and the intricate light reflection or refraction of the eyeball, often requiring the surgeon to first preposition the end-effector accurately. Image-based visual servo (IBVS) control does not rely on depth information, exhibiting potential for addressing the issues mentioned above. Here we describe an enhanced IBVS strategy to achieve high performance and robust autonomous injection navigation. The radial basis function (RBF) kernel with strong learning capability and fast convergence is used to globally map the uncertain nonlinear strong coupling relationship in complex uncalibrated IBVS control. The Siamese neural network (SNN) is then used to compare and analyze the characteristic differences between the current and target poses, thus making an approximation of the mapping relationships between the image feature changes and the end-effector motion. Finally, a robust sliding mode controller (SMC) based on min–max robust optimization is designed to implement effective surgical navigation. Data from the simulation and the physical model experiments indicate that the maximum localization and attitude errors of the proposed method are 0.4 mm and 0.18°, exhibiting desirable accuracy with the actual surgery and robustness to disturbances. These results demonstrate that the enhanced strategy can provide a promising approach that can achieve a high level of autonomous intravitreal injection without a surgeon.https://www.mdpi.com/2079-9292/11/24/4184visual servoneural networksliding mode control |
| spellingShingle | Xiangdong He Hua Luo Yuliang Feng Xiaodong Wu Yan Diao An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection Electronics visual servo neural network sliding mode control |
| title | An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection |
| title_full | An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection |
| title_fullStr | An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection |
| title_full_unstemmed | An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection |
| title_short | An Uncalibrated Image-Based Visual Servo Strategy for Robust Navigation in Autonomous Intravitreal Injection |
| title_sort | uncalibrated image based visual servo strategy for robust navigation in autonomous intravitreal injection |
| topic | visual servo neural network sliding mode control |
| url | https://www.mdpi.com/2079-9292/11/24/4184 |
| work_keys_str_mv | AT xiangdonghe anuncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT hualuo anuncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT yuliangfeng anuncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT xiaodongwu anuncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT yandiao anuncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT xiangdonghe uncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT hualuo uncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT yuliangfeng uncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT xiaodongwu uncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection AT yandiao uncalibratedimagebasedvisualservostrategyforrobustnavigationinautonomousintravitrealinjection |