2019 Fiscal Year Research-status Report
Real-time adaptive control of robots for microsurgery: towards submillimeter accuracy without added sensors
| Project/Area Number |
19K14935
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Keywords | 手術ロボット / 適応制御 / 画像処理 / ロボティクス |
|---|
| Outline of Annual Research Achievements |
The online calibration of surgical instruments using endoscopic images is being investigated.
(1) A method for recognizing and tracking the shaft of surgical instruments on endoscopic images using deep learning was developed. A preliminary evaluation shows state-of-the-art results. Further validation is required.
(2) The theoretical derivation of the adaptative controller equations taking into account workspace constraints has been finalized.
(3) Proof-of-concept simulations showed good results for the online calibration of instruments.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
From April 2019, the SmartArm system was validated in teleoperation experiments, and the collision-avoidance algorithm was improved.
By September 2019, an algorithm for tracking the robotic instruments' shafts in real endoscopic images was developed. After that, the development of the tracking of the whole instrument has begun.
In April 2019, an initial version of the adaptive control algorithm was developed. From February 2020, a new and improved version of the adaptive control algorithm is being studied.
|
| Strategy for Future Research Activity |
Further studies will be done to increase the quality of the shaft tracking algorithm. The shaft tracking algorithm will be quantitatively evaluated in experiments. Moreover, the shaft tracking algorithm will be integrated with the current adaptive controller to assess the proposed online calibration strategy preliminarily.
In parallel, the complete tracking of the surgical instrument will also be investigated.
|
| Causes of Carryover |
The resources are required for manufacturing tool adapters for the robot and machining materials, 3D printer materials for tool adapters, mockup tools, and realistic head models. Moreover, funds will be used for participation and presentation in respected conferences in Japan, in world-renowned conferences, and for editing and proofreading research papers.
|
Research Products
(3 results)
