Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration
Distal-end force information is usually missing in flexible endoscopic robots due to the difficulties of mounting miniature force sensors on their end-effectors. This hurdle creates big challenges in providing a sense of touch for the operating surgeons. Many existing studies have developed models t...
| Váldodahkkit: | , , , , , |
|---|---|
| Eará dahkkit: | |
| Materiálatiipa: | Journal Article |
| Giella: | English |
| Almmustuhtton: |
2020
|
| Fáttát: | |
| Liŋkkat: | https://hdl.handle.net/10356/137860 |
| _version_ | 1826119997120839680 |
|---|---|
| author | Li, Xiaoguo Tiong, Anthony Meng Huat Cao, Lin Lai, Wenjie Phan, Phuoc Thien Phee, Soo Jay |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Li, Xiaoguo Tiong, Anthony Meng Huat Cao, Lin Lai, Wenjie Phan, Phuoc Thien Phee, Soo Jay |
| author_sort | Li, Xiaoguo |
| collection | NTU |
| description | Distal-end force information is usually missing in flexible endoscopic robots due to the difficulties of mounting miniature force sensors on their end-effectors. This hurdle creates big challenges in providing a sense of touch for the operating surgeons. Many existing studies have developed models to calculate the distal-end forces based on the measured proximal-end forces of Tendon-Sheath Mechanisms (TSMs), but these models assume known sheath bending configuration which is unknown during real-life surgeries. This paper presents a two-stage data-driven method that makes dynamic distal-end force prediction of a flexible endoscopic robot without this assumption. In stage one, a convolutional neural network is used to estimate the sheath cumulative bending angle based on the proximal-end force responses of the robot to a probing signal; in stage two, a combination of two long-short-term-memory models pre-trained for the bending angles nearest to the estimated angle (obtained in stage one) makes dynamic estimations of the distal-end force of the robot. The proposed approach overcomes the challenges due to unknown TSM configurations and can robustly identify the correct force hysteresis phases of TSMs. The force prediction is continuous, accurate, and has a mean RMSE of 0.1711 N. This method was validated on an actual flexible surgical robot. In addition, since the proposed approach provides an estimation of the current system cumulative bending angle, it can also be used to facilitate the mathematical modeling methods which require information on the cumulative bending angle. |
| first_indexed | 2024-10-01T05:09:19Z |
| format | Journal Article |
| id | ntu-10356/137860 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:09:19Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1378602023-03-04T17:21:16Z Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration Li, Xiaoguo Tiong, Anthony Meng Huat Cao, Lin Lai, Wenjie Phan, Phuoc Thien Phee, Soo Jay School of Mechanical and Aerospace Engineering Robotics Research Centre Engineering::Mechanical engineering::Robots Flexible Endoscopic Surgical Robots Tendon-sheath Mechanisms Distal-end force information is usually missing in flexible endoscopic robots due to the difficulties of mounting miniature force sensors on their end-effectors. This hurdle creates big challenges in providing a sense of touch for the operating surgeons. Many existing studies have developed models to calculate the distal-end forces based on the measured proximal-end forces of Tendon-Sheath Mechanisms (TSMs), but these models assume known sheath bending configuration which is unknown during real-life surgeries. This paper presents a two-stage data-driven method that makes dynamic distal-end force prediction of a flexible endoscopic robot without this assumption. In stage one, a convolutional neural network is used to estimate the sheath cumulative bending angle based on the proximal-end force responses of the robot to a probing signal; in stage two, a combination of two long-short-term-memory models pre-trained for the bending angles nearest to the estimated angle (obtained in stage one) makes dynamic estimations of the distal-end force of the robot. The proposed approach overcomes the challenges due to unknown TSM configurations and can robustly identify the correct force hysteresis phases of TSMs. The force prediction is continuous, accurate, and has a mean RMSE of 0.1711 N. This method was validated on an actual flexible surgical robot. In addition, since the proposed approach provides an estimation of the current system cumulative bending angle, it can also be used to facilitate the mathematical modeling methods which require information on the cumulative bending angle. Accepted version 2020-04-16T08:51:51Z 2020-04-16T08:51:51Z 2019 Journal Article Li, X., Tiong, A. M. H., Cao, L., Lai, W., Phan, P. T., & Phee, S. J. (2019). Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration. International Journal of Mechanical Sciences, 163, 105129-. doi:10.1016/j.ijmecsci.2019.105129 0020-7403 https://hdl.handle.net/10356/137860 10.1016/j.ijmecsci.2019.105129 2-s2.0-85071974136 163 en International Journal of Mechanical Sciences © 2019 Elsevier Ltd. All rights reserved. This paper was published in International Journal of Mechanical Sciences and is made available with permission of Elsevier Ltd. application/pdf |
| spellingShingle | Engineering::Mechanical engineering::Robots Flexible Endoscopic Surgical Robots Tendon-sheath Mechanisms Li, Xiaoguo Tiong, Anthony Meng Huat Cao, Lin Lai, Wenjie Phan, Phuoc Thien Phee, Soo Jay Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| title | Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| title_full | Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| title_fullStr | Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| title_full_unstemmed | Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| title_short | Deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| title_sort | deep learning for haptic feedback of flexible endoscopic robot without prior knowledge on sheath configuration |
| topic | Engineering::Mechanical engineering::Robots Flexible Endoscopic Surgical Robots Tendon-sheath Mechanisms |
| url | https://hdl.handle.net/10356/137860 |
| work_keys_str_mv | AT lixiaoguo deeplearningforhapticfeedbackofflexibleendoscopicrobotwithoutpriorknowledgeonsheathconfiguration AT tionganthonymenghuat deeplearningforhapticfeedbackofflexibleendoscopicrobotwithoutpriorknowledgeonsheathconfiguration AT caolin deeplearningforhapticfeedbackofflexibleendoscopicrobotwithoutpriorknowledgeonsheathconfiguration AT laiwenjie deeplearningforhapticfeedbackofflexibleendoscopicrobotwithoutpriorknowledgeonsheathconfiguration AT phanphuocthien deeplearningforhapticfeedbackofflexibleendoscopicrobotwithoutpriorknowledgeonsheathconfiguration AT pheesoojay deeplearningforhapticfeedbackofflexibleendoscopicrobotwithoutpriorknowledgeonsheathconfiguration |