End-Effector Contact and Force Detection for Miniature Autonomous Robots Performing Lunar and Expeditionary Surgery
| Autor: | Priscila R. Armijo, Dmitry Oleynikov, Shane Farritor, Laura E. Flores, Eric T. Psota, Nathan Bills, Jay D. Carlson, Ka Chun Siu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
medicine.medical_specialty
Active duty Computer science 030230 surgery Task (project management) law.invention Contact force 03 medical and health sciences 0302 clinical medicine law medicine Torque Humans 030212 general & internal medicine Moon business.industry Public Health Environmental and Occupational Health Robotics General Medicine Robot end effector Automation Surgery Aerospace Medicine Robot Artificial intelligence business |
| Zdroj: | Military medicine. 186(Suppl 1) |
| ISSN: | 1930-613X |
| Popis: | Introduction The U.S. Space Force was stood up on December 20, 2019 as an independent branch under the Air Force consisting of about 16,000 active duty and civilian personnel focused singularly on space. In addition to the Space Force, the plans by NASA and private industry for exploration-class long-duration missions to the moon, near-earth asteroids, and Mars makes semi-independent medical capability in space a priority. Current practice for space-based medicine is limited and relies on a “life-raft” scenario for emergencies. Discussions by working groups on military space-based medicine include placing a Role III equivalent facility in a lunar surface station. Surgical capability is a key requirement for that facility. Materials and Methods To prepare for the eventuality of surgery in space, it is necessary to develop low-mass, low power, mini-surgical robots, which could serve as a celestial replacement for existing terrestrial robots. The current study focused on developing semi-autonomous capability in surgical robotics, specifically related to task automation. Two categories for end-effector tissue interaction were developed: Visual feedback from the robot to detect tissue contact, and motor current waveform measurements to detect contact force. Results Using a pixel-to-pixel deep neural network to train, we were able to achieve an accuracy of nearly 90% for contact/no-contact detection. Large torques were predicted well by a trained long short-term memory recursive network, but the technique did not predict small torques well. Conclusion Surgical capability on long-duration missions will require human/machine teaming with semi-autonomous surgical robots. Our existing small, lightweight, low-power miniature robots perform multiple essential tasks in one design including hemostasis, fluid management, suturing for traumatic wounds, and are fully insertable for internal surgical procedures. To prepare for the inevitable eventuality of an emergency surgery in space, it is essential that automated surgical robot capabilities be developed. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|