A Multi-Modal Learning System for Action Segmentation to Control Assistant Surgeon Robots
| Main Authors: | Giacomo De Rossi, Serena Roin, Fabio Falezza, Francesco Setti, Riccardo Muradore |
|---|---|
| Format: | Proceeding Journal |
| Terbitan: |
, 2020
|
| Subjects: | |
| Online Access: |
https://youtu.be/9nlIgybd264
https://www.youtube.com/watch?v=B9L6-XimhE0 |
Daftar Isi:
- The next stage for robotics development is to introduce autonomy and cooperation with human agents in tasks that require high levels of precision and/or that exert considerable physical strain. To guarantee the highest possible safety standards, the best approach is to devise a deterministic automaton that performs identically for each operation. Clearly, such approach inevitably fails to adapt itself to changing environments or different human companions. In a surgical scenario, the highest variability happens for the timing of different actions performed within the same phases. This paper presents a multi-modal action segmentation system that operates online to specifically target semi-autonomous assistive robotic platforms during RoboticMinimally Invasive Surgery (R-MIS). It provides the required timing for the actions being performed to direct the lower-level control of the assistant robot through supervisory control.