A First Evaluation of a Multi-Modal Learning System to Control Surgical Assistant Robots via Action Segmentation
- Resource Type
- Periodical
- Authors
- De Rossi, G.; Minelli, M.; Roin, S.; Falezza, F.; Sozzi, A.; Ferraguti, F.; Setti, F.; Bonfe, M.; Secchi, C.; Muradore, R.
- Source
- IEEE Transactions on Medical Robotics and Bionics IEEE Trans. Med. Robot. Bionics Medical Robotics and Bionics, IEEE Transactions on. 3(3):714-724 Aug, 2021
- Subject
- Bioengineering
Robotics and Control Systems
Computing and Processing
Robots
Surgery
Task analysis
Safety
Robot kinematics
Manipulators
Laparoscopes
Medical robotics
cognitive robotics
R-MIS
action segmentation
model-predictive control
- Language
- ISSN
- 2576-3202
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 cognitive control architecture that uses a multi-modal neural network trained on a cooperative task performed by human surgeons and produces an action segmentation that provides the required timing for actions while maintaining full phase execution control via a deterministic Supervisory Controller and full execution safety by a velocity-constrained Model-Predictive Controller.