A First Evaluation of a Multi-Modal Learning System to Control Surgical Assistant Robots via Action Segmentation

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 exert considerable physical strain. To guarantee the highest possible safety standards, best approach devise a deterministic automaton performs identically each operation. Clearly, such inevitably fails adapt itself changing environments or different companions. In surgical scenario, variability happens timing actions performed within same phases. This paper presents cognitive control architecture uses multi-modal neural network trained on cooperative task by surgeons produces an action segmentation provides required while maintaining full phase execution via Supervisory Controller velocity-constrained Model-Predictive Controller.