Machine-learned network for medical robot generation from configurable modules

Abstract

A generative adversarial network (GAN) (), or any other generative modeling technique, is used to learn () how to generate () an optimal robotic system given performance, operation, safety, or any other specifications. For instance, the specifications may be modeled () relative to anatomy to confirm satisfaction of anatomy-based or another task specific constraint. A machine-learning system, for instance neural network, is trained () to translate given specifications to a robotic configuration. The network may convert task-specific specifications into one or more configurations of robot modules into a robotic system. The user may enter () changes to performance in order for the network to estimate () appropriate configurations. The configurations may be converted () to estimated performance by another machine-learning system, for instance neural network, allowing modeling () of operation relative to the anatomy, such as anatomy based on medical imaging. The configuration satisfying the constraints from the modeling () may be assembled () and used.