The problem of real-time motion planning

The robot motion planning is generally solved before the robot actually executes the desired motions and in case of motions that must avoid obstacles, this approach may work with static obstacles only. 

If, instead, obstacles are moving, the desired motion must be calculated in real-time, a few milliseconds before its execution.

 The setup used for the experiments. SARAS, Smart Autonomous Robotic Assistant Surgeon.
Read More

A surgical robot with cognitive functions

SARAS will develop a cognitive architecture able to make decisions based on pre-operative knowledge and on scene understanding via advanced machine learning algorithms.

Training Data Collection – Assistant surgeon’s master console.

Dexterity and perception capabilities of surgical robots may soon be improved by cognitive functions that can support surgeons in decision making and performance monitoring, and enhance the impact of automation within the operating rooms.

Read More