Mechanical Engineer Perfecting the Performance of Surgical Robotics

 

Dr. Ann Majewicz Fey knows that nobody is perfect.

But with a five-year, $500,000 grant from the National Science Foundation (NSF), Fey hopes she can help surgeons perform as close to perfect as possible in operating rooms.

Fey, an assistant professor of mechanical engineering in the Erik Jonsson School of Engineering and Computer Science at The University of Texas at Dallas, received an NSF Faculty Early Career Development (CAREER) Award for her project, Human-Centric Control for Teleoperated Surgical Robots. The goal is to build safer and more effective robots designed to interpret and react to the dynamic human operator.

“I think of our work as the human and the robot becoming one,” Fey said. “The human is good at intuition and understanding the big picture in surgery, but the robot is good at being repeatable and inherently safe. Can we design this system so that the surgeon and the robot learn from each other as they go, leveraging each other’s strengths and fixing the other’s weaknesses?”

Teleoperated robots are remotely controlled machines that communicate through a computer. Typically, there are two machines: One robot takes commands from a human operator, and the other robot executes that command exactly as instructed. In the past decade, such machines have become popular in surgery because the robotic arms have the ability to reach tight places where human hands can’t operate. Now, there is an opportunity to integrate these robots with artificial intelligence to improve how they behave.

“This work could lead to significant improvements in the adaptability, capability and usability of teleoperated surgical systems when collaborating with a human user,” Fey said.

Teleoperated surgical robots generally work well but are not foolproof. Fey and her team are trying to prevent mishaps in the operating room. 

“We want to help guide a surgeon’s hands through critical situations with the help of intuitive robots that will first warn him or her of potential dangers the patient may be experiencing, and then help remedy the situation,” Fey said. “For example, if a surgeon encounters unexpected bleeding, the robot will then communicate to the surgeon on the preferred course of action. The decision is calculated through a series of machine learning and control algorithms, and is communicated to the surgeon through haptic feedback, such as a vibration.”

The human element plays a key role in developing such a surgical system.

“Human behavior can be an unpredictable factor and can change as a result of uncertainties and environmental, physical and emotional stress,” Fey said. “We are building real-time, data-driven predictions and interpretations of human intent, surgical style and level of expertise.

“We want to help surgeons of all levels of expertise perform tasks better and feel more confident doing so. Systems that are aware and responsive to user skill and performance could help avoid errors and respond to adverse events more quickly than the human operator could.”

Fey hopes her work will have a large impact.

“This project in the long run will promote the progress of science and advance national health by exploring fundamental relationships between human behavior, motor control and machine manipulation,” she said.