Computer scientists at the University of California at San Diego have developed a more precise navigation system that will allow robots to better negotiate busy clinical environments in general and emergency services more specifically. The researchers also developed an open source video dataset to help train robotic navigation systems in the future.
The team, led by Professor Laurel Riek and Ph.D. Student Angelique Taylor, detail their findings in an article for the International Conference on Robotics and Automation to be held May 30-June 5 in Xi’an , in China.
The project was born out of conversations with clinicians over several years. The consensus was that robots would best help doctors, nurses and emergency department staff by delivering supplies and equipment. But that does mean robots need to know how to avoid situations where clinicians are busy caring for a critically or critically ill patient.
“To perform these tasks, robots must understand the context of complex hospital environments and the people who work around them,” said Riek, who holds both computer and emergency medicine roles at UC. San Diego.
Taylor and his colleagues built the navigation system, the Safety Critical Deep Q-Network (SafeDQN), around an algorithm that takes into account the number of people gathered in a space and the speed and abruptness of those people. This is based on observations of the behavior of clinicians in the emergency department. When a patient’s condition worsens, a team immediately gathers around them to provide assistance. The movements of clinicians are fast, alert and precise. The navigation system orders the robots to move around these grouped groups of people, staying out of the way.
“Our system was designed to deal with the worst-case scenarios that can arise in an emergency,” said Taylor, who is part of Riek’s healthcare robotics lab in the computer science and engineering department of the ‘UC San Diego.
The team trained the algorithm on YouTube videos, mostly from documentaries and reality shows, such as “Trauma: Life in the ER” and “Boston EMS”. The set of more than 700 videos is available for other research teams to train other algorithms and robots.
The researchers tested their algorithm in a simulation environment and compared its performance to other advanced robotic navigation systems. The SafeDQN system generated the most efficient and secure paths in all cases.
The next steps include testing the system on a physical robot in a realistic environment. Riek and his colleagues plan to partner with researchers at UC San Diego Health who operate the campus healthcare training and simulation center.
The algorithms could also be used outside the emergency department, for example during search and rescue missions.
Source of the story:
Material provided by University of California – San Diego. Note: Content can be changed for style and length.