top of page
Research Projects
We advance the social and behavioral understanding of integrating sociotechnical systems including robots, artificial intelligence, and augmented reality (AR) in safety-critical environments with a particular focus on healthcare. Our research agenda involves designing, building, and deploying robots and developing AR applications for SCEs which are challenging to access to evaluate new technologies and practitioners are often overworked and experience physiological strain due to treating critical patients.
Human-Robot Interaction
Participatory Design &
Rapid Prototyping
Healthcare workers are often overburdened with non-value-added tasks that detract from patient care. Robots offer promising solutions to alleviate these burdens and improve healthcare outcomes. To explore this potential, we conducted a long-term co-ideation workshop series comprising 14 sessions over three months with more than 20 participants. These workshops brought together diverse community members, including healthcare workers and non-healthcare stakeholders, to co-create robot solutions for three key healthcare settings: emergency departments, long-term care facilities, and sleep clinics.
Human-Robot Interaction
Robot Perception and Decision-Making Algorithms
As mobile robots work side-by-side with their human teammates, they require computer vision techniques that enable them to perceive groups. To achieve this goal, we develop computer vision algorithms for mobile robots (i.e., robot vision) operating in real-world environments to enable them to sense and perceive people around them and make sense of their actions. Our robot vision algorithms are robust to real-world vision challenges such as occlusion, camera egomotion, shadow, and varying lighting illuminations. We hope this work will enable the development of robots that can more effectively locate and perceive their teammates, particularly in uncertain, unstructured environments.
Hospital teams in the emergency ward are usually made up of experts with different skill sets and specialties. In such a diverse team of healthcare workers, real-world events like role switching between healthcare workers (HCWs) during tasks, assigning tasks toHCWs outside their specialities due to insufficient human resources, and task dependencies pose significant challenges that could hinder optimal patient outcomes due to time delays. In this research, we introduce the MARLAgentHospital as a benchmark environment to provide a systemic evaluation of different classes of MARL algorithms (independent learning and value decomposition) and quantify the effects of changes in team dynamics, roles and skills in safety-critical environments.
The effective deployment of robots in risky, crowded environments requires the specification of robot plans that are consistent with humans' behaviors and models of risk using robot sensor data. As is well known, humans perceive uncertainty and risk in a biased way, which can lead to a diversity of actions and expectations when interacting with others. We develop perception algorithms that enable robots to perceive risk in safety-critical environments to make intelligent navigation decisions. Our hope is that risk-aware navigation algorithms enable robots to operate safely and avoid introducing new errors in safety-critical environments.
Human-Computer/AI Interaction
AI-Driven Technologies that Promote Teamwork & Mental Health
The Emergency Room (ER) is a high-pressure environment where medical procedures require effective team communication and timely decision-making to ensure high-quality patient care. Research shows that augmented reality head-mounted displays (AR-HMDs) can improve decision-making by reducing cognitive load and enhancing shared mental models primarily in well-controlled healthcare settings such as surgery and operations management. Despite their potential benefits, limited research exists on the design of AR-HMDs for action teams including what, how, and when interfaces with decision-making information can facilitate coordination among teams in ER procedures and is the focus of our research.
According to a 2023 report, young adults (ages 18-25) experience anxiety and depression at nearly twice the rate of teenagers. To address this problem, researchers and commercially available products have developed interventions, including artificially intelligent (AI) conversational chatbots and virtual avatars, to reduce mental health issues. Our goal is to effectively engage young adult users long-term through personalized, cognitive behavioral therapy practices outside of therapy sessions in XR environments.
Designing robots to support high-stakes teamwork in emergency settings presents unique challenges, including seamless integration into fast-paced environments, facilitating effective communication among team members, and adapting to rapidly changing situations. While teleoperated robots have been successfully used in high-stakes domains such as firefighting and space exploration, autonomous robots that aid high-stakes teamwork remain underexplored. To address this gap, we conducted a rapid prototyping process to develop a series of seemingly autonomous robot designed to assist clinical teams in the Emergency Room.
bottom of page