Assistive machines such as robotic arms and powered wheelchairs promote independence and ability in those with severe motor impairments. As the field of assistive robotics progresses rapidly, these devices are becoming more capable and dextrous and as a result, higher dimensional and harder to control. The dimensionality mismatch between high-dimensional robots and low-dimensional control interfaces requires the control space to be partitioned into control modes. For full control of the robot the user switches between these partitions and this is known as mode switching.

Real world applications often naturally decompose into several sub-tasks. In many settings (e.g., robotics) demonstrations provide a natural way to specify the sub-tasks. However, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the subtasks can be safely recombined or limit the types of composition available.

This project will design and implement a domain-specific language and compiler for microfluidic laboratory-on-a-chip (LoC) devices based on electrowetting-on-dielectric (EWoD) technology. The Lead PI’s team has designed and implemented BioScript, a domain-specific programming language for programmable microfluidics. The BioScript syntax is programmer friendly, with the intention of being accessible to biologists and other researchers and practitioners in the life sciences.

Abstract: With nearly 10 million individuals carrying a diagnosis of Parkinson’s disease across the globe. Individuals with Parkinson’s disease experience tremors, rigidity, slowness of movement, and difficulties with walking and driving. Currently these individuals are required to attend weekly visits to the doctor's office for consistent reassessment regarding progression of the disease.

This is a collaborative research project between Washington University in St. Louis, Michigan State University and University of Nevada Reno and is investigating a cyber-physical framework for scalable, long-term monitoring and condition-based maintenance of civil infrastructures. Civil infrastructure constitutes a network of interdependent systems and utilities (e.g., highways, bridges, rail systems, buildings) that are necessary for supporting social and economic activities.

Within hazard and disaster response and recovery management, the National Incident Management System (NIMS) has become the dominant organizational model for incident response. The Incident Command System (ICS) provides report and operational templates that structure activities and resources during an incident or event. In an emergency situation, information can be sometimes contradictory and may even not be “clean”.

Abstract: This project is addressing how cyber physical walking systems (CPWS) can be designed to be safe, secure, and resilient despite a variety of unanticipated disturbances and how real-time dynamic control and behavior adaptation can be achieved in a diversity of environments.

Teams comprised of both humans and robots are increasingly becoming a reality. A key barrier to enabling teams fluently working together is that leadership roles of humans and robots are often determined a priori. In successful human-human teams, we find that leadership is an emergent behavior where team members can adaptively take, give up, or share leadership based on changing tasks or environments. To create human-robot teams capable of long-term interactions in dynamically changing environments, they need to be able to fluidly adapt leader and follower roles.