ABCDEF
1
 Robotics Seminar, Spring 2022 (CSE 290-D00)
Prof. Laurel Riek, lriek@eng.ucsd.edu
Mondays, 1pm-1:50pm PT
2
3/28/22
Dr. Angelique Taylor
Meta Reality Labs Research & Cornell University 		Perception and Decision-Making Systems for Human-Robot Teaming in Safety-Critical EnvironmentsDr. Angelique Taylor is a Visiting Research Scientist at Meta Reality Labs Research and incoming Assistant Professor at Cornell Tech this summer. She received her Ph.D. in Computer Science and Engineering from the University of California San Diego in 2021. Her research lies at the intersection of robotics, computer vision, and artificial intelligence. Her research lab designs intelligent systems that work alongside groups of people in real-world, safety-critical environments (e.g., healthcare). These systems are realized through multi-robot systems, robot vision systems, AI, and augmented and virtual reality devices. She has received the NSF GRFP, Microsoft Dissertation Award, the Google Anita Borg Memorial Fellowship, the Arthur J. Schmitt Presidential Fellowship, a GEM Fellowship, and an award from the National Center for Women in Information Technology (NCWIT). More information on her research can be found at angeliquemtaylor.com.In this talk, I will present my current and future work on developing perception and decision-making systems that enable robots to team with groups of people. My core focus is on problems that robots encounter in human-robot teaming, including perceptions of human groups and social navigation, particularly in safety-critical environments. First, I will discuss how I developed computer vision methods that enable robots to detect and track their teammates in real-world environments. Most group perception methods employ fixed, overhead cameras (i.e., an exo-centric / third-person perspective) to sense groups of people, rendering them impractical for mobile robots working in most settings. I have developed a group detection and tracking system designed for ego-centric (i.e., first-person) perspective sensing, which is more suitable for mobile robots, to enable them to enter any environment and accomplish their goals without external sensing requirements. Next, I will discuss this work contextualized within a real-world application: human-robot teaming in healthcare. I am developing systems for hospital Emergency Departments (ED), where frontline healthcare workers have been overwhelmed by the COVID-19 pandemic. I will describe my work characterizing ED care delivery and staff workflow to enable robots to operate in these challenging environments. Building on this, I designed a social navigation system that enables robots to incorporate the severity of patients' health while navigating in the ED, to prevent interruptions in care delivery. My work will enable robots to work in safety-critical, human-centered environments, and ultimately help improve patient outcomes and alleviate clinician workload.
3
4/4/22
Dr. Kris Dorsey
Northeastern University		Sensing and active compression challenges for monitoring persistent edema Dr. Kris Dorsey is an Associate Professor in the Electrical and Computer Engineering and Physical Therapy, Movement, and Rehabilitation Sciences departments at Northeastern University. She is also currently an MLK Visiting Associate Professor at MIT in the Media Lab. She was a President’s Postdoctoral Fellow at the University of California, Berkeley and University of California, San Diego. Dr. Dorsey graduated from Carnegie Mellon University with a Ph.D. in Electrical and Computer Engineering and earned her Bachelors of Science in Electrical and Computer Engineering from Olin College. Her current research interests include novel morphology soft sensors, stability concerns for soft-material sensors, and sensors for soft robots and wearable medical devices. Physically-soft mechanical sensors and actuators are poised to unlock exciting new applications in wearable devices, robotics, and human-machine interfaces. One application where such sensors can make a difference is in diagnosing or monitoring health conditions such as persistent edema (long term fluid retention). A challenge of soft-material sensors is defining and reconfiguring their properties to suit each application and to meet the needs of different body sizes and compositions. As well, sensors used for “self-sensing” in soft actuators must remain mechanically robust if the sensor is placed in a garment or other wearable device. In this talk, I will discuss challenges and recent work related to designing and fabricating soft material sensors and soft actuators for monitoring and treating persistent edema. These sensor designs include variable stiffness approaches, origami-patterned sensors, and low-cost additive manufacturing for wearable devices and sensors. I will also present work in enhancing the stability and mechanical selectivity of stretchable sensors and discuss applications for such sensors in wearable healthcare applications and soft robotics more broadly.
4
4/11/22
Dr. M. Ani Hsieh
University of Pennsylvania		How to Make Your Ocean SmarterDr. M. Ani Hsieh is an Associate Professor in the Department of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania. She is also the Deputy Director of the General Robotics, Automation, Sensing, and Perception (GRASP) Laboratory and Program Chair for the Robotics MSE Program. Her research interests lie at the intersection of robotics, multi-agent systems, and dynamical systems theory. Hsieh and her team design algorithms for estimation, control, and planning for multi-agent robotic systems with applications in environmental monitoring, estimation and prediction of complex dynamics, and design of collective behaviors. She received her B.S. in Engineering and B.A. in Economics from Swarthmore College and her Ph.D. in Mechanical Engineering from the University of Pennsylvania. Prior to Penn, she was an Associate Professor in the Department of Mechanical Engineering and Mechanics at Drexel University. Hsieh is the recipient of a 2012 Office of Naval Research (ONR) Young Investigator Award and a 2013 National Science Foundation (NSF) CAREER Award. Our oceans drive worldwide weather-climate systems; our rivers serve as nutrient conduits; and our marine ecosystems house the largest repository of biodiversity and mineral resources on the planet. Humans have relied on rivers, lakes, and oceans for transportation, energy generation, farming, and recreation throughout our history. And today, robots are critical tools in our stewardship of these resources. However, there are significant autonomy challenges when working in dynamic and uncertain environments like oceans and rivers. Robot dynamics are tightly coupled to those of the environment, while communication and localization are limited.

Control under these conditions can be exacting, but environmental dynamics may be harnessed to plan energy efficient paths and to maintain network connectivity. Networked robot teams can collect data to construct high fidelity models of the environmental dynamics which can be integrated into robot control and planning. Those same models can be used to guide robot control and sampling strategies to increase their predictive power. In this talk, I will present our vision of a smart ocean observational framework to improve forecasting of weather-climate systems, mitigation of contaminant dispersions, and coordination of maritime search and rescue and humanitarian efforts.
5
4/18/22
Dr. Carlos A. Cifuentes
Universidad del Rosario		Human-Robot Interaction for Rehabilitation and AssistanceDr. Carlos A. Cifuentes is a Professor with the School of Engineering, Science and Technology at Universidad del Rosario (Colombia) and Visiting Professor at EPF Graduate School of Engineering (France). In 2017 his work was lauded as one of five history-changing ideas in Latin America by The History Channel. In 2020 he was elevated to the grade of IEEE Senior Member, and in 2022 he was appointed as Associate Editor for IEEE Robotics and Automation Magazine. His research on Human-Robot Interaction is world-leading, and his team’s research has conclusively shown the benefits of using robots in a healthcare context. His work has generated more than 150 outputs, including two books with Springer, 25 book chapters, 39 indexed journal publications and 85 papers in conference proceedings and presentations. Funding agencies such as the Royal Academy of Engineering (RAEng, UK), Ibero-American Programme on Science and Technology for Development (CYTED), and Ministry of Science, Technology, and Innovation (Minciencias, Colombia) present his research as funding success.Recent developments in robotics and AI have allowed the introduction of new strategies for Human-Robot and Robot-Environment Interaction in different scenarios, implementing several technologies such as automatic learning, motion planning, semantic sensing, and cloud computing to provide more natural, efficient, and safe interaction. In particular, assistive robots such as mobile robots, wearable robots, and humanoids have been implemented in complex and dynamic environments. In this sense, this talk presents some remarks on the design of robots for enhanced human-robot interaction along with case-studies showing how robots interact with humans and perform collaborative tasks.
6
4/25/22
Dr. Chris Crawford
University of Alabama		Brain-Robot Interaction & Applying Block-Based Programming to Neurofeedback Application DevelopmentDr. Chris S. Crawford is an Assistant Professor at the University of Alabama’s Department of Computer Science. He directs the Human-Technology Interaction Lab (HTIL). His research focuses on human-robot interaction and Brain-Computer Interfaces (BCIs). He has investigated systems that provide computer applications and robots with information about a user’s cognitive state. In 2016, he developed a brain-drone racing system that was featured on over 800 news outlets including Discovery, USA Today, and the New York Times, and Forbes. Along with investigating brain-robot interaction applications, Dr. Crawford also recently developed Neuroblock, a software platform for developing neurofeedback applications.
Brain-Computer Interface (BCI) systems convert central nervous system (CNS) activity to artificial output that is then used to replace, restore, enhance, supplement, or improve natural CNS output. BCI functions through acquiring brain signals, identifying patterns, and producing actions based on the observed CNS patterns. This process allows users to interact with their environment without having to use their peripheral nerves and muscles. Output produced by a BCI system can be used to interact with applications ranging from wheelchairs to video games. In this talk, Dr. Crawford will discuss his brain-robot interaction research that examines the use of BCI to control robots. This presentation will also cover his related work that investigates leveraging visual programming for neurofeedback application development.
7
5/2/22
Dr. Maya Cakmak
University of Washington		Robot Programming for AllDr. Maya Cakmak is the Robert E. Dinning Associate Professor at the Paul G. Allen School of Computer Science & Engineering, University of Washington, where she directs the Human-Centered Robotics lab. She received her PhD in Robotics from the Georgia Institute of Technology in 2012, after which she spent a year as a post-doctoral research fellow at Willow Garage, one of the most influential robotics companies. Her research interests are in human-robot interaction, end-user programming, and assistive robotics. Her work aims to develop robots that can be programmed and controlled by a diverse group of users with unique needs and preferences to do useful tasks. Maya's work has been published at major Robotics and AI conferences and journals, demonstrated live in various venues and has been featured in numerous media outlets. Tools that she and her students developed have been used by robotics companies like Savioke, Fetch Robotics, and Hello Robot. She received an NSF CAREER award (2015), a Sloan Research Fellowship (2018), and Early Career Spotlight Awards at RSS (2018) and IJCAI (2019).Robots that can assist humans in everyday tasks have the potential to improve people’s quality of life and bring independence to persons with disabilities. A key challenge in realizing such robots is programming them to meet the unique and changing needs of users and to robustly function in their unique environments. Most research in robotics targets this challenge by attempting to develop universal or adaptive robotic capabilities. This approach has had limited success because it is extremely difficult to anticipate all possible scenarios and use-cases for general-purpose robots or collect massive amounts of data that represent each scenario and use-case. Instead, my research aims to develop robots that can be programmed in-context and by end-users after they are deployed, tailoring it for the specific environment and user preferences. To that end, my students and I have been developing new techniques and tools that allow intuitive and rapid programming of robots to do useful tasks. In this talk I will introduce some of these techniques and tools, demonstrate their capabilities, and discuss some of the challenges in making them work in the hands of potential users and deploy them in the real world.
8
5/9/22
Dr. Tahira Reid Smith
Purdue University		 Inclusion in Human-Machine Interactions: Perspectives for the Future of WorkDr. Tahira Reid Smith is an Associate Professor in the School of Mechanical Engineering at Purdue University, the director of the Research in Engineering and Interdisciplinary Design (REID) Laboratory and was a Visiting NASA Scholar from 2020-2021. Her research interests include quantifying and integrating human-centered considerations in the design process and human-machine systems. Her research program has received funding from the National Science Foundation, Air Force Office of Scientific Research, Procter & Gamble, General Motors, Ford Motor Company, and other sources. Prior to arriving at Purdue in 2012, she completed a postdoctoral position in the Mechanical Engineering Department at Iowa State University. Her projects that involved the intersection of diversity and mechanical engineering have been featured in media sources including National Geographic, NBC's Today Show, Essence Magazine, Reuters, National Public Radio and many others. A highly sought out role model for the younger generation, Dr. Reid Smith's story about her Double Dutch jump rope invention is featured in two children's books, was on the 2017 New York State English and Language Arts Common Core Exam administered to over 100,000 4th graders in the state of New York, and was recently featured in the Lemelson Center's Oral History Project and Game Changers Series. In 2010, she received her PhD from the University of Michigan in Design Science, with Mechanical Engineering and Psychology as her focus areas. Dr. Reid received both her BS and MS degrees in Mechanical Engineering from Rensselaer Polytechnic Institute (RPI) in 2000 and 2004, respectively.Human-machine interactions (HMIs) describe how humans engage various systems, including those that are smart, autonomous, or both. Design science addresses the creation of artifacts, which include interfaces between humans and machines, and their embedding in our natural, virtual, psychological, economic, and social environment. Most HMIs either allow the human to control the machine (e.g., an instrument panel), allow the machine to obtain data (e.g., Fit-Bit), or even both. The human in HMI implies inclusion regardless of ability, ethnicity, race, or social class, but the current research paradigm shows many examples of exclusion. In this interactive talk, Dr. Reid Smith will discuss common challenges faced by researchers working in HMI and will propose solutions.
9
5/16/22
Dr. Maira Saboia Da Silva
NASA Jet Propulsion Laboratory		Multi-Material Construction with Robot TeamsDr. Maira Saboia is a post-doctoral research at NASA Jet Propulsion Laboratory, and was a post-doctoral research at Vale Institute of Technology (ITV) in Brazil. She completed her Ph.D in Computer Science and Engineering at University at Buffalo, State University of New York, USA. She has received her M.Sc. in Computer Science from the University of Campinas, Brazil and her B.Sc. in Computer Engineering from the University of Pernambuco, Brazil. Her research interests are in autonomous systems, planetary exploration, bio-inspired robotics, collective robotics, robotic-vision, multi-robot systems, distributed robotics systems, autonomous construction, navigation, task and path planning. She has experience in developing theoretical frameworks, high-level system designs and working with system implementations.Many applications of autonomous construction require reliable operation in highly unstructured and irregular environments, which often coincide with a lack of established infrastructure. For example, disaster relief or operation in extraterrestrial bodies can benefit from robots building temporary or permanent structures. In this talk I will present a mathematical framework that can be used to empower robots with the ability to modify their environment to provide mobility for themselves or others, allowing agents to move in previously non-navigable areas without the need for human intervention. I will also present a system implementation that exploited this formulation to allow a heterogeneous robot team to iteratively choose between different building materials to modify a shared environment.
10
5/23/22
Dr. Maru Cabrera
University of Massachusetts Lowell 		Human-centered approaches in assistive roboticsDr. Maru Cabrera is an Assistant Professor at the University of Massachusetts Lowell (UML). Dr. Cabrera's research interests focus on aspects of Human-Robot Interaction intersecting with accessibility; working on service robots that can help people with mobility limitations or target populations like older adults by collaborating to complete tasks at home. Dr. Cabrera received a PhD from Purdue University in 2018, working in the Intelligent Systems and Assistive Technologies (ISAT) Lab in the School of Industrial Engineering, and following that, a postdoc at the University of Washington. There is almost a symbiotic relationship between designing useful collaborative robots, developing methods for effective interactions between humans and robots, and configuring the environment in which these interactions take place. In this talk I aim to cover the general topic of interaction methods using human expression and context, and their potential applications in assistive robotics; the two domains I will elaborate are surgical applications and service robots at home. I will present some of my work with assistive robotic platforms and applications with different levels of autonomy considering both the users and the tasks at hand. I will showcase algorithms and technologies that leverage human context to adjust the way a robot executes a handover task. I will also address how this line of research contributes to the HRI field in general, and the broader goals of the AI community.
11
5/30/22No seminar, UCSD closed in observence of Memorial Day