Towards Complex Language in Partially Observed Environments
[9:00 - 9:45]
Abstract: Robots can act as a force multiplier for people, whether a robot assisting an astronaut with a repair on the International Space station, a UAV taking flight over our cities, or an autonomous vehicle driving through our streets. Existing approaches use action-based representations that do not capture the goal-based meaning of a language expression and do not generalize to partially observed environments. The aim of my research program is to create autonomous robots that can understand complex goal-based commands and execute those commands in partially observed, dynamic environments. I will describe demonstrations of object-search in a POMDP setting with information about object locations provided by language, and mapping between English and Linear Temporal Logic, enabling a robot to understand complex natural language commands in city-scale environments. These advances represent steps towards robots that interpret complex natural language commands in partially observed environments using a decision theoretic framework.
Bio: Stefanie Tellex is an Associate Professor of Computer Science at Brown University. Her group, the Humans To Robots Lab, creates robots that seamlessly collaborate with people to meet their needs using language, gesture, and probabilistic inference, aiming to empower every person with a collaborative robot. She completed her Ph.D. at the MIT Media Lab in 2010, where she developed models for the meanings of spatial prepositions and motion verbs. Her postdoctoral work at MIT CSAIL focused on creating robots that understand natural language. She has published at SIGIR, HRI, RSS, AAAI, IROS, ICAPs and ICMI, winning Best Student Paper at SIGIR and ICMI, Best Paper at RSS, and an award from the CCC Blue Sky Ideas Initiative. Her awards include being named one of IEEE Spectrum's AI's 10 to Watch in 2013, the Richard B. Salomon Faculty Research Award at Brown University, a DARPA Young Faculty Award in 2015, a NASA Early Career Award in 2016, a 2016 Sloan Research Fellowship, and an NSF Career Award in 2017. Her work has been featured in the press on National Public Radio, BBC, MIT Technology Review, Wired and Wired UK, as well as the New Yorker. She was named one of Wired UK's Women Who Changed Science In 2015 and listed as one of MIT Technology Review's Ten Breakthrough Technologies in 2016.
Experiences with Character-Based Robots
[9:50 - 10:35]
Abstract: Over the past nearly 20 years, we have had two character-based robots deployed at Carnegie Mellon, developed in conjunction with the CMU Drama School. The robots, a robot receptionist and Scrabble-playing robot, have interacted with thousands of people, including students, faculty, staff, and visitors. A copy of the receptionist robot was also deployed for several years at the CMU campus in Qatar. The observations and analyses that we have done during this time provide valuable insights into the way people interact with such robots "in the wild", including based on cultural differences. This talk will present the robots that were developed, some of our key findings, and lessons learned.
Bio: Reid Simmons is a Research Professor in Robotics and Computer Science at Carnegie Mellon University. He is also the director of the first-in-the-country undergraduate major in Artificial Intelligence. Dr. Simmons earned his PhD from MIT in 1988 in the field of Artificial Intelligence. Since coming to CMU in 1988, he has focused on developing self-reliant robots that can autonomously operate over extended periods of time in unknown, unstructured environments. Specific research interests include human-robot social interaction, especially non-verbal communication through affect, proxemics, motion, and gesture, task planning under uncertainty, execution monitoring and failure recovery, and coordination of multiple heterogeneous robots.
Over the years, Dr. Simmons has been involved in the development of nearly two dozen autonomous robots. He has published over 200 papers and articles on autonomous robots, human-robot interaction, multi-robot coordination, robot architectures, planning, and probabilistic reasoning. He is an Associate Editor of the Journal of Artificial Intelligence and is on the Editorial Board of International Journal of Social Robots. Dr. Simmons is a Fulbright Scholar (Israel), a Fellow of the Association for the Advancement of Artificial Intelligence, and served as an NSF Program Officer, overseeing the National Robotics Initiative and the Smart and Autonomous Systems program.
From Single Sessions to Six-Month Deployments: Lessons from 18 Years of HRI and SAR In the Wild
[12:00 - 12:45]
Abstract: Socially assistive robotics (SAR) emerged in the early 2000s as an area of HRI specifically focused on systems capable of measurably assisting people in the contexts of health (therapy, rehabilitation) and learning/training. Proper SAR system evaluation requires deployments in settings where users can engage in realistic activities and interactions. Simulating SAR users—stroke patients, individuals on the autism spectrum, elderly with Alzheimer’s Disease, etc.—is not a productive endeavor. Therefore, SAR researchers are challenged to get their algorithms, systems, and methods out into real-world settings in order to gain meaningful insights. This talk will review 18 years of our SAR research that has involved multi-modal interaction and expressive and persuasive robot behavior for monitoring, coaching, and motivating users to engage in health, wellness, education and training activities, starting in single-session studies in controlled settings and growing into multi-week interactions in schools, month-long and longer deployments in homes, and a 6-month deployment in a memory care center/nursing home. Beyond HRI contributions to a broad spectrum of topics (user modeling, engagement, personality, motivation, adherence, long-term adaptation), such deployments generate key insights about the real challenges of robotics in the wild. The talk will discuss a range of studies and long-term deployments, settings (schools, hospitals, homes), users (children, adults, typically developing, autism, stroke, Alzheimer’s disease), and commercial implications.
Bio: Maja Matarić is Chan Soon-Shiong Distinguished Professor of Computer Science, Neuroscience, and Pediatrics at USC, founding director of the Robotics and Autonomous Systems Center and her Interaction Lab. Her past administrative roles include serving as Interim Vice President of Research (2020-21) and Vice Dean of Research in the Viterbi School of Engineering (2006-2019), and she leads the Viterbi K-12 STEM Center. Her PhD and MS are from MIT, and BS from Kansas University. She is Fellow of AAAS, IEEE, AAAI, and ACM, recipient of the Presidential Award for Excellence in Science, Mathematics & Engineering Mentoring (from President Obama), Anita Borg Institute Women of Vision for Innovation, NSF Career, MIT TR35 Innovation, and IEEE RAS Early Career Awards. She is recognized for her K-12 STEM outreach efforts and for mentoring of women and other underrepresented groups in STEM. She authored "The Robotics Primer”, MIT Press. Her research is developing socially assistive robots for convalescence, rehabilitation, training, and education for children with autism spectrum disorders, stroke and traumatic brain injury survivors, and individuals with Alzheimer's Disease, as well as individuals suffering from anxiety and depression. She is also co-founder of Embodied, Inc.
Before and After: Building long-term research relationships for HRI studies
[12:50 - 13:35]