Most of the TBD Lab projects center on human-robot interaction (HRI) and advanced transportation. We use a wide range of methods and disciplines to gather new scientific evidence and advance the state of the art. Our work falls within two broad themes, often with projects that incorporate questions from both.
Robotics and AI offer new opportunities for helping people live, work, and travel around their community. However, there are many unanswered questions on where, how, and when to provide help. Many of our projects focus on helping people get from one place to another, whether in a vehicle or not.
- AI-CARING: Members of the team are involved in the AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups (AI-CARING). This multi-school effort, led by Georgia Tech, is developing the next generation of personalized collaborative AI systems that improve the quality of life and independence of aging adults living at home. (NSF 2112633)
- Rehabilitation Engineering Research Center on Accessible Public Transportation: This center is researching and developing methods to empower consumers and service providers in the design and evaluation of accessible transportation equipment, information services, and physical environments. This includes work with Tiramisu Transit as a testbed. (NIDILRR 90REGE0007; 90RE5011-01-00, formerly NIDRR H133E080019; & H133E130004)
- Tiramisu Transit: This effort was focused on novel methods for generating and providing transit information. Project research explored crowdsourcing for gathering and disseminating real-time information, generation of data useful for transit planning, and methods for personalizing information to the user. Our smartphone app, publicly available on iPhone and Android, supported daily travel by thousands of transit riders while also enabling novel research on accessibility, transportation, HCI, and machine learning. It has received support through the RERC-APT, a project within the Traffic21 initiative, projects within the T-SET UTC, and a Phase I SBIR. (US DOT DTRT12-G-UTC11 & DTRT57-12-C-10039) Completed
- DRRP on Robotics and Automation for Inclusive Transportation: This multi-site effort was working on research and development to enable seamless, accessible transportation assistance from cloud-based autonomy and shared robots located in and around transportation hubs. (NIDILRR 90DPGE0003-01-00) Completed
- DRRP on Inclusive Cloud and Web Computing: This multi-site effort worked on methods to enable software providers to easily and rapidly implement inclusive user experiences so that consumers are empowered to fully participate in cloud and web systems. (NIDILRR 90DP0061-01-00, formerly NIDRR H133A130057) Completed
- NRI:Small:Assistive Robots for Blind Travelers: This project, with M Bernardine Dias, explored meaningful human-robot interaction in the context of assistive robots for blind travelers. We hypothesized that co-robots can enhance safety and independence by assisting navigation of unfamiliar urban environments and providing support during evacuations. (NSF IIS 1317989) Completed
- Quality of Life Technology (QoLT): This NSF ERC was focused on transforming the lives of people with reduced functional capabilities due to aging or disability through appropriate technology developed in a cross-disciplinary manner. Team members include technologists, clinicians, industry partners, end users, and other stakeholders. The TBD Lab was active in the transportation aspects of the ERC within Safe Driving family of engineered systems activity. (NSF EEEC-0540865) Completed
Recent publication examples:
- Oscar J. Romero, Alexander Haig, Lynn Kirabo, Qian Yang, John Zimmerman, Anthony Tomasic, and Aaron Steinfeld. 2020. A Long-Term Evaluation of Adaptive Interface Design for Mobile Transit Information. In 22nd International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI ’20). DOI: https://doi.org/10.1145/3379503.3403536
- Lynn Kirabo, Elizabeth J. Carter, and Aaron Steinfeld. 2020. “You are asking me to pay for my legs”: Exploring the Experiences, Perceptions, and Aspirations of Informal Public Transportation Users in Kampala and Kigali. In Proceedings of the 3rd ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS ’20). DOI: https://doi.org/10.1145/3378393.3402269
- Qian Yang, Aaron Steinfeld, and John Zimmerman. 2019. Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI ’19). DOI: https://doi.org/10.1145/3290605.3300468
- Aaron Steinfeld, Jordana L. Maisel, and Edward Steinfeld. 2017. Accessible Public Transportation: Designing Service for Riders with Disabilities. Routledge.
End users expect appropriate robot and AI actions, interventions, and requests for help. Our research often explores issues like trust, failure, workflow, and socially appropriate actions. These kinds of issues directly impact acceptance, adoption, and long term use of novel systems.
- MURI – SUCCESS: Self-assessment and Understanding of Competence and Conditions to Ensure System Success: This project is focused on advancing new knowledge and techniques for machine self-assessment of proficiency. (ONR N00014-18-1-2503)
- NRI: FND: Mutually Aware Social Navigation: This project worked to improve the way robots reason about spatial behavior and develop navigation methods that lead to understandable and appropriate motion patterns in social environments. (NSF IIS 1734361) Completed
- NRI: FND: Human-Robot Collaboration with Distributed and Embodied Intelligence: This project, led by John Zimmerman and with Jodi Forlizzi, examined questions around the issue of intelligence re-embodiment in robots. (NSF SES 1734456) Completed
- Human Interactions with Robot Failures: This collaborative project with the UMass Lowell Robotics Lab was focused on bystander interactions with failing robots. (NSF IIS 1552256 & 1552228) Completed
- Social Sensing for Human-Robot Interaction: This collaborative project with Disney Research Pittsburgh and Scott Hudson examined methods for robots to perceive and behave appropriately in social groups. Completed
- HCC:Medium:Understanding and Modeling Trust in Human-Robot Interactions: This collaboration with the Holly Yanco developed quantitative metrics to measure a user’s trust in a robot as well as a model to estimate the user’s level of trust in real time. (NSF IIS 0905148 & 0905228) Completed
- RADAR: This goal of this program was to develop a learning “cognitive personal assistant” that supports a variety of organizational tasks and activities. Within the Test group, led by Steinfeld and Daniel Siewiorek, we deployed a large-scale simulated test environment and conducted human subject experiments on Radar system performance. Free content and experiment resources can be found at the Airspace website. (DARPA NBCHD030010. & FA8750-07-D-0185) Completed
Recent publication examples:
- Xiang Zhi Tan, Elizabeth J. Carter, Samantha Reig, Aaron Steinfeld. Go That Way: Exploring Supplementary Physical Movements by a Stationary Robot When Providing Navigation Instructions. In Proceedings of the 21st ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’19). DOI: https://doi.org/10.1145/3308561.3353805
- Cecilia G. Morales, Elizabeth J. Carter, Xiang Zhi Tan, and Aaron Steinfeld. 2019. Interaction Needs and Opportunities for Failing Robots. In Proceedings of the 2019 on Designing Interactive Systems Conference (DIS ’19). DOI: https://doi.org/10.1145/3322276.3322345
- Michal Luria, Samantha Reig, Xiang Zhi Tan, Aaron Steinfeld, Jodi Forlizzi, and John Zimmerman. Re-Embodiment and Co-Embodiment: Exploration of Sequential Interaction in Social Robots and Voice Agents. In Proceedings of the 2019 Designing Interactive Systems Conference (DIS ’19). DOI: https://doi.org/10.1145/3322276.3322340
- Samantha Reig, Selena Norman, Cecilia G. Morales, Samadrita Das, Aaron Steinfeld, Jodi Forlizzi. A Field Study of Pedestrians and Autonomous Vehicles. In Proceedings of the 10th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI ’18). DOI: https://doi.org/10.1145/3239060.3239064