Luis Sentis, Ph.D. - US grants

Current autonomous mobile robots are able to navigate accurately through sparsely populated areas without bumping into things. However, they have more trouble in situations that commonly arise in public buildings, such as when passing people in narrow hallways, when moving through open, populated spaces, or when crossing a crowd of people exiting an auditorium. Thus, for autonomous robots to reach their full potential, in terms of positive impact on society, they will need to improve their navigational abilities to be more "human-aware." That is, they will explicitly need to take account the characteristics of the people with whom they need to interact in public spaces. With this motivation in mind, the goal of this research is to understand how best to enable mobile robots to navigate smoothly, robustly, and safely through human-populated indoor environments in pursuit of high-level goals, with varying levels of guidance from a human operator in a fully human-aware manner.

This project focuses on two complementary, high-risk, and potentially foundational research thrusts as being crucial to laying the groundwork for eventual development of a robust, human-aware navigation system. First, it aims to develop formal specifications for safe robot-operator-pedestrian interactions, using probabilistic temporal logics. Second, it aims to develop methods for generating learned models of operator preferences that can influence the robot's choice of paths with regards to, for example, trajectory smoothness, order of subgoal achievement, task completion time, travel speed, and proximity of trajectory to pedestrians and fixed objects, learning user preferences and determining how to combine them with task-achieving reward functions.

Future space missions will increasingly rely on autonomous robots like the NASA Valkyrie human-centered robot for deploying equipment, assisting astronauts, and maintaining facilities in real world partially-observable and cluttered environments. Despite significant progress in robotic mobility, manipulation, and perception, there has been relatively little progress on providing formal performance guarantees for these integrated systems. Formal guarantees are critical for achieving long term autonomy, particularly for robots performing complex tasks requiring successful execution of multiple component subtasks. Thus, the goal of this project is to develop performance guarantees for space robots operating in unstructured real world environments. Although robots are used as design examples, the project is of a basic research nature and the results can have impacts on other fields, such as sensor/actuator networks, manufacturing and transportation systems. The multidisciplinary approach taken for this project will help broaden participation of underrepresented groups and positively impact engineering and computer science education.

The objective of this project is to develop new methods to synthesize coordinated manipulation and locomotion plans and control policies that verifiably adhere to formal mission specifications. There are two major thrusts. First, the PIs plan to develop manipulation, locomotion, and motion primitives that can provide performance guarantees in unstructured, partially observable, and dynamic environments. The focus will be on using methods from perception and planning under uncertainty to provide guarantees in cluttered and partially observable environments. The PIs will also leverage new tools from hybrid systems and sampling based methods to achieve controllers with verifiable guarantees through contact mode switches. Second, the PIs plan to devise methods to automatically synthesize mission plans in a way that can guarantee the accomplishment of high-level mission goals or bound the probability of failure. The focus will be on automatic and learning-based design, enabling the system to adapt to changing environments, uncertain faults and potential adversaries. Most of the work performed under this project will be demonstrated in the context of complex space tasks inspired by NASA scenarios.

Given the potentially disruptive consequences of artificial intelligence (AI)-based systems, humanity cannot afford to wait until problems arise to consider their impacts on society. AI’s ethical and societal implications must be considered as systems are designed, developed, and deployed. The increasingly ubiquitous adoption of robots in homes and cities is poised to transform our society. However, it remains an open question whether this technology will develop in a way that increases the divide between haves and have-nots or results in a more just and equitable society. Thus, there is a need for convergent STEM graduate education to ensure that future roboticists are prepared to consider ethical implications of robotics technology and build a more just and equitable future for everyone. This National Science Foundation Research Traineeship (NRT) award to the University of Texas at Austin will address the challenge of integrating responsible and ethical AI at all stages of development, design, and deployment of service robots. The Convergent, Responsible, and Ethical AI Training Experience for Roboticists (CREATE Roboticists) program will integrate ethical robotics education, research, and career development. The program will train 32 funded trainees and 150 additional graduate students from the Departments of Aerospace, Computer Science, Electrical Engineering, and Mechanical Engineering, and Schools of Architecture, Information, and Public Affairs.

CREATE Roboticists will train future roboticists who: (i) understand the ethical implications of service robots and can develop new theories, methods, and techniques to satisfy ethical requirements; (ii) design human-centered ethical service robots that respect human autonomy and ethical values; and (iii) develop robotics policy informed by cutting edge convergent research. This program includes six elements: coursework, research opportunities, mentorship, professional development, internships, and public service. Interdisciplinary coursework will include five new courses, four of which are foundation courses, and a project-based capstone course. Trainees will engage in research projects across four domains: delivery systems, office service mobile robots, personal home robots, and industrial robots. Two faculty members will mentor each trainee over the five years of the program, with at least one mentor external to the student’s home department. Mentors and students will develop personalized individual development plans (IDPs) in the students’ first year as trainees. They will revise these IDPs each semester in subsequent years of the program. The trainees will also participate in ten hours of career development workshops every semester on topics including article publication and grant-writing, startups and industry opportunities, and career planning. Trainees will enhance their education with internships at a private company, government, or non-profit organization. Finally, NRT trainees will spend about one day per month volunteering for a local government program or non-profit organization connected to robotics and AI.

The NSF Research Traineeship (NRT) Program is designed to encourage the development and implementation of bold, new potentially transformative models for STEM graduate education training. The program is dedicated to effective training of STEM graduate students in high priority interdisciplinary or convergent research areas through comprehensive traineeship models that are innovative, evidence-based, and aligned with changing workforce and research needs.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

This project combines methods and expertise in the fields of human-robot interaction, human factors, organizational communication, science and technology studies, team science, and research informatics to achieve sustained access to phenomena at the intersection of communities and autonomous robots that is otherwise impractical or impossible to obtain. The research outcomes will identify and address ethical, privacy, and safety concerns created when multi-purpose robots are deployed into communities.<br/> <br/>The research plan enables transformative expansions of several scientific fields onto a shared research object: community-robot encounters. Specifically, the goal is to expand the fields of human factors for robotics and human-robot interaction beyond their traditional focus on robots encountering small numbers of humans, in episodic or incident-based temporalities, and beyond the confines of laboratory environments. This broadening will enable studying large, changing groups of humans interacting with autonomous robots longitudinally, in real-world environments. This work will allow the field of robot perception for long-term autonomy to expand its scope beyond the navigational challenges in the built environment and the relatively predictable movement of vehicles to also include pedestrian behavior. All three robotics subfields will contribute to important aspects of robotic behavior only testable in real-world conditions, including social navigation through crowds, safety and trust in community spaces, and introspective perception of robotic capabilities.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.