RI Seminar: Siddharth Srivastava : The Unusual Effectiveness of Abstractions for Assistive AI
Siddharth Srivastava
Assistant Professor
School of Computing, Informatics, & Decision Systems Engineering, Arizona State University
October 29, 2021
https://www.ri.cmu.edu/event/ri-seminar-siddharth-srivastava-arizona-state-university-assistant-professor-2021-10-22/
The Unusual Effectiveness of Abstractions for Assistive AI
Abstract: Can we balance efficiency and reliability while designing assistive AI systems? What would such AI systems need to provide? In this talk I will present some of our recent work addressing these questions. In particular, I will show that a few fundamental principles of abstraction are surprisingly effective in designing efficient and reliable AI systems that can plan and act over multiple timesteps. Our results show that abstraction mechanisms are invaluable not only in improving the efficiency of sequential decision making, but also in developing AI systems that can explain their own behavior to non-experts, and in computing user-interpretable assessments of the limits and capabilities of Black-Box AI systems. I will also present some of our work on learning the requisite abstractions in a bottom-up fashion. Throughout the talk I will highlight the theoretical guarantees that our methods provide along with results from empirical evaluations featuring decision-support/digital AI systems and physical robots.
Brief Bio: Siddharth Srivastava is an Assistant Professor of Computer Science in the School of Computing and Augmented Intelligence at Arizona State University. Prof. Srivastava was a Staff Scientist at the United Technologies Research Center in Berkeley. Prior to that, he was a postdoctoral researcher in the RUGS group at the University of California Berkeley. He received his PhD in Computer Science from the University of Massachusetts Amherst. His research interests include robotics and AI, with a focus on reasoning, planning, and acting under uncertainty. His work on integrated task and motion planning for household robotics has received coverage from international news media. He is a recipient of the NSF CAREER award, a Best Paper award at the International Conference on Automated Planning and Scheduling (ICAPS) and an Outstanding Dissertation award from the Department of Computer Science at UMass Amherst. He served as conference chair for ICAPS 2019 and currently serves as an Associate Editor for the Journal of AI Research.
Видео RI Seminar: Siddharth Srivastava : The Unusual Effectiveness of Abstractions for Assistive AI канала CMU Robotics Institute
Assistant Professor
School of Computing, Informatics, & Decision Systems Engineering, Arizona State University
October 29, 2021
https://www.ri.cmu.edu/event/ri-seminar-siddharth-srivastava-arizona-state-university-assistant-professor-2021-10-22/
The Unusual Effectiveness of Abstractions for Assistive AI
Abstract: Can we balance efficiency and reliability while designing assistive AI systems? What would such AI systems need to provide? In this talk I will present some of our recent work addressing these questions. In particular, I will show that a few fundamental principles of abstraction are surprisingly effective in designing efficient and reliable AI systems that can plan and act over multiple timesteps. Our results show that abstraction mechanisms are invaluable not only in improving the efficiency of sequential decision making, but also in developing AI systems that can explain their own behavior to non-experts, and in computing user-interpretable assessments of the limits and capabilities of Black-Box AI systems. I will also present some of our work on learning the requisite abstractions in a bottom-up fashion. Throughout the talk I will highlight the theoretical guarantees that our methods provide along with results from empirical evaluations featuring decision-support/digital AI systems and physical robots.
Brief Bio: Siddharth Srivastava is an Assistant Professor of Computer Science in the School of Computing and Augmented Intelligence at Arizona State University. Prof. Srivastava was a Staff Scientist at the United Technologies Research Center in Berkeley. Prior to that, he was a postdoctoral researcher in the RUGS group at the University of California Berkeley. He received his PhD in Computer Science from the University of Massachusetts Amherst. His research interests include robotics and AI, with a focus on reasoning, planning, and acting under uncertainty. His work on integrated task and motion planning for household robotics has received coverage from international news media. He is a recipient of the NSF CAREER award, a Best Paper award at the International Conference on Automated Planning and Scheduling (ICAPS) and an Outstanding Dissertation award from the Department of Computer Science at UMass Amherst. He served as conference chair for ICAPS 2019 and currently serves as an Associate Editor for the Journal of AI Research.
Видео RI Seminar: Siddharth Srivastava : The Unusual Effectiveness of Abstractions for Assistive AI канала CMU Robotics Institute
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
RI Seminar: Guarav Sukhatme : Robots at SeaComputer VisionRI Special Seminar: Candace L. Sidner : Creating a Real-Time Conversation ManagerBoris Sofman, Co-Founder & CEO, ANKI : Consumer Robotics: Story and LessonsRI Seminar: Dan Stilwell : Autonomy in a tropical riverine systemRI Seminar: Matthew Johnson-Roberson : Lessons from the Field10th Anniversary of CMU's 2007 Driverless Car : Urban ChallengeRI Seminar : Eric N. Johnson : Innovations for Unmanned AircraftMobile Robot Programming Laboratory : Course 16-362 : Fall 20131996 : Xavier "takes instructions from the World Wide Web!" and Reid SimmonsRI Seminar: Rohan Paul : Towards an Intelligence Architecture for Human-Robot Teaming2018 Workshop on Autonomy for Future NASA Science Missions : Day 1, AfternoonRI Seminar: Chelsea Finn : Robots Should Reduce, Reuse, and RecycleRI Seminar: Red Whittaker (2008)Speck Sensor SXSW 2015 Talk : Illah Nourbakhsh Discusses Home Air MonitorrI Seminar: Chung-Wei Lin : Modeling, Design, and Analysis for Intelligent Vehicles...DARPA SUBTERRANEAN CHALLENGE : CMU + Oregon State TeamMobot 2018 : CMU School of Computer Science : Carnival Event1991 : The Robot Shop : CMU Robotics Institute on National Geographic ExplorerEric Horvitz : Microsoft Research : AI & Humanity Archive22 From Textures to Structures: How Computer Graphics Texturing Methods Can...