February 7, 2023 12:00pm to 1:00pm
Class of 1947 Conference Room, HB Library
Join from the meeting link: https://uconn-cmr.webex.com/uconn-cmr/j.php?MTID=mfa127f06b9ae1331ace4ad3084da8d3a
Meeting # 2622 243 9764
Meeting PW kfDAmspe855
Dial In 415-655-0002
Jiachen Li, Postdoc Scholar, Stanford University
Title: Toward Trustworthy Interactive Autonomy with Relational Reasoning
Abstract:
Modern intelligent systems, such as autonomous vehicles and mobile robots, interact frequently with humans. Their behaviors are highly complex and dynamic, which results from unobservable social interactions. Thus, building reliable autonomy that safely navigates multi-agent scenarios requires scalable and generalizable relational reasoning and interaction modeling between interactive agents. Moreover, to make humans understand, accept and trust robotics technology, especially those with black-box modules such as neural networks, robots should be human-centered and transparent, which can provide explanations for their reasoning, predictions, and actions to developers, users, and stakeholders.
In this talk, Dr. Li will first introduce a unified relational reasoning framework for modeling the underlying relations or interactions in multi-agent systems and human-robot interactions, which infers explainable relations between entities at different scales or abstraction levels. He will then discuss the effectiveness of relational reasoning in downstream tasks, including behavior prediction and sequential decision making for autonomous driving and mobile robot navigation. Finally, He will talk about his future research vision and agenda.
Bio: Dr. Jiachen Li is currently a postdoctoral scholar in the Stanford Intelligent Systems Laboratory at Stanford University. Before joining Stanford, he received his Ph.D. degree in Mechanical Engineering from the University of California, Berkeley. At Berkeley, he was affiliated with the Mechanical Systems Control (MSC) Laboratory and Berkeley DeepDrive. His research interest lies at the intersection of robotics, machine learning, control, and their applications to real-world autonomous systems. He was selected as one of the thirty robotics pioneers at the RSS 2022 Pioneers Workshop. He served as an organizer of multiple workshops on machine learning, autonomous driving, and robotics at NeurIPS, ICCV, ICRA, IROS, IV, and ITSC. More details can be found at https://jiachenli94.github.io/.
For more information, contact: Brandy Ciraldo at brandy.ciraldo@uconn.edu