Toward Useful Humanoids: Dexterous Manipulation and Imitation Learning for Real-World Tasks
MIE Department Seminar
October 27, 2026
11:00 AM - 12:00 PM America/Chicago
Presenter: Monroe Kennedy III, PhD, Stanford University
Location: ERF 1043
Abstract: Humanoid robots have recently gained significant attention, with compelling demonstrations of dynamic locomotion and athletic behaviors such as walking, running, and gymnastics. However, for these systems to achieve widespread adoption and real-world impact, they must address critical labor shortages in domains such as caregiving, agriculture, and manufacturing. A central challenge lies in endowing robots with both the dexterity and the contextual knowledge required to perform tasks that are intuitive for humans yet remain highly complex for robotic systems. These tasks often involve contact-rich manipulation, partial observability, and nuanced decision-making. In this talk, we will examine key catalyst challenges spanning tactile sensing for robust interaction, imitation learning for skill acquisition, embodiment and morphology for task alignment, and the development of steerable vision-language-action (VLA) models for generalizable control. We will also discuss emerging design principles and trade-offs that will shape the next generation of robotic hands and manipulation systems.
Speaner Bio: Monroe Kennedy III is an Assistant Professor of Mechanical Engineering, with a courtesy appointment in Computer Science. He is the recipient of the NSF Career Award. He received his Ph.D. in Mechanical Engineering and Applied Mechanics, and a Masters in Robotics from the University of Pennsylvania where he was a recipient of both the NSF and GEM graduate research fellowships. His area of expertise is in collaborative robotics, specifically the development of theoretical and experimental approaches to enhance robotic autonomy and robotic effectiveness in decentralized tasks toward human-robot collaboration. He applies expertise in machine learning, computer vision, collaborative robot teammate intent estimation, dynamical systems analysis, control theory (classical, non-linear, and robust control), state estimation and prediction, and motion planning.
He is the director of the Assistive Robotics and Manipulation Lab (ARMLab) whose broad research objective is to develop technology that improves everyday life by anticipating and acting on the needs of human counterparts. ARMLab specializes in developing intelligent robotic systems that can perceive and model environments, humans, and tasks and leverage these models to predict system processes and understand their assistive role. The research can be divided into the following sub-categories: robotic assistants, connected devices, and intelligent wearables. ARMLab research requires the use of a combination of tools in dynamical systems analysis, control theory (classical, non-linear, and robust control), state estimation and prediction, motion planning, vision for robotic autonomy, teammate intent estimation, and machine learning. ARMLab focuses heavily on both the analytical and experimental components of collaborative robotics. Research applications include autonomous assistive technology, robotic assistants (mobile manipulators and humanoids) with the goal of deployment for service tasks that may be highly dynamic and require dexterity, situational awareness, and human-robot collaboration.
Date posted
Jun 29, 2026
Date updated
Jun 29, 2026