Considerations for Next Generation Dexterous Manipulation

Abstract: Robotic manipulation has long been a foundational capability in robotics, originating with early industrial systems designed for structured pick-and-place operations. Today, rapid advances in visual perception, machine learning, and embodied intelligence are creating new opportunities for robots to operate in unstructured, dynamic environments populated with the diverse objects humans handle with ease. The recent resurgence of interest in humanoid robots further underscores the need for robust, versatile manipulation capabilities, as their practical value ultimately hinges on the reliability and breadth of tasks they can perform. In this talk, I will examine the critical barriers that continue to limit progress toward general-purpose robotic manipulation and discuss the catalyst problems that currently prevent robots from operating effectively at scale in domestic, industrial, and agricultural settings. Drawing from core principles of robotic autonomy—perception, planning, and control—I will outline the algorithmic and hardware innovations required to unlock the next generation of manipulation systems capable of truly impactful real-world deployment.

Bio: Monroe Kennedy is an assistant professor in Mechanical Engineering and by courtesy, Computer Science at Stanford University. Monroe is the recipient of the NSF Faculty Early Career Award. He directs the Assistive Robotics and Manipulation Laboratory (ARMLab), where the focus is on developing collaborative, autonomous robots capable of performing dexterous, complex tasks with human and robotic teammates. Monroe received his Ph.D. in Mechanical Engineering and Applied Mechanics and master’s in Robotics from the University of Pennsylvania.

Please visit https://stanfordasl.github.io/robotics_seminar/ for this quarter’s lineup of speakers. Although we encourage live in-person attendance, recordings of talks will be posted also.