- This event has passed.
Spring 2026 GRASP SFI: Wei-Hsi Chen, University of Pennsylvania, “Toward Task-informed Robot Codesign”
January 28 @ 3:00 pm - 4:00 pm
This presenter is one of the winners of the 2025 GRASP vote for internal PhD or postdoc SFI Speakers!
This was a hybrid event with in-person attendance in Levine 307 and virtual attendance…
ABSTRACT
Robot design remains slow and iterative because morphology and behavior are often engineered separately. In this talk, I present my work toward task-informed robot co-design, which treats morphology and behavior as programmable, composable elements that can be systematically designed for specific objectives. Using origami-inspired robots as a model system, I show how geometric structure, actuation, and compliance can be parameterized to enable scalable actuation, energy modulation, and modular behavioral templates for legged locomotion.
Additionally, I will introduce a task-to-intelligence perspective that links task characteristics to different strategies of embodiment and control, providing guidance for morphology–behavior selection. Together, these ideas motivate a longer-term vision of a robot compiler: a unified framework that translates task specifications into feasible body–behavior designs. This direction aims to accelerate robot design while deepening our scientific understanding of how intelligent behavior emerges from the interaction of body, control, and task.
Presenter
Wei-Hsi Chen
Wei-Hsi Chen is a postdoctoral researcher in the GRASP Laboratory at the University of Pennsylvania. His research studies how robot morphology and behavior can be made programmable through abstraction, scaling, and composition, using origami-inspired fabrication and legged locomotion as model systems. He is interested in task-informed robot co-design and in developing systematic approaches that connect physical structure, control, and task requirements.