Structural materials that are damage-tolerant, lightweight, multifunctional, and sustainable are highly desirable for many engineering applications. Such combinations of properties are often found in the biological world. Organisms from nature […]
As artificial intelligence (AI) transforms industries, state-of-the-art models have exploded in size and capability. However, deploying these models on resource-constrained edge devices remains a significant challenge. Smartphones, wearables, and IoT […]
Generative spatial AI offers unprecedented capabilities for photorealistic scene representation, generation, and novel-view synthesis, among other tasks. In this talk, we discuss recent advances in large-scale 3D scene representations, efficient […]
Abstract: The explosive growth of machine learning and data-driven methodologies have revolutionized numerous fields. Yet, the translation of these successes to the domain of dynamical physical systems remains a significant […]
The Department of Bioengineering at the University of Pennsylvania along with Drs. Brian Litt and Ingo Helbig proudly announce the Doctoral Dissertation Defense of Peter Galer. Title: Quantitative Informatics Approaches to […]
This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom. ABSTRACT Despite recent advances in machine learning for robotics, current approaches often lack […]
Abstract: Biological systems utilize networks of biochemical reactions to drive autonomous and dynamic processes. Examples include the dynamic polymerization of microtubules and the dynamic min protein system in E. Coli. […]
Contact interactions, including adhesion and friction, are critical to the design of many engineered systems. Currently, most systems rely on materials with static mechanical properties, requiring careful selection of materials […]
My group is developing a roadmap for soft actuating materials to replace bulky electric motors in miniature robots requiring large mechanical work output. First, I will describe the materials microstructure and […]
We have recently demonstrated the possibility of learning controllers that are zero-shot transferable to groups of real quadrotors via large-scale, multi-agent, end-to-end reinforcement learning. We train policies parameterized by neural […]
