Spring 2026 GRASP SFI: Levi Cai, University of Colorado, Boulder, “Holistic Ocean Life Monitoring and Exploration Systems: from in-situ robotics observations to global analysis”
April 15 at 3:00 PM - 4:00 PM
This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom.
ABSTRACT
The lives of marine animals play vital roles in influencing policy decisions ranging from conservation to food security and global health. Yet, many species’ behaviors remain elusive to science as we have little to no direct observations of them. Autonomous underwater vehicles (AUVs) have been seen as scalable solutions for bridging these observational gaps to study organisms in their natural habitats. However, there are many challenges from design, perception, and control that prevent their widespread use.
In particular, I show how to apply generalizable machine learning approaches to AUV perception and controls, as well as animal behavior. These combined provide steps towards enabling AUVs to follow any visible marine animal(s), including those that are rare or elusive, across any habitat or environmental conditions, while minimizing invasiveness or observation bias of animal behavior caused by the vehicle itself. Finally, I will discuss future opportunities to couple these approaches with global AI models to creating holistic monitoring and exploration systems to meet the spatiotemporal and multi-species challenges needed to truly explore, understand, and protect the ocean and its inhabitants.
Levi Cai
University of Colorado, Boulder
Levi “Veevee” Cai aims to develop autonomous systems to understand life on Earth, especially in the Oceans. He is currently a postdoctoral fellow at the University of Colorado, Boulder working with Esther Rolf developing geospatial AI models. He recently received his PhD from MIT and the Woods Hole Oceanographic Institution where he worked with Yogesh Girdhar and Daniela Rus on underwater vehicles for animal tracking and monitoring tasks. He also received an MS from the MIT Media Lab, and BSE from the Univ. of Pennsylvania.