Abstract:

A key navigational capability for autonomous agents is to predict the future locations, actions, and behaviors of other agents in the environment. This is particularly crucial for safety in the realm of autonomous vehicles and robots. However, many current approaches to navigation and control assume perfect perception and knowledge of the environment, even though current perception algorithms cannot achieve such level of performance. In a series of works, we have proposed new algorithms for visually forecasting the location and actions of other agents in the scene in multiple levels of abstraction (from future trajectories and human poses, to future semantics and intentions).

BIO:

Ehsan Adeli is an assistant professor (clinical research) at Stanford University, School of Medicine. He is also affiliated with the Department of Computer Science (SVL: Stanford Vision and Learning Lab, SAIL: Stanford AI Lab). Dr. Adeli is the director of Mind and Motion Lab and is co-directing the video research group at SVL. He is an investigator in the Stanford Partnership in AI-Assisted Care (PAC) and the Computational Neuroscience Lab, as well as a principal investigator at the SAIL-Toyota Center for Research and Stanford Trustworthy AI group. He is an associate editor of the Journal of Ambient Intelligence and Smart Environments and IEEE Journal of Biomedical and Health Informatics. Dr. Adeli’s research interests include human action recognition, pose estimations, movement analysis, healthcare, brain imaging, and computational neuroscience.

Homepage:  https://stanford.edu/~eadeli/

Sponsored in part by:   Facebook Reality Labs Pittsburgh