Multi-agent behavior understanding for autonomous driving

©istock

This project aims at improving autonomous driving systems by a better understanding of the behavior of different agents in urban environment.

Detecting and tracking important objects for Advanced Driver-Assistance Systems (ADAS) has experienced tremendous gains in performance in recent years thanks to deep learning. However autonomous vehicles require higher level understanding of the dynamics of their environment to assess, operate in, and interact with that environment in a safe way. The overall scope of this project is to jointly perceive, learn, and understand the behavior of multiple agents of different types (pedestrians, vehicles, cyclists, etc.) to enable better autonomous driving systems.

This two-year project is led by the Visual Intelligence for Transportation Laboratory of professor Alexandre Alahi. It is sponsored by Samsung.

Principal investigator Prof. Alexandre Alahi
Sponsor Samsung
Period 2018-2020
Laboratory VITA