Close

Presentation

Distinguished Speaker
:
Simulation and HPC for Mixed-Autonomy Mobility
Speaker
Event Type
Distinguished Speaker
Passes
Tags
AI/Machine Learning/Deep Learning
Autonomous Driving
Communication Optimization
Energy consumption
Graph Algorithms
TimeTuesday, June 26th4:15pm - 4:45pm
LocationPanorama 2
DescriptionHow will self-driving cars change urban mobility? This talk highlights contributions in machine learning, simulation, and HPC critical for enabling mixed-autonomy mobility, the gradual and complex integration of automated vehicles into the existing transportation system. The talk focuses on a recent enabling study which quantifies the potential impact of a small fraction of automated vehicles on low-level traffic flow dynamics such as traffic congestion, using novel techniques in model-agnostic deep reinforcement learning.