AutonomIA (Autonomous Intelligent Assistant)

Research Members: Jiaman Wu

Autonomia project leverages emergent connected automated vehicles with varied levels of autonomy (CAVs), sensing, and signaling technologies within a unified learning, simulation, and control paradigm to improve energy efficiency by 20% or more and reduce CO2 emissions by at least 20%. Four innovative components are: 1) real-time and context-aware transportation state estimation from fusing traffic data, simulations, and contextual mobility information, 2) scalable and computationally efficient traffic forecast modeling to predict future system-level traffic states in real-time, 3) differentiable predictive control to optimize transportation network operations for system level traffic flow, energy efficiency, and emission reduction, and 4) hierarchical reinforcement learning to generate policies for on-the-fly optimized timings of intersection level traffic signals.


HuMNet Lab