An automatic-differentiation-based simulator for LTM and DUO traffic models enables scalable gradient optimization of dynamic congestion tolls on networks with thousands of links and millions of vehicles.
Discrete adjoint gradient computation for multiclass traffic flow models on road networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
End-to-end differentiable network traffic simulation with dynamic route choice
An automatic-differentiation-based simulator for LTM and DUO traffic models enables scalable gradient optimization of dynamic congestion tolls on networks with thousands of links and millions of vehicles.