Learning Traffic Flow Dynamics with Stochastic Physics-Informed Neural Cellular Automata
A physics-informed neural cellular automaton learns stochastic traffic rules while conserving vehicles and respecting road topology.
Researchers propose a physics-informed neural cellular automaton (PI-NCA) for data-driven traffic flow modeling. The network respects road topology and conserves the total number of vehicles, and a stochastic extension learns probabilistic transition rules under the same constraints. On scenarios generated by the Nagel-Schreckenberg and Kerner-Klenov-Wolf cellular automata, PI-NCA learns both models' dynamics and outperforms a standard neural cellular automaton.
- PI-NCA constrains transitions so total vehicle count is conserved.
- The architecture stays consistent with road topology.
- A stochastic variant learns probabilistic rules under the same constraints.
- Models were tested on Nagel-Schreckenberg and Kerner-Klenov-Wolf traffic.
From the original article
1 min read at arxiv.orgTraffic flow modeling is essential for understanding and predicting the collective dynamics of vehicles on road networks. Cellular automata provide a simple, interpretable yet powerful framework for representing these dynamics via local interaction rules, while retaining the ability to reproduce complex macroscopic traffic phenomena.
By Federica Bragone · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.