Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs
This work addresses the problem of accurate traffic flow estimation for urban planning and traffic management, though it is incremental as it builds on existing neural network methods with domain-specific adaptations.
The paper tackled the challenge of modeling vehicle traffic dynamics at the lane scale by applying neural attention to deep learning architectures, resulting in improved predictions of macroscopic quantities like queue lengths, with explicit encoding of lane-to-lane relationships significantly boosting performance.
Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear spatiotemporal physics problem of vehicle traffic dynamics. We consider problems of estimating macroscopic quantities (e.g., the queue at an intersection) at a lane level. First-principles modeling at the lane scale has been a challenge due to complexities in modeling social behaviors like lane changes, and those behaviors' resultant macro-scale effects. Following domain knowledge that upstream/downstream lanes and neighboring lanes affect each others' traffic flows in distinct ways, we apply a form of neural attention that allows the neural network layers to aggregate information from different lanes in different manners. Using a microscopic traffic simulator as a testbed, we obtain results showing that an attentional neural network model can use information from nearby lanes to improve predictions, and, that explicitly encoding the lane-to-lane relationship types significantly improves performance. We also demonstrate the transfer of our learned neural network to a more complex road network, discuss how its performance degradation may be attributable to new traffic behaviors induced by increased topological complexity, and motivate learning dynamics models from many road network topologies.