Anticipatory model improves vehicle route prediction on road networks
Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories
Artificial IntelligenceMachine Learning
Summary
Predicting the exact path a vehicle will take on city roads is hard because cars move predictably on road segments but can choose many possible turns at intersections. The authors created a new method, called Foresight, that not only simulates vehicle locations but also thinks ahead about future turns when deciding the next move. This approach keeps predicted paths on the roads and better guesses which way vehicles will go next. Their experiments show this method works better than existing ones.
What this means in practice
- •For urban planners: Plan traffic flow and urban infrastructure by simulating realistic vehicle paths anticipating route choices at intersections.
- •For traffic management teams: Improve traffic prediction systems by accurately forecasting vehicle turns and routes in road networks.
Authors
Zhenhao Huang, Li Sun, Philip S. Yu
Abstract
Trajectory generation underpins urban applications such as traffic management and urban planning. Within road networks, vehicle movement along road segments is largely deterministic, whereas transitions at intersections are critical--multiple outgoing paths may appear equally plausible, yet they can lead to substantially different downstream routes. Existing generative methods such as diffusion models simulate location sequences and fail short of next transition selection, even producing trajectories that drift off the road network. To fill this gap, we advocate a fundamental shift: moving beyond location simulation toward behavior modeling on the road network. In this paper, we revisit trajectory generation through the lens of generative route planning, and introduce a new graph-constrained generative paradigm, Anticipatory Generative Modeling, which resolves next transition selection by incorporating the Anticipation of how the future route may unfold toward the destination. Concretely, we propose a novel generative model named Foresight that formulates a probabilistic model for an "anticipate--select--update--re-anticipate" loop that enables longer-term foresight while continuing sequential generation along the historical trajectory. Extensive experiments demonstrate that Foresight wins state-of-the-art baselines.