Estimating the Probability That a Vehicle Reaches a Near-Term Goal State Using Multiple Lane Changes

Traffic Delay Reduction at Highway Diverges Using an Advance Warning System Based on a Probabilistic Prediction Model

“…using one or multiple lane changes [16]. Using that model, the system advises the vehicle on when to change lanes.…”

“…The model introduced in [16] estimates the probability of reaching a near-term goal state using one or multiple lane changes. While a brief overview of the model is provided here, detailed derivation and validation of the model can be found in [16]. Without loss of generality, consider a highway with n lanes, numbered by 1 to n from left to right.…”

“…which is based on the law of total probability [19]. Extensive traffic simulations in VISSIM R for a range of parameters showed that in most cases the model is accurate to within 4% of the actual probability [16]. In summary, the developed model can estimate the probability of reaching a goal state using one or multiple lane changes based on several traffic-and driver-related parameters.…”

“…To address these problems, we propose a new advance warning system for vehicles in a highway based on a probabilistic prediction model that advises them on when to change lanes to reach a highway diverge on time [16]. The model estimates the probability of reaching a goal state on the road using one or multiple lane changes.…”

A Deep Learning Approach for Flight Delay Prediction Through Time-Evolving Graphs

“…Fortunately, utilizing deep learning methods to capture spatial and temporal dependency, timely and accurate traffic prediction has gained growing attention in transportation management area due to the significant benefits it might bring to traffic control and guidance [25]- [28]. More specifically, the graph convolutional neural network (GCN), with the capability of extracting complex non-linear relationships in general graphs, brings opportunities in handling complicated traffic forecasting problems with the consideration of graphstructured information [29]- [32].…”