Taking advantage of communication and sensing technology, trajectory optimization
at signalized intersection (i.e., Eco-Approach and Departure) based on
information from vehicle-to-infrastructure (V2I) communications has been proven
to be effective to improve vehicle energy efficiency while guaranteeing safety
and mobility. However, existing approaches are either rule-based models or
optimization models, which cannot achieve optimality and computational
efficiency at the same time. In this article, we propose and test a novel
learning-based approach, machine learning trajectory planning algorithm (MLTPA),
to achieve real-time optimization by training a machine learning model to
approximate the solution from a previously developed optimization-based method
named graph-based trajectory planning algorithm (GBTPA). Five types of machine
learning techniques, including linear regression, k-nearest
neighbors, decision tree, random forest, and multilayer perceptron (MLP) neural
network, are compared in terms of the prediction accuracy, and the random forest
method is finally selected. The proposed MLTPA reduces computation time from
tens of seconds to a few milliseconds. Simulation results illustrate that MLTPA
can achieve median 5.0%-6.20% improvement on energy savings over multiple
simulation runs. The proposed method also has the potential to approximate other
trajectory planning algorithms to achieve real-time performance while ensuring
optimality.
