Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features

In this work, we propose a novel approach for integrating rules into traffic agent trajectory prediction. Consideration of is important understanding how people behave-yet, it cannot be assumed that are always followed. To address challenge, evaluate different approaches as inductive biases deep learning-based prediction models. We framework based on generative adversarial networks uses tools from formal methods, namely signal temporal logic and syntax trees. This allows us to leverage information rule obedience features in neural improves accuracy without biasing towards lawful behavior. our method real-world driving dataset show improvement performance over off-the-shelf predictors.