Gaussian Lane Keeping: A Robust Prediction Baseline

-- Predicting agents' behavior for vehicles and pedestrians is challenging due to a myriad of factors including the uncertainty attached to different intentions, inter-agent interactions, traffic (environment) rules, individual inclinations, and agent dynamics. Consequently, a plethora of neural network-driven prediction models have been introduced in the literature to encompass these intricacies to accurately predict the agent behavior . Nevertheless, many of these approaches falter when confronted with scenarios beyond their training datasets, and lack interpretability, raising concerns about their suitability for real-world applications such as autonomous driving. Moreover, these models frequently demand additional training, substantial computational resources, or specific input features necessitating extensive implementation endeavors. In response, we propose Gaussian Lane Keeping (GLK), a robust prediction method for autonomous vehicles that can provide a solid baseline for comparison when developing new algorithms and a sanity check for real-world deployment. We provide several extensions to the GLK model, evaluate it on the CitySim dataset, and show that it outperforms the neural-network based predictions. Trajectory prediction is a heavily researched topic with numerous applications including Autonomous Driving (AD). Recent efforts have focused on multi-modal and interactive prediction models [1], often utilizing deep learning to handle complex interdependencies [2]. Observations from researchers suggest that a constant velocity prediction model often provides a more robust baseline in such scenarios [4]. Moreover, many researchers and practitioners prefer to employ more reliable and computationally efficient methods for their systems [5].