Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis
This work addresses pedestrian motion prediction for autonomous vehicles or robotics, offering an incremental improvement by automating behavior clustering to enhance prediction accuracy.
The paper tackles pedestrian motion prediction by introducing a transformer-based framework that automatically clusters pedestrian behaviors and uses these clusters for data-driven reachability analysis, eliminating the need for manually crafted labels and reducing human bias.
In this work, we present a transformer-based framework for predicting future pedestrian states based on clustered historical trajectory data. In previous studies, researchers propose enhancing pedestrian trajectory predictions by using manually crafted labels to categorize pedestrian behaviors and intentions. However, these approaches often only capture a limited range of pedestrian behaviors and introduce human bias into the predictions. To alleviate the dependency on manually crafted labels, we utilize a transformer encoder coupled with hierarchical density-based clustering to automatically identify diverse behavior patterns, and use these clusters in data-driven reachability analysis. By using a transformer-based approach, we seek to enhance the representation of pedestrian trajectories and uncover characteristics or features that are subsequently used to group trajectories into different "behavior" clusters. We show that these behavior clusters can be used with data-driven reachability analysis, yielding an end-to-end data-driven approach to predicting the future motion of pedestrians. We train and evaluate our approach on a real pedestrian dataset, showcasing its effectiveness in forecasting pedestrian movements.