Block-based construction worker trajectory prediction method driven by site risk

Abstract

Different from pedestrian trajectory prediction, construction worker trajectories are usually affected by risks and have complex movement patterns. Track point-based prediction methods require high prediction accuracy for safety management. This paper presents a block-based construction worker trajectory prediction method driven by site risk. First, the construction site is divided into multiple blocks and the site safety risk within different blocks is quantified. Second, stopping, large and small turning segments in worker's trajectory are detected to divide the dataset. Finally, a transformer-based trajectory prediction model for construction workers is developed and trained separately for different datasets. The worker's next go-to block and the duration within the next block are predicted. The results show that the accuracy of block direction prediction within 120° reach 93%, and the error of duration prediction can be 0.52 s. The study has theoretical and practical value for promoting block-based safety management and enhancing safety proactivity.