HISS: A Pedestrian Trajectory Planning Framework using Receding Horizon Optimization

The paper proposes a generative pedestrian trajectory modeling framework named HISS - Human Interactions in Shared Space. is based on receding horizon optimization approach utilizing behavior and interactions that seeks to capture planning execution. benefit of the proposed dynamic generation it requires minimal calibration data under variety traffic scenarios. In this paper, we formalize several pedestrian-pedestrian interaction scenarios implement trajectories’ conflict avoidance through mixed integer linear programming (MILP). We validate two benchmark datasets DUT TrajNet++. shows when framework’s parameters are tuned certain initial conditions rules, generates trajectories similar those observable real-world scenarios, justifying capability provide explanations solutions various situations. This feature makes useful for modelers urban city planners making policy decisions.