A Computationally Efficient Model for Pedestrian Motion Prediction

TL;DR

This paper introduces a computationally efficient mathematical model for predicting pedestrian movement over a finite horizon, aiding collision avoidance in autonomous vehicles, based on rational behavior and road map data.

Contribution

The paper presents a novel, efficient pedestrian motion prediction model that incorporates road map structure and rational behavior assumptions, improving collision avoidance strategies.

Findings

Model shows comparable accuracy to state-of-the-art methods

Effective in simulations and real data comparisons

Highlights limitations and potential improvements

Abstract

We present a mathematical model to predict pedestrian motion over a finite horizon, intended for use in collision avoidance algorithms for autonomous driving. The model is based on a road map structure, and assumes a rational pedestrian behavior. We compare our model with the state-of-the art and discuss its accuracy, and limitations, both in simulations and in comparison to real data.