Comparative Analysis of Human Movement Prediction: Space Syntax and Inverse Reinforcement Learning

TL;DR

This paper compares traditional space syntax with a machine learning-based inverse reinforcement learning approach for predicting human movement in urban environments, showing that MEIRL performs better on simulated data.

Contribution

It provides the first quantitative comparison between space syntax and inverse reinforcement learning for pedestrian movement prediction.

Findings

MEIRL outperforms space syntax in trajectory prediction

Combining both methods could enhance accuracy

Challenges in data collection are discussed

Abstract

Space syntax matrix has been the main approach for human movement prediction in the urban environment. An alternative, relatively new methodology is an agent-based pedestrian model constructed using machine learning techniques. Even though both approaches have been studied intensively, the quantitative comparison between them has not been conducted. In this paper, comparative analysis of space syntax metrics and maximum entropy inverse reinforcement learning (MEIRL) is performed. The experimental result on trajectory data of artificially generated pedestrian agents shows that MEIRL outperforms space syntax matrix. The possibilities for combining two methods are drawn out as conclusions, and the relative challenges with the data collection are highlighted.