INTERPRETABLE MULTI-PEDESTRIAN TRAJECTORY PREDICTION USING SOCIAL GAN AND SOCIAL GCNN

Shin, Kazuki

Permalink

https://hdl.handle.net/2142/124916 Copy

Description

Title

INTERPRETABLE MULTI-PEDESTRIAN TRAJECTORY PREDICTION USING SOCIAL GAN AND SOCIAL GCNN

Author(s)

Shin, Kazuki

Issue Date

2021-05-01

Keyword(s)

trajectory prediction; deep neural networks

Date of Ingest

2024-10-16T10:58:17-05:00

Abstract

This thesis presents explanations in addition to the predictions as a way to improve transparency in these trajectory predictions from prior works. The presentation is twofold: (1) Based on the original Social GAN training model, we explore the interpretability of the latent code, and (2) We improve the prediction performance of Social-STGCNN, based on the integration of physical intuition and attention-based mechanisms. Our parametric study of these physical intuitions shows that including both the velocity and position of neighboring pedestrians in the attention mechanism improves model performance. Furthermore, we demonstrate that single attributes of multi-pedestrian trajectories can be explored without affecting other attributes through latent space disentanglement. Through this technique, various pedestrian behaviors can be identified and controlled by finding meaningful representations from the manifolds. We evaluate our approach on the ETH/UCY pedestrian datasets using average displacement error (ADE) and final displacement error (FDE) metrics. The results show social interactions that are intuitive in understanding why exactly these algorithms make the decisions they do.

Type of Resource

text

Genre of Resource

dissertation/thesis

Language

eng

Owning Collections