Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning

TL;DR

This paper introduces a self-supervised skeleton representation learning approach to enhance the robustness of human trajectory prediction in scenarios with occlusions and missing joint data.

Contribution

It proposes a novel self-supervised pretraining method for skeleton representations that improves trajectory prediction robustness against missing joint data.

Findings

Improves prediction robustness in occlusion scenarios

Outperforms baseline models in missing data regimes

Maintains accuracy with incomplete skeletal data

Abstract

Human trajectory prediction plays a crucial role in applications such as autonomous navigation and video surveillance. While recent works have explored the integration of human skeleton sequences to complement trajectory information, skeleton data in real-world environments often suffer from missing joints caused by occlusions. These disturbances significantly degrade prediction accuracy, indicating the need for more robust skeleton representations. We propose a robust trajectory prediction method that incorporates a self-supervised skeleton representation model pretrained with masked autoencoding. Experimental results in occlusion-prone scenarios show that our method improves robustness to missing skeletal data without sacrificing prediction accuracy, and consistently outperforms baseline models in clean-to-moderate missingness regimes.