Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

human trajectory forecasting

Human trajectory forecasting refers to the computational task of predicting the future spatial positions and movement paths of individuals or crowds over time based on their observed historical motion and surrounding environmental context. Primarily utilized in computer vision, robotics, and autonomous vehicle navigation, this process requires modeling complex spatio-temporal dynamics, such as individual movement intentions, physical scene constraints, and social interactions between pedestrians. Because human motion is inherently non-deterministic, forecasting systems often use machine learning, probabilistic models, or graph neural networks to anticipate multiple socially plausible trajectories, enabling intelligent systems to navigate crowded spaces safely and proactively avoid collisions.

1 item

Adaptive Trajectory Prediction via Transferable GNN

Adaptive Trajectory Prediction via Transferable GNN

Yi Xu, Lichen Wang, Yizhou Wang, Yun Fu

OrganizationsNortheastern University

Why you should read this

Proposes a transferable graph neural network framework that aligns feature distributions across disparate environments to prevent performance drops in cross-domain pedestrian trajectory forecasting.

Pedestrian trajectory prediction is an essential component in a wide range of AI applications such as autonomous driving and robotics. Existing methods usually assume the training and testing motions follow the same pattern while ignoring the potential distribution differences (e.g., shopping mall and street). This issue results in inevitable performance decrease. To address this issue, we propose a novel Transferable Graph Neural Network (T-GNN) framework, which jointly conducts trajectory prediction as well as domain alignment in a unified framework. Specifically, a domain-invariant GNN is proposed to explore the structural motion knowledge where the domain-specific knowledge is reduced. Moreover, an attention-based adaptive knowledge learning module is further proposed to explore fine-grained individual-level feature representations for knowledge transfer. By this way, disparities across different trajectory domains will be better alleviated. More challenging while practical trajectory prediction experiments are designed, and the experimental results verify the superior performance of our proposed model. To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.

Added

2026-09-26