Anqi Shangguan

About

Anqi Shangguan is a researcher whose work sits at the intersection of deep learning and spatiotemporal modeling, with a particular focus on motion trajectory prediction. In their most influential contribution, "Motion trajectory prediction based on a CNN-LSTM sequential model" (2020), Shangguan pioneered a hybrid architecture that combines convolutional neural networks for spatial feature extraction with long short-term memory networks for temporal sequence learning. This work, which has garnered 189 citations, addresses the critical challenge of anticipating dynamic object movements in complex environments—a problem central to autonomous driving, robotics, and surveillance systems. By demonstrating how CNNs can effectively encode spatial patterns from trajectory data before feeding them into LSTMs for sequential forecasting, Shangguan provided a robust framework that significantly improved prediction accuracy over traditional methods. This contribution has been widely adopted and cited by researchers seeking to enhance real-time decision-making in intelligent systems. Shangguan’s research continues to shape advancements in human-robot interaction and autonomous navigation, making their work essential reading for students and professionals exploring the frontiers of predictive modeling and deep learning applications.

Research Focus

Key Achievements

Top Papers

1. 1
   Motion trajectory prediction based on a CNN-LSTM sequential model

   189 citations · 2020

Key Collaborators

Contact & Links