Max Robotics — Global Service Robot Directory + US Certification

About

Tianlu Mao is a leading researcher in computer vision and artificial intelligence, specializing in human trajectory prediction—a critical technology for autonomous vehicles, social robotics, and intelligent surveillance. Her work addresses the fundamental challenge of modeling how pedestrians navigate crowded spaces while avoiding collisions, combining spatial awareness with temporal dynamics. Mao’s most influential contribution is the STGAT model (2019, 634 citations), which introduced a novel spatial-temporal graph attention network for trajectory prediction. This work revolutionized the field by explicitly modeling how pedestrians interact with each other over both space and time, achieving state-of-the-art accuracy. She further advanced the field with CoL-GAN (2020), an attention-based generative adversarial network that produces plausible, collision-free trajectories, and an efficient spatial-temporal model using gated linear units (2021) that improved computational efficiency without sacrificing performance. Her most recent work, DTDNet (2024), introduces a dynamic target-driven approach that incorporates pedestrian intentions into trajectory prediction, addressing a key limitation of existing methods. With over 680 cumulative citations, Mao’s research has fundamentally shaped how autonomous systems understand and anticipate human movement in complex, dynamic environments, directly impacting the safety and reliability of autonomous navigation technologies.