Xiaodan Shi

Papers

Total Citations

H-Index

About

Xiaodan Shi is a leading researcher in autonomous navigation and human motion forecasting, whose work directly addresses the critical challenge of safe robot and vehicle operation in crowded, unpredictable environments. Her primary research areas include trajectory prediction, multimodal interaction modeling, and meta-learning for cross-scene generalization. Shi’s major contribution lies in developing interpretable, socially-aware models that capture the dynamic and heterogeneous nature of human interactions—a key bottleneck in collision avoidance systems. Her most cited work, “Multimodal Interaction-Aware Trajectory Prediction in Crowded Space” (2020, 28 citations), introduced a framework that accounts for the intrinsic multimodality of human motion, significantly improving prediction accuracy in complex social settings. More recently, her MetaTraj model (2023, 9 citations) pioneered a meta-learning approach to enable trajectory prediction across different scenes and object types, reducing the need for retraining. Her 2024 paper on interpretable social interactions further advances the field by making these complex models more transparent and trustworthy. With a growing citation impact and a focus on real-world deployment, Shi’s research is shaping the next generation of autonomous systems that must navigate safely alongside people.