Papers
1
Total Citations
11
H-Index
1
About
Yinke Dong is a rising researcher in autonomous driving, with a focus on trajectory prediction and agent-environment interaction modeling. Their work addresses a critical challenge in safe autonomous navigation: accurately forecasting the future paths of surrounding vehicles and pedestrians amidst complex, dynamic driving scenes. Dong’s key contribution lies in developing novel deep learning frameworks that leverage bidirectional agent-map interactions, enabling models to more effectively capture how both agents influence the environment and vice versa. Their most-cited paper, "Bidirectional Agent-Map Interaction Feature Learning Leveraged by Map-Related Tasks for Trajectory Prediction in Autonomous Driving" (2025), has already garnered 11 citations shortly after publication, signaling strong early impact in this fast-moving field. By integrating map-related auxiliary tasks, Dong’s approach enhances prediction robustness in real-world scenarios, bridging a gap between traditional agent-centric models and map-aware reasoning. This work positions Dong as an emerging voice in intelligent transportation systems, with potential to influence safer, more reliable autonomous vehicle behavior in urban environments.
Research Focus
Key Achievements
Top Papers
- 1