Xinyi Ye

Capital Normal University

Papers

2

Total Citations

34

H-Index

2

About

Xinyi Ye is a rising researcher at the forefront of embodied AI and robotic perception, whose work bridges the critical gap between static assumptions and dynamic real-world deployment. Her most cited paper, "A Dynamic Scene Vision SLAM Method Incorporating Object Detection and Object Characterization" (2023, 19 citations), addresses a fundamental limitation in simultaneous localization and mapping (SLAM). By integrating object detection with RGB-D SLAM, Ye’s method dramatically improves robot navigation robustness in unpredictable, dynamic environments—a breakthrough for real-world autonomy. Building on this, her recent work "SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models" (2025, 15 citations) pioneers a novel approach to robot learning. By re-discretizing pre-learned action grids to capture setup-specific spatial movements, SpatialVLA achieves exceptional in-distribution generalization and out-of-distribution adaptation. This work marks a significant step toward generalist robots that can seamlessly transfer skills across new environments. With a growing citation impact and a clear trajectory from robust perception to flexible action, Xinyi Ye is shaping the future of intelligent, adaptive robotics.

Research Focus

Key Achievements

2
H-Index
2
Papers
34
Total Citations
17
Avg Citations/Paper
🏆 Most Cited Paper
A Dynamic Scene Vision SLAM Method Incorporating Object Detection and Object Characterization
19 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 14
🏛 Institutions: Capital Normal University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago