Papers
1
Total Citations
6
H-Index
1
About
Ziyang Lu is a rising researcher at the forefront of embodied AI and human-robot interaction, with a sharp focus on 3D visual grounding and spatial reasoning. His most cited work, "ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding" (2024, 6 citations), tackles a critical bottleneck in robotics: enabling machines to precisely link natural language descriptions to specific regions within complex 3D point cloud scenes. Lu’s key contribution lies in addressing how recognition errors in 3D grounding can cascade and degrade the reliability of AI systems—a problem he systematically dissects to improve interactive understanding. By advancing embodied reference understanding, his research bridges the gap between human communication and robotic perception, making autonomous systems more intuitive and robust. Though early in his career, Lu’s work on ScanERU has already garnered attention for its practical implications in real-world human-robot collaboration, from assistive robotics to autonomous navigation. His focus on error-aware grounding promises to enhance the safety and accuracy of next-generation AI, marking him as a promising voice in the evolving landscape of embodied intelligence.
Research Focus
Key Achievements
Top Papers
- 1