Jingjing Zheng

Amazon (United States), Shenyang Jianzhu University

Papers

2

Total Citations

15

H-Index

2

About

Jingjing Zheng’s research bridges the critical gap between robotic perception and mechanical adaptability, with a focus on enabling machines to navigate complex, unstructured environments. Her key contributions lie in two complementary areas: monocular depth estimation for robotic vision and novel deformable locomotion mechanisms. In her highly cited 2022 work, *Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation*, Zheng tackled a fundamental challenge in deep learning—enabling models trained on synthetic data to generalize to real-world scenes. This approach, which has garnered 11 citations, is vital for low-cost robotic tasks like obstacle detection and mapping, where ground-truth depth data is scarce. More recently, her 2024 study, *Design and research of deformable wheel-legged robot based on origami mechanisms*, introduces a groundbreaking robot that uses origami-inspired structures to transition between wheeled and legged locomotion. With 4 citations already, this work directly addresses the limited adaptability of traditional wheeled robots, offering a lightweight, transformable solution for search-and-rescue or planetary exploration. Zheng’s dual focus on perception and hardware innovation marks her as a rising figure in robotics, where her work promises to make autonomous systems both smarter and more physically versatile.

Research Focus

Key Achievements

2
H-Index
2
Papers
15
Total Citations
8
Avg Citations/Paper
🏆 Most Cited Paper
Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation
11 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: Amazon (United States), Shenyang Jianzhu University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago