Jinqiang Bai
Papers
8
Total Citations
269
H-Index
7
About
Jinqiang Bai is a researcher specializing in robotics, deep learning, and autonomous systems, with particular expertise in robot perception, navigation, and path planning. His work sits at the intersection of computer vision and intelligent robotics, tackling real-world challenges in both urban and agricultural environments. Bai's most influential contribution is his 2018 paper on a deep learning-powered garbage-picking robot capable of autonomous detection and navigation on grass — a work that has garnered over 160 citations and demonstrated practical applications of neural networks in environmental robotics. He has also made notable advances in visual localization and odometry, proposing deep global-relative networks to address the persistent drift problem in long-term robot navigation, and developing a feedback mechanism-based stereo visual-inertial SLAM system that balances real-time performance with accuracy. Beyond mobile robotics, Bai has contributed to agricultural automation through complete coverage path planning algorithms for transplanting robots, as well as to human-robot interaction via deep learning approaches for facial pose estimation using label distributions. Collectively, his publications reflect a sustained commitment to bridging cutting-edge deep learning techniques with tangible robotic applications, earning him a growing presence in both the robotics and computer vision research communities.
Research Focus
Key Achievements
Top Papers
- 1Deep Learning Based Robot for Automatically Picking Up Garbage on the Grass161 citations · 2018
- 2Facial Pose Estimation by Deep Learning from Label Distributions38 citations · 2019
- 3
- 4
- 5
- 6A Novel Feedback Mechanism-Based Stereo Visual-Inertial SLAM10 citations · 2019
- 7
- 8Facial Pose Estimation by Deep Learning from Label Distributions4 citations · 2019