Zhuangzhuang Zhang
Papers
6
Total Citations
97
H-Index
5
About
Zhuangzhuang Zhang is a rising researcher in robotic manipulation, focusing on the intersection of computer vision, tactile sensing, and reinforcement learning. His work addresses critical challenges in industrial automation, particularly for tasks involving complex, reflective, or textureless metal parts. Zhang’s major contributions include developing a residual reinforcement learning method for robotic assembly that integrates visual and force information, achieving 40 citations. He also pioneered a digital twin-enabled framework for assessing grasp outcomes on unknown objects using visual-tactile fusion perception (23 citations). His research on grasp stability assessment through attention-guided cross-modality fusion and transfer learning (11 citations) advances the fundamental understanding of optimal grasping strategies. Zhang’s work on 6D pose estimation for metal parts, using a Frequency-Guided CNN-Transformer fusion network (10 citations), directly addresses the challenges of color homogeneity and light reflection in industrial settings. He has also developed a novel grasp detection framework using low-cost RGB-D cameras for industrial bin picking (9 citations), demonstrating practical, cost-effective solutions. With a cumulative impact of nearly 100 citations across his key papers, Zhang is establishing himself as an innovator in robotic perception and manipulation, bridging the gap between academic research and real-world industrial applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6