Zhi Peng
Papers
1
Total Citations
11
H-Index
1
About
Zhi Peng is a researcher at the forefront of intelligent robotics, specializing in object recognition, grasping algorithms, and reinforcement learning for mobile manipulators. His most cited work, "An Object Recognition Grasping Approach Using Proximal Policy Optimization With YOLOv5" (2023, 11 citations), tackles critical limitations in traditional grasping methods—namely, narrow application scenarios, low accuracy, and task complexity. By integrating YOLOv5’s real-time object detection with Proximal Policy Optimization (PPO), Peng developed a novel framework that enables robots to autonomously identify and grasp objects with enhanced precision and adaptability. This contribution bridges computer vision and deep reinforcement learning, offering a scalable solution for dynamic, real-world environments. Though early in his career, Peng’s work has already garnered attention for its practical impact on industrial automation and service robotics. His research continues to push boundaries in autonomous manipulation, promising to make robotic systems more versatile and intelligent. For students and researchers exploring the intersection of AI and robotics, Peng’s approach exemplifies how combining state-of-the-art detection with adaptive learning can solve longstanding challenges in robotic grasping.
Research Focus
Key Achievements
Top Papers
- 1