Papers
3
Total Citations
14
H-Index
2
About
Zhuo Sun is a robotics researcher whose work sits at the intersection of perception, planning, and multi-agent coordination. Their primary research areas include visual-inertial SLAM, multi-robot scheduling, and modular self-reconfigurable robotics. In their most cited work, "ORB-YOLO: An Indoor IMU-aided Visual-Inertial SLAM System for Dynamic Environment" (2023, 7 citations), Sun addresses a critical challenge in indoor robotics: maintaining accurate localization in dynamic environments where moving objects disrupt traditional visual SLAM. By fusing inertial measurement unit data with a YOLO-based object detection pipeline, this system demonstrates robust performance where conventional methods fail. Sun’s second major contribution, "Multi-AGV Scheduling based on Hierarchical Intrinsically Rewarded Multi-Agent Reinforcement Learning" (2022, 5 citations), tackles the complex coordination problem of multiple automated guided vehicles in warehouse and manufacturing settings. This work introduces a hierarchical reinforcement learning framework that enables scalable, efficient scheduling without requiring hand-crafted reward functions. Most recently, in "Learning to Self-Reconfigure for Freeform Modular Robots via Altruism Proximal Policy Optimization" (2023, 2 citations), Sun explores how modular robots can autonomously change their shape to adapt to tasks—a fundamental capability for future versatile robotic systems. Across these contributions, Sun consistently applies deep reinforcement learning to solve real-world robotic challenges, from perception to coordination to morphological adaptation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3