Charles Sun
Papers
1
Total Citations
15
H-Index
1
About
Charles Sun is a leading researcher in robotics and artificial intelligence, with a focus on autonomous learning for real-world systems. His work bridges the critical gap between simulation and physical deployment, particularly in mobile manipulation—enabling robots to navigate and interact with objects in unstructured environments. Sun’s most cited paper, "Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation" (2021, 15 citations), tackles the formidable challenge of using reinforcement learning without human intervention or extensive instrumentation. By developing methods that allow robots to learn complex, multi-step tasks—like navigating to an object and grasping it—directly from real-world experience, he has advanced the practicality of autonomous robotics. His contributions highlight how reinforcement learning can move beyond controlled lab settings to dynamic, everyday spaces, addressing key hurdles in sample efficiency and safety. Sun’s work is foundational for students and researchers aiming to deploy intelligent robots in homes, warehouses, and beyond, demonstrating that fully autonomous skill acquisition is not just theoretical but achievable.
Research Focus
Key Achievements
Top Papers
- 1