Papers
8
Total Citations
522
H-Index
6
About
Shangding Gu is a prominent researcher specializing in safe reinforcement learning (RL), multi-agent systems, and autonomous robotics. His work addresses one of the most pressing challenges in modern AI: ensuring that reinforcement learning algorithms operate safely when deployed in real-world environments such as autonomous driving, robotics, and industrial automation. Gu's most influential contribution is his comprehensive review of safe reinforcement learning methods, theories, and applications, which has accumulated nearly 300 citations across its iterations and has become an essential reference for researchers entering the field. His pioneering work on safe multi-agent reinforcement learning for multi-robot control (120 citations) bridges a critical gap by enabling cooperative, safety-aware behavior among robot teams. Beyond theoretical contributions, Gu has tackled practical challenges including high-density autonomous parking scheduling, human-centered safe robot frameworks, and offline RL under uncertainty — demonstrating a consistent drive to translate algorithmic advances into deployable systems. With over 500 cumulative citations and a research portfolio spanning foundational theory to real-world robot control, Gu has established himself as a leading voice in the safe AI community, with his work shaping how researchers and engineers think about building trustworthy autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1A Review of Safe Reinforcement Learning: Methods, Theories, and Applications194 citations · 2024
- 2Safe multi-agent reinforcement learning for multi-robot control120 citations · 2023
- 3A Review of Safe Reinforcement Learning: Methods, Theory and Applications102 citations · 2022
- 4
- 5
- 6
- 7UAC: Offline Reinforcement Learning With Uncertain Action Constraint6 citations · 2023
- 8