Papers
5
Total Citations
53
H-Index
4
About
Yi Dong is a researcher whose work spans the intersection of artificial intelligence, robotics, and autonomous systems, with a particular focus on making intelligent machines more reliable, efficient, and cooperative. His most-cited contribution applies YOLO-based deep learning to real-time object detection for agricultural robotics, demonstrating how machine vision can meaningfully accelerate crop harvesting automation — a paper that has already attracted 29 citations since its 2024 publication. Alongside this applied work, Dong has made significant theoretical contributions to the dependability and safety of Deep Reinforcement Learning (DRL) in robotics, employing probabilistic model checking and reachability verification to rigorously assess and validate DRL-controlled systems — critical advances given the black-box nature of such algorithms in safety-sensitive deployments. His research further extends into multi-robot coordination, where he has explored decentralised cooperative control through distributed optimisation and Nash equilibrium-seeking strategies for non-cooperative heterogeneous robot networks. Collectively, his work addresses both the practical deployment challenges and the formal verification demands facing modern autonomous systems. With a growing citation record and publications spanning top venues, Dong is emerging as a thoughtful contributor to the future of trustworthy, intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5