Papers
2
Total Citations
7
H-Index
1
About
Yunseol Cho’s research lies at the intersection of reinforcement learning and agricultural robotics, with a focus on developing intelligent systems for real-world applications. In their early work, Cho introduced a novel Q-learning method that uses convex clustering to partition continuous state spaces into meaningful regions, solving the structural credit assignment problem—a foundational contribution that has garnered 6 citations and remains relevant for adaptive control systems. More recently, Cho has turned to the pressing challenge of agricultural automation, addressing labor shortages by designing collision-free path planning and optimal position selection algorithms for fruit-picking robots. Their 2025 paper in this area, while newly published with 1 citation, tackles the critical gap between robotic harvesting potential and practical deployment, proposing solutions for navigating complex orchard environments. Cho’s work bridges theoretical machine learning advances with tangible engineering solutions, demonstrating a commitment to both algorithmic innovation and societal impact. By combining reinforcement learning techniques with robotics, Cho is helping to shape a future where autonomous systems can sustainably support global food production.
Research Focus
Key Achievements
Top Papers
- 1Region-based Q-learning using convex clustering approach6 citations · 2002
- 2