Shinjiro Sueda

Texas A&M University, University of British Columbia

Papers

Total Citations

H-Index

About

Shinjiro Sueda is a leading researcher at the intersection of robotics, physics-based simulation, and reinforcement learning. His work is defined by a unique ability to bridge computational control theory with the physical complexities of real-world manipulation. Sueda’s most impactful contribution is in **Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control** (2020), which has garnered 44 citations. This work introduces a framework that leverages predictive models to guide policy learning, enabling robots to balance competing objectives—such as speed, precision, and energy efficiency—in continuous control tasks. More recently, his **ASAP** system (2024) tackles the grand challenge of automated assembly planning for complex, general-shaped parts, ensuring physical feasibility through rigorous physics-based simulation. Sueda’s research extends to biologically inspired systems, including the dynamic simulation of the human hand and the knotting behavior of hagfish, demonstrating a fascination with how natural systems solve intricate manipulation problems. His work is essential reading for anyone interested in advancing robot autonomy in manufacturing, assembly, and dexterous manipulation.