Seiji Shaw

Papers

Total Citations

H-Index

About

Seiji Shaw is a robotics researcher whose work focuses on enabling robots to perform complex, bimanual manipulation tasks safely and efficiently. His primary research areas include motion planning, constrained optimization, and learning for motor skills, with a particular emphasis on ensuring operational safety in dynamic environments. Shaw’s major contributions center on developing novel frameworks that integrate analytic inverse kinematics with nonlinear equality constraints, allowing bimanual robots to maintain a fixed transformation between end effectors during object manipulation—a critical capability for tasks like assembly or cooperative handling. His 2024 paper on constrained bimanual planning has already garnered 11 citations, highlighting its impact on the field. Additionally, Shaw has advanced the use of constrained dynamic movement primitives (DMPs) for safe skill learning, as demonstrated in his 2022 and 2023 works, which address collision avoidance and safety guarantees in novel environments. These contributions bridge the gap between generalization in learning-based methods and the rigorous constraints required for real-world deployment, making Shaw’s research essential reading for students and researchers interested in safe, dexterous robotic manipulation.