Joseph Sun de la Cruz

National Instruments (United States), University of Waterloo

Papers

Total Citations

H-Index

About

Joseph Sun de la Cruz is a leading researcher in robot manipulation and model-based control, with a focused expertise in learning inverse dynamics for high-performance robotic systems. His work addresses the critical challenge of obtaining accurate dynamic models for robot manipulators, particularly in the presence of modeling uncertainties like friction—a problem that limits the performance of classical controllers. Sun de la Cruz pioneered the use of Gaussian Process Regression for online learning of inverse dynamics, enabling robots to adapt their models in real-time. His 2012 paper on this topic has garnered 20 citations, while his foundational 2010 study on learning inverse dynamics for redundant manipulators has been cited 14 times, underscoring its influence in the field. His research is especially relevant for the next generation of humanoid, assistive, and entertainment robots, where precise control is essential. As the sole author of a 2011 thesis on learning inverse dynamics, Sun de la Cruz has established himself as a key contributor to adaptive control strategies that bridge the gap between theoretical models and real-world robotic applications.