Biosketch
Tzu-Yuan Huang received his M.Sc. degree in Electrical Engineering with a specialization in Motion planning & System Identification for Robot manipulators from National Cheng Kung University (NCKU), Taiwan in 2020. Following his graduation, he joined Syntec Technology as an R&D engineer from 2020 to 2023, where he developed trajectory planning algorithms of five-axis machine tool and robot using C++ and python.
Currently, Tzu-Yuan Huang is pursuing his Ph.D. degree at the Chair of Information-Oriented Control (ITR) at Technical University of Munich. He is also a member of the Konrad Zuse School of Excellence in Reliable Artificial Intelligence (relAI). His research interest is data-driven control in robotic system, and he contributes to the SeaClear project, which focuses on automating the collection of underwater waste.
relAI Research
Generation of safe and dynamically consistent trajectories via control-augmented diffusion models
Diffusion models are an expressive family of generative models known to deliver competitive sample quality on image and audio synthesis tasks. Currently, diffusion models start to be considered for generating actions in dynamic systems. Many of the envisioned applications, however, have strict safety requirements as e.g. in robotics. Ensuring constraint satisfaction in diffusion models is still a fundamental open question, that needs to solved to facilitate real-world deployment