Research Statement
My research focuses on developing intelligent motion solutions for robotics and autonomous systems to transform productivity, safety, and reliability in manufacturing, construction, and other industrial domains. These domains continually grapple with a fundamental trade-off - productivity demands faster, more flexible operations, while safety, both physical and psychological, requires careful constraints and predictable behaviour. My work aims to dissolve this tension by enabling robots to generate motions that are efficient, adaptive, and inherently safe for human-centric environments.
Central to this vision is the design of robotic behaviours that are not only physically safe, through compliant control, constraint-aware planning, collision avoidance, and uncertainty-aware decision-making, but also psychologically safe. I investigate how motion can function as an expressive, communicative channel that enhances human trust, reduces cognitive load, and clarifies robot intent during coexistence, cooperation, and collaboration. Intelligent motion generation thus becomes a mechanism for improving both operational throughput and human-robot interaction quality.
A core theme of my research is the fusion of knowledge-driven and data-driven paradigms. I develop hybrid architectures that integrate model-based planning, physics-informed representations, and symbolic task structures with model-free learning, deep reinforcement learning, and neuro-symbolic reasoning. This combination leverages structured priors such as dynamic models, task ontologies, or principles of human movement, while enabling robots to learn generalizable behaviours from data and real-world interaction. The result is motion intelligence that is robust, interpretable, and capable of adapting to unstructured and dynamic industrial settings.
Ultimately, my research seeks to develop a new class of autonomous robotic systems that generate intelligent, expressive motions to achieve high productivity without compromising safety, setting the foundation for the next generation of human-aware, trustworthy, and industry-ready robotic solutions.
Planning Module for Robotic Prefabrication of Structural Steel Components for Buildings
This research aims to investigate the robotization of the manufacturing and assembly stages of structural steel component fabrication with the goal of identifying a potential optimal prefabrication system for buildings by establishing a seamless design-to-fabrication framework.
Design Module for Automated Prefabrication of Structural Steel Components for Buildings
This research seeks to automate the design stage of structural steel components to solve the tasks of optimal Design for Manufacturing and Assembly (DfMA). The primary focus is on the prefabrication of planar building components such as wall panels, roof panels, and floor panels.