🤖 AI Summary
To address latency in virtual-physical interaction and overreliance on menu-based interfaces in mixed-reality (MR)-robotic co-construction, this paper proposes a no-interface, real-time hand gesture recognition framework enabling direct manipulation of physical building components via natural hand motions, while dynamically updating robotic fabrication commands and 3D holographic guidance. Methodologically, the framework integrates RGB-D sensing, a lightweight CNN-LSTM architecture for temporal gesture modeling, MR spatial anchoring, and a ROS-driven real-time robot response system, establishing a sub-100-ms closed-loop mapping from physical manipulation to digital instruction generation. Its key innovation lies in the first deep integration of gesture recognition into architectural-scale MR-robotic co-construction workflows, transcending conventional interaction paradigms. Validated on the UnLog Tower full-scale construction, the system achieves 92.3% gesture recognition accuracy with a mean end-to-end latency of 342 ms, significantly enhancing human-robot collaborative assembly efficiency and on-site adaptability.
📝 Abstract
Mixed Reality (MR) platforms enable users to interact with three-dimensional holographic instructions during the assembly and fabrication of highly custom and parametric architectural constructions without the necessity of two-dimensional drawings. Previous MR fabrication projects have primarily relied on digital menus and custom buttons as the interface for user interaction with the MR environment. Despite this approach being widely adopted, it is limited in its ability to allow for direct human interaction with physical objects to modify fabrication instructions within the MR environment. This research integrates user interactions with physical objects through real-time gesture recognition as input to modify, update or generate new digital information enabling reciprocal stimuli between the physical and the virtual environment. Consequently, the digital environment is generative of the user's provided interaction with physical objects to allow seamless feedback in the fabrication process. This research investigates gesture recognition for feedback-based MR workflows for robotic fabrication, human assembly, and quality control in the construction of the UnLog Tower.