DuploTrack: A Realtime System for Authoring and Guiding Duplo Block Assembly

Ankit Gupta[1], Dieter Fox[1], Brian Curless[1], Michael Cohen[2]

[1] University of Washington, [2] Microsoft Research

Video demonstrating our System

Recording of the system learning how a model is built from scratch


We demonstrate a realtime system which infers and tracks the assembly process of a snap-together block model using a Kinect sensor. The inference enables us to build a virtual replica of the model at every step. Tracking enables us to provide context specific visual feedback on a screen by augmenting the rendered virtual model aligned with the physical model. The system allows users to author a new model and uses the inferred assembly process to guide its recreation by others. We propose a novel way of assembly guidance where the next block to be added is rendered in blinking mode with the tracked virtual model on screen. The system is also able to detect any mistakes made and helps correct them by providing appropriate feedback. We focus on assemblies of Duplo blocks.

We discuss the shortcomings of existing methods of guidance — static figures or recorded videos — and demonstrate how our method avoids those shortcomings. We also report on a user study to compare our system with standard figure-based guidance methods found in user manuals. The results of the user study suggest that our method is able to aid users’ structural perception of the model better, leads to fewer assembly errors, and reduces model construction time.

Download files


Send any comments or questions to Ankit Gupta (Email : ankit [at] cs [dot] washington [dot] edu)