Date of Award

Spring 5-18-2026

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Alex Wong

Abstract

Burr puzzles are interlocking assemblies whose pieces must be inserted and removed through tightly constrained motions. Designing them is difficult because geometric fit, interlocking behavior, and disassembly order are tightly coupled, while existing computational methods remain largely limited to voxelized or template-based constructions.

This work presents a framework for 3D puzzle generation beyond voxelized parts. The method replaces local mobility heuristics with a certified search over geometry edits. Starting from a topological contact specification, it constructs signed distance fields for individual parts, applies complementary local edits, and validates each candidate using exact geometric checks and a kernel disassembly graph. The framework also introduces a more general model of subassembly motion and a finite search procedure that is complete with respect to the chosen discretization.

By enlarging the search space from voxelized, template-constrained constructions to topology-driven search over non-voxelized geometry, this work formulates burr puzzle generation as a topology-driven search problem over non-voxelized geometry and lays a foundation for generating interlocking puzzles with greater geometric flexibility and certified disassembly structure.

Download

Share

COinS