RL-Lock: Reinforcement Learning for Generating Interlocking Assemblies
2026-08-03 • Artificial Intelligence
Artificial IntelligenceGraphics
AI summaryⓘ
The authors study how to create shapes made of pieces that fit together tightly just by their shapes, without using glue or nails. They see this as a step-by-step process, where you decide which piece each tiny part of the shape belongs to. To solve this, they use a type of AI called reinforcement learning combined with a smart search method to efficiently find good ways to split the shape. Their method, RL-Lock, works well and is faster than older methods, especially for tricky shapes that were hard to handle before.
interlocking assemblyshape decompositionvoxel gridreinforcement learningMonte Carlo Tree Search (MCTS)policy-value learningcombinatorial search3D object partitioning
Authors
Xuyang Ma, Chaewoon Kim, Haonan Zhang, Rulin Chen, Ziqi Wang, Peng Song
Abstract
An interlocking assembly is an assembly in which component parts are connected purely through their geometric arrangement, without relying on external connectors such as glue and nails. Such assemblies have been widely used in a variety of real-world applications due to their structural stability. The problem of generating interlocking assemblies is generally formulated as a shape decomposition problem, where a target 3D object represented as a voxel grid is partitioned into a prescribed number of interlocking pieces. We observe that generating interlocking assemblies is inherently a sequential decision-making problem, where an agent repeatedly decides which piece each voxel should be assigned to. Inspired by the observation, we propose the first reinforcement learning framework RL-Lock for generating interlocking assemblies, without relying on handcrafted search heuristics as existing works did. RL-Lock combines structured action chunking with MCTS-guided policy-value learning to efficiently navigate the large combinatorial search space for interlocking assembly generation. We demonstrate through experiments that RL-Lock allows effective generation of interlocking assemblies, especially for challenging cases in which existing approaches take too long or even fail to find a valid solution.