Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Masking
This addresses the challenge of ensuring physical feasibility in assembly planning for robotics and manufacturing, though it is incremental as it builds on existing reinforcement learning methods with a new action masking technique.
The paper tackles the problem of generating physically executable assembly sequences for combinatorial objects using deep reinforcement learning, achieving a 100% success rate on over 250 3D Lego structures while a baseline fails on more than 40 structures.
Combinatorial assembly uses standardized unit primitives to build objects that satisfy user specifications. This paper studies assembly sequence planning (ASP) for physical combinatorial assembly. Given the shape of the desired object, the goal is to find a sequence of actions for placing unit primitives to build the target object. In particular, we aim to ensure the planned assembly sequence is physically executable. However, ASP for combinatorial assembly is particularly challenging due to its combinatorial nature. To address the challenge, we employ deep reinforcement learning to learn a construction policy for placing unit primitives sequentially to build the desired object. Specifically, we design an online physics-aware action mask that filters out invalid actions, which effectively guides policy learning and ensures violation-free deployment. In the end, we apply the proposed method to Lego assembly with more than 250 3D structures. The experiment results demonstrate that the proposed method plans physically valid assembly sequences to build all structures, achieving a $100\%$ success rate, whereas the best comparable baseline fails more than $40$ structures. Our implementation is available at \url{https://github.com/intelligent-control-lab/PhysicsAwareCombinatorialASP}.