# Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Masking

arXiv: https://arxiv.org/abs/2408.10162 · HTML: https://mlsanity.com/paper/2408.10162/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 19 Aug 2024.

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Closer Look at Invalid Action Masking in Policy Gradient Algorithms](https://mlsanity.com/paper/2006.14171/) (2020)
- [IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks](https://mlsanity.com/paper/1911.07246/) (2019)
- [Structured agents for physical construction](https://mlsanity.com/paper/1904.03177/) (2019)
- [Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning](https://mlsanity.com/paper/2203.13733/) (2022)
- [Combining Q-Learning and Search with Amortized Value Estimates](https://mlsanity.com/paper/1912.02807/) (2019)
- [Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning](https://mlsanity.com/paper/2110.15481/) (2021)
- [Combinatorial 3D Shape Generation via Sequential Assembly](https://mlsanity.com/paper/2004.07414/) (2020)
- [Planning Assembly Sequence with Graph Transformer](https://mlsanity.com/paper/2210.05236/) (2022)
- [StableLego: Stability Analysis of Block Stacking Assembly](https://mlsanity.com/paper/2402.10711/) (2024)
- [A Lightweight and Transferable Design for Robust LEGO Manipulation](https://mlsanity.com/paper/2309.02354/) (2023)
- [Simulation-aided Learning from Demonstration for Robotic LEGO Construction](https://mlsanity.com/paper/2309.11010/) (2023)
- [Efficient and Feasible Robotic Assembly Sequence Planning via Graph Representation Learning](https://mlsanity.com/paper/2303.10135/) (2023)
- [Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Control](https://mlsanity.com/paper/2306.11862/) (2023)
- [Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications](https://mlsanity.com/paper/2308.10393/) (2023)
- [Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning](https://mlsanity.com/paper/2404.04772/) (2024)
- [Assembly Planning from Observations under Physical Constraints](https://mlsanity.com/paper/2204.09616/) (2022)

## Built on by (most cited first, 5 of 5)

- [Generating Physically Stable and Buildable Brick Structures from Text](https://mlsanity.com/paper/2505.05469/) (2025)
- [AssemblyComplete: 3D Combinatorial Construction with Deep Reinforcement Learning](https://mlsanity.com/paper/2410.15469/) (2024)
- [Prompt-to-Product: Generative Assembly via Bimanual Manipulation](https://mlsanity.com/paper/2508.21063/) (2025)
- [Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithms](https://mlsanity.com/paper/2603.09090/) (2026)
- [ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planning](https://mlsanity.com/paper/2610.00487/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/intelligent-control-lab/PhysicsAwareCombinatorialASP.