mlsanityData to 14 Oct 2026

A Lightweight and Transferable Design for Robust LEGO Manipulation

arXiv 2309.02354 ↗First posted 5 Sep 2023cs.RO cs.LG cs.NEcited by 4

Not on the map. Why?

Abstract (arXiv)

Lego is a well-known platform for prototyping pixelized objects. However, robotic Lego prototyping (i.e., manipulating Lego bricks) is challenging due to the tight connections and accuracy requirements. This paper investigates safe and efficient robotic Lego manipulation. In particular, this paper reduces the complexity of the manipulation by hardware-software co-design. An end-of-arm tool (EOAT) is designed, which reduces the problem dimension and allows large industrial robots to manipulate small Lego bricks. In addition, this paper uses evolution strategy to optimize the robot motion for Lego manipulation. Experiments demonstrate that the EOAT can reliably manipulate Lego bricks and the learning framework can effectively and safely improve the manipulation performance to a 100% success rate. The co-design is deployed to multiple robots (i.e., FANUC LR-mate 200id/7L and Yaskawa GP4) to demonstrate its generalizability and transferability. In the end, we show that the proposed solution enables sustainable robotic Lego prototyping, in which the robot can repeatedly assemble and disassemble different prototypes.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 19 of its 52 references that are in the map. First posted on arXiv 5 Sep 2023.

Builds on

19 of 52 references.

References · 19

  1. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  2. 2017Data-efficient Deep Reinforcement Learning for Dexterous Manipulationcited by 63
  3. 2020Warm Starting CMA-ES for Hyperparameter Optimizationcited by 19
  4. 2021Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learningcited by 19
  5. 2019Safe Control Algorithms Using Energy Functions: A Unified Framework, Benchmark, and New Directionscited by 17
  6. 2022Translating a Visual LEGO Manual to a Machine-Executable Plancited by 15
  7. 2020Building LEGO Using Deep Generative Models of Graphscited by 14
  8. 2021Image2Lego: Customized LEGO Set Generation from Imagescited by 14
  9. 2020Combinatorial 3D Shape Generation via Sequential Assemblycited by 13
  10. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  11. 2022Break and Make: Interactive Structural Understanding Using LEGO Brickscited by 8
  12. 2018A Learning Framework for High Precision Industrial Assemblycited by 4
7 more
  1. 2022Budget-Aware Sequential Brick Assembly with Efficient Constraint Satisfactioncited by 4
  2. 2023Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Controlcited by 3
  3. 2022Safe Interactive Industrial Robots using Jerk-based Safe Set Algorithmcited by 2
  4. 2022Task-Agnostic Adaptation for Safe Human-Robot Handovercited by 2
  5. 2023Zero-shot Transferable and Persistently Feasible Safe Control for High Dimensional Systems by Consistent Abstractioncited by 2
  6. 2023Robotic LEGO Assembly and Disassembly from Human Demonstrationcited by 2
  7. 2022A Composable Framework for Policy Design, Learning, and Transfer Toward Safe and Efficient Industrial Insertioncited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2025Generating Physically Stable and Buildable Brick Structures from Textcited by 24
  2. 2024Automating Robot Failure Recovery Using Vision-Language Models With Optimized Promptscited by 16
  3. 2024Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Maskingcited by 5
  4. 2025Prompt-to-Product: Generative Assembly via Bimanual Manipulationcited by 1