# Learning Sequences of Manipulation Primitives for Robotic Assembly

arXiv: https://arxiv.org/abs/2011.00778 · HTML: https://mlsanity.com/paper/2011.00778/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models](https://mlsanity.com/paper/2401.03360/) (2023)
- [Factory: Fast Contact for Robotic Assembly](https://mlsanity.com/paper/2205.03532/) (2022)
- [Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation](https://mlsanity.com/paper/2303.02646/) (2023)
- [Fine Robotic Manipulation without Force/Torque Sensor](https://mlsanity.com/paper/2301.13413/) (2023)
- [Ground Manipulator Primitive Tasks to Executable Actions using Large Language Models](https://mlsanity.com/paper/2308.06810/) (2023)
- [A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks](https://mlsanity.com/paper/2504.14820/) (2025)

## Abstract (arXiv)

This paper explores the idea that skillful assembly is best represented as dynamic sequences of Manipulation Primitives, and that such sequences can be automatically discovered by Reinforcement Learning. Manipulation Primitives, such as "Move down until contact", "Slide along x while maintaining contact with the surface", have enough complexity to keep the search tree shallow, yet are generic enough to generalize across a wide range of assembly tasks. Moreover, the additional "semantics" of the Manipulation Primitives make them more robust in sim2real and against model/environment variations and uncertainties, as compared to more elementary actions. Policies are learned in simulation, and then transferred onto a physical platform. Direct sim2real transfer (without retraining in real) achieves excellent success rates on challenging assembly tasks, such as round peg insertion with 0.04 mm clearance or square peg insertion with large hole position/orientation estimation errors.