# Learning Robotic Assembly from CAD

arXiv: https://arxiv.org/abs/1803.07635 · HTML: https://mlsanity.com/paper/1803.07635/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2018.

## Built on by (most cited first, 21 of 21)

- [JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints](https://mlsanity.com/paper/2111.12772/) (2021)
- [Factory: Fast Contact for Robotic Assembly](https://mlsanity.com/paper/2205.03532/) (2022)
- [Offline Meta-Reinforcement Learning for Industrial Insertion](https://mlsanity.com/paper/2110.04276/) (2021)
- [JUICER: Data-Efficient Imitation Learning for Robotic Assembly](https://mlsanity.com/paper/2404.03729/) (2024)
- [ZePHyR: Zero-shot Pose Hypothesis Rating](https://mlsanity.com/paper/2104.13526/) (2021)
- [SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering](https://mlsanity.com/paper/2210.15185/) (2022)
- [Category-Level Multi-Part Multi-Joint 3D Shape Assembly](https://mlsanity.com/paper/2303.06163/) (2023)
- [Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks](https://mlsanity.com/paper/2106.14070/) (2021)
- [RoboAssembly: Learning Generalizable Furniture Assembly Policy in a Novel Multi-robot Contact-rich Simulation Environment](https://mlsanity.com/paper/2112.10143/) (2021)
- [Rearrangement Planning for General Part Assembly](https://mlsanity.com/paper/2307.00206/) (2023)
- [VLMgineer: Vision Language Models as Robotic Toolsmiths](https://mlsanity.com/paper/2507.12644/) (2025)
- [Benchmarking Off-The-Shelf Solutions to Robotic Assembly Tasks](https://mlsanity.com/paper/2103.05140/) (2021)
- [Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection](https://mlsanity.com/paper/2312.10571/) (2023)
- [Contact Skill Imitation Learning for Robot-Independent Assembly Programming](https://mlsanity.com/paper/1908.06272/) (2019)
- [Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors](https://mlsanity.com/paper/2103.03793/) (2021)
- [Combinative Matching for Geometric Shape Assembly](https://mlsanity.com/paper/2508.09780/) (2025)
- [A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation](https://mlsanity.com/paper/2207.13438/) (2022)
- [Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space](https://mlsanity.com/paper/2405.01134/) (2024)
- [Learning A Simulation-based Visual Policy for Real-world Peg In Unseen Holes](https://mlsanity.com/paper/2205.04297/) (2022)
- [Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning](https://mlsanity.com/paper/2205.05963/) (2022)
- [Issues with Measuring Task Complexity via Random Policies in Robotic Tasks](https://mlsanity.com/paper/2602.18856/) (2026)

## Abstract (arXiv)

In this work, motivated by recent manufacturing trends, we investigate autonomous robotic assembly. Industrial assembly tasks require contact-rich manipulation skills, which are challenging to acquire using classical control and motion planning approaches. Consequently, robot controllers for assembly domains are presently engineered to solve a particular task, and cannot easily handle variations in the product or environment. Reinforcement learning (RL) is a promising approach for autonomously acquiring robot skills that involve contact-rich dynamics. However, RL relies on random exploration for learning a control policy, which requires many robot executions, and often gets trapped in locally suboptimal solutions. Instead, we posit that prior knowledge, when available, can improve RL performance. We exploit the fact that in modern assembly domains, geometric information about the task is readily available via the CAD design files. We propose to leverage this prior knowledge by guiding RL along a geometric motion plan, calculated using the CAD data. We show that our approach effectively improves over traditional control approaches for tracking the motion plan, and can solve assembly tasks that require high precision, even without accurate state estimation. In addition, we propose a neural network architecture that can learn to track the motion plan, and generalize the assembly controller to changes in the object positions.