# Deep Reinforcement Learning for High Precision Assembly Tasks

arXiv: https://arxiv.org/abs/1708.04033 · HTML: https://mlsanity.com/paper/1708.04033/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2017.

## Built on by (most cited first, 30 of 39)

- [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)
- [Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study](https://mlsanity.com/paper/2103.11512/) (2021)
- [Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation](https://mlsanity.com/paper/2008.07682/) (2020)
- [TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation](https://mlsanity.com/paper/2409.11047/) (2024)
- [Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation](https://mlsanity.com/paper/2102.01295/) (2021)
- [InsertionNet -- A Scalable Solution for Insertion](https://mlsanity.com/paper/2104.14223/) (2021)
- [Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks](https://mlsanity.com/paper/2102.06838/) (2021)
- [Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty](https://mlsanity.com/paper/2106.04306/) (2021)
- [Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks](https://mlsanity.com/paper/2007.11646/) (2020)
- [InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Input](https://mlsanity.com/paper/2203.01153/) (2022)
- [Break and Make: Interactive Structural Understanding Using LEGO Bricks](https://mlsanity.com/paper/2207.13738/) (2022)
- [Benchmarking Off-The-Shelf Solutions to Robotic Assembly Tasks](https://mlsanity.com/paper/2103.05140/) (2021)
- [Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditions](https://mlsanity.com/paper/2312.16438/) (2023)
- [Contact Skill Imitation Learning for Robot-Independent Assembly Programming](https://mlsanity.com/paper/1908.06272/) (2019)
- [Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptation](https://mlsanity.com/paper/2206.02679/) (2022)
- [Imitation Learning for High Precision Peg-in-Hole Tasks](https://mlsanity.com/paper/2101.01052/) (2020)
- [Combining Learning from Demonstration with Learning by Exploration to Facilitate Contact-Rich Tasks](https://mlsanity.com/paper/2103.05904/) (2021)
- [Renaissance Robot: Optimal Transport Policy Fusion for Learning Diverse Skills](https://mlsanity.com/paper/2207.00978/) (2022)
- [Zero-Shot Transfer of Haptics-Based Object Insertion Policies](https://mlsanity.com/paper/2301.12587/) (2023)
- [Sim-and-Real Reinforcement Learning for Manipulation: A Consensus-based Approach](https://mlsanity.com/paper/2302.13423/) (2023)
- [The State of Robot Motion Generation](https://mlsanity.com/paper/2410.12172/) (2024)
- [Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation](https://mlsanity.com/paper/2609.01596/) (2026)
- [Accelerating Laboratory Automation Through Robot Skill Learning For Sample Scraping](https://mlsanity.com/paper/2209.14875/) (2022)
- [Generalizable Human-Robot Collaborative Assembly Using Imitation Learning and Force Control](https://mlsanity.com/paper/2212.01434/) (2022)
- [Learning Human-Inspired Force Strategies for Robotic Assembly](https://mlsanity.com/paper/2303.12440/) (2023)
- [A Peg-in-hole Task Strategy for Holes in Concrete](https://mlsanity.com/paper/2403.19946/) (2024)
- [Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space](https://mlsanity.com/paper/2405.01134/) (2024)
- [Leveraging Extrinsic Dexterity for Occluded Grasping on Grasp Constraining Walls](https://mlsanity.com/paper/2507.14721/) (2025)
- [AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool Use](https://mlsanity.com/paper/2509.15153/) (2025)

## Abstract (arXiv)

High precision assembly of mechanical parts requires accuracy exceeding the robot precision. Conventional part mating methods used in the current manufacturing requires tedious tuning of numerous parameters before deployment. We show how the robot can successfully perform a tight clearance peg-in-hole task through training a recurrent neural network with reinforcement learning. In addition to saving the manual effort, the proposed technique also shows robustness against position and angle errors for the peg-in-hole task. The neural network learns to take the optimal action by observing the robot sensors to estimate the system state. The advantages of our proposed method is validated experimentally on a 7-axis articulated robot arm.