Deep Reinforcement Learning for High Precision Assembly Tasks

2017/08/14 by Tadanobu Inoue, Inoue, Tadanobu, Giovanni De Magistris +7 · 29 citations
Computer Science · Engineering · #Artificial intelligence #Artificial neural network #Computer science #Engineering #Position (finance) #Reinforcement Learning in Robotics #Reinforcement learning #Robot #Robot Manipulation and Learning #Robotic Mechanisms and Dynamics #Robotic arm #Robustness (evolution) #Simulation #Software deployment #Task (project management) #cs.AI #cs.RO

paper · pdf · doi:10.48550/arxiv.1708.04033

published in arXiv (Cornell University) (Cornell University) · Conference: Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 24-28, 2017. Video: https://youtu.be/b2pC78rBGH4

openalex publication_date 2017/08/14 · arxiv created 2017/09/22 · arxiv updated 2017/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• The Curse of Precision: A Data Scaling Law for High-Precision Robotic Manipulation
• Proactive Action Visual Residual Reinforcement Learning for Contact-Rich Tasks Using a Torque-Controlled Robot
• U-LAG: Uncertainty-Aware, Lag-Adaptive Goal Retargeting for Robotic Manipulation
• AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool Use
• A robust and compliant robotic assembly control strategy for batch precision assembly task with uncertain fit types and fit amounts
• Experimental Force-Torque Dataset for Robot Learning of Multi-Shape Insertion
• Leveraging Extrinsic Dexterity for Occluded Grasping on Grasp Constraining Walls
• Progressive extension of reinforcement learning action dimension for asymmetric assembly tasks
• Robust Peg-in-Hole Assembly under Uncertainties via Compliant and Interactive Contact-Rich Manipulation
• Fast Skill Learning for Variable Compliance Robotic Assembly
• Master Rules from Chaos: Learning to Reason, Plan, and Interact from Chaos for Tangram Assembly
• Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks

Related

• Mastering Autonomous Assembly in Fusion Application with Learning-by-doing: a Peg-in-hole Study
• A Learning Approach to Robot-Agnostic Force-Guided High Precision Assembly
• Learning Robotic Assembly from CAD
• A robust and compliant robotic assembly control strategy for batch precision assembly task with uncertain fit types and fit amounts
• Reinforcement Learning with Parameterized Manipulation Primitives for Robotic Assembly