Development of a Robotic System for Automated Decaking of 3D-Printed Parts

With the rapid rise of 3D-printing as a competitive mass manufacturing method, manual "decaking" – i.e. removing the residual powder that sticks to a 3D-printed part – has become a significant bottleneck. Here, we introduce, for the first time to our knowledge, a robotic system for automated decaking of 3D-printed parts. Combining Deep Learning for 3D perception, smart mechanical design, motion planning, and force control for industrial robots, we developed a system that can automatically decake parts in a fast and efficient way. Through a series of decaking experiments performed on parts printed by a Multi Jet Fusion printer, we demonstrated the feasibility of robotic decaking for 3D-printing-based mass manufacturing.

• Publication year

  2020

• Venue

  IEEE International Conference on Robotics and Automation

• Publication date

  2020-03-11

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/ICRA40945.2020.9197110arXiv 2003.05115
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Improving Aesthetics Through Post-Processing for 3D Printed Parts

  2019cited by this paper
• Can robots assemble an IKEA chair?

  2018cited by this paper
• Mask R-CNN

  2017cited by this paper
• Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems

  2016cited by this paper
• A Summary of Team MIT's Approach to the Amazon Picking Challenge 2015

  2016cited by this paper
• Team Delft's Robot Winner of the Amazon Picking Challenge 2016

  2016cited by this paper
• A Review of Algorithms for Compliant Control of Stiff and Fixed-Compliance Robots

  2016cited by this paper
• Lessons from the Amazon Picking Challenge

  2016cited by this paper
• YOLO9000: Better, Faster, Stronger

  2016cited by this paper
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  2015cited by this paper
• An exploration of binder jetting of copper

  2015cited by this paper
• SSD: Single Shot MultiBox Detector

  2015cited by this paper
• A review on selective laser sintering/melting (SLS/SLM) of aluminium alloy powders: Processing, microstructure, and properties

  2015cited by this paper
• Combining visual and inertial features for efficient grasping and bin-picking

  2014cited by this paper
• A probabilistic approach to high-confidence cleaning guarantees for low-cost cleaning robots

  2014cited by this paper
• Microsoft COCO: Common Objects in Context

  2014cited by this paper
• Flexible 3D localization of planar objects for industrial bin-picking with monocamera vision system

  2013cited by this paper
• Null space optimization for effective coverage of 3D surfaces using redundant manipulators

  2012cited by this paper
• Experimental evaluation of a trajectory/force tracking controller for a humanoid robot cleaning a vertical surface

  2011cited by this paper
• Unified Impedance and Admittance Control

  2010cited by this paper
• Model globally, match locally: Efficient and robust 3D object recognition

  2010cited by this paper
• Automated Construction of Robotic Manipulation Programs

  2010cited by this paper
• ROS: an open-source Robot Operating System

  2009cited by this paper
• Imitation learning with generalized task descriptions

  2009cited by this paper
• CAD/CAM-based position/force controller for a mold polishing robot

  2007cited by this paper
• Robots at the tipping point: the road to iRobot Roomba

  2006cited by this paper
• Active compliant motion : a survey

  2005cited by this paper
• A Navigation System for Cleaning Robots

  2000cited by this paper
• RRT-connect: An efficient approach to single-query path planning

  2000cited by this paper
• Object recognition from local scale-invariant features

  1999cited by this paper
• An overview of robot force control

  1997cited by this paper

• Synthesizing Depowdering Trajectories for Robot Arms using Deep Reinforcement Learning

  2025cites this paper
• The Role of 3D Printing in Advancing Automated Manufacturing Systems: Opportunities and Challenges

  2025cites this paper
• Depowdering of an Additively Manufactured Heat Exchanger with Narrow and Turning Channels

  2024cites this paper
• 6D edge pose detection for powder-printed parts using Convolutional Neural Networks and point cloud processing

  2024influential citation
• Monte-Carlo Tree Search with Prioritized Node Expansion for Multi-Goal Task Planning

  2023cites this paper
• Geometry-Aware Coverage Path Planning on Complex 3D Surfaces

  2023cites this paper
• Geometry-Aware Coverage Path Planning for Depowdering on Complex 3D Surfaces

  2023cites this paper
• Design and Implementation of an Autonomous Cleaning Robot to Work Indoors

  2023cites this paper
• Robotic Depowdering for Additive Manufacturing Via Pose Tracking

  2022cites this paper
• Vision-based holistic scene understanding towards proactive human-robot collaboration

  2022cites this paper
• Automated post-processing of 3D-printed parts: artificial powdering for deep classification and localisation

  2021influential citation
• A High-Resolution Network-Based Approach for 6D Pose Estimation of Industrial Parts

  2021cites this paper
• Autonomous Industrial Ambient Robotic System

  2020cites this paper