The Robot Report

  • Home
  • News
  • Technologies
    • Batteries / Power Supplies
    • Cameras / Imaging / Vision
    • Controllers
    • End Effectors
    • Microprocessors / SoCs
    • Motion Control
    • Sensors
    • Soft Robotics
    • Software / Simulation
  • Development
    • Artificial Intelligence
    • Human Robot Interaction / Haptics
    • Mobility / Navigation
    • Research
  • Robots
    • AGVs
    • AMRs
    • Consumer
    • Collaborative Robots
    • Drones
    • Humanoids
    • Industrial
    • Self-Driving Vehicles
    • Unmanned Maritime Systems
  • Business
    • Financial
      • Investments
      • Mergers & Acquisitions
      • Earnings
    • Markets
      • Agriculture
      • Healthcare
      • Logistics
      • Manufacturing
      • Mining
      • Security
    • RBR50
      • RBR50 Winners 2025
      • RBR50 Winners 2024
      • RBR50 Winners 2023
      • RBR50 Winners 2022
      • RBR50 Winners 2021
  • Resources
    • Automated Warehouse Research Reports
    • Digital Issues
    • eBooks
    • Publications
      • Automated Warehouse
      • Collaborative Robotics Trends
    • Search Robotics Database
    • Videos
    • Webinars / Digital Events
  • Events
    • RoboBusiness
    • Robotics Summit & Expo
    • DeviceTalks
    • R&D 100
    • Robotics Weeks
  • Podcast
    • Episodes
  • Advertise
  • Subscribe

AutoSaw Robot Carpenter Eases Pain of Building Furniture

By Steve Crowe | February 28, 2018

Have you ever built custom furniture? It can be a dangerous, expensive and tedious process. Researchers at MIT CSAIL, however, have created a robot-assisted carpentry system called AutoSaw to, hopefully one day, democratize custom furniture building.

AutoSaw consists of OnShape’s CAD system, a modified Roomba Create outfitted with a circular saw and two Kuka youBots, which Kuka stopped manufacturing in 2016. At the moment, AutoSaw can only make chairs, desks and tables. But MIT hopes to expand its capabilities to larger furniture and add drilling and gluing capabilities.

AutoSaw is applying computer numerical control (CNC) technology, which is used in larger scale machinery. CNC converts designs into numbers that are then fed to specially programmed tools to execute. With AutoSaw, users select a template from the CAD software and adjust it to their liking, tweaking the size and shape.

Read MIT’s Paper: Robot Assisted Carpentry for Mass Customization

This design is then turned into instructions for the robots. The jigsaw-rigged Roomba Create can cut lumber of any shape on a plank, while the youBots transport and lift the wood onto a chop saw.

AutoSaw

AutoSaw’s Cutting Process

The wood is then autonomously cut to the appropriate lengths. To cut lumber, MIT uses a Vicon positioning system and previously developed planning algorithms. MIT said its used the youBots because of their small footprint and cost compared to larger robot arms.

Related: MIT Develops VR Robot Control System

To cut lumber, the robots are assigned a length and a spec for the dimensioned lumber. The robots identify the lumber using Vicon markers and position themselves one-quarter of the way in from each side. They lift their grippers in place, grab the lumber and then lift further to separate the lumber from its stand.

The robots then form a fleet, and move towards the saw in a synchronized and coordinated fashion. Once near the saw, they move down towards the height of the chop saw’s base plane. They proceed to move slightly past the back plane of the chop saw and lower the lumber down. Because the grippers have compliance, the lumber aligns to the chop saw. The realignment occurs as long as the position of the grippers can be within a tolerance window.

AutoSaw

youBots transfer the wood to be cut. (Credit: Jason Dorfman/MIT CSAIL)

Once the lumber is placed on the chop saw, the youBots re-grasp the wood. They position themselves at the expected center of mass location for the two pieces of post-cut lumber. One robot then releases its grip and acts as a support while the other robot uses its gripper to adjust the position of the wood so the desired length of lumber is left on one side of the blade. The support robot re-grasps and the chop saw is activated. Once the part is cut, the desired length of lumber is transported to the user, and the other is returned to the stock.

AutoSaw’s Custom Grippers

The youBots each have a special complaint gripper (see below) that can clamp onto the material, drive the material along a direction, and are complaint perpendicular to the major axis of the lumber. When lumber is placed in the gripper, a force perpendicular to the lumber and parallel to the gripper can cause the gripper to shift its grip. The chop saw is automated by attaching a relay to the 120V line and a linear actuator is attached to the saw. Both are connected to a ROS node via a micro- controller.

AutoSaw

AutoSaw custom soft gripper. (Credit: Jason Dorfman/MIT CSAIL)

“We added soft grippers to the robots to give them more flexibility, like that of a human carpenter,” said CSAIL postdoc Jeffrey Lipton, a lead author on a paper about AutoSaw. “This meant we could rely on the accuracy of the power tools instead of the rigid-bodied robots.”

After the robots finish with cutting, the user then assembles their new piece of furniture using step-by-step directions from the system. Lipton, who trained as a carpenter in high school, said AutoSaw is all about exploring what technology can do to make working with wood easier and more productive. But this isn’t the first time MIT has built furniture assembling robots.

Building Upon MIT’s IKEABot

In 2013, MIT showed off the IKEABot that, you guessed it, autonomously assembled flat-pack IKEA furniture. IKEABot also used Kuka youBots to autonomously build IKEA furniture in as little as 10 minutes. AutoSaw also took inspiration from InstantCAD, software developed at MIT that makes it easier to tweak designs by automatically calculating things like internal stress and resistance.

IKEABot infers how furniture parts fit together based on hole positions. Then it plans a sequence of assembly steps for multiple youBots. The robots distribute tasks based on delivery and assembly roles. Assembly robots are equipped with a system of modular tools that fit onto the youBot’s gripper like a glove. The screwing device seen here can be docked when it is not in use. After the assembly is complete, the robots coordinate motions to flip over the table.

“There have been many recent AI achievements in virtual environments, like playing Go and composing music,” says Hod Lipson, a professor of mechanical engineering and data science at Columbia University. “Systems that can work in unstructured physical environments, such as this carpentry system, are notoriously difficult to make. This is truly a fascinating step forward.”

AutoSaw is a proof-of-concept at this point, but simulations showed the robot could build a table with an accuracy comparable to a human, without a real hand ever getting near a blade.

“Our aim is to democratize furniture-customization,” says Adriana Schulz, an MIT researcher who worked on AutoSaw. “We’re trying to open up a realm of opportunities so users aren’t bound to what they’ve bought at Ikea. Instead, they can make what best fits their needs.”

About The Author

Steve Crowe

Steve Crowe is Executive Editor, Robotics, WTWH Media, and chair of the Robotics Summit & Expo and RoboBusiness. He is also co-host of The Robot Report Podcast, the top-rated podcast for the robotics industry. He joined WTWH Media in January 2018 after spending four-plus years as Managing Editor of Robotics Trends Media. He can be reached at scrowe@wtwhmedia.com

Tell Us What You Think! Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Articles Read More >

The Loomia Smart Skin Developer Kit can help roboticists test flexible tactile sensing, as shown here with robotic hands.
Loomia Smart Skin Developer Kit to help give humanoid robots a sense of touch
close up view of the TUM robot tree.
Unveiling the Tree of Robots: A new taxonomy for understanding robotic diversity
Two cobot arms putting a gear on a bike tire.
TRI: pretrained large behavior models accelerate robot learning
reachy mini sitting on a desktop.
Hugging Face launches Reachy Mini robot as embodied AI platform

RBR50 Innovation Awards

“rr
EXPAND YOUR KNOWLEDGE AND STAY CONNECTED
Get the latest info on technologies, tools and strategies for Robotics Professionals.
The Robot Report Listing Database

Latest Episode of The Robot Report Podcast

Automated Warehouse Research Reports

Sponsored Content

  • How to Set Up a Planetary Gear Motion with SOLIDWORKS
  • Sager Electronics and its partners, logos shown here, will exhibit at the 2025 Robotics Summit & Expo. Sager Electronics to exhibit at the Robotics Summit & Expo
  • The Shift in Robotics: How Visual Perception is Separating Winners from the Pack
  • An AutoStore automated storage and retrieval grid. Webinar to provide automated storage and retrieval adoption advice
  • Smaller, tougher devices for evolving demands
The Robot Report
  • Automated Warehouse
  • RoboBusiness Event
  • Robotics Summit & Expo
  • About The Robot Report
  • Subscribe
  • Contact Us

Copyright © 2025 WTWH Media LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media
Privacy Policy | Advertising | About Us

Search The Robot Report

  • Home
  • News
  • Technologies
    • Batteries / Power Supplies
    • Cameras / Imaging / Vision
    • Controllers
    • End Effectors
    • Microprocessors / SoCs
    • Motion Control
    • Sensors
    • Soft Robotics
    • Software / Simulation
  • Development
    • Artificial Intelligence
    • Human Robot Interaction / Haptics
    • Mobility / Navigation
    • Research
  • Robots
    • AGVs
    • AMRs
    • Consumer
    • Collaborative Robots
    • Drones
    • Humanoids
    • Industrial
    • Self-Driving Vehicles
    • Unmanned Maritime Systems
  • Business
    • Financial
      • Investments
      • Mergers & Acquisitions
      • Earnings
    • Markets
      • Agriculture
      • Healthcare
      • Logistics
      • Manufacturing
      • Mining
      • Security
    • RBR50
      • RBR50 Winners 2025
      • RBR50 Winners 2024
      • RBR50 Winners 2023
      • RBR50 Winners 2022
      • RBR50 Winners 2021
  • Resources
    • Automated Warehouse Research Reports
    • Digital Issues
    • eBooks
    • Publications
      • Automated Warehouse
      • Collaborative Robotics Trends
    • Search Robotics Database
    • Videos
    • Webinars / Digital Events
  • Events
    • RoboBusiness
    • Robotics Summit & Expo
    • DeviceTalks
    • R&D 100
    • Robotics Weeks
  • Podcast
    • Episodes
  • Advertise
  • Subscribe