• Home
  • News
  • Big Data & Analytics
  • DevOps
  • Security
  • GDPR
  • AI & ML
  • Diversity
  • Cloud & Infrastructure
  • CIO
  • Events
  • Whitepapers
  • Spotlights
  • Research
  • Newsletters
  • Sign in
  • Events
    • Upcoming events
      event logo
      Computing webinar - Is your security infrastructure a risk to the business?

      In this Computing web seminar our expert panel explains how we got here, our research shows the scale of the problem facing enterprises, and we look at practical steps that enterprises can take to reduce complexity, manage risk, and speed up incident resolution.

      • Date: 26 Feb 2019
      • Your Computer
      event logo
      Computing Webinar - Does consolidating security providers improve security?

      In this web seminar, our expert panel discusses why it is that executives at major organisations struggle to understand security and articulate their risks – and thus to adequately fund security - and who is considered responsible when breaches occur. And, using data from Computing Research, we exam

      • Date: 27 Feb 2019
      • Your Computer
      event logo
      DevOps Live

      DevOps has become an inescapable word in technology circles recently with many firms wanting to reap the benefits of bringing developers and operations together. This conference will bring senior IT decision-makers to discuss the latest strategies for DevOps implementation.

      • Date: 20 Mar 2019
      • London Marriot Hotel Grosvenor Square, London W1K 6JP , London
      event logo
      DevOps Excellence Awards 2019

      Computing's DevOps Excellence Awards showcases outstanding achievement from organisations, personalities and solutions operating within the DevOps space.

      • Date: 20 Mar 2019
      • London
      View all events
  • Whitepapers
    • LATEST WHITEPAPERS
      Darktracelogo800800 120x194
      The Next Paradigm Shift: AI Driven Cyber Attacks

      In The Next Paradigm Shift: AI-Driven Cyber-Attacks, Max Heinemeyer, Darktrace Director of Threat Hunting, explains how certain characteristics of today's most sophisticated threats can prdict what we expect to see in the AI-driven cyber-attacks of the near future. 

      To develop an understanding of the enhanced abilities of AI-driven cyber-attacks, the report presents three real case studies of advanced threats.

      Download
      Darktracelogo800800 120x194
      Darktrace Antigena: The Future of AI – Powered Autonomous Response

      This white paper will explore the critical challenges that security teams face in this new era of cyber-threat, and how Darktrace Antigena is leveraging AI to autonomously fight back against advanced attacks, giving human responders the critical time needed to catch up.

      Download
      Find whitepapers
      Search by title or subject area
      View all whitepapers
  • Spotlights
    • Spotlights

      Welcome to Computing's Spotlight section, where we focus in on particularly important themes and topics of enterprise IT.

      Data Strategy Spotlight

      Computing, in association with Liaison Technologies, is hosting the Data Strategy channel.

  • Top 100 CIOs
  • Research
  • Sign in
  •  
    • You are currently accessing Computing via your Enterprise account.

      If you already have an account please use the link below to sign in.

      If you have any problems with your access or would like to request an individual access account please contact our customer service team.

      Phone: +44 (0) 1858 438800

      Email: customerservices@incisivemedia.com

      • Sign in
     
     
      • Newsletters
      • Account details
      • Contact support
      • Sign out
     
  • Follow us
    • RSS
    • Twitter
    • LinkedIn
    • Newsletters
    • Facebook
    • YouTube
  • Register
Computing
Computing
  • Home
  • News
  • Big Data & Analytics
  • DevOps
  • Security
  • GDPR
  • AI & ML
  • Diversity
  • Cloud & Infrastructure
  • CIO
 
  • You are currently accessing Computing via your Enterprise account.

    If you already have an account please use the link below to sign in.

    If you have any problems with your access or would like to request an individual access account please contact our customer service team.

    Phone: +44 (0) 1858 438800

    Email: customerservices@incisivemedia.com

    • Sign in
 
 
    • Newsletters
    • Account details
    • Contact support
    • Sign out
 
Computing
  • Hardware

Robot with vision and touch-sensing capabilities learns how to play the game of Jenga

The technology could be useful in production units where delicate touch and careful vision are needed

Robot with vision and touch-sensing capabilities learns how to play the game of Jenga
The Jenga-playing robot. Image: MIT
  • Dev Kundaliya
  • 31 January 2019
  • Tweet  
  • Facebook  
  • LinkedIn  
  • Google plus  
  • Send to  
0 Comments

A team of researchers from the Massachusetts Institute of Technology (MIT) claims to have designed a robot that can teach itself the complex physics of Jenga.

Researchers say the manipulator arm of the robot relies on a machine learning algorithm, visual data, and tactile feedback to teach itself how to correctly move blocks in the game of Jenga.

Jenga is the classic block-staking game which demands physical skills. Players remove one block at a time from a tower comprised of 54 wooden blocks. The block removed is gently put on the top of the tower, so with each move, the tower becomes both taller and more unstable.

Playing the game requires a soft touch to prevent the tower from tumbling down. It also demands mastery of other skills, such as pushing, pulling, probing, placing, and aligning the blocks in the tower.

The success rate of the robot in keeping the tower upright while removing the wooden blocks was almost on a par with that of human players

In the current research, the team equipped an industrial ABB IRB 20 robotic arm with a soft-pronged gripper, an external camera, and a force-sensing wrist cuff. To train the machine, it was directed to randomly select a block in the Jenga tower and also select a location on that block to push and move it.

Each time the arm pushed the block, a connected computer recorded the force and visual measurements, and compared those measurements to previous moves. The system also categorised the attempt as successful or unsuccessful.

Rather than performing thousands of such attempts, the robot was trained on just about 300 attempts. The team grouped attempts of similar measurements and outcomes in different clusters, each signifying specific block behaviour. Within around 300 attempts, the robot learned to intelligently anticipate its moves, guessing which blocks would be more difficult to move than others, and which might cause the tower to collapse.

The performance of the robotic arm was also compared with the performance of human players. The team found the success rate of the robot in keeping the tower upright while removing the wooden blocks was almost on a par with that of human players. 

The team believes this technology could be useful in production units where delicate touch and careful vision are needed, for example, assembly of cellular phones or other smaller parts in a, separating recycling items from waste, etc.

"In a cellphone assembly line, in almost every single step, the feeling of a snap-fit, or a threaded screw, is coming from force and touch rather than vision," says Alberto Rodriguez, Assistant Professor in the Department of Mechanical Engineering at MIT, and the lead researcher of the study.

"Learning models for those actions is prime real-estate for this kind of technology."

The findings of the research are published in journal Science Robotics.

Further reading

Ocado develops "visions system" for warehouse robotics
  • Strategy
  • 10 Apr 2014
Google seeks a buyer for robotics developer Boston Dynamics
  • Internet of Things
  • 18 Mar 2016
Five million jobs at risk from AI and robotics, warns World Economic Forum
  • Careers and Skills
  • 18 Jan 2016
Will Ocado's robotics change the supermarket trade?
  • Internet of Things
  • 16 Oct 2017
  • Tweet  
  • Facebook  
  • LinkedIn  
  • Google plus  
  • Send to  
  • Topics
  • Hardware
  • Jenga
  • Massachusetts Institute of Technology
  • ABB IRB 20 robotic arm
  • robots
  • MIT

More news

UK invests in blackhole-hunting LIGO facilities in Louisiana and Washington to get an upgrade to 'see' further
UK invests in blackhole-hunting LIGO facilities in Louisiana and Washington to get an upgrade to 'see' further

Scientists will be able to detect three blackhole collision events in a single day after upgrading work is completed by the mid-2020s

  • Hardware
  • 15 February 2019
Microsoft now working on 2020 build of Windows 10
Microsoft now working on 2020 build of Windows 10

Windows 10 build for the first half of 2020 will require more intensive testing than usual

  • Software
  • 15 February 2019
Thousands of Android apps are tracking users through MAC address or Android ID
Thousands of Android apps are tracking users through MAC address or Android ID

And they continue tracking users even when asked to stop

  • Security
  • 15 February 2019
Chinese brands claimed one-third of all smartphones sales in European in 2018
Chinese brands claimed one-third of all smartphones sales in European in 2018

Companies like Huawei and Xiaomi look to Europe in the fall-out from the US government's action against Huawei

  • Hardware
  • 15 February 2019
Back to Top

Most read

 jp-morgan.jpg
Blockchain latest news: Bank JP Morgan bets on blockchain, unveils its own digital currency
EU states consider coordinated response to cyber attacks by China-linked hackers
EU states consider coordinated response to cyber attacks by China-linked hackers
Thousands of Android apps are tracking users through MAC address or Android ID
Thousands of Android apps are tracking users through MAC address or Android ID
Microsoft now working on 2020 build of Windows 10
Microsoft now working on 2020 build of Windows 10
IBM reveals top-five tech that will transform the world in the next five years
IBM reveals top-five tech that will transform the world in the next five years
  • Contact
  • Marketing solutions
  • Enterprise IT Events
  • About Incisive Media
  • Terms & conditions
  • Privacy policy
  • RSS
  • Twitter
  • LinkedIn
  • Newsletters
  • Facebook
  • YouTube

© Incisive Business Media (IP) Limited, Published by Incisive Business Media Limited, New London House, 172 Drury Lane, London WC2B 5QR, registered in England and Wales with company registration numbers 09177174 & 09178013

Digital publisher of the year
Digital publisher of the year 2010, 2013, 2016 & 2017