Robohub.org
 

Transforming robots to transform your room


by
24 May 2014



share this:
Roombots1
In the future, Roombots could replace furniture (Biorobotics Laboratory, EPFL).

The word “robot” conjures up many different things to many people, but how many of them immediately think of furniture? It sounds futuristic but the Biorobotics laboratory at EPFL, sponsored by NCCR Robotics is working on exactly that – robotic furniture, or Roombots.

Roombots are a modular self-reconfiguring robotic system, and are a direct response to the pressure on space that is so common within large cities today. Each Roombots module is made of two spheres, approximately the size of a grapefruit, and contains three motors (for rotational movements), on-board computation, and a battery that allows for at least one hour of operating time. Modules also contain a latch-based connection mechanism that allows them to connect to each other or to connector ports in the environment.  The rotational movements and the dynamic connectors allow the modules to form any shape that may be desired – this means that you could have breakfast on a table, but while you are at work during the day, the Roombots transform into a series of chairs for a party that you are hosting that evening.

Internal view of modular Roombots (Biorobotics Laboratory, EPFL)
Internal view of modular Roombots (Biorobotics Laboratory, EPFL)

Using connector ports embedded in the floor, walls and ceiling, Roombots can crawl and climb on any surface, meaning that furniture does not need to be connected only to the floor, but can also hang from the ceiling or stick to the wall.  As it may not always be possible to embed ports everywhere in the room, the Roombots have also been designed to be able to “walk” using an oscillating motion controlled by a network of coupled oscillators in the modules, to allow them to travel across a room. The net result is that the modules appear to walk like a turtle or wiggle like a worm until they reach their intended point and fix on to a connector port.

The team behind the Roombots have had to overcome a series of research challenges in terms of hardware and control. For the dynamic connector for instance, the locking mechanism must be strong but flexible, and must be able to lock in any position and arrangement with no translation or rotation of the structure after locking. Next, grippers must be large enough that even when modules do not match up perfectly, the locking mechanism must still be able to fit into place, but small enough so as to still be fully contained within the robot. The connection mechanism has been designed to deal with both issues by employing a scooping mechanism, which researchers say allows up to 3.5 mm misalignment. Many other problems had to be solved for the Roombots to work properly as demonstrated on a series of videos found here.

So far, Roombots modules have been used to walk, negotiate corners and autonomously create simple table structures by connecting with each other and using connections to lift the tabletop, but researchers are still working on research and technical challenges such as compensating unwanted bending in the mechanical structure (related to building larger complex 3D structures), developing the best-suited algorithms for reconfiguration or locomotion control, and finding the most appropriate interaction strategy for the end-users.



tags: ,


NCCR Robotics

            AUAI is supported by:



Subscribe to Robohub newsletter on substack



Related posts :

Robot Talk Episode 153 – Origami-inspired robots, with Chenying Liu

  24 Apr 2026
In the latest episode of the Robot Talk podcast, Claire chatted to Chenying Liu from University of Oxford about how a robot's physical form can actively contribute to sensing, processing, decision-making, and movement.

Sony AI table tennis robot outplays elite human players

  22 Apr 2026
New robot and AI system has beaten professional and elite table tennis players.

AI system learns to keep warehouse robot traffic running smoothly

  20 Apr 2026
This new approach adapts to decide which robots should get the right of way at every moment, avoiding congestion and increasing throughput.

Robot Talk Episode 152 – Dexterous robot hands, with Rich Walker

  17 Apr 2026
In the latest episode of the Robot Talk podcast, Claire chatted to Rich Walker from Shadow Robot Company about their advanced robotic hands for research and industry.

What I’ve learned from 25 years of automated science, and what the future holds: an interview with Ross King

and   14 Apr 2026
Ross King created the first robot scientist back in 2009. He spoke to us about the nature of scientific discovery, the role AI has to play, and his recent work in DNA computing.

Robot Talk Episode 151 – Robots to study the ocean, with Simona Aracri

  10 Apr 2026
In the latest episode of the Robot Talk podcast, Claire chatted to Simona Aracri from National Research Council of Italy about innovative robot designs for oceanography and environmental monitoring.

Generative AI improves a wireless vision system that sees through obstructions

  08 Apr 2026
With this new technique, a robot could more accurately detect hidden objects or understand an indoor scene using reflected Wi-Fi signals.

Resource-constrained image generation and visual understanding: an interview with Aniket Roy

  07 Apr 2026
Aniket tells us about his research exploring how modern generative models can be adapted to operate efficiently while maintaining strong performance.



AUAI is supported by:







Subscribe to Robohub newsletter on substack




 















©2026.02 - Association for the Understanding of Artificial Intelligence