Credit: Daewoo

Everybody has been in a situation when we wish we had stronger arms or, even better, an extra pair of them. Whether it is attaching something large overhead or manipulating something heavy, we all know we are bound to run into the limitations of our own anatomical design. In some professions, such as construction work, these difficulties can surface practically every day. To make physical drudgery less stressful and traumatic, researchers around the globe are now developing a new kind of robots that will be worn on the body just like your regular backpack.

Wearable robotics flourishes on the collaboration between the human and the machine and has a huge potential in all kinds of physically challenging work. This idea has already been put to test by Daewoo Shipbuilding & Marine Engineering, one of the biggest shipbuilders in the world. Korean shipyards have long been known for their high degree of automatisation. Now it appears the Korean company has decided to go one step further.

The company has developed a wearable exoskeleton that allows workers to carry huge pieces of metal and other heavy components with no or little effort. The exoskeleton weighs around 30 kg, none of which, however, is felt by the wearer since the suit is designed to support itself and follow the wearer’s movements.

Credit: Daewoo

The prototype can lift and precisely manipulate objects with a mass of up to 30 kg. The test has demonstrated that this technology can indeed help workers with their daily tasks, although those who had a chance to take part in the test run say they would like to be able to move faster and lift even heavier weights – a goal the research team is already working towards: the current research target is an exoskeleton that can lift up to 100 kg and be used on a daily basis at shipyard facilities.

Another example of how wearable robots can literally give a hand to future workers comes from the MIT’s d’Arbeloff Laboratory for Information Systems and Technology. The lab is working on a pair of lightweight robotic arms attached to a backpack that are envisioned to assist people with those tasks where our two arms are just not enough.

The project called SRL (Supernumerary Robot Limbs) is supported by Boeing and was recently used in a demo that involved installing ceiling panels in an airplane, a highly repetitive task that is difficult to perform on your own. By pushing the panels against the ceiling, the device can alleviate the worker from the necessity of simultaneously holding the panel, inserting the screws and using the screwdriver to attach it.

Watch the video below to see the prototype in action.

Both humans and robots work in manufacturing plants however, they don’t usually work alongside one another. Robots are most often used in repetitive, exhausting or hazardous work, while people are needed for tasks that require finer skill and detail. An earlier post on this blog discussed some of the ways robots have started working alongside humans but there are of course some important issues to consider if we really want to make this kind of collaboration work.

Humans are individuals and we like to do things our own way. According to Julie Shah, an Assistant Professor of Aeronautics and Astronautics at MIT, robots need to display an almost seamless understanding of how they can help people. To give robots the ability to do this, Shah and her team at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a new algorithm that allows a robot to quickly learn how people prefer to do particular tasks so that it can adapt accordingly to give them a hand.Shah stresses that without this ability, people are likely to get frustrated and forego any assistance from the robot which could potentially increase their efficiency on the task.

Watch the video above to see how the algorithm works in a test case involving spar assembly, a specific part of airplane manufacturing. The algorithm is also being used  in simulations to train robots and humans to work together; findings will be presented at the Robotics: Science and Systems Conference in Sydney, Australia this July.

What started out as an undergraduate summer project at the Distributed Robotics Lab (DRL), part of the Computer Science and Artificial Intelligence Lab at MIT, has now turned into a long-term plan to
develop an autonomous gardening system.

DRL researcher Jason Dorfman explains the concept: ¨We consider plants, pots and robots to be systems with different levels of mobility, sensing, actuation, and autonomy. As a whole, the system can be considered a mixed artificial/natural society, which transforms energy, water and nutrients into produce.¨

Within this unusual garden pots and plants are enhanced with computation, sensing, and communication, while autonomous robots cruise around, sensitive to the needs of the vegetation. This system allows for ¨precision agriculture¨per say; water and nutrients are delivered exactly when needed and  fruit is harvested optimally.

The team at DRL hopes that this type of system may be implemented to reduce water consumption and pesticide use on farms and to make plant populations  less prone to depleting the soil of specific nutrients. They also envision applications for this in green architecture, whereby fruits and vegetables can be cultivated on the inside and outside of buildings, increasing energy efficiency of the building.

Remember that scene in the 1964 Mary Poppins film where Julie Andrews manages to retrieve everything from plants to coat hangers out of her hand bag? Well… there’s no magic involved however,   the  Distributed Robotics Lab (DRL) and the Computer Science and Artificial Intelligence lab (CSAIL) at MIT are currently working on something rather similar.

Imagine tossing a tiny replica of a common tool like a screwdriver into a bag full of sand and being able to pull out the real thing moments later. To accomplish something akin to this, researchers are working with small cubic robots enabled with rudimentary microprocessors and special magnets on each of their four sides. Unlike permanent magnets, these ones can be turned on and off and they don’t require a constant current to maintain their magnetism. The cubes’ magnets allow them to connect, communicate and  share power.

The form of the desired object is defined by placing a miniature model of the obeject among the robotic cubes, algorithms then guide then guide them into shape. However, these aren’t your everyday reconfigurable robots; instead of putting themselves together like pieces of a puzzle, it’s rather a process of elimination. Eventually, researchers hope to be working with elements much smaller than the 10 mm squared cubes they’re working with now; a material they’re calling ¨smart sand¨.

¨A heap of smart sand would be analogous to the rough block of stone that a sculptor begins with. The individual grains would pass messages back and forth and selectively attach to each other to form a three-dimensional object; the grains not necessary to build that object would simply fall away,¨ explains Larry Hardesty of the MIT News Office.

At the IEEE International Conference on Robotics and Automation this May, researchers from the DRL and CSAIL will present a paper that describes the algorithms that could enable such a material.

Check out the video above to get a better idea of what this looks like in action! Could robotic technology be applied in other unexpected ways? Click HERE to find out about a European initiative that believes in investigating new areas where robotics research can be applied.

Currently it takes a lot of time and money to produce, program and design a functioning robot. Although the project’s in its early phases, it aims to ¨dramatically reduce the development time for a variety of useful robots, opening the doors to potential applications in manufacturing, education, personalized healthcare, and even disaster relief,” explains Rob Wood, an associate professor at Harvard University.

On a larger scale, the project aims to democratize access to robots by advancing the state of the art of today’s increasingly accessible 3D printers- allowing individuals to design and build functional robots from material as readily available as a sheet of paper.

Researchers also envision that these types of robots could provide fix-it-yourself solutions for household problems;you could simply head to a printing store and pick out a blueprint from a catalog of robotic designs and customise an easy-to-use robotic device built to tackle the problem. Within a day, the robot would be printed, assembled, programmed and ready for use.

Can we make robots to help solve problems that are part of our daily lives? Click HERE to find out about a European initiative which envisions robots as companions for everyday citizens.

Turkle stresses that although we are still very far from the point where robots are indistinguishable from humans- as in the movie Blade Runner, based on Phillip K. Dick’s novel Do Androids Dream of Electric Sheep?- humans are capable of forming attachments to robots. During the interview Turkle discusses some of the issues raised through her studies with Cynthia Breazeal, founder and director of the Personal Robots Group at the MIT Media Lab.

Turkle’s most recent book   Alone Together: Why we Expect More from Technology and Less from Each Other (2011)  explores some of the effects of a host of digital technologies; from new forms of social media, to sociable robots akin to the ones discussed in the interview above.

Turkle predicts that future robots will be ¨fantastic creatures,¨ capable of helping humans in many important ways; however, she is firm on her opinion that humans cannot love robots and that such machines will never be capable of love because they cannot be included in the arc of a human life cycle, experiencing things like birth, death, and loss.

Regardless of her belief, she shares an account of the impressive moment she had with MIT’s robot Cog. She describes  the uncontrollable feeling of wanting the object’s attention in spite of knowing that it had no ¨real¨attention to give her. Considering this a deeply impacting experience, Turkle believes the issue of attachment between  humans and machines is something that should be followed with close attention.

David Levy on the other hand would disagree with Turkle’s views on love and robots. Although he has taken his share of criticism, he was right on his prediction in his 2007 book   that sex with robots would be made possible and he thinks we could love them too. Check out this article in  Scientific American that discusses some of his views published in his book Love and Sex with Robots.