Popular Posts

Thursday, July 19, 2012

Robot swarms aim to bring buildings to life

Science and techno world topic: Future


Meet the man who wants to create architecture that understands everything about us – down to our emotional states – and learns from its mistakes

It doesn’t take much to be considered smart if you’re a building. Add some lights that turn themselves off when nobody is around or install an “intelligent” air conditioning system to regulate the ambient temperature and you’re well on your way. But compared to the living buildings proposed by Akira Mita, today’s smart buildings are the architectural equivalent of single-celled organisms.

Mita is an engineer, not an architect, and it shows in both the sophistication of his designs and the scale of his ambition. Using swarms of robotic sensors that “chase” a structure's human occupants, he wants buildings to understand everything about us, down to our emotional state. These robot sensors will learn from their mistakes, self-regulate using digital “hormones”, and record information over the course of years, building up a record of experiences to be used as “DNA” to program future versions of themselves, or even other buildings.

"Living organisms give birth to the next generation, and have immunity to viruses such as influenza," says Mita in a video promoting his work. "Our idea was that we wanted to give architecture this kind of biological response capability."

Mita's vision of buildings that know more about us than we know about ourselves is enabled by a fundamental re-think of how "smart" buildings should be constructed. In conventional smart homes, arrays of sensors and control systems are built into the walls – for example, sensors that detect whether or not anyone is in a room turn on and off lights or control the ambient temperature. The problem with systems like these is that they are obsolete as soon as they are embedded into a structure, and replacing them in the future could be costly or impossible.

Mita's solution is to replace all those sensor networks with something like an iPhone on wheels. Early prototypes, called the "e-bio", are about as big as the Roomba robotic vacuum cleaners. They're equipped with a pair of bat-like ears that can determine the precise location of sounds. They also have an "eye" that sweeps a laser beam around the robot, allowing it build a complete, three-dimensional picture of its surroundings ten times a second.

Like our phones, these mobile, independent "e-bio" sensors can be upgraded with new technology as it becomes available, and are easily replaced if they fail. In other words, they're robust in all the ways that traditional home sensor networks aren't.

Another unconventional dimension of Mita's approach is his replacement of a whole variety of sensors with humans themselves. In contrast to a home automation system that strives to maintain a particular temperature set-point, Mita's team is concentrating on making his robots hyper-attuned to signals given off by the human beings in a building.

Take the body language or words we use to express the discomfort we feel with the temperature in a building. In cases like this, the attendant robots would communicate via a "hormonal" signal. In our body, hormones have the power to change how our entire nervous system operates, and over an extended period of time. When Mita’s fire off a hormonal signal, it’s more than a conventional communication – it’s like an override that changes how the entire network behaves. In the case of temperature, the network shifts into a state in which it prioritises the climate of a room. In this way, control over temperature, humidity, fans and whatever other climate control measures are present is automatic and invisible to the building’s occupants.

Smart swarms

The more of these robots we have in our homes, the more intelligent they could be. Picture a carpet of cockroach-like insectoid sensors on your living room floor but, hopefully, less creepy. Borrowing ideas from "swarm robotics" – the study of robots that make decisions in the same distributed way that ants and other insects do – Mita wants his robots to make consensus decisions about how to alter a building's environment.

It's very similar to how our immune system operates through a kind of "swarm intelligence", where individual cells aren't that smart, but collectively they constitute an extremely adaptable system. For example, your immune system learns to identify and combat an invader without central coordination – instead, individual elements try a variety of strategies, and whatever works is eventually copied across your entire immune response.

In one example of swarm intelligence solving a thorny problem, Mita’s team figured out how to program a building’s ambient music to shape the mood of its human occupants. The system has pre-set goals – in this case, keeping people productive during the day – and accomplishes them by experimentally adjusting both the familiarity and the tempo of the music piped through a building. By integrating observations of all the humans present, the system used a relatively unsophisticated but “swarm intelligent” algorithm to increase productivity by 69% versus a no-music control.

Another characteristic of living things that Mita is copying is a concept called "homeostasis," which is just a fancy word for the fact that organisms are good at maintaining their state of being, even in the face of things that would perturb them, like an injury or a change in temperature. (A conventional thermostat is actually a primitive homeostatic system, in that it reacts to changes in temperature by trying to bring the house back to a particular set-point, regardless of the source of the disturbance.)

For example, rather than simply being programmed with simple instructions like "if a person walks into a room, turn the light on", Mita's "e-bio" sensors might learn how much light a user likes. Equipped with their own light sensors, they can adjust ambient light levels to fit a user's demonstrated preferences. This way, the system automatically takes into account time of day, clouds, even whether or not the blinds are drawn, all without actually knowing the state of any of those variables. (This sort of thing makes even more sense with next-generation LED lighting systems, which are dimmable and can be formed into almost any shape, not just that of a lightbulb.)

Reaching Mita's goals for really advanced living buildings may require something of a handover of the world of architecture, from designers to engineers. "I think the most interesting thing is that this research theme has been very hard to handle in previous architectural faculties," says Mita. "For example, the researchers need to know about sensors, and to know a lot about information processing as well."

In re-thinking buildings as responsive structures, Mita doesn't place any limits on how much he thinks we can borrow from biology. "Ultimately, it would be good if buildings themselves could make their own DNA and build the next building. But that's a really difficult subject, so all of us, including the students, are having fun working towards it step by step."

Source: BBC

No comments:

Post a Comment