This is the third part of a multi-year conversation about the developing role of Data and technology in creating more People-centric design. We wrote about it user Experience as a lens, through the assumptions about design and create environments that enable performance and satisfaction. In our second, we are discussing How Measure happiness– which is far more practical than many People believe – offers new opportunities to explore the interface between space and performance. Below, we are discussing Some predictions for the near future are based on ours Experience with customers.
When talking about work and real estate on the disruptive potential of artificial intelligenceSometimes we offer a pithy answer: it’s impossible to have artificial intelligence In front one Has regular intelligence. This is, one I can’t hope to teach a machine to do things that flesh and blood people don’t yet understand well. As we have learned more about cognition and psychology, the gap between what we can observe and what can be automated actually feels bigger and not narrower.
So it is perhaps not surprising that AI for architecture and design is still at an early stage of development. Despite quite a bit of pedagogy and thinking about designWe don’t really know how people do it – not in a linear, describable, procedural sense that a computer could understand. Computers can be restricted and programmed with aesthetic rules of thumb such as the golden ratio. However, these are only human heuristics and not the ability to make actual quality judgments.
Even Therefore, the information that is already available to us is more valuable than we might think. As we recently wrote for Corporate Real Estate Journalis a job Surroundings full of tools that are Data– –activatedor could be easy: sure access Points, elevators, computers, mobile devices and even smart devices. Today’s techactivated Jobs now offer enough Data to start distinguishing between human factors that are relatively consistent from place to place– for example the positive effects of access Daylight and a clear sense of perspective – and those that are specific to an individual Surroundings and culture.
The ubiquity of low-cost computing power and the availability of extensive data sources have created the conditions for a phase of rapid innovation in intelligent offices. Innovators in programs like MITDesignX continue to explore the interfaces between technology and design – their annual cohort regularly includes at least one AI-themed project. What form could all of this take in the near future?
Social data, the difference between mathematics and AI
Compared to human consciousness, much of what is true AI These days are really chic mathematics with one side of marketing. The exact dividing line between AI and regular calculation is a fuzzy one. ON fascinating piece by AI Researcher Arend Hintze makes it clear: when one think about AI On a scale from digital alarm clocks to self-confident machines that can serve the world, we are still quite far from the latter. once one understands the way the algorithms are built, the artistry of intelligence often falls away.
StillA smart speaker differs qualitatively from a calculator. By creating a program of sufficient complexity and access to an extensive collection of human-generated data, we created a simulacrum of intelligence. While it can do not be intelligent in the philosophical sense– There is a lack of free will or self-confidence – it exists in the space between a simple machine and consciousness and provides the user with a value.
What is really artificially defined intelligence by doing sense that people tend to use it can be the kind of Data This informs the decision making of an algorithm. Simulate or expand man intelligenceMachines have to be given first man-centric Data on which to use and man Criteria against which it can be assessed. As we like to say intelligent buildings are social building.
There is good news on this front, especially for the built environment. The measurements we use in architecture are at the root man. We measure Rooms in feet and count things in numbers. Ours intelligent buildings– Entry and exit, use of Rooms or amenities – is inherently tied to them man Experience. The technology for collecting this data is increasingly being installed building from the beginning of the design process. After-market solutions like PODD by the LMN architect, do it possible retrofit existing ones Rooms also.
As these technologies become more sophisticated, there are opportunities to gain insight become multiply. More consistent collection of files is required for all scales do smarter AI building possible. These tools become Produce the pool of files The can do AI for the built environment is a reality.
Typologies of AI for architecture
Great progress has already been made in the development of complementary systems man Intelligence in design. This effort can can be divided into three broad categories: mathematically design, Behavior modeling and responsive environments.
Iteration and filtering
In the years since Kasparov lost to Deep BlueThere was a consensus on this the best possible chess Player is none man Yet machine-it is man and machine. By combining a person’s strategic instincts with the raw computing power of a computer one Could get it the best from both. Machines are now being created that can teach itself to play. Despite its amazing mathematical complexity chess is still a game with a finite end point and a clear one sentence of Regulate.
Architecture is a lot of more open. one inherent in the challenges a lot of Design work is that the decision space is so large that it seems practically infinite. Accepted sentence of Requirements, the number of possible designs is limited only by the time and willingness of the designer to experiment. What if you never find the optimal solution? This is one Area in which algorithms can seem to be.
energy Model was one the first areas where this type of advanced intelligence was widespread. The smartest human teams are still tense optimize the large number of variables that can Affect something like a building energy Use – e.g. the impact of the facade on the amount of natural light, the cost and efficiency of different renewable energies based on historical weather patterns, the heat transfer functions of different building materials and more. In one computer-supported process, people say computer What optimizeThen have the system rate thousands of options and only spit out four or five of the best options that users can choose from. In addition to the prototyping of the physics and the appearance of a building, such models can be helpful in assessing the experience aspects. Customers can Experience the surroundings directly virtual reality.
Simulation and prediction
Collaborative Work is essential for most companies. Researchers and thoughts leader have worked to quantify these impacts and convince the business leader of its importance for years. So far, the practical development of more has been approached much less strictly Collaborative Environments. It is an outlier in a management culture that claims to evaluate measurements and experiments.
This is now To change. The effects of space on the behavior of Inmates is now directly quantifiable, analyzable and modelable. Crowd simulation software that has been used in the past to evaluate emergency exit patterns in buildings can simulate the behavior of Crowds of dozens or even thousands of people in a given environment. Open source versions –for example, Vadere– Allow everyone to experiment and reuse these tools.
We use some of these tools in our work with our customers. For exampleWhen a financial services company thought about changing the layout of its trading room, we simulated all possible routes that people could take through the room depending on the configuration. Extend such approaches to broader social and behavioral sources Data will enable more sophisticated modeling and decision making.
Real-time data informs about interactions
The next level of sophistication, which seems closer to what people mean when they say “AI,” is reaction spaces. Real-time data is already improving Experience in curated hospitality environments to like Theme parks, shopping malls and Cruise ships.
It is entirely possible to extend similar approaches to any environment that can be connected to a single digital platform. even on an urban scale. For example, imagine an integrated one Experience for the many restaurants in a busy travel destination to like Times Square. Due to a variety of factors, one can get crowded with customers while another is slow. Without human intervention, sensors could detect or anticipate this overcrowding and make adjustments to promote it People go to unused rooms. This may even This includes the introduction of a special food or drink People and balance the amount in a subtle way.
Jobs and buildings that use Real time Data to customize the experience for users already exist, and will become increasingly widespread and capable like the technologies become omnipresent. Network effects also apply here. As a physical Rooms are sensor– Equipped, the value of everyone increases. When sensor Data is combined with the planning Datait can used to optimize that use and comfort of Rooms.
While AI isn’t there yet for work, the investment is can Activate it anyway to recover. Systems that collect what is required Data do their own business case; she do the environment better experience in the short term while collecting the Data that will be useful later.
The combination of these different typologies leads to an intelligent approach for design that optimized from beforedesign by occupancy.
Imagine a building that is built for one existing Business. Before a single sketch has been drawn, the project team has already done detailed research on the existing building and its residents. You used what you learned to create a model, not just one building, but individual users, including observations of their behavior patterns and results of their engagement surveys. The design team can now simulate the social environment in the current or future space.
For example, when the head of the IT department normally closes the coffee bar After their first meeting of the day, this becomes an input for the model. Who could she meet on the way? How does that change when the location of the coffee bar is changed? Which potential configurations use your time most efficiently and increase your job satisfaction the most? Such an interaction modeling is not only theoretical, but a refinement of Methods that already exist.
The value of one approach is currently limited by the quality and quantity of the input. The results of Workplace Research and People analytics projects can be used as inputs in these models. Environmental factors can also be included. All that data can be used to set that Workplace Experience in real time. However, for this to be possible, we need a more holistic view of what may be measured in the environment, with a corresponding shift in the approach to Research and Model.
For example, if a simulation indicates that a number of People will tend to go to the cafe at some point time, Model can predict the change in the noise Levels both in the cafe ((you go up) and in the work areas that they no longer occupy (you go Low). How different People then answer it change is another thing that can can be simulated, taking into account their preferences. If that’s loud coffee shop– Walkers are likely to be distracted People who are still work, white noise Generators could be activated automatically. Or if the goal is to get everyone to this Make contacts, information about the environment, mobile notifications to nearby users or responsive signage can encourage everyone to this join for lunch.
Many of these developments are still Years or even decades away. The seeds for these developments are sown in AI for architecture now. The examples offered here are not “pie-in-the-sky”. The fact that they can The development of today’s tools is evidence of the remarkable progress in measurement and analysis skills in recent years Years.
What we need now is more Data– thorough research across the full spectrum of human experience of the built environment. The Data we collect and use The inputs are required today to develop smarter algorithms tomorrow. As designers and real estate professionals, it is our job to find out what is valuable for current and future residents. The AI tools that are just around the corner allow us to provide spaces that perform better and are fun use.
Note: We are not the author of this content. For the Authentic and complete version,
Check itsOriginal Source