The Impact of Artificial Intelligence (AI) in LED Lighting

by | May 25, 2021 | News

Photo Credit: SCENEunderLIGHT (OSRAM)

The lighting industry commonly employs novel techniques in lighting design, and control and Artificial Intelligence has emerged as an evolutionary force, demonstrating its potential to radically change existing processes. In the context of the Lighting Industry, the scope for applying AI is intriguingly broad, impacting the various stages involved in the lighting life-cycle such as design, installation, commissioning and configuration.

Nearly 20 percent of all the electricity consumed in the world is for lighting. And about 80 percent of that lighting is attributed to professional applications such as building, office, industry or street lighting, and about 20 percent to private residential lighting. Today, individually adjustable lighting applications are rather the exception than the rule. No matter the time of day or season, whether inside or outside, at home, school, the factory or at the office, there is usually only one continuous brightness level or lighting color to be set.

European energy policy is striving in many ways towards an entirely renewable energy-based power supply by 2050. This means that in the future, we will have to get used to weather-dependent fluctuations in the supply from wind and solar energy sources. Power must be used when it is produced – and intelligent lighting systems help to control power consumption without compromising the user experience.

A combination of LED lights and artificial intelligence may in the future provide better lighting of the buildings we live in, while lowering energy consumption at the same time. With artificial intelligence, the light can have a quality of being in constant motion, just like daylight – Changes are so fluid that you almost don’t notice them. This has many advantages because our sense of sight doesn’t like being in the same conditions all the time. The way we have understood light so far – as either turned on or off – does not take into account the fact that humans can see in many light spectrums and actually prefer variation in lighting. LED lights are very different from the lamps we have used previously as they allow precise control of color and brightness and can also be built into materials like walls and ceilings. This offers ample opportunities for designing artificial light similar to daylight.

A self-learning network of lighting components can communicate and set up itself without requiring human intervention similar to auto commissioning systems used in the IT industry. This will decrease the time needed to commission new lighting installations. By observing and measuring indoor environments, an AI based lighting system can optimize and tune light parameters accordingly to impact user experience and wellbeing. The utility of such a system is not limited to end users or tenants but extends to other stakeholders, such as building owners and facility managers as well. A data-driven network of lighting components continuously generates data which is collected and stored at a centralized server. AI algorithms can be designed to run at the source component, such as a sensor, for decentralized, real-time decisions, or at a server for making centralized decisions. Furthermore, the collected data can be utilized for other Building Management Systems or access management.

However, the technology is not without its caveats. Cameras augmented with AI can detect precise occupancy and movements in a room or space, but the visual feed would require strict adherence to privacy laws. Another significant challenge is the limited human understanding of AI, which impedes its speed of adoption as well. In summary, there are a lot of opportunities for applying AI within the lighting industry with significant improvements to user experience, comfort, productivity and ultimately profitability.

European scientists have developed an artificial intelligence algorithm which can trick office workers into believing that all the building’s lights are illuminated when they are not. The European Union-funded Project, SceneUnderLight, has successfully combined advanced research in computer vision and modern technology to develop a lighting control paradigm in which each person in the office perceives the entire office as “all lit,” while lights, which are not visible, are switched off. The software estimates the light propagation in offices in real-time and computes how much of it is perceived by the people. Then smart lighting control adjusts the lighting autonomously based on the presence of people and on their position within the office. The concept works particularly well in large open-plan offices, as fartheraway luminaires may be dimmed without altering the comfort of employees and their sense of security. The four-year project dubbed SceneUnderLight, is a collaboration between Osram, the University of Verona and the Italian Institute of Technology (IIT) in Genova. Its remit was to come up with a method of delivering maximum comfort and sense of security while granting large savings in energy consumption.”

The participants estimate that technology using this AI lighting control could save in energy consumptions up to 65 per cent. Since 2015, the project members have targeted two main goals: the understanding of the light and scene structure in an office, as well as the understanding of the human factor in an illuminated scene. IIT provided unique expertise in the 3D light estimation in large and complex office scenes, from color and depth images provided by a modern RGB-D camera. Meanwhile, the University of Verona brought in expert knowledge and design skills to estimate the gaze of people and their future motion with deep neural network model. Fabio Galasso, head of the computer vision R&D activities at Osram, brought together the team consisting of Marco Cristani, heading the department of Vision, Processing and Sound of University of Verona, and Alessio Del Bue, head of the Visual Geometry and Modelling Lab of IIT. SceneUnderLight was funded by the EU within the Horizon 2020 framework as a Marie Skłodowska- Curie Actions Project. It’s not clear at this stage if any lighting company plans to commercialize the technology.

Another completed research project named OpenLicht, which stands for the design of smart and launched in September 2016, customized light solutions based on open source and new materials. OpenLicht was funded by the German Ministry of Education and Research (BMBF), with the goal of enabling new forms of collaboration between science, business, maker and startup community. Infineon Technologies AG is supervising the project in close cooperation with Bernitz Electronics GmbH, Deggendorf Institute of Technology and the Technical University of Dresden. OpenLicht is one of ten research projects supported by the German Ministry of Education and Research is supporting as part of its “Open Photonics” funding program. The Open Photonics projects are pursuing a wide range of goals, including open innovation approaches for improving the use of photonic components and systems and open source approaches for promoting their broader use. They also include approaches that will enable the public to be more directly involved in scientific projects.

The results are now being made public, and they include the prototype of a smart lighting system based on artificial intelligence. It automatically adjusts the light in the room to the user’s position and activity, such as reading or watching TV, learns the person’s preferences and can even respond to a certain degree to novel circumstances. The solution developed in the project is based on open-source approaches like openHAB, a smart home system, and machine learning libraries. Use of freely available development environments, software frameworks and low-cost hardware solutions enables integration of a wide range of different sensor data and further development of existing results by the community. Intelligent light design is entering the smart home and will accompany us through our everyday life with fully automated solutions. However, the ones currently available on the market so far often pose a raft of challenges for users. It is frequently the case that they are, at most, partly automated and are complicated to program. Moreover, the systems often fail to safeguard privacy or unnecessarily consume power, since light usage is not tailored ideally to the user’s needs, which in turn has a negative impact on CO 2 emissions. OpenLicht found answers to these challenges. The use of AI in the local network creates smart light solutions that are safe, yet sustainable and safeguard the user’s privacy. The AI acts on a system that is closed off from the outside world and does not have to be connected to the Internet. An open source gateway based on a Raspberry Pi and an Infineon Trusted Platform Module (TPM) has been developed to enable that. That means data does not have to be sent to the cloud, but can instead be processed locally, which ensures security and privacy for households. These factors are vital in increasing the acceptance of smart home solutions. In addition, automatic adjustment to the user’s activities makes sure the light required at a particular moment is available. That avoids unnecessary “floodlighting” and helps protect the climate without the need to appeal to users’ conscience.

Besides setting high aspirations and preparing to tackle new challenges, we all may be wondering what the future of lighting might look like in 10 years. With such dazzling transformation and digitalization that we are witnessing in the lighting industry now, how could anyone predict what the industry might look like? If you pay attention to some of the key technology advances that are already taking place outside of the lighting industry, the answer is pretty evident. These advances will further transform the solid-state lighting industry within the next decade. Primarily, there are three disruptive technologies that will shape our future: machine learning, augmented reality (AR), and all-digital lighting infrastructure, which is arguably the most important building block for the future, this will be the foundation that will fully realize the potential of machine learning and AR for lighting. By all-digital, I do mean every component of the lighting system, including the light source (e.g. LED), sensors, LED drivers, and of course controls.

The answer lies in a future state called the “mirror world.” A mirror world is a digital replica of the physical world that we occupy today. In the mirror world, digital information is seamlessly integrated into the physical world, and with the use of devices, we could easily access that information where and when we want it, through an immersive experience. This digital construct of the physical world will become the new platform that drives innovation.

For the lighting industry, potential use cases in the mirror world will transform the current mode of operation. In initial lighting system design, a lighting designer, together with the client, could visualize how various lighting options would look at the job site using AR. A smartphone, a tablet, a pair of smart glasses — or even a pair of smart contact lenses — could allow us to enter the mirror world. Imagine the richness of user experience, and the unprecedented level of engagement, not to mention the design flexibility that you could achieve by walking around the mirror world to preview how the new lighting system would look and behave. Within this decade, the mirror world will start to take shape and its impact will be felt by everyone in the SSL industry. Every LED lighting retrofit and every new installation presents a golden opportunity to lay down the foundation for a future-proof, all-digital lighting system.

Artificial Intelligence seems to be the mutual evolutionary force in every industry, which promises to switch things up altogether. While the whole commotion around the technology is quite exciting and optimistic, for the general public, it’s still an obscure dimension.

This article was originally featured in the April issue of designing lighting (dl)