Utah-based PassiveLogic is working with Pacific Northwest National Laboratory (PNNL) to advance machine-learning technology for building autonomy.

Solving pressing climate problems, the partnership aims to advance research that enables building autonomy and energy efficiency.

PassiveLogic is the creator of the first platform for generalised autonomy and a specialist in artificial intelligence and machine-learning research for high-performance, industrial-grade applications. The deal with PNNL aims to develop deep artificial intelligence for predictive building controls.

Funded by the US Department of Energy (DoE) to support its mandate to improve the energy efficiency of four million buildings by 2030, the 24-month research collaboration will focus on super-learners, a foundational machine-learning technology that enables autonomy for all building applications.

“The only way to meet the world’s decarbonisation goals is through breakthroughs in building automation and control,” said PassiveLogic’s CEO Troy Harvey. “PassiveLogic is solving the biggest technology challenge in the energy economy, developing the first autonomous platform for buildings and industrial systems capable of optimally driving these systems in real time.”

Buildings are the largest controlled system vertical in the economy and the largest energy consumer, roughly twice that of the transportation market. PassiveLogic’s autonomous platform provides an API for buildings, enabling anyone to develop their own applications with little programming and integration effort.

PNNL’s autonomous learning and reasoning team initiated the PassiveLogic collaboration in a partnership called a cooperative research and development agreement (crada), which has long been a DoE tool for encouraging public-private collaborations and advancing technologies in the marketplace. The DoE will fund $1m for the PNNL to contribute to PassiveLogic’s technology.

The agreement will enable PNNL and PassiveLogic to develop and apply their capabilities and foster a technology that will help energy systems in buildings, such as heating and cooling units and lighting, become fully autonomous, capable of identifying and addressing their own operational issues, and able to self-optimise their operation.

“We’re eager to work with PassiveLogic and advance energy efficiency for commercial buildings,” said Draguna Vrabie, chief data scientist in the data sciences and machine intelligence group. “Our work at PNNL is deepened by working with partners in the private sector like PassiveLogic because they provide the use cases, data sets and market access to develop R&D efforts into commercially viable applications.”

Earlier this year, PassiveLogic announced the launch of the Quantum Alliance, a cooperative effort between public and private entities to move the building industry towards full autonomy with support from the DoE, PNNL and Brookfield. The alliance aims to develop an industry-spanning consensus known as the Quantum Standard, a physics-based digital-twin description language that enables complete building autonomy. 

PassiveLogic is reimagining how to design, build, operate, maintain and manage buildings using deep-physics digital twins, and AI-enabled future-forward controls, and make this technology accessible to all kinds of buildings, big and small, new construction and retrofit.