Built Robotics and the Safe Autonomous Systems Lab (xLAB) at Penn Engineering launched a research collaboration today to advance physical AI models for construction, with an initial deployment of Built's personnel-detection AI on a fleet of survey robots at active solar projects. The partnership, announced June 16, targets the gap between controlled lab validation and the messy, unpredictable conditions of real job sites where safety failures have immediate consequences.
xLAB, led by Professor Rahul Mangharam, has spent years developing safety-critical autonomous systems. "xLAB is committed to building safety-critical autonomous systems for real-world deployment, and construction represents one of the most demanding frontiers for that work," Mangharam said. "The fundamental challenge is bridging the gap between validation in controlled environments and robust performance under operational conditions." The collaboration gives the lab access to high-fidelity mapping data and operational parameters from live construction environments, enabling practical systems that solve real-world needs.
Built Robotics has refined its edge AI model for personnel detection across industrial sites with hundreds of workers and thousands of acres. "What xLAB has built in safety architecture is precisely the kind of rigorous foundation that physical AI demands," said Noah Ready-Campbell, CEO of Built Robotics. Liam Osler, the company's engineering director for AI, added that both teams share a conviction that physical AI must be safe before it can set a new standard for construction.
The collaboration underscores a broader shift in AI for Real Estate & Construction, where autonomous systems are moving beyond pilot programs to operate on active jobsites.
Initial deployment on solar construction sites
The research pilot will put the edge AI model on construction survey robots that collect high-fidelity sensor data at live solar projects. The data will then improve Built's existing models and help extend them to other vehicle platforms and construction tasks beyond surveying. This setup gives researchers direct exposure to the variables that make real sites challenging - dust, weather, moving equipment, and hundreds of personnel.
Academic roots, industrial scale
Ready-Campbell pointed to a personal link: Penn Engineering is his alma mater, and Dean Vijay Kumar's pioneering work on quadcopters and multi-robot coordination at the GRASP Lab shaped his founding of Built Robotics. "As our fleet of robots has scaled in the field, the mission alignment with xLAB has become crystal clear," he said. "I couldn't be more excited to partner with Professor Mangharam to set a new bar for how physical AI is designed, validated, and deployed in the field."
Why this matters for real estate and construction professionals
For project managers and developers, the most immediate promise is a measurable drop in safety incidents on large sites. Physical AI that reliably detects personnel and navigates hazards without false alarms or blind spots reduces liability risks and the delays that follow accidents. As survey robots become more autonomous, firms can shift human workers to higher-value tasks, directly addressing chronic labor shortages. This partnership moves the industry toward autonomous systems that perform not just in controlled settings but under real conditions - sun, rain, mud, and constant change.
Your membership also unlocks:
