FORT and NVIDIA launch AI-driven Outside-In Safety blueprint
FORT Robotics has joined the NVIDIA Halos for Robotics ecosystem, the companies announced today, unveiling an AI-powered “Outside-In Safety” solution designed to enhance both autonomous robot productivity and worker safety. The system uses external infrastructure sensors to extend robot perception beyond traditional onboard sensors, enabling real-time, safety-certifiable functional safety.
The companies will showcase the new application this week at the Automate conference in Chicago, ahead of a joint presentation with NVIDIA in the Humanoid Robotics Pavilion on June 23rd. The NVIDIA Outside-In Safety Blueprint combines with the FORT Trust Layer to dynamically adjust robot behavior based on environmental conditions.
Key benefits of outside-in safety
The solution offers several advantages over conventional safety systems, which rely solely on onboard sensors and often impose conservative slowdowns that limit throughput. By using external infrastructure and visual AI agents, the system automatically adjusts robot efficiency to suit dynamic environments, reducing costly slowdowns while maintaining safety.
Worker safety is enhanced through proactive situational awareness in mixed human-robot workspaces, helping prevent accidents before they occur. The approach also maximizes return on investment by allowing industries such as warehousing and manufacturing to repurpose existing building-mounted cameras for tasks like inventory replenishment and truck unloading.
The system runs on NVIDIA IGX Thor and NVIDIA Holoscan Sensor Bridge for AI compute and sensor connectivity, enabling robots to operate at high efficiency alongside workers while adapting to complex environments. NVIDIA noted the system provides value beyond traditional inside-out functional safety, which is constrained by onboard sensors and conservative operating limits.
A robotics safety ecosystem built for scale
FORT is a member of the NVIDIA Halos AI Systems Inspection Lab, an ANSI National Accreditation Board-accredited facility dedicated to verifying functional safety, cybersecurity, and AI compliance for autonomous vehicles, robotics, and sensor technologies. The collaboration builds on FORT’s ongoing work with NVIDIA to make physical AI trustworthy at industrial scale.
“Safety has always been the precondition for scale — you can't deploy robots broadly if you can't guarantee they'll operate safely around people and valuable infrastructure,” said Samuel Reeves, CEO of FORT. “What collaborating with NVIDIA gives us is enhanced perception that makes safety genuinely intelligent. Agentic robots that understand their environment and respond in real time aren't just safer, they're more productive. That's the combination the industry has been waiting for.”
FORT’s Outside-In Safety expands its existing Trust Layer for Physical AI, which already includes Onboard Active Safety—perception technology that enables machines to detect, anticipate, and respond to environments in real time—and Human-in-the-Loop control for safe remote operation and intervention.
The source for this article is https://www.therobotreport.com/fort-and-nvidia-launch-ai-driven-outside-in-safety-blueprint/.