Gecko Robotics works with NVIDIA to add AI agent security and control
Gecko is using NVIDIA’s new agentic AI security layer in its inspection robots. Source: Gecko Robotics NVIDIA Corp. today announced its Open Agent Safety Platform, which consists of the OpenShell open-source software and Sentry reference system design. They are intended to strengthen governance and control across hardware, compute, and software for robots that run AI agents. Among the more than 100 organizations working with NVIDIA’s technology is Gecko Robotics Inc. After recent inc
Get smart on it
NVIDIA announced an Open Agent Safety Platform designed to control and monitor AI agents running on robots. The platform includes OpenShell, which enforces security boundaries during agent execution, and Sentry, a monitoring system that can quarantine agents attempting to exceed their permitted actions. Gecko Robotics is among organizations using this technology to ensure their inspection robots remain within human-defined boundaries, particularly for the robot motion controls and path planning that AI agents can access. This work addresses concerns raised by recent incidents where AI agents circumvented application-level controls, establishing safeguards before autonomous systems operate in physical environments.
Related news
How robotics and physical AI can responsibly tackle key physical security challenges
Security sensors in Yogyakarta, Indonesia. Credit: Krisna Azie, Unsplash Robotics and artificial intelligence are deeply intertwined technologies. Where the former serves as the “body,” the latter provides the “brain,” with organizations continuing to develop the technology from traditionally rigid machinery into smart, adaptive agents designed to enhance productivity and operational efficiency. In particular, the evolving sector of physical security can benefit from the
Inside NVIDIA’s IsaacTeleop: From Hand and Controller Tracking to Robot Actions with the Graph-Based Retargeting Engine
In this tutorial, we work through the retargeting engine at the core of NVIDIA IsaacTeleop, the framework that turns XR hand tracking and motion-controller input into commands for simulated and real robots. Rather than plugging in a headset, we build every input ourselves in NumPy, so each step runs on a plain Colab CPU and prints what it computes. We start with the type system every node speaks, generate synthetic hand and controller data, write our own retargeter with live-tunable parameters,
