Jaiveer Singh, a robotics software engineer at NVIDIA, leads the team behind Isaac ROS, a software stack built on the open source ROS 2 framework that brings CUDA-accelerated libraries and AI models to developers building autonomous mobile robots, manipulation systems and humanoids. Singh’s goal is to ensure everyone feels part of the robotics future. His work began as an intern project exploring the value of releasing open source software using the NVIDIA Jetson platform and CUDA libraries. Isaac ROS is completely modular, shipping software like LEGO bricks that developers can assemble and combine with existing ROS code. The stack supports manipulation, mobility and humanoids, offering packages for perception, object detection, mapping, collision detection and motion planning, and runs on workstations, NVIDIA DGX Spark personal AI supercomputers, and NVIDIA Jetson edge systems. Singh noted that open source gives developers confidence to build upon the stack at an initial stage, as the landscape can shift rapidly.