NVIDIA's Isaac ROS, led by roboticist Jaiveer Singh, is an open-source software platform that equips developers with CUD

Jaiveer Singh, a robotics software engineer at NVIDIA, leads the team behind Isaac ROS, which builds on the open source ROS 2 framework to bring CUDA-accelerated libraries and AI models to developers creating autonomous mobile robots, manipulation systems and humanoids. Singh's goal, as he put it, is to make sure everyone feels like they are a part of the robotics future.

Singh's path to this work began in middle school with LEGO Mindstorms programmable robotics kits and continued through robotics competitions in high school. He studied electrical engineering, computer science and business at UC Berkeley before joining NVIDIA after an internship with the robotics team. His current work began as that intern project. As Singh recalled, "We wanted to see what would happen if we just released some software as open source that uses the NVIDIA Jetson platform and NVIDIA CUDA libraries for robotics. Would there be any value there? And the answer was, of course, yes, because developers always want to be able to unlock the full power of their GPUs."

Isaac ROS supports manipulation, mobility and humanoid systems. It provides developers with 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. Compared with the original Isaac SDK, Isaac ROS is completely modular. As Singh explained, "We ship the software like a bunch of LEGO bricks — you get to assemble them however you want, and you can easily combine our packages with existing ROS code written by you or others in the global robotics community."

The value of open source in robotics lies in the confidence it provides. Developers can inspect the code, change it, contribute fixes and carry it forward. This matters because robotics is changing rapidly, particularly with humanoid robots moving from science fiction to active engineering. As Singh noted, "When more people can build robots, the future gets here faster."