BMW Group has selected the new NVIDIA Isaac robotics platform for use in its automotive factories, utilizing logistics robots built on advanced AI computing and visualization technologies. Autonomous AI-powered logistics robots, called BMW Smart Transport Robots (STRs), assist the current production process in order to assemble customized vehicles on the same production line.  

99 percent of BMW’s customer orders are uniquely different from each other. BMW Group’s response is to use NVIDIA’s Isaac robotics platform to develop five AI-enabled robots to improve their logistics workflow, powered by a variety of NVIDIA Jetson AGX Xavier and EGX edge computers. These include both navigation robots to transport material autonomously, as well as manipulation robots to select and organize parts. 

Developed with the NVIDIA Isaac SDK, the robots utilize a number of deep neural networks, addressing perception, segmentation, pose estimation, and human pose estimation to perceive their environment, detect objects, navigate autonomously, and move objects. These robots are trained both on real and synthetic data using NVIDIA GPUs to render ray-traced machine parts in a variety of lighting and occlusion conditions to augment real data.

The real and synthetic data are then used to train deep neural networks on NVIDIA DGX systems. The robots are then tested in NVIDIA’s Isaac Simulators for both navigation and manipulation, operating on NVIDIA’s Omniverse platform, where multiple BMW Group personnel in different geographies can all work in one simulated environment.

For more information, visit: http://nvidianews.nvidia.com/.