Up until now we used the Nvidia Jetson Nano for machine learning acceleration purposes. Sadly, running our object detection models wasn’t viable on the Jetson Nano despite using its CUDA-capable GPU. Our Jetson Nano only managed a poor 5 spf (seconds per frame) and had both its RAM and VRAM running out of space constantly. In order to remedy this, we looked for stronger hardware. Luckily for us, ViGEM agreed to provide us with the much more capable Nvidia Jetson Xavier NX. Thank you to ViGEM.
Integration into our robot was rather straight forward except for some pecularities with compiling onnx-runtime which we use to deploy our models.