OpenVINO#

OpenVINO is the primary toolkit for optimizing and deploying deep-learning inference in Robotics AI Suite applications. It supports models from common frameworks and can target available Intel compute devices.

Use the current OpenVINO installation documentation for the selected environment.

Reference Applications#

OpenVINO reference applications cover object detection, segmentation, and RealSense camera workflows.

Semantic Segmentation with RealSense

Run semantic segmentation on RealSense image data using OpenVINO inference.

clickable cards
Object Detection

Deploy object-detection workloads with ROS 2 camera inputs and OpenVINO acceleration.

clickable cards
OpenVINO Multi-Camera Demo

Process multiple camera streams in a single OpenVINO-powered demo pipeline.

clickable cards
YOLOv8 with OpenVINO

Use a YOLOv8 model with OpenVINO for accelerated object detection on robotics systems.

clickable cards
OpenVINO Model Guidance

Optimize and deploy perception, manipulation, and vision-language-action models with OpenVINO.

clickable cards
Pi0.5 Model Optimization

Convert, compress, benchmark, and validate the Pi0.5 vision-language-action model.

clickable cards

Additional Guidance#

Benchmarking#

Use the upstream OpenVINO Benchmark Tool to estimate deep-learning inference throughput and latency on supported Intel® devices. Install OpenVINO and its samples with the OpenVINO sample guidance before benchmarking.

Use the same OpenVINO version to convert a model and to run inference unless the model’s documentation explicitly supports a different compatibility path.