AI Developer Tools and Frameworks#

Here you will find guidance that covers the frameworks, models, and tools used to build and optimize robot perception and intelligence workloads.

Developer Tools#

Use these tools to develop, optimize, and profile AI workloads for Robotics AI Suite applications. Install versions supported by the relevant application or Blueprint; do not combine independently pinned toolkit versions without validating the resulting environment.

Tool

Use

PyTorch XPU

Accelerate model prototyping, training, and rapid iteration on Intel GPUs.

OpenVINO™

Optimize and deploy deep-learning inference workloads.

Intel oneAPI Toolkits

Develop and profile heterogeneous C++, SYCL, and data-parallel workloads.

OpenVINO™ Physical AI

Accelerate your OpenVINO™-powered deployment with a unified API for connecting cameras, robots, and policy inference.

Intel Physical AI Studio

Train and deploy VLA models with an easy-to-use imitation learning dataset generation platform.

Geti

Use an end-to-end pipeline to create vision AI models optimized for Intel.

For performance analysis, see Benchmarking and Profiling.

OpenVINO™

Optimize and deploy deep-learning inference on available Intel compute devices.

clickable cards
Geti

Use an end-to-end pipeline to create vision AI models.

clickable cards
AI Skills

Find skills for use with the Robotics AI Suite to power AI-enabled development.

clickable cards