3 Repos
Compiling and deploying machine learning models to bare-metal or RTOS environments on specialized embedded hardware.
Distinct from Embedded Systems Development: Focuses specifically on the AI model deployment lifecycle for embedded systems rather than general software development for resource-constrained hardware.
Explore 3 awesome GitHub repositories matching software engineering & architecture · Embedded AI Deployment. Refine with filters or upvote what's useful.
OpenCat-Quadruped-Robot ist ein Entwicklungs-Framework und Motion-Control-API für den Bau vierbeiniger Roboter. Es bietet eine umfassende Umgebung für die Entwicklung von Quadruped-Robotern, mit Tools für Locomotion-Gait-Design, inverse Kinematik und eine geschichtete Steuerungsarchitektur, die High-Level-Intelligenz von Low-Level-Bewegungen trennt. Das Projekt zeichnet sich als Embedded-KI-Deployment-Tool aus, das es Benutzern ermöglicht, Machine-Learning-Modelle zu trainieren, zu quantisieren und auf Vision-Module für Aufgaben wie Objekterkennung und visuelles Target-Tracking bereitzustellen. Es unterstützt zudem komplexe Mensch-Roboter-Interaktion durch Offline-Sprachbefehlsverarbeitung, Imitation menschlicher Bewegungen und ein visuelles Block-Programmier-Interface für grafische Logikgenerierung. Das System deckt eine breite Funktionsfläche ab, einschließlich Echtzeit-Balance-Stabilisierung mittels IMU-Daten, autonomer Navigation mittels 3D-Kameras und verschiedener Fernsteuerungs-Interfaces via Bluetooth und WiFi. Es enthält zudem Tools für Roboter-Gait-Simulation, Reinforcement-Learning-Policy-Transfer und eine dedizierte Python-API für externe Software-Integration. Firmware-Management wird über eine Suite von Deployment-Tools abgewickelt, die USB, Bluetooth und Over-the-Air-Updates für Mainboards und Mikrocontroller-Module unterstützen.
Integrates and optimizes machine learning models on robotic hardware for real-time object detection and autonomous behavior.
ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,
Integrates and runs machine learning models on Android, iOS, and microcontrollers with multi-language runtime bindings.
IREE is an MLIR-based compiler toolchain and runtime designed to translate machine learning models from various frameworks into optimized binaries for execution across diverse hardware targets. It provides a unified pipeline to ingest models from PyTorch, TensorFlow, JAX, and ONNX, lowering them into a common intermediate representation for deployment on CPUs, GPUs, and bare-metal embedded systems. The project distinguishes itself through a bytecode virtual machine and a hardware abstraction layer that decouple high-level model logic from specific hardware instruction sets. It supports sophis
Compiles and deploys machine learning models to resource-constrained environments including mobile and bare-metal systems.