Projects sharing features with UniAD

Autoware is a modular autonomous driving stack and open-source platform for advanced driver assistance systems. It functions as an integrated operating environment that manages the full pipeline from sensor data processing to vehicle actuation, utilizing the ROS 2 robotics framework for distributed communication and hardware abstraction. The system provides a comprehensive software architecture to enable autonomous driving across various vehicle platforms. It coordinates perception, planning, and control systems to operate vehicles without human intervention. The platform covers several core

Autoware is an open-source autonomous driving software platform built on the robotics middleware standard. It provides a comprehensive stack for managing perception, planning, and control, enabling the development and deployment of full-stack autonomous driving software on commercial transport hardware. The platform utilizes a component-based modular architecture that organizes driving functions into isolated, interchangeable nodes. This design is supported by a hardware-abstraction layer and plugin-based sensor integration, which allow the software to interface with diverse hardware configur

Openpilot is an open-source driver assistance system that integrates with vehicle control units to provide automated steering, acceleration, and braking. It functions as an automotive robotics middleware, utilizing a specialized runtime environment to process sensor data and execute real-time control commands that manage vehicle dynamics. The platform distinguishes itself through a hardware-agnostic interface that translates standardized driving commands into the proprietary protocols required by a wide range of vehicle makes and models. It employs neural-network-based path planning to predic

Qwen3-Omni is an omni-modal large language model designed to process and generate text, audio, images, and video within a single unified neural architecture. It functions as a real-time voice assistant and multimodal AI agent capable of reasoning across different media types and executing external tool-calling functions via APIs. The system supports low-latency conversational AI through autoregressive token streaming and natural turn-taking. It enables multilingual speech translation and generation across dozens of languages, featuring customizable speaker profiles and tones. The model's cap

GOT-OCR2.0 is an end-to-end optical character recognition system and document text extractor. It utilizes a unified transformer architecture to recognize and extract plain and formatted text from diverse images and documents. The system features a multi-crop processing method that divides high-resolution or dense documents into smaller sections to maintain recognition detail. It also includes a renderer that transforms recognized text into HTML to preserve the original structure and layout of the document. The project provides a framework for fine-tuning pre-trained models on custom datasets

TripoSR is a single-image 3D reconstruction system that generates a high-quality textured mesh from one photograph in under half a second. It uses a feedforward neural network to process a single image through a transformer architecture, compressing the input into a compact latent vector that conditions the entire reconstruction pipeline. The system outputs a separate UV texture map with configurable resolution, replacing vertex colors for higher-quality surface detail. The project is built around an end-to-end differentiable pipeline that trains the entire reconstruction system from image in

This project is a PyTorch object detection framework that implements the Faster R-CNN architecture. It serves as a vision model for predicting precise bounding boxes around multiple objects within images and live video feeds. The system is optimized for multi-GPU training to reduce the time required for model convergence. It utilizes a GPU-accelerated design to handle the training and inference of complex detection networks. The framework covers the full object detection lifecycle, including custom network training and inference for static images and real-time video streams. It includes capa

This project is a research framework and toolkit designed for training large-scale vision transformers and multimodal language models. It provides a comprehensive suite for vision-language pretraining, enabling the development of models that map images and text into shared latent spaces. The framework is distinguished by its capabilities in high-fidelity image generation and multimodal research, utilizing normalizing flows and variational autoencoders to produce images from text prompts or class labels. It supports the development of both generative and contrastive models, allowing for a wide

This project is a machine learning toolkit designed for the development, training, and deployment of automatic speech recognition engines. It provides a comprehensive framework for converting spoken audio into written text, specifically supporting models trained on Mandarin and English datasets. The library utilizes an end-to-end neural architecture that processes raw audio input directly into character sequences, bypassing the need for intermediate linguistic alignment. It incorporates signal processing techniques to transform sound waves into numerical spectrograms and feature vectors, whic

Navigation2 is a ROS 2 navigation framework for autonomous mobile robots. It provides the core identity of a path planner, costmap management system, kinematic motion controller, and behavior tree orchestrator to compute collision-free routes and execute movement commands. The framework is distinguished by its use of behavior trees to coordinate modular task servers, enabling complex navigation routines and autonomous recovery actions. It supports a plugin-based architecture that allows planners and controllers to be swapped at runtime to adapt to different environments. The system covers a

This project is a distributed machine learning platform and sparse deep learning framework designed for training and serving models with high-dimensional sparse data. It functions as an online model serving infrastructure and recommendation system engine, enabling real-time item retrieval and scoring using deep tree matching and neural networks. The system distinguishes itself through a multi-task learning framework that optimizes multiple objective functions within a shared representation space. It features a specialized online serving infrastructure that supports dynamic model hot-loading a

AlphaFold is a deep learning biology framework and machine learning pipeline designed to predict the three-dimensional coordinates of proteins based on their amino acid sequences. It functions as a bioinformatics inference system for calculating protein folding patterns and estimating prediction confidence. The system includes a protein multimer predictor for determining the 3D structures of protein complexes, supporting both homomers and heteromers. It utilizes specialized model presets to handle these complex structural predictions. The framework covers biological database management for m

This project provides a complete set of design files and hardware specifications for a 3D-printable industrial-style robot arm. The system includes a CAN bus robot controller for managing stepper motors and sensors, a kinematics engine for calculating joint angles and poses, and a UDP-based Python API for sending motion commands and monitoring telemetry. The system features a force-controlled robotic gripper that utilizes field-oriented control on stepper motors to enable compliant grasping and precise force sensing. It also includes a 3D position visualization tool for real-time telemetry tr

This project is a deep learning framework designed for facial landmark detection. It functions as a computer vision library that provides the necessary routines to locate precise points on human faces within images by generating spatial probability maps. The architecture distinguishes itself through high-resolution parallel branching, which maintains detailed visual representations throughout the entire network. By utilizing multi-scale feature fusion, the model repeatedly exchanges information across these parallel streams to integrate fine-grained spatial details with broader semantic conte

SlowFast is a PyTorch video understanding framework and spatiotemporal neural network library. It serves as a toolset for video action recognition, enabling the training and evaluation of models designed to classify complex activities and objects within video sequences. The framework is distinguished by its use of dual-pathway spatiotemporal sampling to capture both slow and fast motions. It supports self-supervised video learning for pre-training models on unlabeled data and employs multigrid spatiotemporal training to optimize learning across multiple spatial and temporal resolutions. The

This project is a deep learning computer vision library designed for video action recognition. It provides a framework for training and evaluating neural networks that identify and categorize human activities within recorded footage by processing temporal sequences of frames. The library focuses on the implementation of three-dimensional neural network architectures, specifically utilizing three-dimensional convolutional layers to capture both spatial and temporal patterns. By aggregating features across consecutive frame sequences, the models learn to represent the evolution of actions over

:robot: The MoveIt motion planning framework

Gaussian Process Motion Planner 2

The Open Motion Planning Library (OMPL)

Optimal Control for Switched Systems

Robust and efficient coverage paths for autonomous agricultural vehicles. A modular and extensible Coverage Path Planning library

Simplifying optimal control with metaprogramming

Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

Behavior Trees Library for ROS (Robot Operating System). In C++ and python

Motion Generation for Robots and Machines. Real-time. Jerk-constrained. Time-optimal.