#robotics

A robust C++17 library for constructing efficient Behavior Trees, suitable for robotics and gaming AI. Features include non-blocking asynchronous actions, XML-based tree scripting, and comprehensive logging/tooling. Compatible with ROS, ROS2, and multiple build systems, offering commercial support and a GUI editor for improved design workflows.

Theseus is a versatile PyTorch library for nonlinear optimization layers in robotics and vision, featuring differentiable optimization for enhancing neural models. It includes user-centric tools for various optimizers such as Gauss-Newton and Levenberg-Marquardt, supports dense and sparse linear solvers, and has functionalities for robotic kinematics and lie groups. Designed for computational efficiency, it offers GPU acceleration and seamless integration via PyPI or source.

openpilot, an advanced operating system for robotics, enhances driver assistance systems in over 275 car models. It's user-friendly with straightforward implementation using compatible devices and cars. Comprehensive resources and forums support developers and contributors in continuous improvement. The platform adheres to ISO26262 safety guidelines, offering robust testing. Customizable data management options ensure transparency. Discover this open-source solution for integrating advanced automotive technology.

Join a collaborative initiative to share prompt examples for large language models in robotics. This repository, with a sample robotics simulator integrating ChatGPT, welcomes contributions across diverse robotics fields. Engage with LLMs such as ChatGPT, GPT-3, and Codex. Participate in a community dedicated to evolving robotics and AI interfaces by submitting innovative prompt examples.

The open-source project LeRobot empowers real-world robotics with AI models, datasets, and tools compatible with PyTorch. It seeks to lower entry barriers so that anyone can participate in sharing and utilizing datasets and pretrained models. Emphasizing imitation and reinforcement learning, LeRobot ensures effective real-world application, offering users access to a variety of pretrained models and simulation environments. Planned expansions aim to support more cost-effective robotics solutions. Hosted on Hugging Face, LeRobot's community encourages exploration and collaboration in ongoing robotics advancements.

Donkeycar is a Python library tailored for those interested in autonomous vehicles, fostering easy experimentation and community involvement. It's widely adopted in schools and universities, enabling testing of self-driving technologies before robot construction through a simulation environment. Key features include deep learning, computer vision, and GPS navigation-driven autopilot systems. With Raspberry Pi as its standard hardware, setup is seamless. Comprehensive documentation aids in constructing and customizing self-driving vehicles, promoting innovation and community engagement in cutting-edge technology exploration.

GRID advances AI in robotics by integrating perception, control, and safety models with its Foundation Mosaic. With AirGen simulator, it supports vast data creation for various scenarios, aided by a language model for problem-solving. Available for non-commercial research, it offers frameworks for studies on applications like wildfire rescue and infrastructure inspection.

RoboticsAcademy presents an open-source platform for learning robotics, artificial intelligence, and computer vision through practical exercises. Incorporating ROS tools such as Gazebo and Rviz, it offers a rich environment for those interested in robotics. The platform's documentation aids in setup and usage, facilitating collaboration via GitHub for contributors. Discover robotics through experiential learning and community-driven resources.

MuJoCo is a flexible physics engine designed for accurate and efficient simulations across varied domains including robotics, biomechanics, and machine learning. Managed by Google DeepMind, it features a robust C API and Python bindings, allowing easy integration for researchers and developers. The engine includes an OpenGL-rendered GUI and numerous physics utility functions. Available as prebuilt binaries or source code, MuJoCo's comprehensive documentation and tutorials support users. It also includes multiple language bindings for cross-platform access and integration with tools such as Unity and WebAssembly.

Explore a flexible framework facilitating the creation of robotics environments for reinforcement learning. Leveraging ScenarIO, gym-ignition provides key abstractions such as Task and Runtime to focus on logic development. While not currently maintained, it eases simulation setup and domain randomization with dynamic algorithms. Ideal for custom RL environment creation, despite lacking pre-built settings, with ample examples available.

Bullet Physics SDK offers comprehensive solutions for real-time collision detection and multi-physics simulations across various domains including VR, gaming, visual effects, and more. With Python bindings through PyBullet, it provides enhanced functionalities in robotics and machine learning. Installation is straightforward via pip, supporting multiple platforms with a C++ compiler. Optional OpenGL demonstrations and experimental OpenCL GPGPU support for advanced GPU performance are available. Licensed under zlib, it is adaptable through vcpkg or premake with compatibility for Visual Studio and Xcode.

jaxlie offers efficient Lie groups for JAX-based rigid body transformations in computer vision and robotics. Inspired by the Sophus C++ library, it includes high-level classes like SO2, SE2, SO3, and SE3. These classes support essential operations such as exp(), log(), and multiply(), designed for forward- and reverse-mode automatic differentiation. Users benefit from manifold optimization, compatibility with JAX transformations, and support for broadcasting. Additionally, it provides utilities for uniform random sampling and Euler angle conversions, making it versatile for pose graph optimization and radiance field construction in projects like jaxfg and tensorf-jax.