{
  "library": "AutomotiveCloudWatch Repository Library",
  "domain": "robotics",
  "title": "Robotics and Physical AI",
  "edition": 1,
  "published": "2026-10-19",
  "checked": "2026-10-19",
  "next_edition": "2026-11-02",
  "page_url": "https://automotivecloudwatch.com/repositories/robotics",
  "markdown_url": "https://automotivecloudwatch.com/repositories/robotics.md",
  "changes_url": "https://automotivecloudwatch.com/repositories/robotics#changes",
  "changes": [
    {
      "edition": 1,
      "date": "2026-10-19",
      "summary": "First edition. Every repository is new, checked on this date against its GitHub page."
    }
  ],
  "teams": [
    {
      "name": "Robot Software Platform teams",
      "order": 1,
      "description": "Own the ROS 2 distribution, middleware choices, hardware abstraction and logging formats that the rest of the robot software runs on.",
      "anchor": "team-robot-software-platform",
      "repository_count": 5
    },
    {
      "name": "Motion Planning and Control teams",
      "order": 2,
      "description": "Own kinematics, dynamics, trajectory optimization and collision-aware planning that turn tasks into safe, feasible motion.",
      "anchor": "team-motion-planning-and-control",
      "repository_count": 5
    },
    {
      "name": "Robot Learning and Foundation Model teams",
      "order": 3,
      "description": "Own the data pipelines, training code, benchmarks and pretrained vision-language-action models used to teach robots new skills.",
      "anchor": "team-robot-learning-and-foundation-model",
      "repository_count": 7
    },
    {
      "name": "Simulation and Sim-to-Real teams",
      "order": 4,
      "description": "Own physics engines, robot models and GPU training environments, and the process of moving policies from simulation onto hardware.",
      "anchor": "team-simulation-and-sim-to-real",
      "repository_count": 6
    },
    {
      "name": "Manipulation and Humanoid teams",
      "order": 5,
      "description": "Own arms, hands and humanoid platforms, including inverse kinematics, retargeting from human motion and whole-body control.",
      "anchor": "team-manipulation-and-humanoid",
      "repository_count": 6
    },
    {
      "name": "Mobile Robot and Fleet teams",
      "order": 6,
      "description": "Own AMR navigation, mapping for navigation and the fleet control layer, including VDA 5050 integration and multi-vendor traffic management.",
      "anchor": "team-mobile-robot-and-fleet",
      "repository_count": 5
    },
    {
      "name": "Perception teams",
      "order": 7,
      "description": "Own state estimation, odometry, SLAM and 3D data processing that tell a robot where it is and what is around it.",
      "anchor": "team-perception",
      "repository_count": 4
    },
    {
      "name": "Robot Safety and Reliability teams",
      "order": 8,
      "description": "Own security hardening, real-time tracing, safe-control benchmarking and vulnerability awareness across the robot software stack.",
      "anchor": "team-robot-safety-and-reliability",
      "repository_count": 4
    }
  ],
  "repositories": [
    {
      "full_name": "ros2/ros2",
      "team": "Robot Software Platform teams",
      "level": "Start here",
      "license": "NOASSERTION",
      "license_flag": "No license detected",
      "stars": 6185,
      "last_activity": "2026-10-07",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ros2/ros2",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ros2-ros2",
      "what": "The entry repository for ROS 2 that lists the core packages and points to the documentation and release process.",
      "why": "Start here to get the full picture of the ROS 2 distribution, and note that the license lives in the individual packages, which are mostly Apache-2.0."
    },
    {
      "full_name": "ros-controls/ros2_control",
      "team": "Robot Software Platform teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 1037,
      "last_activity": "2026-10-18",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ros-controls/ros2_control",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ros-controls-ros2-control",
      "what": "A framework for connecting ROS 2 controllers to real or simulated hardware through a common hardware interface.",
      "why": "Use it when you integrate a new robot or actuator so that standard controllers, MoveIt and Nav2 work without custom glue."
    },
    {
      "full_name": "ros2/rmw_zenoh",
      "team": "Robot Software Platform teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 509,
      "last_activity": "2026-10-16",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ros2/rmw_zenoh",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ros2-rmw-zenoh",
      "what": "A ROS 2 middleware layer that uses Zenoh instead of DDS for discovery and transport.",
      "why": "Try it when DDS discovery struggles on Wi-Fi, across networks or with large fleets, which are common pain points in deployed robots."
    },
    {
      "full_name": "foxglove/mcap",
      "team": "Robot Software Platform teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 1116,
      "last_activity": "2026-10-16",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/foxglove/mcap",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-foxglove-mcap",
      "what": "An open container file format for timestamped multimodal robot data, with libraries in several languages.",
      "why": "It is now the default rosbag2 storage format and a good choice for any robot or vehicle logging pipeline that needs fast indexed reads."
    },
    {
      "full_name": "dora-rs/dora",
      "team": "Robot Software Platform teams",
      "level": "Deep end",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 4019,
      "last_activity": "2026-10-19",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/dora-rs/dora",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-dora-rs-dora",
      "what": "A dataflow framework written in Rust for composing robot and AI nodes with shared-memory messaging, usable from Python, Rust and C++.",
      "why": "Look at it when ROS 2 overhead or Python integration of AI models is the bottleneck and you can accept a younger ecosystem."
    },
    {
      "full_name": "moveit/moveit2",
      "team": "Motion Planning and Control teams",
      "level": "Start here",
      "license": "BSD-3-Clause",
      "license_flag": null,
      "stars": 2077,
      "last_activity": "2026-10-09",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/moveit/moveit2",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-moveit-moveit2",
      "what": "The standard ROS 2 framework for manipulator motion planning, collision checking and grasp execution.",
      "why": "It is the usual starting point for any arm application on ROS 2 and connects to most other planning tools on this list."
    },
    {
      "full_name": "ompl/ompl",
      "team": "Motion Planning and Control teams",
      "level": "Practitioner",
      "license": "BSD-3-Clause",
      "license_flag": null,
      "stars": 2178,
      "last_activity": "2026-09-25",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ompl/ompl",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ompl-ompl",
      "what": "A library of sampling-based motion planning algorithms such as RRT and PRM variants.",
      "why": "Learn it to understand what MoveIt does underneath and to try planners directly on new robots or state spaces."
    },
    {
      "full_name": "stack-of-tasks/pinocchio",
      "team": "Motion Planning and Control teams",
      "level": "Deep end",
      "license": "BSD-2-Clause",
      "license_flag": null,
      "stars": 3798,
      "last_activity": "2026-10-19",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/stack-of-tasks/pinocchio",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-stack-of-tasks-pinocchio",
      "what": "A fast C++ and Python library for rigid body kinematics, dynamics and their analytical derivatives.",
      "why": "Reach for it when building model predictive control or trajectory optimization, where fast dynamics derivatives decide performance."
    },
    {
      "full_name": "NVlabs/curobo",
      "team": "Motion Planning and Control teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 1926,
      "last_activity": "2026-09-10",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/NVlabs/curobo",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-nvlabs-curobo",
      "what": "A GPU-accelerated library for collision-free motion generation, inverse kinematics and trajectory optimization.",
      "why": "Use it when planning time matters, for example in high-throughput picking cells, since it runs many optimizations in parallel on a GPU."
    },
    {
      "full_name": "RobotLocomotion/drake",
      "team": "Motion Planning and Control teams",
      "level": "Deep end",
      "license": "BSD-3-Clause",
      "license_flag": null,
      "stars": 4227,
      "last_activity": "2026-10-19",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/RobotLocomotion/drake",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-robotlocomotion-drake",
      "what": "A toolbox for model-based design and verification of robots, combining multibody dynamics, optimization and systems modeling.",
      "why": "It is the tool to study when you need rigorous dynamics, contact modeling and mathematical programming in one framework."
    },
    {
      "full_name": "huggingface/lerobot",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Start here",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 28278,
      "last_activity": "2026-10-19",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/huggingface/lerobot",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-huggingface-lerobot",
      "what": "Hugging Face's library for real-world robot learning, covering data collection, a shared dataset format, training and deployment of policies.",
      "why": "It is the easiest end-to-end entry point into imitation learning and VLA fine-tuning on affordable hardware."
    },
    {
      "full_name": "google-deepmind/open_x_embodiment",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 2076,
      "last_activity": "2025-11-05",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/google-deepmind/open_x_embodiment",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-google-deepmind-open-x-embodiment",
      "what": "The home of the Open X-Embodiment dataset, which pools robot demonstrations from many labs and robot types, along with RT-1-X model code.",
      "why": "Read it to understand the cross-embodiment data that most current open VLA models were pretrained on."
    },
    {
      "full_name": "droid-dataset/droid",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Practitioner",
      "license": "NOASSERTION",
      "license_flag": "No license detected",
      "stars": 457,
      "last_activity": "2025-09-15",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/droid-dataset/droid",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-droid-dataset-droid",
      "what": "The code for the DROID platform and its large in-the-wild Franka manipulation dataset collected across many sites.",
      "why": "Study it for its data collection hardware and software setup, which is a strong template for building your own demonstration pipeline."
    },
    {
      "full_name": "Lifelong-Robot-Learning/LIBERO",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 2444,
      "last_activity": "2025-03-15",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/Lifelong-Robot-Learning/LIBERO",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-lifelong-robot-learning-libero",
      "what": "A simulated benchmark of language-conditioned manipulation task suites for lifelong and multitask robot learning.",
      "why": "Many VLA papers report results on it, so it is a practical place to reproduce claims and compare models on equal terms."
    },
    {
      "full_name": "real-stanford/diffusion_policy",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 4656,
      "last_activity": "2024-12-24",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/real-stanford/diffusion_policy",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-real-stanford-diffusion-policy",
      "what": "The reference code for Diffusion Policy, which generates robot actions with a denoising diffusion model trained on demonstrations.",
      "why": "It is a canonical reference that many later VLA action heads build on, although the code itself has not been updated since December 2024."
    },
    {
      "full_name": "openvla/openvla",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 7171,
      "last_activity": "2025-03-23",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/openvla/openvla",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-openvla-openvla",
      "what": "An open 7B-parameter vision-language-action model with training and fine-tuning code.",
      "why": "Use it to learn how a VLA is assembled from a vision-language model and action tokens, and how to fine-tune one on your own data."
    },
    {
      "full_name": "Physical-Intelligence/openpi",
      "team": "Robot Learning and Foundation Model teams",
      "level": "Deep end",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 14293,
      "last_activity": "2026-08-24",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/Physical-Intelligence/openpi",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-physical-intelligence-openpi",
      "what": "Physical Intelligence's open release of its pi-zero family of VLA models with weights, fine-tuning and inference code.",
      "why": "It is one of the strongest open generalist policies to fine-tune for a new robot or task."
    },
    {
      "full_name": "google-deepmind/mujoco",
      "team": "Simulation and Sim-to-Real teams",
      "level": "Start here",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 15745,
      "last_activity": "2026-10-18",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/google-deepmind/mujoco",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-google-deepmind-mujoco",
      "what": "A fast and accurate physics engine for robotics and biomechanics, maintained by Google DeepMind.",
      "why": "It is the common physics baseline for robot learning research and runs on CPU or, through MJX and Warp, on accelerators."
    },
    {
      "full_name": "google-deepmind/mujoco_menagerie",
      "team": "Simulation and Sim-to-Real teams",
      "level": "Start here",
      "license": "NOASSERTION",
      "license_flag": "No license detected",
      "stars": 4216,
      "last_activity": "2026-10-15",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/google-deepmind/mujoco_menagerie",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-google-deepmind-mujoco-menagerie",
      "what": "A curated collection of tuned MuJoCo models of commercial robots, arms, hands and humanoids.",
      "why": "Use it to avoid weeks of model building and tuning, and check each model folder for its own license."
    },
    {
      "full_name": "isaac-sim/IsaacLab",
      "team": "Simulation and Sim-to-Real teams",
      "level": "Practitioner",
      "license": "BSD-3-Clause",
      "license_flag": null,
      "stars": 8377,
      "last_activity": "2026-10-19",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/isaac-sim/IsaacLab",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-isaac-sim-isaaclab",
      "what": "NVIDIA's open framework on top of Isaac Sim for GPU-parallel robot learning, including reinforcement and imitation learning.",
      "why": "It is a common path for training locomotion and manipulation policies at scale and transferring them to hardware."
    },
    {
      "full_name": "newton-physics/newton",
      "team": "Simulation and Sim-to-Real teams",
      "level": "Deep end",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 5804,
      "last_activity": "2026-10-18",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/newton-physics/newton",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-newton-physics-newton",
      "what": "A GPU physics engine built on NVIDIA Warp and hosted by the Linux Foundation, with contributions from Disney Research, Google DeepMind and NVIDIA.",
      "why": "Watch it as the likely shared physics core for future Isaac Lab and MuJoCo workflows, with differentiable simulation built in."
    },
    {
      "full_name": "Genesis-Embodied-AI/genesis-world",
      "team": "Simulation and Sim-to-Real teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 30084,
      "last_activity": "2026-10-17",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/Genesis-Embodied-AI/genesis-world",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-genesis-embodied-ai-genesis-world",
      "what": "A Python physics platform for robotics and embodied AI that combines several solvers with fast parallel simulation and rendering.",
      "why": "Evaluate it as an alternative training environment, and benchmark it on your own tasks before relying on headline speed claims."
    },
    {
      "full_name": "gazebosim/gz-sim",
      "team": "Simulation and Sim-to-Real teams",
      "level": "Start here",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 1542,
      "last_activity": "2026-10-18",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/gazebosim/gz-sim",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-gazebosim-gz-sim",
      "what": "The core library of Gazebo, the long-standing open robot simulator tightly integrated with ROS 2.",
      "why": "Use it for system-level testing of ROS 2 robots with sensors and worlds, where learning-focused simulators are less complete."
    },
    {
      "full_name": "TheRobotStudio/SO-ARM100",
      "team": "Manipulation and Humanoid teams",
      "level": "Start here",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 7804,
      "last_activity": "2026-10-06",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/TheRobotStudio/SO-ARM100",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-therobotstudio-so-arm100",
      "what": "Open hardware designs for low-cost SO-100 and SO-101 robot arms that work directly with LeRobot.",
      "why": "It gives teams a cheap physical platform to try imitation learning before spending on industrial arms."
    },
    {
      "full_name": "kevinzakka/mink",
      "team": "Manipulation and Humanoid teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 1582,
      "last_activity": "2026-09-30",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/kevinzakka/mink",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-kevinzakka-mink",
      "what": "A Python library for differential inverse kinematics on MuJoCo models with tasks, limits and priorities.",
      "why": "Reach for it when you need clean, constraint-aware IK for arms, hands or humanoids in prototypes and teleoperation."
    },
    {
      "full_name": "dexsuite/dex-retargeting",
      "team": "Manipulation and Humanoid teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 1282,
      "last_activity": "2025-08-21",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/dexsuite/dex-retargeting",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-dexsuite-dex-retargeting",
      "what": "Tools for mapping human hand poses from video or motion capture onto different robot hands.",
      "why": "It is a key piece for teleoperation and for turning human demonstrations into training data for dexterous hands."
    },
    {
      "full_name": "unitreerobotics/unitree_rl_gym",
      "team": "Manipulation and Humanoid teams",
      "level": "Practitioner",
      "license": "BSD-3-Clause",
      "license_flag": null,
      "stars": 3623,
      "last_activity": "2025-07-25",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/unitreerobotics/unitree_rl_gym",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-unitreerobotics-unitree-rl-gym",
      "what": "Unitree's reinforcement learning examples for training and deploying locomotion policies on its Go2, H1 and G1 robots.",
      "why": "It shows the full sim-to-real loop for legged and humanoid locomotion on hardware many labs actually own."
    },
    {
      "full_name": "LeCAR-Lab/ASAP",
      "team": "Manipulation and Humanoid teams",
      "level": "Deep end",
      "license": "MIT",
      "license_flag": null,
      "stars": 2128,
      "last_activity": "2026-01-06",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/LeCAR-Lab/ASAP",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-lecar-lab-asap",
      "what": "Research code from CMU for aligning humanoid simulation with real physics so that agile whole-body skills transfer to hardware.",
      "why": "Read it to understand current methods for closing the sim-to-real gap on humanoids beyond plain domain randomization."
    },
    {
      "full_name": "NVIDIA/Isaac-GR00T",
      "team": "Manipulation and Humanoid teams",
      "level": "Deep end",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 8224,
      "last_activity": "2026-10-15",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/NVIDIA/Isaac-GR00T",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-nvidia-isaac-gr00t",
      "what": "NVIDIA's open GR00T N foundation models for humanoid and general robot control, with fine-tuning and deployment code.",
      "why": "Look at it when targeting humanoids or the NVIDIA Jetson Thor stack, since it ties into Isaac Lab and NVIDIA data tools."
    },
    {
      "full_name": "ros-navigation/navigation2",
      "team": "Mobile Robot and Fleet teams",
      "level": "Start here",
      "license": "NOASSERTION",
      "license_flag": "No license detected",
      "stars": 4835,
      "last_activity": "2026-10-18",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ros-navigation/navigation2",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ros-navigation-navigation2",
      "what": "Nav2, the ROS 2 navigation framework for planning, control, recovery behaviors and behavior trees on mobile robots.",
      "why": "It is the standard open base for AMR navigation and is used in many commercial robots, with mixed Apache-2.0, BSD and LGPL licensing by package."
    },
    {
      "full_name": "SteveMacenski/slam_toolbox",
      "team": "Mobile Robot and Fleet teams",
      "level": "Start here",
      "license": "LGPL-2.1",
      "license_flag": "Weak copyleft",
      "stars": 2681,
      "last_activity": "2026-10-15",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/SteveMacenski/slam_toolbox",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-stevemacenski-slam-toolbox",
      "what": "A 2D laser SLAM package for ROS 2 that supports mapping, localization and multi-session map merging.",
      "why": "It is the default mapping tool used with Nav2 for warehouse and indoor mobile robots."
    },
    {
      "full_name": "VDA5050/VDA5050",
      "team": "Mobile Robot and Fleet teams",
      "level": "Start here",
      "license": "MIT",
      "license_flag": null,
      "stars": 524,
      "last_activity": "2026-09-28",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/VDA5050/VDA5050",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-vda5050-vda5050",
      "what": "The official source of the VDA 5050 interface specification for communication between AGVs or AMRs and a master control system, now at version 3.0.0.",
      "why": "Read it before any multi-vendor fleet project, since it defines the MQTT messages and state model that vendors are expected to implement."
    },
    {
      "full_name": "openTCS/opentcs",
      "team": "Mobile Robot and Fleet teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 592,
      "last_activity": "2026-09-17",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/openTCS/opentcs",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-opentcs-opentcs",
      "what": "A Fraunhofer IML open fleet control system for AGVs and AMRs with built-in VDA 5050 support.",
      "why": "Use it to prototype or run vendor-neutral fleet control, including routing, order management and traffic handling."
    },
    {
      "full_name": "open-rmf/rmf_ros2",
      "team": "Mobile Robot and Fleet teams",
      "level": "Deep end",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 120,
      "last_activity": "2026-10-12",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/open-rmf/rmf_ros2",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-open-rmf-rmf-ros2",
      "what": "The ROS 2 core of Open-RMF, a framework for coordinating fleets of different robots with shared infrastructure such as doors and lifts.",
      "why": "It fits facilities that must run robots from several vendors together and manage traffic and task allocation between them."
    },
    {
      "full_name": "borglab/gtsam",
      "team": "Perception teams",
      "level": "Deep end",
      "license": "BSD-2-Clause",
      "license_flag": null,
      "stars": 3758,
      "last_activity": "2026-10-18",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/borglab/gtsam",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-borglab-gtsam",
      "what": "A C++ library with Python bindings for smoothing and mapping with factor graphs.",
      "why": "It is the estimation back end behind many SLAM and sensor fusion systems, so learning it pays off across localization work."
    },
    {
      "full_name": "PRBonn/kiss-icp",
      "team": "Perception teams",
      "level": "Start here",
      "license": "MIT",
      "license_flag": null,
      "stars": 2350,
      "last_activity": "2026-06-09",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/PRBonn/kiss-icp",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-prbonn-kiss-icp",
      "what": "A simple LiDAR odometry pipeline based on point-to-point ICP that works across sensors with little tuning.",
      "why": "Use it as a strong baseline before reaching for more complex LiDAR SLAM systems."
    },
    {
      "full_name": "NVIDIA-ISAAC-ROS/isaac_ros_visual_slam",
      "team": "Perception teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 1489,
      "last_activity": "2026-09-22",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_visual_slam",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-nvidia-isaac-ros-isaac-ros-visual-slam",
      "what": "A GPU-accelerated stereo visual-inertial odometry and SLAM package for ROS 2 on NVIDIA Jetson.",
      "why": "Use it when you need camera-based localization at frame rate on embedded NVIDIA hardware."
    },
    {
      "full_name": "isl-org/Open3D",
      "team": "Perception teams",
      "level": "Practitioner",
      "license": "MIT",
      "license_flag": null,
      "stars": 14105,
      "last_activity": "2026-09-30",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/isl-org/Open3D",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-isl-org-open3d",
      "what": "A C++ and Python library for 3D data processing, including point cloud registration, surface reconstruction and visualization.",
      "why": "Keep it in the toolbox for inspecting, filtering and aligning point clouds while developing LiDAR and depth camera pipelines."
    },
    {
      "full_name": "ros2/sros2",
      "team": "Robot Safety and Reliability teams",
      "level": "Practitioner",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 119,
      "last_activity": "2026-10-07",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ros2/sros2",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ros2-sros2",
      "what": "Tools for enabling and managing DDS security in ROS 2, including keystores, certificates and access control policies.",
      "why": "Use it to add authentication, encryption and access control to ROS 2 traffic, which is required for any robot on a shared network."
    },
    {
      "full_name": "ros2/ros2_tracing",
      "team": "Robot Safety and Reliability teams",
      "level": "Deep end",
      "license": "Apache-2.0",
      "license_flag": null,
      "stars": 271,
      "last_activity": "2026-10-12",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/ros2/ros2_tracing",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-ros2-ros2-tracing",
      "what": "Instrumentation and tools for low-overhead tracing of ROS 2 systems with LTTng.",
      "why": "Reach for it when you need evidence of end-to-end latency and executor behavior for real-time or safety analysis."
    },
    {
      "full_name": "learnsyslab/safe-control-gym",
      "team": "Robot Safety and Reliability teams",
      "level": "Deep end",
      "license": "MIT",
      "license_flag": null,
      "stars": 927,
      "last_activity": "2026-04-29",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/learnsyslab/safe-control-gym",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-learnsyslab-safe-control-gym",
      "what": "A benchmark suite from the University of Toronto for comparing control and reinforcement learning methods under safety constraints.",
      "why": "Use it to evaluate how learned controllers behave against constraints and disturbances before trusting them on hardware."
    },
    {
      "full_name": "aliasrobotics/RVD",
      "team": "Robot Safety and Reliability teams",
      "level": "Practitioner",
      "license": "GPL-3.0",
      "license_flag": "Strong copyleft",
      "stars": 244,
      "last_activity": "2026-07-14",
      "checked": "2026-10-19",
      "state": "ok",
      "flags": [],
      "github_url": "https://github.com/aliasrobotics/RVD",
      "acw_url": "https://automotivecloudwatch.com/repositories/robotics#repo-aliasrobotics-rvd",
      "what": "The Robot Vulnerability Database, a public record of security flaws and bugs found in robots and robot software.",
      "why": "Check it during threat modeling and supplier reviews to see the kinds of weaknesses that have already been found in common platforms."
    }
  ]
}