{"id":28421683,"url":"https://github.com/nvidia-isaac-ros/isaac_ros_freespace_segmentation","last_synced_at":"2025-10-16T23:16:58.784Z","repository":{"id":169592050,"uuid":"620539588","full_name":"NVIDIA-ISAAC-ROS/isaac_ros_freespace_segmentation","owner":"NVIDIA-ISAAC-ROS","description":"NVIDIA-accelerated, deep-learned freespace segmentation","archived":false,"fork":false,"pushed_at":"2025-02-28T01:47:14.000Z","size":93,"stargazers_count":40,"open_issues_count":2,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-29T19:39:47.074Z","etag":null,"topics":["deep-learning","deep-neural-networks","freespace","gpu","jetson","nvidia","ros2","ros2-humble"],"latest_commit_sha":null,"homepage":"https://developer.nvidia.com/isaac-ros-gems","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIA-ISAAC-ROS.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-03-28T22:12:25.000Z","updated_at":"2025-06-25T18:46:21.000Z","dependencies_parsed_at":"2025-02-28T00:29:35.077Z","dependency_job_id":"f40ef425-e695-4981-9737-a73574491ab2","html_url":"https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_freespace_segmentation","commit_stats":null,"previous_names":["nvidia-isaac-ros/isaac_ros_freespace_segmentation"],"tags_count":8,"template":false,"template_full_name":null,"purl":"pkg:github/NVIDIA-ISAAC-ROS/isaac_ros_freespace_segmentation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-ISAAC-ROS%2Fisaac_ros_freespace_segmentation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-ISAAC-ROS%2Fisaac_ros_freespace_segmentation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-ISAAC-ROS%2Fisaac_ros_freespace_segmentation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-ISAAC-ROS%2Fisaac_ros_freespace_segmentation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA-ISAAC-ROS","download_url":"https://codeload.github.com/NVIDIA-ISAAC-ROS/isaac_ros_freespace_segmentation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-ISAAC-ROS%2Fisaac_ros_freespace_segmentation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279253839,"owners_count":26134834,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-16T02:00:06.019Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","deep-neural-networks","freespace","gpu","jetson","nvidia","ros2","ros2-humble"],"created_at":"2025-06-05T06:09:17.691Z","updated_at":"2025-10-16T23:16:58.778Z","avatar_url":"https://github.com/NVIDIA-ISAAC-ROS.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Isaac ROS Freespace Segmentation\n\nNVIDIA-accelerated, deep-learned freespace segmentation\n\n\u003cdiv align=\"center\"\u003e\u003ca class=\"reference internal image-reference\" href=\"https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_bi3d_real_opt.gif/\"\u003e\u003cimg alt=\"Isaac ROS Freespace Segmentation Sample Output\" src=\"https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_bi3d_real_opt.gif/\" width=\"500px\"/\u003e\u003c/a\u003e\u003c/div\u003e\n\n## Overview\n\nIsaac ROS Freespace Segmentation contains an ROS 2 package to produce\noccupancy grids for navigation. By processing a freespace segmentation\nmask with the pose of the robot relative to the ground, Bi3D Freespace\nproduces an occupancy grid for\n[Nav2](https://github.com/ros-planning/navigation2), which is used to\navoid obstacles during navigation. This package is GPU accelerated to\nprovide real-time, low latency results in a robotics application. Bi3D\nFreespace provides an additional occupancy grid source for mobile robots\n(ground based).\n\n\u003cdiv align=\"center\"\u003e\u003ca class=\"reference internal image-reference\" href=\"https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_freespace_segmentation_nodegraph.png/\"\u003e\u003cimg alt=\"Isaac ROS Freespace Segmentation Sample Output\" src=\"https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_freespace_segmentation_nodegraph.png/\" width=\"700px\"/\u003e\u003c/a\u003e\u003c/div\u003e\n\n`isaac_ros_bi3d` is used in a graph of nodes to provide a freespace\nsegmentation mask as one output from a time-synchronized input left and\nright stereo image pair. The freespace mask is used by\n`isaac_ros_bi3d_freespace` with TF pose of the camera relative to the\nground to compute planar freespace into an occupancy grid as input to\n[Nav2](https://github.com/ros-planning/navigation2).\n\nThere are multiple methods to predict the occupancy grid as an input to\nnavigation. None of these methods are perfect; each has limitations on\nthe accuracy of its estimate from the sensor providing measured\nobservations. Each sensor has a unique field of view, range to provide\nits measured view of the world, and corresponding areas it does not\nmeasure. Bi3D Freespace provides a diverse approach to\nidentifying obstacles from freespace. Stereo camera input used for this\nfunction is diverse relative to lidar, and has a better vertical field\nof view than most lidar units, allowing for perception of low lying\nobstacles that lidar can miss. Bi3D Freespace provides a\nrobust, vision-based complement to lidar occupancy scanning.\n\n## Isaac ROS NITROS Acceleration\n\nThis package is powered by [NVIDIA Isaac Transport for ROS (NITROS)](https://developer.nvidia.com/blog/improve-perception-performance-for-ros-2-applications-with-nvidia-isaac-transport-for-ros/), which leverages type adaptation and negotiation to optimize message formats and dramatically accelerate communication between participating nodes.\n\n## Performance\n\n| Sample Graph\u003cbr/\u003e\u003cbr/\u003e                                                                                                                                                                                 | Input Size\u003cbr/\u003e\u003cbr/\u003e     | AGX Orin\u003cbr/\u003e\u003cbr/\u003e                                                                                                                                               | Orin NX\u003cbr/\u003e\u003cbr/\u003e                                                                                                                                               | Orin Nano Super 8GB\u003cbr/\u003e\u003cbr/\u003e                                                                                                                                     | x86_64 w/ RTX 4090\u003cbr/\u003e\u003cbr/\u003e                                                                                                                                      |\n|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Freespace Segmentation Node](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/benchmarks/isaac_ros_bi3d_freespace_benchmark/scripts/isaac_ros_bi3d_fs_node.py)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e   | 576p\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e | [3340 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-agx_orin.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e1.7 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e | [2530 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-orin_nx.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e1.5 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e | [2140 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-orin_nano.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e1.9 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e | [3500 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-x86-4090.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e0.44 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e |\n| [Freespace Segmentation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/benchmarks/isaac_ros_bi3d_freespace_benchmark/scripts/isaac_ros_bi3d_fs_graph.py)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e | 576p\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e | [40.3 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-agx_orin.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e79 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e | [27.6 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-orin_nx.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e98 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e | [31.8 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-orin_nano.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e55 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e | [102 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-x86-4090.json)\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e30 ms @ 30Hz\u003cbr/\u003e\u003cbr/\u003e   |\n\n---\n\n## Documentation\n\nPlease visit the [Isaac ROS Documentation](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_freespace_segmentation/index.html) to learn how to use this repository.\n\n---\n\n## Packages\n\n* [`isaac_ros_bi3d_freespace`](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_bi3d_freespace/index.html)\n  * [Quickstart](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_bi3d_freespace/index.html#quickstart)\n  * [Try More Examples](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_bi3d_freespace/index.html#try-more-examples)\n  * [API](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_freespace_segmentation/isaac_ros_bi3d_freespace/index.html#api)\n\n## Latest\n\nUpdate 2024-12-10: Update to be compatible with JetPack 6.1\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnvidia-isaac-ros%2Fisaac_ros_freespace_segmentation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnvidia-isaac-ros%2Fisaac_ros_freespace_segmentation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnvidia-isaac-ros%2Fisaac_ros_freespace_segmentation/lists"}