{"data":{"slug":"nvidia-ai-iot-redtail","name":"redtail","tagline":"Perception and AI components for autonomous mobile robotics.","github_url":"https://github.com/NVIDIA-AI-IOT/redtail","owner":"NVIDIA-AI-IOT","repo":"redtail","owner_avatar_url":"https://avatars.githubusercontent.com/u/29582968?v=4","primary_language":"C++","stars":1044,"forks":339,"topics":["ai","artificial-intelligence","computer-vision","deep-learning","drones","jetson","robotics"],"archived":false,"github_pushed_at":"2020-11-17T18:29:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/nvidia-ai-iot-redtail","markdown_url":"https://www.graphcanon.com/tools/nvidia-ai-iot-redtail.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-ai-iot-redtail","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-ai-iot-redtail","description":"Perception and AI components for autonomous mobile robotics.","homepage_url":null,"license":"BSD-3-Clause","open_issues":48,"watchers":100,"ai_summary":null,"readme_excerpt":"# NVIDIA Redtail project\n\nAutonomous visual navigation components for drones and ground vehicles using deep learning. Refer to [wiki](https://github.com/NVIDIA-Jetson/redtail/wiki) for more information on how to get started.\n\nThis project contains deep neural networks, computer vision and control code, hardware instructions and other artifacts that allow users to build a drone or a ground vehicle which can autonomously navigate through highly unstructured environments like forest trails, sidewalks, etc. Our TrailNet DNN for visual navigation is running on NVIDIA's Jetson embedded platform. Our [arXiv paper](https://arxiv.org/abs/1705.02550) describes TrailNet and other runtime modules in detail.\n\nThe project's deep neural networks (DNNs) can be trained from scratch using publicly available data. A few [pre-trained DNNs](../master/models/pretrained/) are also available as a part of this project. In case you want to train TrailNet DNN from scratch, follow the steps on [this page](../../wiki/Models).\n\nThe project also contains [Stereo DNN](../master/stereoDNN/) models and runtime which allow to estimate depth from stereo camera on NVIDIA platforms.\n\n**IROS 2018**: we presented our work at [IROS 2018](https://www.iros2018.org/) conference as a part of [Vision-based Drones: What's Next?](https://www.seas.upenn.edu/~loiannog/workshopIROS2018uav/) workshop.\n\n**CVPR 2018**: we presented our work at [CVPR 2018](http://cvpr2018.thecvf.com/) conference as a part of [Workshop on Autonomous Driving](http://www.wad.ai/index.html).\n\n## References and Demos\n* [Stereo DNN, CVPR18 paper](https://arxiv.org/abs/1803.09719), [Stereo DNN video demo](https://youtu.be/0FPQdVOYoAU)\n* [TrailNet Forest Drone Navigation, IROS17 paper](https://arxiv.org/abs/1705.02550), [TrailNet DNN video demo](https://youtu.be/H7Ym3DMSGms)\n* GTC 2017 talk: [slides](http://on-demand.gputechconf.com/gtc/2017/presentation/s7172-nikolai-smolyanskiy-autonomous-drone-navigation-with-deep-learning.pdf), [video](http://on-demand.gputechconf.com/gtc/2017/video/s7172-smolyanskiy-autonomous-drone-navigation-with-deep-learning%20(1).PNG.mp4)\n* [Demo video showing 250m autonomous flight with TrailNet DNN flying the drone](https://youtu.be/H7Ym3DMSGms)\n* [Demo video showing our 1 kilometer autonomous drone flight with TrailNet DNN](https://youtu.be/USYlt9t0lZY)\n* [Demo video showing TrailNet DNN driving a robotic rover around the office](https://youtu.be/lOmT4yWcJrM)\n* [Demo video showing TrailNet generalization to ground vehicles and other environments](https://youtu.be/ZKF5N8xUxfw)\n\n# News\n* **2020-02-03**: Alternative implementations.\n    **redtail** is no longer being developed, but fortunately our community stepped in and continued developing the project.\n    We thank our users for the interest in **redtail**, questions and feedback!\n\n    Some alternative implementations are listed below.\n  \n  * @mtbsteve: https://github.com/mtbsteve/redtail\n\n* **2018-10-10**: Stereo DNN ROS node and fixes.\n  * Added Stereo DNN ROS node and visualizer node.\n  * Fixed issue with nvidia-docker v2.\n* **2018-09-19**: Updates to Stereo DNN.\n  * Moved to TensorRT 4.0\n  * Enabled FP16 support in `ResNet18 2D` model, resulting in 2x performance increase (20fps on Jetson TX2).\n  * Enabled TensorRT serialization in `ResNet18 2D` model to reduce model loading time from minutes to less than a second.\n  * Better logging and profiler support.\n\n* **2018-06-04**: CVPR 2018 workshop. Fast version of Stereo DNN.\n  * Presenting our work at [CVPR 2018](http://cvpr2018.thecvf.com/) conference as a part of [Workshop on Autonomous Driving](http://www.wad.ai/index.html).\n  * Added fast version of Stereo DNN model based on ResNet18 2D model. The model runs at 10fps on Jetson TX2. See [README](../master/stereoDNN/) for details and check out updated [sample_app](../master/stereoDNN/sample_app).\n\n* **GTC 2018**: Here is our [Stereo DNN session page at GTC18](https://2018gputechconf.smarteventscloud.com/connect/sessionDetai","github_created_at":"2017-09-07T16:34:37+00:00","created_at":"2026-07-11T12:26:39.819399+00:00","updated_at":"2026-07-11T12:26:44.613009+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"jetson","name":"jetson"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"ai","name":"ai"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"drones","name":"drones"},{"slug":"robotics","name":"robotics"},{"slug":"c","name":"c++"},{"slug":"computer-vision","name":"computer-vision"}],"trust":{"provenance":{"is_fork":false,"github_id":102761243,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:26:40.572Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":2061,"last_release_at":"2018-03-22T20:24:17Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:26:41.393Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:26:41.118Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-07-11T12:26:41.118Z"},"license_spdx":{"value":"BSD-3-Clause","source":"github.license","observed_at":"2026-07-11T12:26:41.118Z"}}}}