# NVIDIA-AI-IOT/redtail

Perception and AI components for autonomous mobile robotics.

Repository: https://github.com/NVIDIA-AI-IOT/redtail
Canonical: https://ross.abutalabs.com/products/redtail
Language: C++
License: BSD-3-Clause
License Family: permissive
Topics: jetson, drones, ai, deep-learning, artificial-intelligence, robotics, computer-vision
Last push: 2020-11-17T18:29:42+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3282, "days_push": 2115, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1047, forks 341 (observed 2026-08-28T04:03:22.098967+00:00)

## What it is
NVIDIA Redtail provides deep learning and computer vision components for autonomous visual navigation of drones and ground vehicles, centered on the TrailNet DNN and Stereo DNN models running on NVIDIA Jetson. It includes pre-trained networks, training instructions, ROS nodes, and hardware guidance for building autonomous robots in unstructured environments.

## Use cases
- build an autonomously navigating drone for forest trails
- estimate depth from a stereo camera with deep learning
- run visual navigation DNNs on Jetson
- train a trail-following neural network from scratch
- drive a ground rover autonomously with vision
- get pre-trained navigation models for mobile robots

## When to choose
- you need reference DNN models and ROS code for vision-based robot navigation on Jetson hardware
- you want to reproduce TrailNet or Stereo DNN research results

## When to avoid
- you need an actively maintained project - it is no longer developed by NVIDIA
- you work outside ROS/Jetson ecosystems or need modern framework support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, robotics
- domain: robotics, computer-vision, autonomous-vehicles, deep-learning
- platform: cpp, embedded
- tags: trailnet, stereo-depth-estimation, drones, ros, autonomous-navigation, nvidia-jetson, pretrained-models, jetson, linux, gpu

## Member repositories
- NVIDIA-AI-IOT/redtail (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.098967+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:01:04.430645+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA-AI-IOT/redtail (fetched 2026-08-28T04:03:22.098967+00:00, sha e76a6583d406)
- Data as of 2026-08-30T08:39:29.467469+00:00.