# SullyChen/Autopilot-TensorFlow

A TensorFlow implementation of this Nvidia paper: https://arxiv.org/pdf/1604.07316.pdf with some changes

Repository: https://github.com/SullyChen/Autopilot-TensorFlow
Canonical: https://ross.abutalabs.com/products/autopilot-tensorflow
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-16T15:15:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3623, "days_push": 808, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1276, forks 433 (observed 2026-08-28T04:04:13.140249+00:00)

## What it is
A TensorFlow implementation of Nvidia's end-to-end self-driving steering angle prediction paper (arXiv 1604.07316) with some modifications. It trains a convolutional neural network on driving datasets and can run predictions on a live webcam feed or a recorded dataset.

## Use cases
- reproduce the Nvidia end-to-end self-driving paper in TensorFlow
- train a CNN to predict steering angles from camera images
- run a trained driving model on a live webcam feed
- evaluate a steering prediction model on a driving dataset
- learn how deep learning is applied to autonomous driving
- visualize training progress with TensorBoard

## When to choose
- you want a simple, readable implementation of the Nvidia steering model for study or research
- you need a baseline CNN regression model for driving datasets
- you are learning about end-to-end learning for self-driving cars

## When to avoid
- you intend to actually control a real vehicle - the author explicitly forbids this as dangerous and illegal
- you need a production-grade or actively maintained autonomous driving stack
- you need modern TensorFlow 2.x or PyTorch compatibility without modifications

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: machine-learning, deep-learning, computer-vision, autonomous-vehicles, education
- platform: python, cross-platform
- tags: self-driving-car, steering-angle-prediction, nvidia-paper, cnn-regression, research-code, tensorflow

## Member repositories
- SullyChen/Autopilot-TensorFlow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.140249+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 2026-08-30T05:02:54.816926+00:00, confidence not recorded.
  - readme: https://github.com/SullyChen/Autopilot-TensorFlow (fetched 2026-08-28T04:04:13.140249+00:00, sha 39aafcb48531)
- Data as of 2026-08-30T08:39:29.467469+00:00.