# aitorzip/DeepGTAV

A plugin for GTAV that transforms it into a vision-based self-driving car research environment.

Repository: https://github.com/aitorzip/DeepGTAV
Canonical: https://ross.abutalabs.com/products/deepgtav
Language: C++
License: GPL-3.0
License Family: copyleft
Topics: dataset-generation, reinforcement-learning, gtav, deep-learning, self-driving-car
Last push: 2020-01-14T21:16:53+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": 3649, "days_push": 2423, "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 1186, forks 274 (observed 2026-08-28T04:03:55.033456+00:00)

## What it is
DeepGTAV is a C++ plugin for Grand Theft Auto V that converts the game into a vision-based self-driving car research environment. It exposes a TCP server on port 8000 through which clients can configure the environment, send driving commands, and receive sensor and scene data in JSON format.

## Use cases
- generate driving datasets from a game engine
- train reinforcement learning agents for self-driving cars
- run computer vision experiments on simulated driving footage
- control a simulated vehicle programmatically over TCP
- research autonomous driving without real-world hardware

## When to choose
- you need a photorealistic simulated driving environment for deep learning research
- you want to collect labeled driving data from GTA V
- you are building a self-driving agent with the companion VPilot Python interface

## When to avoid
- you need a maintained or actively supported simulator
- your GTA V version is newer than 1.0.1180.2
- you need a general-purpose driving simulator rather than a GTA V mod
- you require commercial licensing - it is GPL-3.0

## Facets
- artifact type: plugin
- maturity: maintenance
- function: simulation, machine-learning, reinforcement-learning, computer-vision, data-generation
- domain: autonomous-vehicles, machine-learning, deep-learning, simulation, gaming-tools
- platform: windows, cpp
- tags: gtav, self-driving-car, research-environment, tcp-server, game-mod, dataset-generation

## Member repositories
- aitorzip/DeepGTAV (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.033456+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 2026-08-30T06:23:47.669645+00:00, confidence not recorded.
  - readme: https://github.com/aitorzip/DeepGTAV (fetched 2026-08-28T04:03:55.033456+00:00, sha 096b981b5b47)
- Data as of 2026-08-30T08:39:29.467469+00:00.