# autonomousvision/transfuser

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

Repository: https://github.com/autonomousvision/transfuser
Canonical: https://ross.abutalabs.com/products/transfuser
Language: Python
License: MIT
License Family: permissive
Topics: imitation-learning, autonomous-driving, transformers, sensor-fusion
Last push: 2025-10-19T17:12:20+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 47, release rhythm 35, longevity 100
- inputs: {"age_days": 1986, "days_push": 318, "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 1599, forks 244 (observed 2026-08-28T04:05:09.483886+00:00)

## What it is
Official PyTorch implementation of TransFuser, a transformer-based multi-modal sensor fusion model for end-to-end autonomous driving, published at CVPR 2021 and PAMI 2023. It includes training, dataset generation, and evaluation pipelines on the CARLA simulator.

## Use cases
- train an end-to-end autonomous driving agent in CARLA
- fuse camera and LiDAR data with a transformer for driving
- reproduce PAMI 2023 TransFuser results on the CARLA leaderboard
- run imitation learning for self-driving research
- evaluate driving agents in CARLA 0.9.10
- compare multi-modal fusion approaches for autonomous driving

## When to choose
- you need a state-of-the-art imitation learning baseline for CARLA-based driving research
- you want to study transformer-based camera-LiDAR fusion for end-to-end driving
- you need reproducible code from a peer-reviewed autonomous driving paper

## When to avoid
- you need a production autonomous driving stack for real vehicles
- you cannot run CARLA or lack a GPU
- you want a general-purpose sensor fusion library outside driving simulation

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, computer-vision, simulation
- domain: autonomous-vehicles, deep-learning, machine-learning, simulation
- platform: python
- tags: sensor-fusion, imitation-learning, transformers, carla, autonomous-driving, research-code, linux, gpu

## Member repositories
- autonomousvision/transfuser (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:09.483886+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 2026-08-30T03:53:13.052542+00:00, confidence not recorded.
  - readme: https://github.com/autonomousvision/transfuser (fetched 2026-08-28T04:05:09.483886+00:00, sha 548173f6fcba)
- Data as of 2026-08-30T08:39:29.467469+00:00.