Papers › TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving

TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving

31 May 2022arXiv:2205.15997archive 2025-07-28

Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, Andreas Geiger

How should we integrate representations from complementary sensors for autonomous driving? Geometry-based fusion has shown promise for perception (e.g. object detection, motion forecasting). However, in the context of end-to-end driving, we find that imitation learning based on existing sensor fusion methods underperforms in complex driving scenarios with a high density of dynamic agents. Therefore, we propose TransFuser, a mechanism to integrate image and LiDAR representations using self-attention. Our approach uses transformer modules at multiple resolutions to fuse perspective view and bird's eye view feature maps. We experimentally validate its efficacy on a challenging new benchmark with long routes and dense traffic, as well as the official leaderboard of the CARLA urban driving simulator. At the time of submission, TransFuser outperforms all prior work on the CARLA leaderboard in terms of driving score by a large margin. Compared to geometry-based fusion, TransFuser reduces the average collisions per kilometer by 48%.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2205.15997")

Code

Syntology Ran 1 of 5 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · violated contract.

By repository: community (archive-listed): 5 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

autonomousvision/transfuser officialmentioned in papermentioned on GitHubpytorch report
autonomousvision/navsim mentioned on GitHub report
pagand/e2etransfuser mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested; 1 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
4unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from pagand/e2etransfuser. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

normalize_imagenet pagand/e2etransfuser/aim/model.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · af36a314f4f4a4be · report
IOU pagand/e2etransfuser/LetFuser/predict_expert.py community (archive-listed) unverified MIT (permissive) · 6f4eddf7f8def829 · report
scale_and_crop_image pagand/e2etransfuser/LetFuser/data.py community (archive-listed) unverified MIT (permissive) · a1e4d64b4544efcd · report
scale_and_crop_image_cv pagand/e2etransfuser/LetFuser/data.py community (archive-listed) unverified MIT (permissive) · afd3cd0b6fbb903f · report
swap_RGB2BGR pagand/e2etransfuser/LetFuser/data.py community (archive-listed) unverified MIT (permissive) · 1648fc9d8f6ed785 · report

Tasks

Autonomous DrivingCARLA longest6Imitation LearningMotion ForecastingNavSimObject DetectionSensor Fusion

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Autonomous Driving CARLA Leaderboard TransFuser Driving Score 61.181 #6 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard TransFuser Infraction penalty 0.714 #6 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard TransFuser Route Completion 86.694 #6 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard TransFuser (Reproduced) Driving Score 55.04 #7 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard TransFuser (Reproduced) Infraction penalty 0.63 #7 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard TransFuser (Reproduced) Route Completion 89.65 #7 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard Latent TransFuser Driving Score 45.20 #9 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard Latent TransFuser Infraction penalty 0.72 #9 of 18 Archive leaderboard report
Autonomous Driving CARLA Leaderboard Latent TransFuser Route Completion 66.31 #9 of 18 Archive leaderboard report
CARLA longest6 CARLA TransFuser (TF) Driving Score 47 #14 of 21 Archive leaderboard report
CARLA longest6 CARLA TransFuser (TF) Infraction Score 0.50 #14 of 21 Archive leaderboard report
CARLA longest6 CARLA TransFuser (TF) Route Completion 93 #14 of 21 Archive leaderboard report
CARLA longest6 CARLA Latent TransFuser (LTF) Driving Score 37 #16 of 21 Archive leaderboard report
CARLA longest6 CARLA Latent TransFuser (LTF) Infraction Score 0.38 #16 of 21 Archive leaderboard report
CARLA longest6 CARLA Latent TransFuser (LTF) Route Completion 95 #16 of 21 Archive leaderboard report
CARLA longest6 CARLA Geometric Fusion (GF) Driving Score 27 #18 of 21 Archive leaderboard report
CARLA longest6 CARLA Geometric Fusion (GF) Infraction Score 0.30 #18 of 21 Archive leaderboard report
CARLA longest6 CARLA Geometric Fusion (GF) Route Completion 91 #18 of 21 Archive leaderboard report
CARLA longest6 CARLA Late Fusion (LF) Driving Score 22 #20 of 21 Archive leaderboard report
CARLA longest6 CARLA Late Fusion (LF) Infraction Score 0.27 #20 of 21 Archive leaderboard report
CARLA longest6 CARLA Late Fusion (LF) Route Completion 83 #20 of 21 Archive leaderboard report
NavSim OpenScene TransFuser PDMS 84.0 #20 of 29 Archive leaderboard report
NavSim OpenScene Latent TransFuser PDMS 83.8 #22 of 29 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CARLAEntropy RegularizationPPO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections