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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (autonomousvision/transfuser) is linked to this paper; the 5 samples below come from 1 community repository. Syntology harvested code from autonomousvision/transfuser for another paper.

autonomousvision/transfuser: Syntology's graph links these samples to Multi-Modal Fusion Transformer for End-to-End Autonomous Driving (arXiv:2104.09224; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.

Syntology 5 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

autonomousvision/transfuser officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Modal Fusion Transformer for End-to-End Autonomous Driving (arXiv:2104.09224; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
autonomousvision/navsim mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking (arXiv:2406.15349; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pagand/e2etransfuser mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

5 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran

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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

pagand/e2etransfuser community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
IOU in 17 papers LetFuser/predict_expert.py ran fingerprinted MIT (permissive) · 6f4eddf7f8def829 · report fixture: signature Yp:Tensor/2/float, Yt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
normalize_imagenet in 9 papers aim/model.py ran · violated contract fingerprinted MIT (permissive) · af36a314f4f4a4be · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
scale_and_crop_image LetFuser/data.py ran MIT (permissive) · a1e4d64b4544efcd · report fixture: signature image:Image/0/?, scale:int/0/int, crop:tuple/1/int · returned ndarray · level recorded 2026-09-24
scale_and_crop_image_cv LetFuser/data.py ran MIT (permissive) · afd3cd0b6fbb903f · report fixture: signature image:ndarray/3/int, scale:int/0/int, crop:list/1/int · returned ndarray · level recorded 2026-09-24
swap_RGB2BGR LetFuser/data.py ran fingerprinted MIT (permissive) · 1648fc9d8f6ed785 · report fixture: signature matrix:ndarray/3/int · returned ndarray · level recorded 2026-09-24

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