Papers › Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction

Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction

19 Feb 2021ICLR 2022 4arXiv:2104.00563archive 2025-07-28

Roger Girgis, Florian Golemo, Felipe Codevilla, Martin Weiss, Jim Aldon D'Souza, Samira Ebrahimi Kahou, Felix Heide, Christopher Pal

Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently learn a representation that approximates the true joint distribution of contextual, social, and temporal information to enable planning. We propose Latent Variable Sequential Set Transformers which are encoder-decoder architectures that generate scene-consistent multi-agent trajectories. We refer to these architectures as "AutoBots". The encoder is a stack of interleaved temporal and social multi-head self-attention (MHSA) modules which alternately perform equivariant processing across the temporal and social dimensions. The decoder employs learnable seed parameters in combination with temporal and social MHSA modules allowing it to perform inference over the entire future scene in a single forward pass efficiently. AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene. For the single-agent prediction case, our model achieves top results on the global nuScenes vehicle motion prediction leaderboard, and produces strong results on the Argoverse vehicle prediction challenge. In the multi-agent setting, we evaluate on the synthetic partition of TrajNet++ dataset to showcase the model's socially-consistent predictions. We also demonstrate our model on general sequences of sets and provide illustrative experiments modelling the sequential structure of the multiple strokes that make up symbols in the Omniglot data. A distinguishing feature of AutoBots is that all models are trainable on a single desktop GPU (1080 Ti) in under 48h.

PaperPDFConference PDFCodeCode 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

Syntology 17 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 11 ran (9 with no instrument failure; 2 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

roggirg/AutoBots officialmentioned on GitHubpytorchBSD-3-ClauseSyntology: 17 samples, 11 ran (2 instrument-failed) · 6 unverified report
vita-epfl/unitraj pytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction (arXiv:2403.15098; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

17 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
9ran
6unverified

Licence: 2 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from roggirg/AutoBots. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

roggirg/AutoBots official repository 17 samples, 11 ran (2 instrument-failed) · 6 unverified
angle_of_rotation datasets/argoverse/create_h5_argo.py ran fingerprinted BSD-3-Clause (permissive) · db4fd23bb7142d4b · report fixture: signature yaw:float/0/float · returned float64 · level recorded 2026-09-25
convert_global_coords_to_local datasets/argoverse/create_h5_argo.py ran BSD-3-Clause (permissive) · 4efe4a6acb3051fb · report fixture: signature coordinates:ndarray/2/float, translation:tuple/1/float, yaw:float/0/float · returned ndarray · level recorded 2026-09-25
create_results_folder process_args.py ran BSD-3-Clause (permissive) · b61e662d9f8a3be9 · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-25
drop_distant datasets/trajnetpp/create_data_npys.py ran fingerprinted BSD-3-Clause (permissive) · 3dba06ecf04eff9a · report fixture: signature xy:ndarray/3/float, max_num_peds:int/0/int · returned ndarray · level recorded 2026-09-25
drop_inactive datasets/trajnetpp/create_data_npys.py ran fingerprinted BSD-3-Clause (permissive) · 577c3685905bbabc · report fixture: signature xy:ndarray/3/float, obs_horizon:int/0/int · returned ndarray · level recorded 2026-09-25
get_BVG_distributions utils/train_helpers.py ran BSD-3-Clause (permissive) · 519ae373e4e4d7cd · report fixture: signature pred:Tensor/3/float · returned MultivariateNormal · level recorded 2026-09-25
init in 55 papers models/autobot_joint.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · 9de355e93051e4ad · report fixture: signature module:callable/0/?, weight_init:callable/0/?, bias_init:callable/0/?, gain:int/0/int · returned Linear · level recorded 2026-09-22
init in 55 papers models/autobot_ego.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · d7a51202f8456490 · report fixture: signature module:callable/0/?, weight_init:callable/0/?, bias_init:callable/0/?, gain:int/0/int · returned Linear · level recorded 2026-09-24
interpolate_trajectories utils/metric_helpers.py ran fingerprinted BSD-3-Clause (permissive) · 4e0c5fccd80c3976 · report fixture: signature preds:Tensor/5/float · returned Tensor · level recorded 2026-09-25
make_2d_rotation_matrix datasets/argoverse/create_h5_argo.py ran fingerprinted BSD-3-Clause (permissive) · cd4282007f2ad836 · report fixture: signature angle_in_radians:float/0/float · returned ndarray · level recorded 2026-09-25
shift in 22 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
datasets/trajnetpp/create_data_npys.py ran BSD-3-Clause (permissive) · 1761d9ef84caa582 · report fixture: signature xy:ndarray/4/float, center:ndarray/1/float · returned ndarray · level recorded 2026-09-25
get_Laplace_dist utils/train_helpers.py unverified BSD-3-Clause (permissive) · 5112337a26b088f3 · report
load_config in 389 papers process_args.py unverified BSD-3-Clause (permissive) · 3eb3d4a61fbb224d · report
min_xde_K utils/metric_helpers.py unverified BSD-3-Clause (permissive) · b10ff2bd7a695f93 · report
nll_pytorch_dist utils/train_helpers.py unverified BSD-3-Clause (permissive) · 2e9627477244b6e9 · report
recompute_probs useful_scripts/generate_nuscene_results.py unverified BSD-3-Clause (permissive) · 29e4fbe72133e718 · report
yaw_from_predictions utils/metric_helpers.py unverified BSD-3-Clause (permissive) · 21100d7d06393031 · report

Tasks

Autonomous DrivingDecoderPredictionTrajectory ModelingTrajectory Predictionmotion prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSet TransformerSoftmaxTransformer

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