SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16910 · CVPR · 2022

End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps

Jia Pan, Ke Guo, Wenxi Liu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.16910.json · badge: /api/ran/2203.16910.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Kguo-cs/TDOR canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
attention Ran
ran on a synthesized input
Kguo-cs/TDOR/model/transformer.py
code served (permissive licence) · get_code("fcdea34a2fb23b2d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 2, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.nn.functional as F
import math

torch.manual_seed(0)

# Build tiny tensors for scaled dot product attention
batch_size = 2
seq_len = 3
d_k = 4

# Query, Key, Value tensors with shapes (batch, seq_len, d_k)
query = torch.randn(batch_size, seq_len, d_k)
key = torch.randn(batch_size, seq_len, d_k)
value = torch.randn(batch_size, seq_len, d_k)

# Mask: shape (batch, 1, seq_len, seq_len) - attention mask with 1s and 0s
mask = torch.ones(batch_size, 1, seq_len, seq_len)
# Make bottom-left triangular part 0 (causal mask example)
mask[:, :, 1, 0] = 0
mask[:, :, 2, 0] = 0
mask[:, :, 2, 1] = 0

# Dropout layer - needs to have __call__ method
dropout = nn.Dropout(p=0.1)

ARGS = {
    "query": query,
    "key": key,
    "value": value,
    "mask": mask,
    "dropout": dropout
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 2, 3, 4) — shape (2, 2, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
clones Ran
ran; our contract draft was wrong, not the code
Kguo-cs/TDOR/model/transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from DSE-MSU/R-transformer, is pointer only (licence: NONE) · get_code("b1bec2c4b1c9b491")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from DSE-MSU/R-transformer, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gaussian_2d Ran
ran on a synthesized input
Kguo-cs/TDOR/model/utils.py
code served (permissive licence) · get_code("b3ce0a5e8e83e340")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create sample tensors for the function parameters
# mu1mu2s1s2rho: batch of 2, with 5 parameters each (mu1, mu2, s1, s2, rho)
mu1mu2s1s2rho = torch.tensor([
    [0.5, 0.3, 1.0, 0.8, 0.2],
    [0.1, 0.9, 1.2, 0.9, 0.3]
], dtype=torch.float32)

# x1x2: batch of 2, with 2 coordinates each (x1, x2)
x1x2 = torch.tensor([
    [0.6, 0.4],
    [0.2, 0.8]
], dtype=torch.float32)

ARGS = {
    "mu1mu2s1s2rho": mu1mu2s1s2rho,
    "x1x2": x1x2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
min_ade_k Ran
ran on a synthesized input
Kguo-cs/TDOR/model/utils.py
code served (permissive licence) · get_code("17916884b2a3db5f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Parameters for min_ade_k function
batch_size = 2
max_k = 4
prediction_horizon = 3
coordinate_dim = 2

# y_pred: (Batchsize, maxK, prediction_horizon, 2)
y_pred = torch.randn(batch_size, max_k, prediction_horizon, coordinate_dim)

# y_gt: (Batchsize, prediction_horizon, 2)
y_gt = torch.randn(batch_size, prediction_horizon, coordinate_dim)

# scale parameter
scale = 1.0

ARGS = {
    "y_pred": y_pred,
    "y_gt": y_gt,
    "scale": scale,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
clones 79 other papers
40 dated earlier, 4 the same month, 35 later · 11 only as an assembly brick
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1706.03762 (2017-06)
Attention Is All You Need
and 76 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we aim to forecast a future trajectory distribution of a moving agent in the real world, given the social scene images and historical trajectories. Yet, it is a challenging task because the ground-truth distribution is unknown and unobservable, while only one of its samples can be applied for supervising model learning, which is prone to bias. Most recent works focus on predicting diverse trajectories in order to cover all modes of the real distribution, but they may despise the precision and thus give too much credit to unrealistic predictions. To address the issue, we learn the distribution with symmetric cross-entropy using occupancy grid maps as an explicit and scene-compliant approximation to the ground-truth distribution, which can effectively penalize unlikely predictions. In specific, we present an inverse reinforcement learning based multi-modal trajectory distribution forecasting framework that learns to plan by an approximate value iteration network in an end-to-end manner. Besides, based on the predicted distribution, we generate a small set of representative trajectories through a differentiable Transformer-based network, whose attention mechanism helps to model the relations of trajectories. In experiments, our method achieves state-of-the-art performance on the Stanford Drone Dataset and Intersection Drone Dataset.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.16910")
get_code_for_paper("2203.16910")
have("2203.16910")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.16910.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.16910.svg)](https://syntology.ai/paper/2203.16910)

Connect an agent — have() is free.