SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.12890 · 2022

It Takes Two: Learning to Plan for Human-Robot Cooperative Carrying

arXiv · PDF · Open in the Atlas

Code that ran

5 of 13 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 5 have no contract verdict; 0 failures of our instrument; 8 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/2209.12890.json · badge: /api/ran/2209.12890.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
eleyng/table-carrying-ai canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
eleyng/cooperative_planner canonical (classifier label)
classifier basis not recorded on the link
1 ran · 6 no recorded run
FunctionStatusWhere it lives
consec_repeat_starts Ran
ran on a synthesized input
eleyng/table-carrying-ai/cooperative_transport/gym_table/envs/utils.py
code served (permissive licence) · get_code("12fdd162d3a52743")
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 ndarray, ndim 1, dtype family int, shape (3,) 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 numpy as np

# Create a 1D array with consecutive repeats
# For example: [1, 1, 1, 2, 2, 3, 3, 3, 3]
# With n=2, should find starts of pairs: indices 0, 3, 6
# With n=3, should find starts of triples: indices 0, 6
a = np.array([1, 1, 1, 2, 2, 3, 3, 3, 3], dtype=np.int32)

# Length of repeat to detect
n = 3

ARGS = {
    "a": a,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (3,) — shape (3,) 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
euler_from_quaternion Ran
ran on a synthesized input
eleyng/table-carrying-ai/libs/real_robot_utils.py
code served (permissive licence) · get_code("5e747c8b5743d80b")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 math

torch_available = False
try:
    import torch
    torch.manual_seed(0)
    torch_available = True
except ImportError:
    pass

# The function takes 4 scalar parameters: x, y, z, w (components of a quaternion)
# It performs arithmetic operations on them and returns euler angles
# All parameters should be numeric (int or float)

ARGS = {
    "x": 0.0,
    "y": 0.0,
    "z": 0.0,
    "w": 1.0,
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
frange_cycle_linear Ran
ran on a synthesized input
eleyng/cooperative_planner/utils/learning.py
code served (permissive licence) · get_code("f985673c9758b37a")
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 ndarray, ndim 1, dtype family float, shape (100,) 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 numpy as np

ARGS = {
    "n_iter": 100,
    "beta_min": 0.0,
    "beta_max": 1.0,
    "cycle": 4,
    "R": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (100,) — shape (100,) 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
get_idx_repeats_of_len_n Ran
ran on a synthesized input
eleyng/table-carrying-ai/cooperative_transport/gym_table/envs/utils.py
code served (permissive licence) · get_code("95635062a3a4b57a")
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 ndarray, ndim 1, dtype family int, 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 numpy as np

# Create a small 2D array with shape (n, 2) for states_xy
# The array contains coordinates that will have some repeating consecutive sequences
states_xy = np.array([
    [1.0, 2.0],
    [1.0, 2.0],
    [1.0, 2.0],
    [3.0, 4.0],
    [3.0, 4.0],
    [5.0, 6.0],
    [5.0, 6.0],
    [5.0, 6.0]
])

# Length of repeat to search for
n = 3

ARGS = {
    "states_xy": states_xy,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, 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
interaction_forces_reward Ran
ran on a synthesized input
eleyng/table-carrying-ai/cooperative_transport/gym_table/envs/custom_rewards.py
code served (permissive licence) · get_code("8228b6508b89d5aa")
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 2, dtype family float, shape (2, 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 numpy as np

torch.manual_seed(0)

# The function takes interaction_forces as input and performs arithmetic operations on it
# It divides by 1000**2 and multiplies by 0.5, then negates
# interaction_forces should be a numeric tensor or array

interaction_forces = torch.randn(2, 4)

ARGS = {
    "interaction_forces": interaction_forces
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
calc_stats Not yet run
unverified (harvested, no recorded run)
eleyng/cooperative_planner/utils/stats.py
code served (permissive licence) · get_code("037d07da4ca79032")
How it ran

no invocation recorded.

calculate_fid Not yet run
unverified (harvested, no recorded run)
eleyng/cooperative_planner/utils/stats.py
code served (permissive licence) · get_code("4994ba2de5da1d5f")
How it ran

no invocation recorded.

calculate_frechet_distance Not yet run
unverified (harvested, no recorded run)
eleyng/cooperative_planner/utils/stats.py
code served (permissive licence) · get_code("0168dd940e79bdef")
How it ran

no invocation recorded.

get_cmap Not yet run
unverified (harvested, no recorded run)
eleyng/cooperative_planner/utils/vis.py
code served (permissive licence) · get_code("96f99dd13b447c11")
How it ran

no invocation recorded.

gmm_loss Not yet run
unverified (harvested, no recorded run)
eleyng/cooperative_planner/utils/learning.py
code served (permissive licence) · get_code("d14cce6d041bf661")
How it ran

no invocation recorded.

load_cfg Not yet run
unverified (harvested, no recorded run)
eleyng/cooperative_planner/utils/vis.py
code served (permissive licence) · get_code("a62a926cd953718c")
How it ran

no invocation recorded.

load_cfg Not yet run
unverified (harvested, no recorded run)
eleyng/table-carrying-ai/cooperative_transport/gym_table/envs/utils.py
code served (permissive licence) · get_code("b84672293599a617")
How it ran

no invocation recorded.

natural_sort_key Not yet run
unverified (harvested, no recorded run)
eleyng/table-carrying-ai/libs/real_robot_utils.py
code served (permissive licence) · get_code("7c0d126c0751adae")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 11 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
get_cmap 3 other papers
2 dated earlier, 1 later
2110.07586 (2021-10)
Can Explanations Be Useful for Calibrating Black Box Models?
2203.09978 (2022-03)
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
2303.13446 (2023-03)
On the Utility of Koopman Operator Theory in Learning Dexterous Manipulation Skills
gmm_loss 2 other papers
2 dated earlier
1906.08857 (2019-06)
Deep Neuroevolution of Recurrent and Discrete World Models
aaai_17470 (2021 (year only))
Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures

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

Cooperative table-carrying is a complex task due to the continuous nature of the action and state-spaces, multimodality of strategies, and the need for instantaneous adaptation to other agents. In this work, we present a method for predicting realistic motion plans for cooperative human-robot teams on the task. Using a Variational Recurrent Neural Network (VRNN) to model the variation in the trajectory of a human-robot team across time, we are able to capture the distribution over the team's future states while leveraging information from interaction history. The key to our approach is leveraging human demonstration data to generate trajectories that synergize well with humans during test time in a receding horizon fashion. Comparison between a baseline, sampling-based planner RRT (Rapidly-exploring Random Trees) and the VRNN planner in centralized planning shows that the VRNN generates motion more similar to the distribution of human-human demonstrations than the RRT. Results in a human-in-the-loop user study show that the VRNN planner outperforms decentralized RRT on task-related metrics, and is significantly more likely to be perceived as human than the RRT planner. Finally, we demonstrate the VRNN planner on a real robot paired with a human teleoperating another robot.

For agents

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

get_harvested_code_for_paper("2209.12890")
get_code_for_paper("2209.12890")
have("2209.12890")

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

curl https://syntology.ai/api/ran/2209.12890.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.12890.svg)](https://syntology.ai/paper/2209.12890)

Connect an agent — have() is free.