SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.04330 · 2023

Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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 6 have no contract verdict; 0 failures of our instrument; 2 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/2301.04330.json · badge: /api/ran/2301.04330.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
pkicki/cnp-b canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
air_hockey_puck Ran
ran on a synthesized input
pkicki/cnp-b/losses/constraint_functions.py
code served (permissive licence) · get_code("9653ec67ee81d70a")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)
np.random.seed(0)

# Create small test data
batch_size = 2
num_timesteps = 4
spatial_dim = 2

# xyz: shape (batch_size, num_timesteps, 2, 1)
# The function accesses xyz[:, :, :2, 0], so we need at least 3 spatial dimensions
# and a last dimension of size >= 1
xyz = tf.constant(np.random.randn(batch_size, num_timesteps, 3, 1), dtype=tf.float32)

# dt: scalar or array for time step
dt = tf.constant(0.01, dtype=tf.float32)

# puck_pose: shape (batch_size, 2) - x,y position of puck
puck_pose = tf.constant(np.random.randn(batch_size, 2), dtype=tf.float32)

ARGS = {
    "xyz": xyz,
    "dt": dt,
    "puck_pose": puck_pose,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
huber Ran
ran on a synthesized input
pkicki/cnp-b/losses/utils.py
code served (permissive licence) · get_code("5e178c7f41639d65")
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 EagerTensor, ndim 2, dtype family float, shape (1, 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 tensorflow as tf

# Create a small tensor to pass to the huber function
x = tf.constant([[-2.0, -0.5, 0.0, 1.5]], dtype=tf.float32)

# Set delta parameter
delta = 1.0

# Define ARGS mapping all parameters
ARGS = {
    "x": x,
    "delta": delta,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (1, 4) — shape (1, 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
mean Ran
ran on a synthesized input
pkicki/cnp-b/plots_and_stats/plot_air_hockey_hitting_real.py
code served (permissive licence) · get_code("b433888057f05208")
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 float64, ndim 0, 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 numpy as np

# Construct a results dictionary
# The function iterates over r.items() and accesses v[k] where k is a string key
# It builds a list of values at that key (or their absolute values if abs=True)
r = {
    'result_1': {'accuracy': 0.85, 'loss': 0.15},
    'result_2': {'accuracy': 0.92, 'loss': -0.08},
    'result_3': {'accuracy': 0.78, 'loss': 0.22},
}

# k is the key to extract from each value dict
k = 'accuracy'

# abs is a boolean flag to take absolute values
abs_flag = True

ARGS = {
    'r': r,
    'k': k,
    'abs': abs_flag,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
mean Ran
ran on a synthesized input
pkicki/cnp-b/plots_and_stats/plot_air_hockey_hitting_simulation.py
code served (permissive licence) · get_code("a8ae03c9567b7ec5")
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 float64, ndim 0, 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 numpy as np

# Construct a dictionary `r` that the function will iterate over
# The function expects r.items() to yield (key, dict_value) pairs
# where dict_value is a dict that may contain the key `k`

r = {
    "sample_1": {
        "loss": 0.5,
        "accuracy": 0.95,
    },
    "sample_2": {
        "loss": 0.3,
        "accuracy": 0.98,
    },
    "sample_3": {
        "loss": -0.2,
        "accuracy": 0.92,
    },
}

# The function parameter `k` is a key to look up in each inner dict
k = "loss"

# The `abs` parameter controls whether to take absolute value
abs_param = True

ARGS = {
    "r": r,
    "k": k,
    "abs": abs_param,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
read_results Ran
ran on a synthesized input
pkicki/cnp-b/plots_and_stats/plot_air_hockey_hitting_simulation.py
code served (permissive licence) · get_code("3228a3e8730d5ce2")
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 dict. The image it ran in was not recorded. If your copy returns the same type 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 os
import pickle
import tempfile
from pathlib import Path

# Create a temporary directory with mock .res files
temp_dir = tempfile.mkdtemp()

# Create sample pickle files with the expected naming convention
# Format: x{number}_y{number}.res
sample_data_1 = {'value': 1, 'data': [1, 2, 3]}
sample_data_2 = {'value': 2, 'data': [4, 5, 6]}
sample_data_3 = {'value': 3, 'data': [7, 8, 9]}

with open(os.path.join(temp_dir, 'x1.5_y2.3.res'), 'wb') as f:
    pickle.dump(sample_data_1, f)

with open(os.path.join(temp_dir, 'x3.7_y4.2.res'), 'wb') as f:
    pickle.dump(sample_data_2, f)

with open(os.path.join(temp_dir, 'x0.5_y1.1.res'), 'wb') as f:
    pickle.dump(sample_data_3, f)

ARGS = {
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
scoring_ratio Ran
ran on a synthesized input
pkicki/cnp-b/plots_and_stats/plot_air_hockey_hitting_real.py
code served (permissive licence) · get_code("929cdadf576c534c")
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 float64, ndim 0, 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 numpy as np

# Construct a results dictionary with the expected structure
# The function expects a dict where values are dicts containing 'scored' keys
r = {
    'result_1': {'scored': 0.85, 'other_metric': 0.5},
    'result_2': {'scored': -0.92, 'other_metric': 0.7},
    'result_3': {'scored': 0.45},
    'result_4': {'scored': -0.30, 'other_metric': 0.2},
}

ARGS = {
    'r': r
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
model_inference Not yet run
unverified (harvested, no recorded run)
pkicki/cnp-b/utils/model.py
code served (permissive licence) · get_code("149fe2c1473bd4d1")
How it ran

no invocation recorded.

plot_scatter Not yet run
unverified (harvested, no recorded run)
pkicki/cnp-b/plots_and_stats/plot_air_hockey_hitting_real.py
code served (permissive licence) · get_code("608460184c3c82d0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

Motion planning is a mature area of research in robotics with many well-established methods based on optimization or sampling the state space, suitable for solving kinematic motion planning. However, when dynamic motions under constraints are needed and computation time is limited, fast kinodynamic planning on the constraint manifold is indispensable. In recent years, learning-based solutions have become alternatives to classical approaches, but they still lack comprehensive handling of complex constraints, such as planning on a lower-dimensional manifold of the task space while considering the robot's dynamics. This paper introduces a novel learning-to-plan framework that exploits the concept of constraint manifold, including dynamics, and neural planning methods. Our approach generates plans satisfying an arbitrary set of constraints and computes them in a short constant time, namely the inference time of a neural network. This allows the robot to plan and replan reactively, making our approach suitable for dynamic environments. We validate our approach on two simulated tasks and in a demanding real-world scenario, where we use a Kuka LBR Iiwa 14 robotic arm to perform the hitting movement in robotic Air Hockey.

For agents

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

get_harvested_code_for_paper("2301.04330")
get_code_for_paper("2301.04330")
have("2301.04330")

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

curl https://syntology.ai/api/ran/2301.04330.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.04330.svg)](https://syntology.ai/paper/2301.04330)

Connect an agent — have() is free.