SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.02609 · 2020

UAV Coverage Path Planning under Varying Power Constraints using Deep Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 8 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2003.02609.json · badge: /api/ran/2003.02609.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
theilem/uavSim canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
XGX-CURRY/uavSim community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_all_distances Ran
ran on a synthesized input
theilem/uavSim/src/gym/utils.py
code served (permissive licence) · get_code("a2c1f53a2b3b7f87")
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 4, dtype family int, shape (4, 3, 4, 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

# The function takes a single parameter: nfz
# Looking at the function body:
# - nfz is padded, so it should be a 2D numpy array
# - It's used with np.logical_or, so it should contain boolean-like values
# - The function computes distances in this array
# - A small 4x3 array will serve as a good test case

# Create a simple 2D numpy array with some obstacle/free space values
# Using distinct dimensions (4x3) for clarity
nfz = np.array([
    [0, 1, 0],
    [0, 1, 0],
    [1, 0, 0],
    [0, 0, 1]
], dtype=bool)

ARGS = {
    'nfz': nfz
}
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 4, dtype family int, shape (4, 3, 4, 3) — shape (4, 3, 4, 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
calculate_landing_distances Ran
ran on a synthesized input
theilem/uavSim/src/gym/utils.py
code served (permissive licence) · get_code("153aa00389098f16")
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 2, dtype family int, shape (3, 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 small test arrays for the function
# nfz: no-fly zone (binary mask where 1 = no-fly, 0 = safe)
nfz = np.array([
    [0, 1, 0],
    [1, 0, 1],
    [0, 1, 0]
], dtype=int)

# slz: safe landing zone (binary mask where 1 = safe landing, 0 = not safe)
slz = np.array([
    [1, 0, 0],
    [0, 0, 1],
    [0, 0, 0]
], dtype=int)

# init: optional initial distance map
# -1 indicates unreachable, other values indicate initial distances
init = np.array([
    [-1, -1, -1],
    [-1, -1, -1],
    [-1, -1, -1]
], dtype=int)

ARGS = {
    "nfz": nfz,
    "slz": slz,
    "init": init
}
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 2, dtype family int, shape (3, 3) — shape (3, 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
calculate_shadowing Ran
ran on a synthesized input
theilem/uavSim/src/gym/utils.py
code served (permissive licence) · get_code("9f6d4dc33546086a")
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 4, dtype family float, shape (3, 3, 3, 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 small obstacle map
# The function expects a 2D boolean array where True indicates an obstacle
obst = np.array([
    [False, False, True],
    [False, False, False],
    [True, False, False]
], dtype=bool)

ARGS = {
    "obst": obst
}
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 4, dtype family float, shape (3, 3, 3, 3) — shape (3, 3, 3, 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
getattr_recursive Ran
ran on a synthesized input
theilem/uavSim/utils.py
code served (permissive licence) · get_code("b4909cfbe907bd79")
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 Parameter, ndim 2, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple nested object with attributes
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.params = nn.Linear(2, 5)

# Create test objects
nested_obj = SimpleModule()

# Test with string path
string_path = "linear/weight"

# Test with list path
list_path = ["linear", "weight"]

# Test with dict-based object
dict_obj = {
    "linear": {
        "weight": torch.randn(3, 4),
        "bias": torch.randn(3)
    },
    "params": {
        "data": torch.randn(2, 5)
    }
}

# Arguments for getattr_recursive function
ARGS = {
    "obj": nested_obj,
    "s": string_path
}
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 Parameter, ndim 2, dtype family float — no output shape is stated: observe_signature.py recorded Tensor ndim 2, 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
getattr_recursive Ran
ran on a synthesized input
XGX-CURRY/uavSim/utils.py
code served (permissive licence) · get_code("e4b9c8f2263b5b24")
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 torch.nn as nn

torch.manual_seed(0)

# Create a nested object structure that supports recursive getattr
class Inner(nn.Module):
    def __init__(self):
        super().__init__()
        self.value = torch.randn(2, 4)
        self.name = "inner_module"

class Middle(nn.Module):
    def __init__(self):
        super().__init__()
        self.inner = Inner()
        self.layer = nn.Linear(4, 3)

class Outer(nn.Module):
    def __init__(self):
        super().__init__()
        self.middle = Middle()
        self.config = {"hidden_size": 64}

# Instantiate the nested structure
obj = Outer()

# Test case 1: string path with '/' separators
s_string = "middle/inner/value"

# Test case 2: list path (alternative format)
s_list = ["middle", "inner", "name"]

# Choose one for the main test
ARGS = {
    "obj": obj,
    "s": s_string
}
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 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
pad_centered Ran
ran on a synthesized input
XGX-CURRY/uavSim/src/StateUtils.py
code served (permissive licence) · get_code("25b3547a6b165090")
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 3, dtype family float, shape (11, 9, 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 math
import numpy as np

class MockState:
    def __init__(self, no_fly_zone_shape, position):
        self.no_fly_zone = np.zeros(no_fly_zone_shape)
        self.position = position

# Create a small state object
state = MockState(
    no_fly_zone_shape=(4, 3),
    position=(1, 2)
)

# Create a small map_in with shape (height, width, channels)
map_in = np.ones((8, 6, 2), dtype=np.float32)

# Define pad_value
pad_value = 0

ARGS = {
    "state": state,
    "map_in": map_in,
    "pad_value": pad_value
}
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 3, dtype family float, shape (11, 9, 2) — shape (11, 9, 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
polynomial_activation Ran
ran on a synthesized input
theilem/uavSim/src/trainer/trainer.py
code served (permissive licence) · get_code("090b8510bfaa7d78")
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 (2, 12) 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

# Create a small TensorFlow tensor for the layer parameter
# Shape: (batch_size=2, features=4)
layer = tf.constant(np.array([[1.0, 2.0, 3.0, 4.0],
                               [5.0, 6.0, 7.0, 8.0]]), dtype=tf.float32)

# Define ARGS dictionary with all function parameters
ARGS = {
    "layer": layer,
    "degree": 3
}
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 2, dtype family float, shape (2, 12) — shape (2, 12) 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
read_config Ran
ran on a synthesized input
XGX-CURRY/uavSim/utils.py
code served (permissive licence) · get_code("5bda7405a5ea8f9c")
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 SimpleNamespace. 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 json
import tempfile
import os
from types import SimpleNamespace as Namespace

# Create a temporary config file with valid JSON
config_dict = {
    "learning_rate": 0.001,
    "batch_size": 32,
    "num_epochs": 10,
    "model": {
        "hidden_dim": 128,
        "num_layers": 2
    },
    "optimizer": "adam"
}

# Create a temporary file and write the JSON config
temp_dir = tempfile.gettempdir()
config_path = os.path.join(temp_dir, "test_config.json")

with open(config_path, 'w') as f:
    json.dump(config_dict, f)

ARGS = {
    "config_path": config_path
}
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 SimpleNamespace — a SimpleNamespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleNamespace 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
getattr_recursive_ Not yet run
unverified (harvested, no recorded run)
theilem/uavSim/utils.py
code served (permissive licence) · get_code("3095d6f31688db4c")
How it ran

no invocation recorded.

setattr_recursive Not yet run
unverified (harvested, no recorded run)
theilem/uavSim/utils.py
code served (permissive licence) · get_code("29ae5e96e15b8a6e")
How it ran

no invocation recorded.

setattr_recursive Not yet run
unverified (harvested, no recorded run)
XGX-CURRY/uavSim/utils.py
code served (permissive licence) · get_code("b73771b17be0a364")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Coverage path planning (CPP) is the task of designing a trajectory that enables a mobile agent to travel over every point of an area of interest. We propose a new method to control an unmanned aerial vehicle (UAV) carrying a camera on a CPP mission with random start positions and multiple options for landing positions in an environment containing no-fly zones. While numerous approaches have been proposed to solve similar CPP problems, we leverage end-to-end reinforcement learning (RL) to learn a control policy that generalizes over varying power constraints for the UAV. Despite recent improvements in battery technology, the maximum flying range of small UAVs is still a severe constraint, which is exacerbated by variations in the UAV's power consumption that are hard to predict. By using map-like input channels to feed spatial information through convolutional network layers to the agent, we are able to train a double deep Q-network (DDQN) to make control decisions for the UAV, balancing limited power budget and coverage goal. The proposed method can be applied to a wide variety of environments and harmonizes complex goal structures with system constraints.

For agents

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

get_harvested_code_for_paper("2003.02609")
get_code_for_paper("2003.02609")
have("2003.02609")

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

curl https://syntology.ai/api/ran/2003.02609.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.02609.svg)](https://syntology.ai/paper/2003.02609)

Connect an agent — have() is free.