SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.05700 · 2020

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 0 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/2002.05700.json · badge: /api/ran/2002.05700.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
gkahn13/badgr canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
get_files_ending_with Ran
ran on a synthesized input
gkahn13/badgr/src/badgr/utils/file_utils.py
code served (permissive licence) · get_code("79e939b587e72c92")
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 list, 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 os
import tempfile
import shutil

# Create temporary directories with test files
temp_dir1 = tempfile.mkdtemp()
temp_dir2 = tempfile.mkdtemp()

# Create some test files with .txt extension
open(os.path.join(temp_dir1, "file1.txt"), "w").close()
open(os.path.join(temp_dir1, "file2.txt"), "w").close()
open(os.path.join(temp_dir1, "file3.py"), "w").close()

# Create some test files in second directory
open(os.path.join(temp_dir2, "file4.txt"), "w").close()
open(os.path.join(temp_dir2, "file5.log"), "w").close()

# Test case 1: single folder as string
ARGS = {
    "folder_or_folders": temp_dir1,
    "ext": ".txt"
}

# Cleanup function to be called after test
def cleanup():
    shutil.rmtree(temp_dir1)
    shutil.rmtree(temp_dir2)
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 list, ndim 1, dtype family float — a list 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
import_config Ran
ran on a synthesized input
gkahn13/badgr/src/badgr/utils/python_utils.py
code served (permissive licence) · get_code("99e4d32d2509ed72")
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 tempfile
import os

# Create a temporary Python config file
temp_dir = tempfile.mkdtemp()
config_file = os.path.join(temp_dir, 'config.py')

with open(config_file, 'w') as f:
    f.write("""
params = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'num_epochs': 10,
    'model_name': 'test_model'
}
""")

ARGS = {
    'config_fname': config_file
}
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
imrectify Ran
ran on a synthesized input
gkahn13/badgr/src/badgr/utils/np_utils.py
code served (permissive licence) · get_code("a9397bd099471e7d")
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 int, shape (480, 640, 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 cv2
import numpy as np

# Create a small fisheye image (480x640x3 BGR format)
# Using a simple pattern to make a valid image
img = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)

# Create a valid camera intrinsic matrix K for a 640x480 image
# Typical fisheye camera matrix
focal_length = 500.0
cx, cy = 320.0, 240.0
K = np.array([
    [focal_length, 0.0, cx],
    [0.0, focal_length, cy],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Create distortion coefficients for fisheye model (4 coefficients)
D = np.array([0.1, 0.05, -0.02, 0.01], dtype=np.float32)

# Balance parameter controls the trade-off between retaining valid pixels
# and minimizing the area of the image that gets mapped
balance = 0.0

ARGS = {
    'img': img,
    'K': K,
    'D': D,
    'balance': balance
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (480, 640, 3) — shape (480, 640, 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
imresize Ran
ran on a synthesized input
gkahn13/badgr/src/badgr/utils/np_utils.py
code served (permissive licence) · get_code("7aaa497de4c09c3a")
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 int, shape (4, 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
import PIL.Image

# Create a small test image
# The function checks that image.shape[0] / image.shape[1] == shape[0] / shape[1]
# So we need matching aspect ratios
# Let's use a 4:3 aspect ratio: image is 8x6, target shape is 4x3x3 (4 height, 3 width, 3 channels)
image_array = np.random.randint(0, 256, (8, 6, 3), dtype=np.uint8)

# Target shape: (height, width, channels)
# Must maintain aspect ratio: 4/3 == 8/6
target_shape = (4, 3, 3)

# Resize method - using default PIL.Image.LANCZOS
resize_method = PIL.Image.LANCZOS

ARGS = {
    "image": image_array,
    "shape": target_shape,
    "resize_method": resize_method,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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 int, shape (4, 3, 3) — shape (4, 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
yaw_rotmat Ran
ran on a synthesized input
gkahn13/badgr/src/badgr/utils/np_utils.py
code served (permissive licence) · get_code("f7904e71a7eda7d9")
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 float, 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

def yaw_rotmat(yaw):
    return np.array([[np.cos(yaw), -np.sin(yaw), 0.0], [np.sin(yaw), np.cos(yaw), 0.0], [0.0, 0.0, 1.0]])

# yaw_rotmat takes a single parameter 'yaw' which should be a scalar angle value
# The function computes a 3x3 rotation matrix around the z-axis

ARGS = {
    "yaw": 0.5  # A scalar angle in radians
}
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 float, 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can can be insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience. Our approach, which we call BADGR, is an end-to-end learning-based mobile robot navigation system that can be trained with self-supervised off-policy data gathered in real-world environments, without any simulation or human supervision. BADGR can navigate in real-world urban and off-road environments with geometrically distracting obstacles. It can also incorporate terrain preferences, generalize to novel environments, and continue to improve autonomously by gathering more data. Videos, code, and other supplemental material are available on our website https://sites.google.com/view/badgr

For agents

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

get_harvested_code_for_paper("2002.05700")
get_code_for_paper("2002.05700")
have("2002.05700")

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

curl https://syntology.ai/api/ran/2002.05700.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.05700.svg)](https://syntology.ai/paper/2002.05700)

Connect an agent — have() is free.