SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.06974 · 2026

FeudalNav: A Simple Framework for Visual Navigation

Shubham Jain, Kristin Dana, Bryan Cao, Faith Johnson, Ashwin Ashok, Waynet Generates, High Level Manager

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2602.06974.json · badge: /api/ran/2602.06974.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
visnavdev/feudalnav community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
Graph Ran
ran on a synthesized input · constructed an object; no result was computed
visnavdev/feudalnav/deterministicTrials/models.py
code served (permissive licence) · get_code("93ff753eb230e959")
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 an instance of its own class, Graph: the run constructed the object and did not call it, so no result was computed. 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 numpy as np
import cv2
import tempfile
import os

# Create a minimal stand-in for orientation that has an angle() method
class Orientation:
    def __init__(self, angle_val):
        self._angle = angle_val
    
    def angle(self):
        return self._angle

# Create temporary image files for testing
def create_temp_image(height=100, width=100):
    """Create a temporary image file and return its path"""
    img = np.random.randint(0, 255, (height, width, 3), dtype=np.uint8)
    fd, path = tempfile.mkstemp(suffix='.png')
    cv2.imwrite(path, img)
    os.close(fd)
    return path

def create_temp_depth(height=100, width=100):
    """Create a temporary depth image file and return its path"""
    depth = np.random.randint(0, 255, (height, width, 3), dtype=np.uint8)
    fd, path = tempfile.mkstemp(suffix='.png')
    cv2.imwrite(path, depth)
    os.close(fd)
    return path

# Create temporary image and depth paths
img_path_1 = create_temp_image(100, 100)
img_path_2 = create_temp_image(100, 100)
depth_path_1 = create_temp_depth(100, 100)
depth_path_2 = create_temp_depth(100, 100)

# Create location and orientation arrays
location_1 = np.array([1.0, 2.0, 3.0])
location_2 = np.array([4.0, 5.0, 6.0])
orientation_1 = Orientation(0.5)
orientation_2 = Orientation(1.5)

# Create click points
click_point_1 = np.array([10, 20])
click_point_2 = np.array([30, 40])

# Construct the Graph with all required parameters
ARGS = {
    'env_name': 'test_environment',
    'goal_location': np.array([10.0, 20.0, 30.0])
}
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 Graph — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Graph 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
Node Ran
ran on a synthesized input · constructed an object; no result was computed
visnavdev/feudalnav/deterministicTrials/models.py
code served (permissive licence) · get_code("d48f9e86671b3bca")
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 an instance of its own class, Node: the run constructed the object and did not call it, so no result was computed. 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 numpy as np
import cv2

# Create a minimal Orientation class with an angle() method
class Orientation:
    def __init__(self, angle_value):
        self._angle = angle_value
    
    def angle(self):
        return self._angle

# Create temporary image files for testing
def create_test_image(path, shape=(10, 10, 3)):
    img = np.random.randint(0, 255, shape, dtype=np.uint8)
    cv2.imwrite(path, cv2.cvtColor(img, cv2.COLOR_RGB2BGR))
    return path

def create_test_depth(path, shape=(10, 10, 3)):
    depth = np.random.randint(0, 255, shape, dtype=np.uint8)
    cv2.imwrite(path, depth)
    return path

# Create test image and depth files
import tempfile
import os

temp_dir = tempfile.gettempdir()
img_path = os.path.join(temp_dir, "test_img.png")
depth_path = os.path.join(temp_dir, "test_depth.png")

create_test_image(img_path)
create_test_depth(depth_path)

# Build the ARGS dictionary
ARGS = {
    'img_path': img_path,
    'location': np.array([1.0, 2.0, 3.0]),
    'orientation': Orientation(0.5),
    'depth_path': depth_path,
    'click_point': np.array([5, 7]),
    'reason': 'test_reason'
}
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 Node — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Node 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
saveOBS Ran
ran; our contract draft was wrong, not the code
visnavdev/feudalnav/deterministicTrials/models.py
code served (permissive licence) · get_code("2d5ac98a9ac937ea")
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 numpy as np
import tempfile
import os

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create obs dict with color_sensor and depth_sensor
obs = {
    'color_sensor': np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8),
    'depth_sensor': np.random.randint(0, 1000, (480, 640), dtype=np.uint16)
}

folder_path = temp_dir
i = 42

ARGS = {
    'obs': obs,
    'folder_path': folder_path,
    'i': i
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — 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
Worker Not yet run
unverified (harvested, no recorded run)
visnavdev/feudalnav/deterministicTrials/models.py
code served (permissive licence) · get_code("3c0a07d7355176ea")
How it ran

no invocation recorded.

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, 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 4 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

Visual navigation for robotics is inspired by the human ability to navigate environments using visual cues and memory, eliminating the need for detailed maps. In unseen, unmapped, or GPS-denied settings, traditional metric mapbased methods fall short, prompting a shift toward learningbased approaches with minimal exploration. In this work, we develop a hierarchical framework 1 that decomposes the navigation decision-making process into multiple levels. Our method learns to select subgoals through a simple, transferable waypoint selection network. A key component of the approach is a latent-space memory module organized solely by visual similarity, as a proxy for distance. This alternative to graph-based topological representations proves sufficient for navigation tasks, providing a compact, lightweight, simple-to-train navigator that can find its way to the goal in novel locations. We show competitive results with a suite of SOTA methods in Habitat AI environments without using any odometry in training or inference. An additional contribution leverages the interpretability of the framework for interactive navigation. We consider the question: how much direction intervention/interaction is needed to achieve success in all trials? We demonstrate that even minimal human involvement can significantly enhance overall navigation performance.

For agents

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

get_harvested_code_for_paper("2602.06974")
get_code_for_paper("2602.06974")
have("2602.06974")

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

curl https://syntology.ai/api/ran/2602.06974.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.06974.svg)](https://syntology.ai/paper/2602.06974)

Connect an agent — have() is free.