SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.16822 · NeurIPS · 2022

Towards Versatile Embodied Navigation

Luc Van Gool, Wenguan Wang, Wei Liang, Hanqing Wang

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure 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/2210.16822.json · badge: /api/ran/2210.16822.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
hanqingwangai/vxn canonical (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
euclidean_distance Ran
ran, honoured the contract we drafted
hanqingwangai/vxn/habitat_extensions/measures.py
code served (permissive licence) · get_code("35967088b93afc46")
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
from typing import List, Union

# Construct arguments for euclidean_distance function
# The function takes two positions (either lists or ndarrays) and computes euclidean distance

pos_a = [1.0, 2.0, 3.0]  # List of floats
pos_b = np.array([4.0, 5.0, 6.0])  # ndarray

ARGS = {
    "pos_a": pos_a,
    "pos_b": pos_b,
}
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
fft_convolve_torch Ran
ran on a synthesized input
hanqingwangai/vxn/habitat_extensions/audionav_sensor.py
code served (permissive licence) · get_code("a18cf65f468918d9")
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 1, dtype family float, shape (6,) 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 torch

torch.manual_seed(0)

# Create two 1D tensors for convolution
# a and b should be 1D tensors (or batches of 1D tensors)
# The function uses shape[-1] to get the last dimension
a = torch.randn(4)  # 1D tensor of size 4
b = torch.randn(3)  # 1D tensor of size 3

ARGS = {
    "a": a,
    "b": b,
}
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 1, dtype family float, shape (6,) — shape (6,) 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
static_to_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hanqingwangai/vxn/habitat_extensions/maps.py
code served (permissive licence) · get_code("e3de2e386766be00")
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 int; 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 numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - realworld_x: float - a real-world x coordinate
# - realworld_y: float - a real-world y coordinate
# - grid_resolution: Tuple[int, int] - grid dimensions (width, height)
# - bounds: Dict[str, Tuple[float, float]] - dictionary with 'upper' and 'lower' keys
#   Each containing tuples with at least 3 elements (indices 0 and 2 are accessed)

# The function accesses:
# bounds['upper'][2] - z-coordinate of upper bound
# bounds['lower'][2] - z-coordinate of lower bound
# bounds['upper'][0] - x-coordinate of upper bound
# bounds['lower'][0] - x-coordinate of lower bound

ARGS = {
    'realworld_x': 5.5,
    'realworld_y': 3.2,
    'grid_resolution': (10, 8),
    'bounds': {
        'upper': (10.0, 0.0, 20.0),  # (x_max, y, z_max)
        'lower': (0.0, 0.0, 0.0)      # (x_min, y, z_min)
    }
}
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 tuple, ndim 1, dtype family int — 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
colorize_topdown_map Not yet run
unverified (harvested, no recorded run)
hanqingwangai/vxn/habitat_extensions/maps.py
code served (permissive licence) · get_code("3559a5421dd17ce5")
How it ran

no invocation recorded.

load_metadata Not yet run
unverified (harvested, no recorded run)
hanqingwangai/vxn/habitat_extensions/audionav_sensor.py
code served (permissive licence) · get_code("deea512d3e44113c")
How it ran

no invocation recorded.

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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
colorize_topdown_map 7 other papers
2 dated earlier, 5 later
2110.02207 (2021-10)
Waypoint Models for Instruction-guided Navigation in Continuous Environments
2203.02764 (2022-03)
Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation
2304.03047 (2023-04)
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
and 4 more not named here
static_to_grid 6 other papers
1 dated earlier, 5 later
2110.02207 (2021-10)
Waypoint Models for Instruction-guided Navigation in Continuous Environments
2304.03047 (2023-04)
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
2404.01943 (2024-04)
Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation
and 3 more not named here
euclidean_distance 2 other papers
1 dated earlier, 1 later
2110.02207 (2021-10)
Waypoint Models for Instruction-guided Navigation in Continuous Environments
2601.18188 (2026-01)
NaVIDA: Vision-Language Navigation with Inverse Dynamics Augmentation

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

With the emergence of varied visual navigation tasks (e.g., image-/object-/audiogoal and vision-language navigation) that specify the target in different ways, the community has made appealing advances in training specialized agents capable of handling individual navigation tasks well. Given plenty of embodied navigation tasks and task-specific solutions, we address a more fundamental question: can we learn a single powerful agent that masters not one but multiple navigation tasks concurrently? First, we propose VXN, a large-scale 3D dataset that instantiates four classic navigation tasks in standardized, continuous, and audiovisual-rich environments. Second, we propose VIENNA, a versatile embodied navigation agent that simultaneously learns to perform the four navigation tasks with one model. Building upon a full-attentive architecture, VIENNA formulates various navigation tasks as a unified, parse-and-query procedure: the target description, augmented with four task embeddings, is comprehensively interpreted into a set of diversified goal vectors, which are refined as the navigation progresses, and used as queries to retrieve supportive context from episodic history for decision making. This enables the reuse of knowledge across navigation tasks with varying input domains/modalities. We empirically demonstrate that, compared with learning each visual navigation task individually, our multitask agent achieves comparable or even better performance with reduced complexity.

For agents

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

get_harvested_code_for_paper("2210.16822")
get_code_for_paper("2210.16822")
have("2210.16822")

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

curl https://syntology.ai/api/ran/2210.16822.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.16822.svg)](https://syntology.ai/paper/2210.16822)

Connect an agent — have() is free.