SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.00744 · NeurIPS · 2025

Open-World Drone Active Tracking with Goal-Centered Rewards

Mingkui Tan, Zhirui Zhang, Xiaohua Xie, Haowei Sun, Jinwu Hu, Haoyuan Tian, Xinze Xie, Yufeng Wang, Yun Lin, Zhuliang Yu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures 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/2412.00744.json · badge: /api/ran/2412.00744.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
SHWplus/DAT_Benchmark canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
Identity Ran
ran, honoured the contract we drafted
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/envs/environment.py
code served (permissive licence) · get_code("d5f78640d43410f5")
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 numpy as np

torch.manual_seed(0)

# The Identity function takes state and env as parameters
# and simply returns the state unchanged.
# We need to provide valid arguments for both parameters.

# state can be any object - let's use a tensor
state = torch.randn(2, 4)

# env can be any object - the function doesn't use it,
# so we can pass a simple placeholder
env = None

ARGS = {
    "state": state,
    "env": env
}
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 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
clip_to_range Ran
ran, honoured the contract we drafted
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/utils.py
code served (permissive licence) · get_code("b5c8b6f2a867869f")
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 float, ndim 0, dtype family float, shape () 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 numpy as np

torch.manual_seed(0)

# clip_to_range takes three parameters: x, min_value, max_value
# x is clipped to be between min_value and max_value
# min_value defaults to 0, max_value defaults to 1

ARGS = {
    "x": 0.5,
    "min_value": 0,
    "max_value": 1,
}
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 float, ndim 0, dtype family float, shape () — shape () 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
create_logger Ran
ran; our contract draft was wrong, not the code
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/envs/logger_cfg.py
code served (permissive licence) · get_code("93005e19b3fdaa71")
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 Logger. 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 logging
import os
import tempfile
import shutil

# Create a temporary directory for logs
temp_log_dir = tempfile.mkdtemp()
original_cwd = os.getcwd()

# Change to temp directory to avoid creating logs in current working directory
os.chdir(temp_log_dir)

# Create logs directory
os.makedirs('./logs', exist_ok=True)

ARGS = {
    'process_id': 0
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
norm_col_init Ran
ran, honoured the contract we drafted
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from unrealtracking/tom2c, is pointer only (licence: NONE) · get_code("21a7f97ee3e0b7cc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from unrealtracking/tom2c, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

process_frame Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/envs/environment.py
code served (permissive licence) · get_code("c9e788d1c0920a2e")
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 (3, 32, 32) 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 minimal environment class with render method
class MinimalEnv:
    def render(self, mode='rgb_array'):
        # Return a small BGR image (3 channels, height=64, width=64)
        return np.random.randint(0, 256, (64, 64, 3), dtype=np.uint8)

# Create configuration dict
conf = {
    'Need_render': False,
    'State_size': 32,
    'State_channel': 3,
    'Norm_Type': 0
}

# Create a sample state (BGR image, 64x64x3)
state = np.random.randint(0, 256, (64, 64, 3), dtype=np.uint8)

# Create environment instance
env = MinimalEnv()

ARGS = {
    'state': state,
    'conf': conf,
    'env': env
}
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 float, shape (3, 32, 32) — shape (3, 32, 32) 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; our contract draft was wrong, not the code
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/utils.py
code served (permissive licence) · get_code("4000c95fa330f2ce")
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 json
import tempfile
import os

# Create a temporary JSON config file
temp_dir = tempfile.mkdtemp()
config_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256]
}

with open(config_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "file_path": config_file_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 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
GE Not yet run
unverified (harvested, no recorded run)
SHWplus/DAT_Benchmark/Alg_Base/DAT_Benchmark/envs/envs_parallel.py
code served (permissive licence) · get_code("29bec8d973f8c6e5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 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.

FunctionAlso present inEarliest-datedOthers named
read_config 5 other papers
5 dated earlier
1809.00397 (2018-09)
Visual Transfer between Atari Games using Competitive Reinforcement Learning
2002.03519 (2020-02)
Self-Attentive Associative Memory
2008.01976 (2020-08)
Robust Deep Reinforcement Learning through Adversarial Loss
and 2 more not named here
norm_col_init 4 other papers
4 dated earlier · 2 only as an assembly brick
2002.03519 (2020-02)
Self-Attentive Associative Memory
2010.13110 (2020-10)
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
2109.02066 (2021-09)
Hierarchical Object-to-Zone Graph for Object Navigation
and 1 more not named here

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

Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations, providing a more practical solution for effective tracking in dynamic environments. However, accurate Drone Visual Active Tracking using reinforcement learning remains challenging due to the absence of a unified benchmark and the complexity of open-world environments with frequent interference. To address these issues, we pioneer a systematic solution. First, we propose DAT, the first open-world drone active air-to-ground tracking benchmark. It encompasses 24 city-scale scenes, featuring targets with human-like behaviors and high-fidelity dynamics simulation. DAT also provides a digital twin tool for unlimited scene generation. Additionally, we propose a novel reinforcement learning method called GC-VAT, which aims to improve the performance of drone tracking targets in complex scenarios. Specifically, we design a Goal-Centered Reward to provide precise feedback across viewpoints to the agent, enabling it to expand perception and movement range through unrestricted perspectives. Inspired by curriculum learning, we introduce a Curriculum-Based Training strategy that progressively enhances the tracking performance in complex environments. Besides, experiments on simulator and real-world images demonstrate the superior performance of GC-VAT, achieving a Tracking Success Rate of approximately 72% on the simulator. The benchmark and code are available at https://github.com/SHWplus/DAT_Benchmark.

For agents

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

get_harvested_code_for_paper("2412.00744")
get_code_for_paper("2412.00744")
have("2412.00744")

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

curl https://syntology.ai/api/ran/2412.00744.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.00744.svg)](https://syntology.ai/paper/2412.00744)

Connect an agent — have() is free.