SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.12152 · 2025

Learning Getting-Up Policies for Real-World Humanoid Robots

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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, 1 violated it and 3 have no contract verdict; 4 failures of our instrument; 0 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/2502.12152.json · badge: /api/ran/2502.12152.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
RunpeiDong/HumanUP canonical (classifier label)
classifier basis not recorded on the link
8 ran · 0 no recorded run
FunctionStatusWhere it lives
class_to_dict Ran
ran on a synthesized input
RunpeiDong/HumanUP/simulation/legged_gym/legged_gym/gym_utils/helpers.py
code served (permissive licence) · get_code("d2cce27928409d52")
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 torch

class SimpleClass:
    def __init__(self):
        self.value = 42
        self.name = "test"
        self.items = [1, 2, 3]

class NestedClass:
    def __init__(self):
        self.simple = SimpleClass()
        self.number = 3.14

class ClassWithList:
    def __init__(self):
        self.objects = [SimpleClass(), SimpleClass()]
        self.data = "hello"

ARGS = {
    "obj": ClassWithList()
}
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 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
conv Ran
ran on a synthesized input
RunpeiDong/HumanUP/simulation/rsl_rl/rsl_rl/utils/layers.py
code served (permissive licence) · get_code("cb6ee0a52ebbdb38")
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 Sequential. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_shape': (3, 64, 64),
    'num_channels': 16,
    'act': nn.Identity()
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
enc Ran
ran; our contract draft was wrong, not the code
RunpeiDong/HumanUP/simulation/rsl_rl/rsl_rl/utils/layers.py
code served (permissive licence) · get_code("2f282677fc4db332")
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 ModuleDict. 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 torch
import torch.nn as nn

torch.manual_seed(0)

class Config:
    def __init__(self):
        self.obs_shape = {
            'state': (5,),
            'rgb': (3, 64, 64)
        }
        self.task_dim = 2
        self.num_enc_layers = 3
        self.enc_dim = 8
        self.latent_dim = 4
        self.num_channels = 4
        self.simnorm_dim = 2

cfg = Config()

ARGS = {
    'cfg': cfg,
    'out': {}
}
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 ModuleDict — a ModuleDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModuleDict output the recorded ndim 1 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
get_activation Ran
ran; our contract draft was wrong, not the code
RunpeiDong/HumanUP/simulation/rsl_rl/rsl_rl/modules/actor_critic.py
code served (permissive licence) · get_code("596f8f6ee188440a")
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) and returned ReLU. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function takes a single parameter: act_name (a string)
# It returns an activation function module based on the string name
# We need to test with a valid activation name

ARGS = {
    'act_name': 'relu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
get_load_path Ran
ran on a synthesized input
RunpeiDong/HumanUP/simulation/legged_gym/legged_gym/gym_utils/helpers.py
code served (permissive licence) · get_code("841f29b15d58ff76")
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 str. 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_base = tempfile.mkdtemp()
temp_run_dir = tempfile.mkdtemp(dir=temp_base)

# Create a checkpoint file in the directory
checkpoint_file = os.path.join(temp_run_dir, "model_checkpoint_1.pt")
with open(checkpoint_file, 'w') as f:
    f.write("")

# Also create another model file to test sorting
checkpoint_file_2 = os.path.join(temp_run_dir, "model_checkpoint_2.pt")
with open(checkpoint_file_2, 'w') as f:
    f.write("")

ARGS = {
    'root': temp_run_dir,
    'load_run': -1,
    'checkpoint': -1,
    'model_name_include': 'model'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
mlp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RunpeiDong/HumanUP/simulation/rsl_rl/rsl_rl/utils/layers.py
code served (permissive licence) · get_code("fc4e341b9c79e617")
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 Sequential. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_dim': 4,
    'mlp_dims': [8, 16],
    'out_dim': 3,
    'act': nn.ReLU(),
    'dropout': 0.1,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
torch_rand_sqrt_float Ran
ran; our contract draft was wrong, not the code
RunpeiDong/HumanUP/simulation/legged_gym/legged_gym/gym_utils/math.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ziyanx02/multiagent-quadruped-environment, is pointer only (licence: NONE) · get_code("078b120ca1398556")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ziyanx02/multiagent-quadruped-environment, 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.

wrap_to_pi Ran
ran, violated the contract we drafted
RunpeiDong/HumanUP/simulation/legged_gym/legged_gym/gym_utils/math.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ziyanx02/multiagent-quadruped-environment, is pointer only (licence: NONE) · get_code("a25affa7af382246")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ziyanx02/multiagent-quadruped-environment, 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.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 2 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
enc 2 other papers
2 later
2605.16692 (2026-05)
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
2608.07870 (2026-08)
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
mlp 2 other papers
2 later
2605.16692 (2026-05)
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
2608.07870 (2026-08)
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
class_to_dict 1 other paper
1 the same month
2502.03132 (2025-02)
SPARK: Safe Protective and Assistive Robot Kit
get_activation 1 other paper
1 dated earlier
2303.16958 (2023-03)
PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations
torch_rand_sqrt_float 1 other paper
1 dated earlier
2403.16015 (2024-03)
MQE: Unleashing the Power of Interaction with Multi-agent Quadruped Environment
wrap_to_pi 1 other paper
1 dated earlier
2403.16015 (2024-03)
MQE: Unleashing the Power of Interaction with Multi-agent Quadruped Environment

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

Automatic fall recovery is a crucial prerequisite before humanoid robots can be reliably deployed. Hand-designing controllers for getting up is difficult because of the varied configurations a humanoid can end up in after a fall and the challenging terrains humanoid robots are expected to operate on. This paper develops a learning framework to produce controllers that enable humanoid robots to get up from varying configurations on varying terrains. Unlike previous successful applications of learning to humanoid locomotion, the getting-up task involves complex contact patterns (which necessitates accurately modeling of the collision geometry) and sparser rewards. We address these challenges through a two-phase approach that induces a curriculum. The first stage focuses on discovering a good getting-up trajectory under minimal constraints on smoothness or speed / torque limits. The second stage then refines the discovered motions into deployable (i.e. smooth and slow) motions that are robust to variations in initial configuration and terrains. We find these innovations enable a real-world G1 humanoid robot to get up from two main situations that we considered: a) lying face up and b) lying face down, both tested on flat, deformable, slippery surfaces and slopes (e.g., sloppy grass and snowfield). This is one of the first successful demonstrations of learned getting-up policies for human-sized humanoid robots in the real world.

For agents

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

get_harvested_code_for_paper("2502.12152")
get_code_for_paper("2502.12152")
have("2502.12152")

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

curl https://syntology.ai/api/ran/2502.12152.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.12152.svg)](https://syntology.ai/paper/2502.12152)

Connect an agent — have() is free.