SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.04184 · 2026

Natural Language Instructions for Scene-Responsive Human-in-the-Loop Motion Planning in Autonomous Driving using Vision-Language-Action Models

Ross Greer, Angel Martinez-Sanchez, Parthib Roy

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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, 2 violated it and 0 have no contract verdict; 10 failures of our instrument; 2 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/2602.04184.json · badge: /api/ran/2602.04184.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
Mi3-Lab/doScenes-VLM-Planning canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
TransformPoint Ran
ran, violated the contract we drafted
Mi3-Lab/doScenes-VLM-Planning/src/utils.py
pointer only (licence: AGPL-3.0) · get_code("db969bb3c9928409")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

divide_to_patches Ran
ran; our contract draft was wrong, not the code
Mi3-Lab/doScenes-VLM-Planning/src/llava/mm_utils.py
pointer only (licence: AGPL-3.0) · get_code("7e03b180fa317c9a")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

divide_to_patches_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Mi3-Lab/doScenes-VLM-Planning/src/llava/mm_utils_differentiable.py
pointer only (licence: AGPL-3.0) · get_code("d583af3c197aa7a2")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

encode_image Ran
ran; our contract draft was wrong, not the code
Mi3-Lab/doScenes-VLM-Planning/src/utils.py
pointer only (licence: AGPL-3.0); the stored copy get_code serves, from jongwoopark7978/LVNet, is pointer only (licence: NONE) · get_code("f41cb1a19b154297")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

list_dirs Ran
ran; our contract draft was wrong, not the code
Mi3-Lab/doScenes-VLM-Planning/src/automate_doscenes.py
pointer only (licence: AGPL-3.0) · get_code("51b3a6d94677efe3")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

newest_timestamp_folder Ran
ran; our contract draft was wrong, not the code
Mi3-Lab/doScenes-VLM-Planning/src/automate_doscenes.py
pointer only (licence: AGPL-3.0) · get_code("f9ffcd28ecc6eac9")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

resize_and_pad_image Ran
ran; our contract draft was wrong, not the code
Mi3-Lab/doScenes-VLM-Planning/src/llava/mm_utils.py
pointer only (licence: AGPL-3.0) · get_code("468eedeba67f1b00")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

resize_and_pad_image_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Mi3-Lab/doScenes-VLM-Planning/src/llava/mm_utils_differentiable.py
pointer only (licence: AGPL-3.0) · get_code("90f7965ceca36e63")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

select_best_resolution Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Mi3-Lab/doScenes-VLM-Planning/src/llava/mm_utils.py
pointer only (licence: AGPL-3.0) · get_code("3999ff487573f32c")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

select_best_resolution Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Mi3-Lab/doScenes-VLM-Planning/src/llava/mm_utils_differentiable.py
pointer only (licence: AGPL-3.0) · get_code("3c876f5095840dc7")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

slugify_instruction Ran
ran; our contract draft was wrong, not the code
Mi3-Lab/doScenes-VLM-Planning/src/automate_doscenes.py
pointer only (licence: AGPL-3.0) · get_code("2af5c33484dbfdff")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

violates_moderation Ran
ran, violated the contract we drafted
Mi3-Lab/doScenes-VLM-Planning/src/llava/utils.py
pointer only (licence: AGPL-3.0) · get_code("f9939a84b9a65279")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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.

pretty_print_semaphore Not yet run
unverified (harvested, no recorded run)
Mi3-Lab/doScenes-VLM-Planning/src/llava/utils.py
pointer only (licence: AGPL-3.0) · get_code("37899f22fb191b37")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

query_gpt4 Not yet run
unverified (harvested, no recorded run)
Mi3-Lab/doScenes-VLM-Planning/src/utils.py
pointer only (licence: AGPL-3.0) · get_code("dc765bbcb632d812")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, Mi3-Lab/doScenes-VLM-Planning, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 5 later) and 8 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
encode_image 76 other papers
74 dated earlier, 1 the same month, 1 later
2309.05950 (2023-09)
Language Models as Black-Box Optimizers for Vision-Language Models
2311.15732 (2023-11)
GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
2312.14867 (2023-12)
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
and 73 more not named here
select_best_resolution 73 other papers
68 dated earlier, 1 the same month, 4 later · 7 only as an assembly brick
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2304.08485 (2023-04)
Visual Instruction Tuning
2308.13566 (2023-08)
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
and 70 more not named here
resize_and_pad_image 65 other papers
61 dated earlier, 1 the same month, 3 later
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2308.13566 (2023-08)
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
2310.08588 (2023-10)
Octopus: Embodied Vision-Language Programmer from Environmental Feedback
and 62 more not named here
divide_to_patches 64 other papers
60 dated earlier, 1 the same month, 3 later
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2308.13566 (2023-08)
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
2310.08588 (2023-10)
Octopus: Embodied Vision-Language Programmer from Environmental Feedback
and 61 more not named here
violates_moderation 56 other papers
56 dated earlier
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2308.03279 (2023-08)
UniversalNER: TARGETED DISTILLATION FROM LARGE LANGUAGE MODELS FOR OPEN NAMED ENTITY RECOGNITION
2308.13437 (2023-08)
Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models
and 53 more not named here
pretty_print_semaphore 54 other papers
53 dated earlier, 1 later
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2308.13437 (2023-08)
Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models
2309.07120 (2023-09)
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
and 51 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

Instruction-grounded driving, where passenger language guides trajectory planning, requires vehicles to understand intent before motion. However, most prior instruction-following planners rely on simulation or fixed command vocabularies, limiting real-world generalization. doScenes, the first real-world dataset linking free-form instructions (with referentiality) to nuScenes ground-truth motion, enables instruction-conditioned planning. In this work, we adapt OpenEMMA, an open-source MLLM-based end-to-end driving framework that ingests frontcamera views and ego-state and outputs 10-step speed-curvature trajectories, to this setting, presenting a reproducible instructionconditioned baseline on doScenes and investigate the effects of human instruction prompts on predicted driving behavior. We integrate doScenes directives as passenger-style prompts within OpenEMMA's vision-language interface, enabling linguistic conditioning before trajectory generation. Evaluated on 849 annotated scenes using ADE, we observe that instruction conditioning substantially improves robustness by preventing extreme baseline failures, yielding a 98.7% reduction in mean ADE. When such outliers are removed, instructions still influence trajectory alignment, with well-phrased prompts improving ADE by up to 5.1%. We use this analysis to discuss what makes a "good" instruction for the OpenEMMA framework. We release the evaluation prompts and scripts to establish a reproducible baseline for instruction-aware planning. GitHub: https://github.com/Mi3-Lab/doScenes-VLM-Planning

For agents

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

get_harvested_code_for_paper("2602.04184")
get_code_for_paper("2602.04184")
have("2602.04184")

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

curl https://syntology.ai/api/ran/2602.04184.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.04184.svg)](https://syntology.ai/paper/2602.04184)

Connect an agent — have() is free.