The DOI matches its Crossref record; the references it cites are not checked yet.
Generating Executable Action Plans with Environmentally-Aware Language Models
Open accessAbstract
Large Language Models (LLMs) trained using massive text datasets have recently shown promise in generating action plans for robotic agents from high-level text queries. However, these models typically do not consider the robot's environment, resulting in generated plans that may not actually be executable, due to ambiguities in the planned actions or environmental constraints. In this paper, we propose an approach to generate environmentally-aware action plans that agents are better able to execute. Our approach involves integrating environmental objects and object relations as additional inputs into LLM action plan generation to provide the system with an awareness of its surroundings, resulting in plans where each generated action is mapped to objects present in the scene. We also design a novel scoring function that, along with generating the action steps and associating them with objects, helps the system disambiguate among object instances and take into account their states. We evaluated our approach using the VirtualHome simulator and the ActivityPrograms knowledge base and found that action plans generated from our system had a 310% improvement in executability and a 147% improvement in correctness over prior work. The complete code and a demo of our method is publicly available at https://github.com/hri-ironlab/scene_aware_language_planner.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“[55] further improves [54] by incorporating examples that are similar to the queries in the prompts.”
From A survey on large language model based autonomous agents (2024) · cites this paper as [55]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
The citation lists are queued
They are fetched later and appear here then.
References 75 · Cited by 26
Research works printed but not linked: 15
- Radford, 2019, Language Models are Unsupervised Multitask Learners
- Reid, 2022, Can Wikipedia Help Offline Reinforcement Learning
- Nair, 2021, Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation, CoRL
- Blukis, 2021, A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution
- Akakzia, 2021, Grounding Language to Autonomously-Acquired Skills via Goal Generation
- Humphreys, 2022, A data-driven approach for learning to control computers, 162, 9466
- Xu, Regression Planning Networks
- Eysenbach, 2019, Search on the replay buffer: Bridging planning and reinforcement learning, 32
- Silver, Inventing relational state and action abstractions for effective and efficient bilevel planning
- Nair, 2020, Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
- Pu, 2020, [Re] Language as an Abstraction for Hierarchical Deep Reinforcement Learning, submitted to NeurIPS 2019 Reproducibility Challenge
- Shah, 2022, Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
- Vaswani, 2017, Attention is all you need, 30
- Tsimpoukelli, 2021, Multimodal few-shot learning with frozen language models
- Zellers, 2021, Merlot: Multimodal neural script knowledge models, 34, 23634
Metadata
- Authors
- Gramopadhye, M., & Szafir, D.
- Affiliations
- University of North Carolina at Chapel Hill (US)
- Venue
- 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 3568-3575
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W4389667254
- Semantic Scholar
- ceae37066de82dd3fcd970073e88966728a60c6f
- Cited by
- 26
- References
- 75
- Citations by year
- 2026: 1 · 2025: 11 · 2024: 10 · 2023: 3
- FWCI
- 4.42
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- large language models, robot planning, environmental awareness, object relations, robotic agents
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Generating Executable Action Plans with Environmentally-Aware Language Models. https://app.cochat.ai/papers/10.1109/iros55552.2023.10341989
- The paper
- Gramopadhye, M., & Szafir, D. (2023). Generating Executable Action Plans with Environmentally-Aware Language Models. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). https://doi.org/10.1109/iros55552.2023.10341989
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.