Classical planning in AI and Robotics addresses complex tasks by shifting from imperative to declarative approaches (e.g., PDDL). However, these methods often fail in real scenarios due to limited robot perception and the need to ground perceptions to planning predicates. This often results in heavily hard-coded behaviors that struggle to adapt, even with scenarios where goals can be achieved through relaxed planning. Meanwhile, Large Language Models (LLMs) lead to planning systems that leverage commonsense reasoning but often at the cost of generating unfeasible and/or unsafe plans. To address these limitations, we present an approach integrating classical planning with LLMs, leveraging their ability to extract commonsense knowledge and ground actions. We propose a hierarchical formulation that enables robots to make unfeasible tasks tractable by defining functionally equivalent goals through gradual relaxation. This mechanism supports partial achievement of the intended objective, suited to the agent's specific context. Our method demonstrates its ability to adapt and execute tasks effectively within environments modeled using 3D Scene Graphs through comprehensive qualitative and quantitative evaluations. We also show how this method succeeds in complex scenarios where other benchmark methods are more likely to fail. Code, dataset, and additional material are released to the community.
View on arXiv@article{musumeci2025_2506.15828,
title={ Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning },
author={ Emanuele Musumeci and Michele Brienza and Francesco Argenziano and Vincenzo Suriani and Daniele Nardi and Domenico D. Bloisi },
journal={arXiv preprint arXiv:2506.15828},
year={ 2025 }
}