paper-with-me

홈 › Papers

SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning

2023-07-12 · Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian Reid, Niko Suenderhauf

Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant challenge for robotics. We introduce SayPlan, a scalable approach to LLM-based, large-scale task planning for robotics using 3D scene graph (3DSG) representations. To ensure the scalability of our approach, we: (1) exploit the hierarchical nature of 3DSGs to allow LLMs to conduct a 'semantic search' for task-relevant subgraphs from a smaller, collapsed representation of the full graph; (2) reduce the planning horizon for the LLM by integrating a classical path planner and (3) introduce an 'iterative replanning' pipeline that refines the initial plan using feedback from a scene graph simulator, correcting infeasible actions and avoiding planning failures. We evaluate our approach on two large-scale environments spanning up to 3 floors and 36 rooms with 140 assets and objects and show that our approach is capable of grounding large-scale, long-horizon task plans from abstract, and natural language instruction for a mobile manipulator robot to execute. We provide real robot video demonstrations on our project page https://sayplan.github.io.

📄 PDF Abstract BibTeX arXiv:2307.06135

Code (0)

등록된 구현이 없습니다.

Tasks

Robot Task PlanningTask Planning

Similar Papers 제목 키워드 기반

LookPlanGraph: Embodied Instruction Following Method with VLM Graph Augmentation

2025-12-24 · Anatoly O. Onishchenko, Alexey K. Kovalev, Aleksandr I. Panov arxiv

Methods that use Large Language Models (LLM) as planners for embodied instruction following tasks have become widespread. To successfully complete tasks, the LLM must be grounded in the environment in which the robot ope…

Instruction Following

Structured Interfaces for Automated Reasoning with 3D Scene Graphs

2025-10-18 · Aaron Ray, Jacob Arkin, Harel Biggie, Chuchu Fan 외 arxiv

In order to provide a robot with the ability to understand and react to a user's natural language inputs, the natural language must be connected to the robot's underlying representations of the world. Recently, large lan…

Instruction FollowingCode Generation

From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs

2026-06-08 · Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth, Sonja Schimmler arxiv

Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but the key bottleneck, grounding scene objects to formal ontology classes, still relies on manually curated dictionaries tha…

Knowledge Graphs

SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes

2026-01-09 · Chuhan Wang, Xintong Li, Jennifer Yuntong Zhang, Junda Wu 외 arxiv

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness freque…

Multimodal ReasoningVisual ReasoningVisual Grounding

Incremental Object Grounding Using Scene Graphs

2022-01-06 · John Seon Keun Yi, Yoonwoo Kim, Sonia Chernova

Object grounding tasks aim to locate the target object in an image through verbal communications. Understanding human command is an important process needed for effective human-robot communication. However, this is chall…

Object