Guardado en:
Detalles Bibliográficos
Autores principales: Źróbek, Karolina, Pulli, Tessa, Gajewski, Paweł, Gonzalez, Antonio Galiza Cerdeira, Indurkhya, Bipin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.08330
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909028296163328
author Źróbek, Karolina
Pulli, Tessa
Gajewski, Paweł
Gonzalez, Antonio Galiza Cerdeira
Indurkhya, Bipin
author_facet Źróbek, Karolina
Pulli, Tessa
Gajewski, Paweł
Gonzalez, Antonio Galiza Cerdeira
Indurkhya, Bipin
contents We present a hierarchical language-driven framework for robotic task and motion planning to improve natural, intuitive human-robot interaction in service and assistance scenarios. The proposed system employs two large language model (LLM) modules: a high-level planning agent and a low-level spatial reasoning sub-module. The primary agent processes natural language commands and generates action sequences using a ReAct-style prompt, interacting with tools for object perception and manipulation (e.g., pick, place, release). For precise spatial placement, such as interpreting "place the mug next to the plate", a separate sub-prompting module handles 3D reasoning based on object geometry and scene layout. The system integrates YOLOX-GDRNet for object detection and pose estimation, along with a motion execution stub. We evaluated the system in 24 test scenarios, ranging from simple spatial commands to high-level instructions and infeasible requests. The system achieved an overall task success rate of 86%.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08330
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning
Źróbek, Karolina
Pulli, Tessa
Gajewski, Paweł
Gonzalez, Antonio Galiza Cerdeira
Indurkhya, Bipin
Robotics
We present a hierarchical language-driven framework for robotic task and motion planning to improve natural, intuitive human-robot interaction in service and assistance scenarios. The proposed system employs two large language model (LLM) modules: a high-level planning agent and a low-level spatial reasoning sub-module. The primary agent processes natural language commands and generates action sequences using a ReAct-style prompt, interacting with tools for object perception and manipulation (e.g., pick, place, release). For precise spatial placement, such as interpreting "place the mug next to the plate", a separate sub-prompting module handles 3D reasoning based on object geometry and scene layout. The system integrates YOLOX-GDRNet for object detection and pose estimation, along with a motion execution stub. We evaluated the system in 24 test scenarios, ranging from simple spatial commands to high-level instructions and infeasible requests. The system achieved an overall task success rate of 86%.
title Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning
topic Robotics
url https://arxiv.org/abs/2605.08330