Szczegóły publikacji
Opis bibliograficzny
Hierarchical prompting with dual LLM modules for robotic task and motion planning / Karolina Źróbek, Tessa Pulli, Paweł GAJEWSKI, Antonio Galiza Cerdeira Gonzalez, Bipin Indurkhya // W: 2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO) [Dokument elektroniczny] : 10-12 June 2026, Vienna, Austria : proceedings. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, 2026. — ( Conference proceedings (IEEE Workshop on Advanced Robotics and its Social Impacts) ; ISSN 2162-7568 ). — Dod. ISBN: 979-8-3315-6446-9 (print on demand). — e-ISBN: 979-8-3315-6445-2. — S. 245–250. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 250, Abstr. — P. Gajewski - dod. afiliacja: Jagiellonian University, Krakow, Poland
Autorzy (5)
- Źróbek Karolina
- Pulli Tessa
- AGHGajewski Paweł
- Gonzalez Antonio Galiza Cerdeira
- Indurkhya Bipin
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 168669 |
|---|---|
| Data dodania do BaDAP | 2026-07-28 |
| DOI | 10.1109/ARSO68304.2026.11536120 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Czasopismo/seria | Conference proceedings (IEEE Workshop on Advanced Robotics and its Social Impacts) |
Abstract
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%. © 2026 IEEE.
