LLM-Based Agentic Exploration for Robot Navigation & Manipulation with Skill Orchestration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918269198270464 |
|---|---|
| author | Syarubany, Abu Hanif Muhammad Rahmani, Farhan Zaki Widianto, Trio |
| author_facet | Syarubany, Abu Hanif Muhammad Rahmani, Farhan Zaki Widianto, Trio |
| contents | This paper presents an end-to-end LLM-based agentic exploration system for an indoor shopping task, evaluated in both Gazebo simulation and a corresponding real-world corridor layout. The robot incrementally builds a lightweight semantic map by detecting signboards at junctions and storing direction-to-POI relations together with estimated junction poses, while AprilTags provide repeatable anchors for approach and alignment. Given a natural-language shopping request, an LLM produces a constrained discrete action at each junction (direction and whether to enter a store), and a ROS finite-state main controller executes the decision by gating modular motion primitives, including local-costmap-based obstacle avoidance, AprilTag approaching, store entry, and grasping. Qualitative results show that the integrated stack can perform end-to-end task execution from user instruction to multi-store navigation and object retrieval, while remaining modular and debuggable through its text-based map and logged decision history. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00555 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-Based Agentic Exploration for Robot Navigation & Manipulation with Skill Orchestration Syarubany, Abu Hanif Muhammad Rahmani, Farhan Zaki Widianto, Trio Robotics This paper presents an end-to-end LLM-based agentic exploration system for an indoor shopping task, evaluated in both Gazebo simulation and a corresponding real-world corridor layout. The robot incrementally builds a lightweight semantic map by detecting signboards at junctions and storing direction-to-POI relations together with estimated junction poses, while AprilTags provide repeatable anchors for approach and alignment. Given a natural-language shopping request, an LLM produces a constrained discrete action at each junction (direction and whether to enter a store), and a ROS finite-state main controller executes the decision by gating modular motion primitives, including local-costmap-based obstacle avoidance, AprilTag approaching, store entry, and grasping. Qualitative results show that the integrated stack can perform end-to-end task execution from user instruction to multi-store navigation and object retrieval, while remaining modular and debuggable through its text-based map and logged decision history. |
| title | LLM-Based Agentic Exploration for Robot Navigation & Manipulation with Skill Orchestration |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.00555 |