Quadrupped-Legged Robot Movement Plan Generation using Large Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911404484722688 |
|---|---|
| author | Muhtadin M., Vincentius Gusti Putu A. B. Zaini, Ahmad Purnomo, Mauridhi Hery Purnama, I Ketut Eddy Fatichah, Chastine |
| author_facet | Muhtadin M., Vincentius Gusti Putu A. B. Zaini, Ahmad Purnomo, Mauridhi Hery Purnama, I Ketut Eddy Fatichah, Chastine |
| contents | Traditional control interfaces for quadruped robots often impose a high barrier to entry, requiring specialized technical knowledge for effective operation. To address this, this paper presents a novel control framework that integrates Large Language Models (LLMs) to enable intuitive, natural language-based navigation. We propose a distributed architecture where high-level instruction processing is offloaded to an external server to overcome the onboard computational constraints of the DeepRobotics Jueying Lite 3 platform. The system grounds LLM-generated plans into executable ROS navigation commands using real-time sensor fusion (LiDAR, IMU, and Odometry). Experimental validation was conducted in a structured indoor environment across four distinct scenarios, ranging from single-room tasks to complex cross-zone navigation. The results demonstrate the system's robustness, achieving an aggregate success rate of over 90\% across all scenarios, validating the feasibility of offloaded LLM-based planning for autonomous quadruped deployment in real-world settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quadrupped-Legged Robot Movement Plan Generation using Large Language Model Muhtadin M., Vincentius Gusti Putu A. B. Zaini, Ahmad Purnomo, Mauridhi Hery Purnama, I Ketut Eddy Fatichah, Chastine Robotics Human-Computer Interaction Traditional control interfaces for quadruped robots often impose a high barrier to entry, requiring specialized technical knowledge for effective operation. To address this, this paper presents a novel control framework that integrates Large Language Models (LLMs) to enable intuitive, natural language-based navigation. We propose a distributed architecture where high-level instruction processing is offloaded to an external server to overcome the onboard computational constraints of the DeepRobotics Jueying Lite 3 platform. The system grounds LLM-generated plans into executable ROS navigation commands using real-time sensor fusion (LiDAR, IMU, and Odometry). Experimental validation was conducted in a structured indoor environment across four distinct scenarios, ranging from single-room tasks to complex cross-zone navigation. The results demonstrate the system's robustness, achieving an aggregate success rate of over 90\% across all scenarios, validating the feasibility of offloaded LLM-based planning for autonomous quadruped deployment in real-world settings. |
| title | Quadrupped-Legged Robot Movement Plan Generation using Large Language Model |
| topic | Robotics Human-Computer Interaction |
| url | https://arxiv.org/abs/2512.21293 |