Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.05547 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914079003639808 |
|---|---|
| author | Vorobiov, Eugene Mahmood, Ammar Jaleel Rezvani, Salim Chhabra, Robin |
| author_facet | Vorobiov, Eugene Mahmood, Ammar Jaleel Rezvani, Salim Chhabra, Robin |
| contents | We present ARRC (Advanced Reasoning Robot Control), a practical system that connects natural-language instructions to safe local robotic control by combining Retrieval-Augmented Generation (RAG) with RGB-D perception and guarded execution on an affordable robot arm. The system indexes curated robot knowledge (movement patterns, task templates, and safety heuristics) in a vector database, retrieves task-relevant context for each instruction, and conditions a large language model (LLM) to produce JSON-structured action plans. Plans are executed on a UFactory xArm 850 fitted with a Dynamixel-driven parallel gripper and an Intel RealSense D435 camera. Perception uses AprilTag detections fused with depth to produce object-centric metric poses. Execution is enforced via software safety gates: workspace bounds, speed and force caps, timeouts, and bounded retries. We describe the architecture, knowledge design, integration choices, and a reproducible evaluation protocol for tabletop scan, approach, and pick-place tasks. Experimental results demonstrate the efficacy of the proposed approach. Our design shows that RAG-based planning can substantially improve plan validity and adaptability while keeping perception and low-level control local to the robot. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05547 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ARRC: Advanced Reasoning Robot Control - Knowledge-Driven Autonomous Manipulation Using Retrieval-Augmented Generation Vorobiov, Eugene Mahmood, Ammar Jaleel Rezvani, Salim Chhabra, Robin Robotics We present ARRC (Advanced Reasoning Robot Control), a practical system that connects natural-language instructions to safe local robotic control by combining Retrieval-Augmented Generation (RAG) with RGB-D perception and guarded execution on an affordable robot arm. The system indexes curated robot knowledge (movement patterns, task templates, and safety heuristics) in a vector database, retrieves task-relevant context for each instruction, and conditions a large language model (LLM) to produce JSON-structured action plans. Plans are executed on a UFactory xArm 850 fitted with a Dynamixel-driven parallel gripper and an Intel RealSense D435 camera. Perception uses AprilTag detections fused with depth to produce object-centric metric poses. Execution is enforced via software safety gates: workspace bounds, speed and force caps, timeouts, and bounded retries. We describe the architecture, knowledge design, integration choices, and a reproducible evaluation protocol for tabletop scan, approach, and pick-place tasks. Experimental results demonstrate the efficacy of the proposed approach. Our design shows that RAG-based planning can substantially improve plan validity and adaptability while keeping perception and low-level control local to the robot. |
| title | ARRC: Advanced Reasoning Robot Control - Knowledge-Driven Autonomous Manipulation Using Retrieval-Augmented Generation |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.05547 |