ATLASv2: LLM-Guided Adaptive Landmark Acquisition and Navigation on the Edge
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915243596185600 |
|---|---|
| author | Walczak, Mikolaj Kallakuri, Uttej Mohsenin, Tinoosh |
| author_facet | Walczak, Mikolaj Kallakuri, Uttej Mohsenin, Tinoosh |
| contents | Autonomous systems deployed on edge devices face significant challenges, including resource constraints, real-time processing demands, and adapting to dynamic environments. This work introduces ATLASv2, a novel system that integrates a fine-tuned TinyLLM, real-time object detection, and efficient path planning to enable hierarchical, multi-task navigation and manipulation all on the edge device, Jetson Nano. ATLASv2 dynamically expands its navigable landmarks by detecting and localizing objects in the environment which are saved to its internal knowledge base to be used for future task execution. We evaluate ATLASv2 in real-world environments, including a handcrafted home and office setting constructed with diverse objects and landmarks. Results show that ATLASv2 effectively interprets natural language instructions, decomposes them into low-level actions, and executes tasks with high success rates. By leveraging generative AI in a fully on-board framework, ATLASv2 achieves optimized resource utilization with minimal prompting latency and power consumption, bridging the gap between simulated environments and real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10784 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ATLASv2: LLM-Guided Adaptive Landmark Acquisition and Navigation on the Edge Walczak, Mikolaj Kallakuri, Uttej Mohsenin, Tinoosh Robotics Artificial Intelligence Autonomous systems deployed on edge devices face significant challenges, including resource constraints, real-time processing demands, and adapting to dynamic environments. This work introduces ATLASv2, a novel system that integrates a fine-tuned TinyLLM, real-time object detection, and efficient path planning to enable hierarchical, multi-task navigation and manipulation all on the edge device, Jetson Nano. ATLASv2 dynamically expands its navigable landmarks by detecting and localizing objects in the environment which are saved to its internal knowledge base to be used for future task execution. We evaluate ATLASv2 in real-world environments, including a handcrafted home and office setting constructed with diverse objects and landmarks. Results show that ATLASv2 effectively interprets natural language instructions, decomposes them into low-level actions, and executes tasks with high success rates. By leveraging generative AI in a fully on-board framework, ATLASv2 achieves optimized resource utilization with minimal prompting latency and power consumption, bridging the gap between simulated environments and real-world applications. |
| title | ATLASv2: LLM-Guided Adaptive Landmark Acquisition and Navigation on the Edge |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2504.10784 |