NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observation
On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
Abstract (arXiv)
As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged between onboard collection and actionable ground intelligence. This paper presents NAVI-Orbital, a software system deployed on a Low Earth Orbit (LEO) spacecraft. On April 16, 2026, NAVI-Orbital achieved what is, to the authors' knowledge, the first in-orbit demonstration of a vision-language model performing autonomous multi-modal inference entirely onboard. NAVI-Orbital uses a local vision-language model (Gemma 3) to classify each captured scene, produce a text description of its content and the relationships between its features, and respond to operator follow-up via natural-language dialogue. The system is re-tasked through plain-English prompts in place of conventional command sequences, and is orchestrated by a graph-based state machine (LangGraph) coordinating dedicated agents for detection and dialogue. Results across ground benchmarking (88.16% accuracy on the 7,960-image curated AID benchmark), Flatsat validation, and live in-orbit captures of newly acquired, previously unseen Earth imagery (including uncorrected YAM-9 imagery, processed onboard with hardware-accelerated GPU inference and no fine-tuning for the flight instrument) demonstrate the feasibility of running foundation models on satellite-class edge computers to invert the conventional acquire-then-downlink-everything bandwidth profile through semantic compression of Earth observations in-orbit.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 12 of its 35 references that are in the map. First posted on arXiv 5 Jun 2026.
Builds on
12 of 35 references.
Closest ancestors · 2
Same direction, newest first
- 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov
- 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensing19 Jun
Other references · 10
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2025Gemma 3 Technical Reportcited by 1,686
- 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
- 2020Open-Vocabulary Object Detection Using Captionscited by 427
- 20218-bit Optimizers via Block-wise Quantizationcited by 395
- 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 343
- 2025TerraMind: Large-Scale Generative Multimodality for Earth Observationcited by 101
- 2024Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Modelscited by 27
- 2026Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instructcited by 7
- 2025ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomycited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection
- 2025Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Models
- 2025A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation
- 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks
- 2026Annotation Free Spacecraft Detection and Segmentation using Vision Language Models
- 2026LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
- 2026RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs
- 2026Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation