IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling
2026-04-09 • Artificial Intelligence
Artificial IntelligenceMultiagent SystemsNetworking and Internet Architecture
AI summaryⓘ
The authors address a challenge in smart systems that use many sensors: how to decide what to sense and when, rather than just analyzing all past data. They formalize this as Semantic-Spatial Sensor Scheduling and find that directly using large language models (LLMs) for planning doesn't work well. To solve this, they propose a new method called Spatial Trajectory Graph (STG) that turns planning into a checkable problem. They build a system named IoT-Brain and test it on a large camera network, showing it improves success and efficiency significantly compared to other methods.
Large Language Models (LLMs)Semantic-Spatial Sensor Scheduling (S3)Spatial Trajectory Graph (STG)Neuro-symbolic methodsSensor networksIoT-BrainGraph optimizationIntent-driven sensingSemantic-to-Physical MappingBenchmarking
Authors
Zhaomeng Zhou, Lan Zhang, Junyang Wang, Mu Yuan, Junda Lin, Jinke Song
Abstract
Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap. While large language models (LLMs) excel at semantic understanding, existing perception-centric pipelines operate retrospectively, overlooking the fundamental decision of what to sense and when. We formalize this proactive decision as Semantic-Spatial Sensor Scheduling (S3) and demonstrate that direct LLM planning is unreliable due to inherent gaps in representation, reasoning, and optimization. To bridge these gaps, we introduce the Spatial Trajectory Graph (STG), a neuro-symbolic paradigm governed by a verify-before-commit discipline that transforms open-ended planning into a verifiable graph optimization problem. Based on STG, we implement IoT-Brain, a concrete system embodiment, and construct TopoSense-Bench, a campus-scale benchmark with 5,250 natural-language queries across 2,510 cameras. Evaluations show that IoT-Brain boosts task success rate by 37.6% over the strongest search-intensive methods while running nearly 2 times faster and using 6.6 times fewer prompt tokens. In real-world deployment, it approaches the reliability upper bound while reducing 4.1 times network bandwidth, providing a foundational framework for LLMs to interact with the physical world with unprecedented reliability and efficiency.