facility managers

Abstract: Reliable indoor positioning remains a central unsolved problem in spatial computing. Existing systems depend on fixed, provider-owned infrastructure (WiFi access points, Bluetooth beacons, UWB anchors) whose deployment, calibration, and ownership models limit their scalability. Meanwhile, personal trackers, wearables, smart luggage tags, and tagged industrial assets are becoming densely embedded in the very indoor environments where positioning infrastructure is weakest. This paper argues that these devices point to a new class of spatial infrastructure: non-stationary, user-owned, and semantically interpretable. We present TrackerNet, a vision for transforming personal trackers from private object-finders into a decentralized substrate for ubiquitous positioning. The key shift is to stop treating anchor mobility as noise: TrackerNet models mobile anchors as probabilistic references whose stability, trust, and semantic role are inferred over time, reframing indoor localization as non-stationary spatial graph inference. We identify three research frontiers (non-stationary SLAM over mobile, intermittently visible anchors; semantic reasoning that connects ranging signals to interpretations of anchor behavior; and consent-based, privacy-preserving governance for cross-vendor cooperation) and a staged pathway by which the vendors and venue operators who already run tracker networks can realize them with academia. We do not claim a finished system; we define a research agenda.

Abstract: Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret. Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require substantial technical expertise and provide limited flexibility for dynamic, context-aware inquiry. Conversational XAI systems offer a promising alternative; however, previous approaches, such as TalkToModel, were constrained by rigid custom grammars and achieved only 76.8% intent-parsing accuracy. This paper introduces the Explainability Assistant, an open-source conversational XAI system that leverages the function-calling capabilities of modern Large Language Models (LLMs) to overcome these limitations. The system achieves 94% intent-parsing accuracy, supports flexible natural language interaction, and adapts to different ML problem types without task-specific fine-tuning. We present the system's architecture and report results from a comparative evaluation conducted with energy domain specialists, contrasting the Explainability Assistant with a traditional XAI dashboard. The evaluation suggests improved usability and consistent task accuracy, with all experts unanimously preferring the conversational interface for practical use.