Sensor Model Identification via Simultaneous Model Selection and State Variable Determination

2025-06-12

AI Summary

Manual modeling and calibration of novel sensors in localization systems pose significant challenges for non-expert users. Method: This paper proposes an unsupervised gray-box sensor model identification framework that jointly optimizes model selection, rigid-body calibration state estimation, and necessity assessment of a reference coordinate system—termed the “model–state–coordinate system” co-inference paradigm. A health metric is introduced to suppress erroneous model selection, while supporting dynamic library expansion and runtime modality integration. Parameter optimization leverages a likelihood-based search strategy to enhance automation and accuracy. Results: Evaluated on multimodal robotic platforms, the method significantly reduces configuration errors by non-specialist users and accelerates plug-and-play sensor integration, demonstrating robustness across diverse sensing modalities and operational conditions.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We present a method for the unattended gray-box identification of sensor models commonly used by localization algorithms in the field of robotics. The objective is to determine the most likely sensor model for a time series of unknown measurement data, given an extendable catalog of predefined sensor models. Sensor model definitions may require states for rigid-body calibrations and dedicated reference frames to replicate a measurement based on the robot's localization state. A health metric is introduced, which verifies the outcome of the selection process in order to detect false positives and facilitate reliable decision-making. In a second stage, an initial guess for identified calibration states is generated, and the necessity of sensor world reference frames is evaluated. The identified sensor model with its parameter information is then used to parameterize and initialize a state estimation application, thus ensuring a more accurate and robust integration of new sensor elements. This method is helpful for inexperienced users who want to identify the source and type of a measurement, sensor calibrations, or sensor reference frames. It will also be important in the field of modular multi-agent scenarios and modularized robotic platforms that are augmented by sensor modalities during runtime. Overall, this work aims to provide a simplified integration of sensor modalities to downstream applications and circumvent common pitfalls in the usage and development of localization approaches.

Problem

• Identify sensor models for unknown measurement data
• Detect false positives in sensor model selection
• Simplify sensor integration for modular robotic platforms

Innovation

• Simultaneous model selection and state variable determination
• Health metric for reliable model verification
• Automatic parameterization for state estimation applications