Sensor Model Identification via Simultaneous Model Selection and State Variable Determination
Christian Brommer, Alessandro Fornasier, Jan Steinbrener, Stephan Weiss
AI summary
Problem
Integrating new sensors into robotic localization systems typically requires expert knowledge to determine sensor type, extrinsic calibration, and reference frames, making the process time-consuming and error-prone. Existing approaches lack automated, runtime capabilities for unknown or gray-box sensor modalities.
Approach
The method simultaneously selects the most likely sensor model from a predefined catalog and estimates its calibration states and reference frame requirements using noisy localization data, while applying a health metric to filter out false positives.
Key results
- Automated identification of unknown sensor models and parameters from noisy data
- Simultaneous estimation of extrinsic calibration states and reference frame requirements
- Introduction of a health metric to validate selections and prevent false positives
- Successful validation on simulated data and real-world UAV and ground vehicle platforms
Why it matters
Enables seamless, expert-free sensor integration for modular robots and multi-agent systems, accelerating development and improving localization robustness.
Abstract
We present a method for the unattended gray-box identification of sensor models commonly used by localization algo- rithms 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 the 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 multiagent 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.