Orientation-Free Neural Network-Based Bias Estimation for Low-Cost Stationary Accelerometers
This work improves the reliability of low-cost inertial sensors in navigation, robotics, and consumer devices by eliminating the need for leveled calibration, though it is incremental in advancing orientation-free calibration methods.
The paper tackles the problem of bias errors in low-cost accelerometers by proposing a model-free learning-based calibration method that estimates bias without requiring sensor orientation or rotation, achieving over 52% lower error than traditional techniques in experiments on a 13.39-hour dataset.
Low-cost micro-electromechanical accelerometers are widely used in navigation, robotics, and consumer devices for motion sensing and position estimation. However, their performance is often degraded by bias errors. To eliminate deterministic bias terms a calibration procedure is applied under stationary conditions. It requires accelerom- eter leveling or complex orientation-dependent calibration procedures. To overcome those requirements, in this paper we present a model-free learning-based calibration method that estimates accelerometer bias under stationary conditions, without requiring knowledge of the sensor orientation and without the need to rotate the sensors. The proposed approach provides a fast, practical, and scalable solution suitable for rapid field deployment. Experimental validation on a 13.39-hour dataset collected from six accelerometers shows that the proposed method consistently achieves error levels more than 52% lower than traditional techniques. On a broader scale, this work contributes to the advancement of accurate calibration methods in orientation-free scenarios. As a consequence, it improves the reliability of low-cost inertial sensors in diverse scientific and industrial applications and eliminates the need for leveled calibration.