1. Zero Velocity Detection Without Motion Pre-Classification: Uniform AI Model for All Pedestrian Motions (UMAM)
- Author
-
Yacouba Kone, Ni Zhu, Valérie Renaudin, Géolocalisation (AME-GEOLOC), and Université Gustave Eiffel
- Subjects
Computer science ,ZERO-VELOCITY DETECTION ,LEGGED LOCOMOTION ,01 natural sciences ,Field (computer science) ,EXTRACTION DE CARACTERISTIQUES ,[SPI]Engineering Sciences [physics] ,Velocity Moments ,ZERO VELOCITY UPDATE ,SENSORS ,UNITE DE MESURE INERTIELLE (IMU) ,Instrumentation ,CHAUSSURES ,ESSAI EN MILIEU OUVERT ,Detector ,Zero (complex analysis) ,LOCOMOTION SUR PIED ,UNITE DE MESURE ,PEDESTRIAN NAVIGATION ,SITES D&apos ,NAVIGATION ,MACHINE LEARNING ,Algorithm ,OPEN AREA TEST SITES ,FEATURE EXTRACTION ,FOOT ,CAPTEURS ,ESSAI ,Computation ,AUTOMATIQUE ,DETECTION DE LA VITESSE NULLE ,INERTIAL SENSORS ,APPRENTISSAGE ,FOOTWEAR ,DISPOSITIFS DE POSITIONNEMENT MONTES SUR LE PIED ,PIETON ,Set (abstract data type) ,MISE A JOUR DE LA VITESSE NULLE ,Inertial measurement unit ,NAVIGATION PEDESTRE ,PIED ,CAPTEUR ,Electrical and Electronic Engineering ,CAPTEURS INERTIELS ,APPRENTISSAGE AUTOMATIQUE ,Propagation of uncertainty ,FOOT-MOUNTED POSITIONING DEVICES ,NAVIGATION INERTIELLE ,010401 analytical chemistry ,CAPTEUR INERTIEL ,0104 chemical sciences ,INERTIAL MEASUREMENT UNIT (IMU) - Abstract
Foot-mounted positioning devices are becoming more and more popular in the different application field. For example, inertial sensors are now embedded in safety shoes to monitor security. They allow positioning with zero velocity update to bound the error growth of foot-mounted inertial sensors. High positioning accuracy depends on robust zero velocity detector (ZVD). Existing Artificial Intelligent (AI)-based methods classify the pedestrian dynamics to adjust ZVD at the cost of high computation costs and error propagation from miss-classification. We propose a machine learning model to detect zero velocity moments without any pre-classification step, named Uniform AI Model for All pedestrian Motions (UMAM). Performance is evaluated by benchmarking on two new subjects of opposite gender and different size, not included in the training data set, over complex indoor/outdoor paths of 2 km for subject 1 and 2.1 km for subject 2. We obtain an average 2D loop closure error of less than 0.37%.
- Published
- 2022
- Full Text
- View/download PDF