Elevator, Escalator or Neither? Classifying Pedestrian Conveyor State Using Inertial Navigation System

2024-05-06

arXiv.org

AI Summary

To address the challenge of real-time classification of pedestrian transport states (elevator, escalator, or static/no-transport) in indoor navigation, this paper proposes the first on-device, robust recognition method leveraging only smartphone-integrated IMU signals (accelerometer, gyroscope, magnetometer), eliminating reliance on dedicated wearables or assumptions about walking behavior. We introduce ELESON, a lightweight deep learning model featuring: (i) a causal feature disentanglement mechanism to separate intrinsic transport dynamics from gait-induced disturbances; (ii) a magnetometer-specific feature extractor capturing distinctive magnetic field patterns induced by elevators and escalators; and (iii) an evidential classifier that outputs interpretable, uncertainty-aware state confidence scores. Evaluated on a real-world dataset, ELESON achieves a 14% improvement in F1-score and an AUROC of 0.81, demonstrating high accuracy, strong confidence calibration, and low computational overhead suitable for edge deployment.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Knowing a pedestrian's conveyor state of"elevator,""escalator,"or"neither"is fundamental in many applications such as indoor navigation and people flow management. We study, for the first time, classifying the conveyor state of a pedestrian, given the multimodal INS (inertial navigation system) readings of accelerometer, gyroscope and magnetometer sampled from the pedestrian phone. This problem is challenging because the INS signals of the conveyor state are entangled with unpredictable independent pedestrian motions, confusing the classification process. We propose ELESON, a novel, effective and lightweight INS-based deep learning approach to classify whether a pedestrian is in an elevator, escalator or neither. ELESON utilizes a causal feature extractor to disentangle the conveyor state from pedestrian motion, and a magnetic feature extractor to capture the unique magnetic characteristics of moving elevators and escalators. Given the results of the extractors, it then employs an evidential state classifier to estimate the confidence of the conveyor states. Based on extensive experiments conducted on real pedestrian data, we demonstrate that ELESON outperforms significantly previous INS-based classification approaches, achieving 14% improvement in F1 score, strong confidence discriminability of 0.81 in AUROC (Area Under the Receiver Operating Characteristics), and low computational and memory requirements for smartphone deployment.

Problem

• Classify pedestrian conveyor state using smartphone sensors
• Overcome reliance on specialized sensors or behavior assumptions
• Extract conveyor features independent of pedestrian behavior

Innovation

• Uses smartphone INS for conveyor state classification
• Employs causal decomposition and adversarial learning
• Lightweight deep-learning with evidential classifier