Unsupervised Anomaly Detection for Autonomous Robots via Mahalanobis SVDD with Audio-IMU Fusion

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Yizhuo, Zhao, Jiulin, Xu, Xinhang, Cao, Kun, Yuan, Shenghai, Xie, Lihua
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913828290166784
author Yang, Yizhuo
Zhao, Jiulin
Xu, Xinhang
Cao, Kun
Yuan, Shenghai
Xie, Lihua
author_facet Yang, Yizhuo
Zhao, Jiulin
Xu, Xinhang
Cao, Kun
Yuan, Shenghai
Xie, Lihua
contents Reliable anomaly detection is essential for ensuring the safety of autonomous robots, particularly when conventional detection systems based on vision or LiDAR become unreliable in adverse or unpredictable conditions. In such scenarios, alternative sensing modalities are needed to provide timely and robust feedback. To this end, we explore the use of audio and inertial measurement unit (IMU) sensors to detect underlying anomalies in autonomous mobile robots, such as collisions and internal mechanical faults. Furthermore, to address the challenge of limited labeled anomaly data, we propose an unsupervised anomaly detection framework based on Mahalanobis Support Vector Data Description (M-SVDD). In contrast to conventional SVDD methods that rely on Euclidean distance and assume isotropic feature distributions, our approach employs the Mahalanobis distance to adaptively scale feature dimensions and capture inter-feature correlations, enabling more expressive decision boundaries. In addition, a reconstruction-based auxiliary branch is introduced to preserve feature diversity and prevent representation collapse, further enhancing the robustness of anomaly detection. Extensive experiments on a collected mobile robot dataset and four public datasets demonstrate the effectiveness of the proposed method, as shown in the video https://youtu.be/yh1tn6DDD4A. Code and dataset are available at https://github.com/jamesyang7/M-SVDD.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Anomaly Detection for Autonomous Robots via Mahalanobis SVDD with Audio-IMU Fusion
Yang, Yizhuo
Zhao, Jiulin
Xu, Xinhang
Cao, Kun
Yuan, Shenghai
Xie, Lihua
Robotics
Reliable anomaly detection is essential for ensuring the safety of autonomous robots, particularly when conventional detection systems based on vision or LiDAR become unreliable in adverse or unpredictable conditions. In such scenarios, alternative sensing modalities are needed to provide timely and robust feedback. To this end, we explore the use of audio and inertial measurement unit (IMU) sensors to detect underlying anomalies in autonomous mobile robots, such as collisions and internal mechanical faults. Furthermore, to address the challenge of limited labeled anomaly data, we propose an unsupervised anomaly detection framework based on Mahalanobis Support Vector Data Description (M-SVDD). In contrast to conventional SVDD methods that rely on Euclidean distance and assume isotropic feature distributions, our approach employs the Mahalanobis distance to adaptively scale feature dimensions and capture inter-feature correlations, enabling more expressive decision boundaries. In addition, a reconstruction-based auxiliary branch is introduced to preserve feature diversity and prevent representation collapse, further enhancing the robustness of anomaly detection. Extensive experiments on a collected mobile robot dataset and four public datasets demonstrate the effectiveness of the proposed method, as shown in the video https://youtu.be/yh1tn6DDD4A. Code and dataset are available at https://github.com/jamesyang7/M-SVDD.
title Unsupervised Anomaly Detection for Autonomous Robots via Mahalanobis SVDD with Audio-IMU Fusion
topic Robotics
url https://arxiv.org/abs/2505.05811