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

--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. T o 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 V ector 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. NOMAL Y detection is essential for ensuring the safety and reliability of many safety-critical systems, including industrial automation [1], aerospace [2] and robotic systems [3], [4]. In the context of autonomous mobile robots, the ability to detect anomalies, such as mechanical faults or unexpected collisions, is important for maintaining safe operations and preventing potential hazards. With the increasing deployment of robots in dynamic and unstructured environments, robust anomaly detection has become an indispensable component of autonomous operation.