Non-Intrusive Contactless Gesture Recognition for Human-Robot Interaction

Abstract

As robots increasingly integrate into collaborative and assistive environments, interpretation of natural gesture becomes crucial for effective and efficient human-robot interaction. While vision-based gesture recognition systems face privacy concerns and performance limitations under occlusion and varying lighting conditions, wearable sensor approaches often compromise user comfort and interaction naturalness. These challenges necessitate alternative approaches that balance recognition accuracy with user acceptance in real-world deployment scenarios. This work proposes a lightweight transformer-based feature extractor, in which test-time augmentation with majority voting is employed during inference to enhance classification performance. With approximately 2 M trainable parameters, the network maintains reasonable efficiency on modern acceleration hardware. Its modular architecture also indicates an easy adaptation to a variety of sensor configurations. It reached an overall accuracy of 97.21%, with similarly high scores for f1-score, precision, and recall. The pipeline inference time of 16 ms on GPU and 40 ms on CPU demonstrate its suitability for real-time applications in collaborative robotics.