Event Augmentation for Contact Force Measurements

Neuromorphic vision sensor is an attractive technology that offers high dynamic range, and low latency which are crucial in robotic applications. However, the lack of event-based data this field, limits sensors’ performance a real-world environments. In paper, we propose novel augmentation technique for neuromorphic sensors to improve contact force measurements from events. The proposed method shifts proportion events across time domain, ’Temporal Event Shifting’, augment dataset. A new set grasping experiments performed validate analyze effectiveness measurements. results indicate temporal event shifting highly effective improves models’ accuracy estimation by thirty percent without performing experiments.