Static and Dynamic Representations for Tactile Contact-Angle Estimation with Event-Based Sensors
For robotic manipulation requiring high-frequency tactile angle estimation, this work provides a low-latency event-based approach, though the improvements are incremental over existing methods.
This paper investigates contact-angle estimation using event streams from an event-based tactile sensor (NeuroTac), comparing three spatial contour representations. The static representation achieved the best performance with a mean overall MAE of 0.160° during continuous rolling and 0.251° during motion interruptions, with all pipelines exhibiting P99 latency below 10 ms.
Event-based tactile sensing offers low-latency signal acquisition for contact-rich robotic interaction. This paper investigates contact-angle estimation using event streams from an event-based tactile sensor (NeuroTac) and compares three event-derived spatial contour representations: a dynamic representation capturing recent event activity, a static representation recovering a more persistent contact state, and their combined representation. Across the evaluated motion scenarios, all representation pipelines exhibited P99 processing latency below 10 ms at all tested sampling intervals, demonstrating their potential for high-frequency event-based tactile angle estimation in robotic manipulation. The static representation consistently achieved marginally better performance than the dynamic and combined representations under scenario-specific training, yielding a mean overall MAE of 0.160° during continuous sensor rolling and a stop-phase mean MAE of 0.251° during randomly inserted motion interruptions. It also exhibited smaller performance fluctuations across speed and indentation depth variations than the other two representations.