SpikingTac: A Miniaturized Neuromorphic Visuotactile Sensor for High-Precision Dynamic Tactile Imprint Tracking
🤖 AI Summary
This work addresses the limitations of conventional bulky event cameras that hinder the deployment of high-speed event-driven tactile sensors in anthropomorphic dynamic manipulation. The authors propose SpikingTac, a miniaturized neuromorphic visuotactile sensor integrating a custom-designed micro event camera module and a global dynamic state map. To effectively compensate for viscoelastic hysteresis in silicone-based tactile materials, they introduce an innovative incremental update rule informed by material hysteresis characteristics and a spatial gain damping mechanism. Coupled with an unsupervised denoising network, the system achieves high-precision and stable tactile tracking: it attains 100% zero-return success rate with an average offset of 0.8039 pixels, reduces obstacle-avoidance overshoot to 6.2 mm (a fivefold improvement over frame-based sensors), and achieves RMSEs of 0.0952 mm and 0.0452 mm in position and radius estimation, respectively.
Application Category
📝 Abstract
High-speed event-driven tactile sensors are essential for achieving human-like dynamic manipulation, yet their integration is often limited by the bulkiness of standard event cameras. This paper presents SpikingTac, a miniaturized, highly integrated neuromorphic tactile sensor featuring a custom standalone event camera module, achieved with a total material cost of less than \$150. We construct a global dynamic state map coupled with an unsupervised denoising network to enable precise tracking at a 1000~Hz perception rate and 350~Hz tracking frequency. Addressing the viscoelastic hysteresis of silicone elastomers, we propose a hysteresis-aware incremental update law with a spatial gain damping mechanism. Experimental results demonstrate exceptional zero-point stability, achieving a 100\% return-to-origin success rate with a minimal mean bias of 0.8039 pixels, even under extreme torsional deformations. In dynamic tasks, SpikingTac limits the obstacle-avoidance overshoot to 6.2~mm, representing a 5-fold performance improvement over conventional frame-based sensors. Furthermore, the sensor achieves sub-millimeter geometric accuracy, with Root Mean Square Error (RMSE) of 0.0952~mm in localization and 0.0452~mm in radius measurement.
Problem
Research questions and friction points this paper is trying to address.
spiking tactile sensor
neuromorphic vision
dynamic tactile tracking
miniaturized sensor
viscoelastic hysteresis
Innovation
Methods, ideas, or system contributions that make the work stand out.
neuromorphic tactile sensor
event-driven sensing
viscoelastic hysteresis compensation
unsupervised denoising
high-precision tactile tracking
🔎 Similar Papers
No similar papers found.
