We build a low-level reflex control layer driven by fast tactile feedback for multifinger grasp stabilization. Our hybrid approach combines learned tactile slip detection with model-based internal-force control to halt in-hand slip while preserving the object-level wrench. The multimodal tactile stack integrates piezoelectric sensing (PzE) for fast slip cues and piezoresistive arrays (PzR) for contact localization, enabling online construction of a contact-centric grasp representation without prior object knowledge. Experiments demonstrate reactive stabilization of multifingered grasps under external perturbations, without explicit friction models or direct force sensing. In controlled trials, slip onset is detected after 20.4 +/- 6 ms. The framework yields a theoretical grasp response latency on the order of 30 ms, with grasp-model updates in less than 5 ms and internal-force selection in about 4 ms. The analysis supports the feasibility of sub-50 ms tactile-driven grasp responses, aligned with human reflex baselines.
Figures & tables
Fig. 1: Modular 3-phalange finger with hybrid tactile pads. Each phalanx combines spatial localization (PzR) and fast dynamics sensing (PzE) for the RSC pipeline.
Fig. 2: Overview of the Reactive Slip Control (RSC) pipeline for multifingered grippers. Forces are coordinated across fingers to increase grip without disturbing the object. The system continuously monitors the contact state via tactile sensing, integrating both modalities of the hybrid PzE and PzR sensors. Piezoelectric sensors capture friction vibrations to detect slip through machine learning with spectral features. Piezoresistive arrays provide pressure distribution and contact localization enabling online construction of the grasp matrix G and selection of an internal-force profile f0⋆ in the null-space via a quadratic program. Upon slip detection, this internal-force update reinforces contact stability while preserving the object-level wrench.
Fig. 3: Slip control scenario with predefined force trajectories, illustrating slip–detection and control dynamics under continuous grasp-force increase. The external load increases from 3 N to 7 N, inducing object motion. After a predetermined delay of 350 ms, the grasp force is progressively increased from 8 N to 16 N over 150 ms, providing sufficient friction to halt the slip. Slip-detection delays are 30 ms for onset and 130 ms for offset.
Fig. 4: Reactive slip control in a symmetrical grasp with two parallel fingers. Equilibrium is trivially obtained by applying forces uniformly across both fingers. PzR sensors show increasing contact pressure. The slip event can be detected independently by any finger in contact with the object, providing redundancy and robustness.
Fig. 5: Reactive slip control with traction force increasing from 2 N to 6 N, inducing slip. The theoretical detection delay is 20 ms, but RSC happens after 220 ms due to setup delays. Over this period, the traveled distance is 3 mm.
Fig. 6: Reactive slip control in an asymmetric three-finger planar grasp. An external traction force of 10 N is applied to the object, inducing slip. Reactive slip control is triggered after 130 ms, during which the object travels 19 mm. Slip events are detected from PzE signals (FFT-based features), and grip is reinforced to stop the object motion. Forces must be coordinated across fingers to preserve object stability. This internal-force update is computed in the null-space of the grasp matrix, with grasp geometry estimated from PzR sensors (tactile) and forward kinematics (proprioception).