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).
Multi-fingered hands offer great potential for compliant and robust grasping of unknown objects, yet their high-dimensional force control presents a significant challenge. This work addresses two key problems: (1) distributing forces across multiple contacts to counteract an object's weight, and (2) preventing rotational slip caused by gravitational torque when a grasp is distant from the object's center of mass. We address these challenges via tactile feedback and a Second-Order Cone Programming (SOCP)-based controller, without explicit torque modeling or slip detection. Our key insights are (1) rotational slip inevitably induces translational slip at some contact points for a multi-fingered grasp, and (2) the ratio of tangential to normal force at each contact is an effective early stability indicator. By actively constraining this ratio for each finger below the estimated friction coefficient, our controller maintains grasp stability against both translational and rotational slip. Real-world experiments on 12 diverse objects demonstrate the robustness and compliance of our approach.
Yubin Ke, Jiayi Chen, Hang Lv +2
Peking University · Galbot · Beijing Academy of Artificial Intelligence
Regulating grasping force to reduce slippage during dynamic object interaction remains a fundamental challenge in robotic manipulation, especially when objects are manipulated by multiple rolling contacts, have unknown properties (such as mass or surface conditions), and when external sensing is unreliable. In contrast, humans can quickly regulate grasping force by touch, even without visual cues. Inspired by this ability, we aim to enable robotic hands to rapidly explore objects and learn tactile-driven grasping force control under motion and limited sensing. We propose a physics-informed energy abstraction that models the object as a virtual energy container. The inconsistency between the fingers' applied power and the object's retained energy provides a physically grounded signal for inferring slip-aware stability. Building on this abstraction, we employ model-based learning and planning to efficiently model energy dynamics from tactile sensing and perform real-time grasping force optimization. Experiments in both simulation and hardware demonstrate that our method can learn grasping force control from scratch within minutes, effectively reduce slippage, and extend grasp duration across diverse motion-object pairs, all without relying on external sensing or prior object knowledge. (Video: https://youtu.be/l3TJV29Mo6w)
Cheng-Yu Kuo, Hirofumi Shin, Takamitsu Matsubara
Graduated School of Science and Technology, Nara Institute of Science and Technology, Nara 630-0192, Japan · Honda R&D, Ltd., Saitama 351-0114, Japan
Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present SlipSense, a multimodal tactile slip-detection framework built on TacV5, a compact sensor integrating a 32×32 piezoresistive array operating at 240 Hz and a 3-axis MEMS accelerometer operating at 8 kHz. The piezoresistive array captures spatial pressure distributions, while the accelerometer captures friction-induced vibrations, providing complementary slip cues. The framework performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. Experiments on a dataset of 1.4 million frames spanning 37 objects demonstrate the complementarity of the two modalities. SlipSense achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. When trained solely on UMI data, SlipSense generalizes zero-shot to a Tesollo dexterous hand, transferring across unseen objects, distinct sensor units, and robotic platforms without retraining.
Tong Jian, Aditya Thurvas Senthil Kumar, Xinyi Li +7