tactile sensor integration

The field of tactile surface modeling and data representation has long lacked a systematic treatment from a signal processing perspective, resulting in technical fragmentation across modeling, acquisition, rendering, and perception. Method: This paper presents the first unified taxonomy, comparative analysis, and critical review of tactile surface modeling methods—organized along core signal processing dimensions: signal sampling, feature extraction, compression coding, geometry–physics hybrid modeling, and cross-modal representation. Contribution/Results: We construct an end-to-end technical roadmap, identifying six fundamental modeling paradigms and three critical representation bottlenecks: (1) resolution–bandwidth trade-offs, (2) insufficient physical fidelity, and (3) challenges in cross-modal alignment. Our framework provides a scalable theoretical foundation and concrete technical pathways toward standardized tactile modeling, real-time rendering, and closed-loop perception.

Existing robotic tactile sensing faces challenges including high cost, complex integration, and unreliable feature extraction. To address these, this paper proposes a low-cost, compact, fully embedded multimodal fingertip sensor that integrates strain gauges (for 2D static force measurement) and contact microphones (for high-frequency vibration perception), achieving both wear resistance and rich tactile expressivity. A modality-coordinated scheduling strategy and signal-level fusion significantly enhance tactile information reliability. The sensor effectively compensates for perceptual deficiencies of vision-only systems under visual occlusion, enabling robust dexterous manipulation across 0%–100% occlusion levels: success rates for paper-cup counting and stacking/unstacking tasks reach 100%, substantially outperforming vision-only baselines. Key contributions include (1) a low-cost multimodal hardware architecture and (2) a tactile modality dynamic scheduling mechanism explicitly designed for closed-loop manipulation.

To address the challenge of adapting legacy tactile sensor data (e.g., BioTac) to modern image-based sensors (e.g., DIGIT), this paper proposes a cross-modal representation framework grounded in 3D surface deformation modeling. The core innovation is a calibration-free, physically interpretable deformation mesh serving as an intermediate representation; deformation field alignment and geometry-driven signal remapping enable end-to-end differentiable translation from low-dimensional BioTac time-series signals to high-resolution DIGIT images. Crucially, the method requires neither paired training data nor hardware calibration, facilitating heterogeneous sensor data reuse and interoperability. Experimental results demonstrate that synthesized DIGIT images retain over 92% of the original performance on downstream tasks—including slip detection and object recognition—thereby substantially reducing the cost and effort associated with collecting new sensor data.

This study addresses the challenge of simultaneously rendering multidimensional tactile cues—such as shape, stiffness, and friction—which existing tactile displays struggle to deliver with high fidelity, thereby limiting perceptual realism. The authors propose a 4×4 piezoelectric-driven tactile display that employs a three-stage micro-lever mechanism for displacement amplification and integrates Hall-effect sensors for closed-loop control. This design enables, for the first time, high-fidelity synchronous rendering of shape, stiffness, and friction within a single device. Building upon this hardware, the work further introduces an end-to-end vision-to-tactile translation framework and demonstrates a real-time tele-tactile palpation system operating across distances exceeding 1,000 kilometers. User studies show that first-time participants accurately identify object physical properties, and untrained volunteers achieved 100% accuracy in identifying and precisely localizing both the number and type of tumors in a breast phantom during remote trials.

This work addresses the challenge of simultaneously achieving high-precision 3D surface reconstruction, triaxial force estimation, and real-time performance in compact curved visual tactile sensors. The authors propose an end-to-end perception framework that integrates multispectral photometric stereo, boundary-prior Poisson depth reconstruction, and position-aware dynamic convolution (HyperForce), with FPGA-based hardware acceleration. By leveraging a single image sensor for synchronized multispectral imaging, the method significantly enhances both geometric and mechanical sensing capabilities: it achieves a depth reconstruction mean absolute error (MAE) of 0.0415 mm, normalized mean absolute errors (NMAE) of 2.74% and 2.39% for normal and tangential forces, respectively, and reduces processing latency from 3.26 ms to 1.09 ms. This represents the first demonstration of sub-millimeter accuracy and millisecond-level response in curved tactile sensing, enabling multi-object reconstruction, feedback-based grasping, and vibration measurement.

This work addresses the limitations of existing social touch sensing designs, which often rely on predefined configurations and lack empirical grounding for coverage of diverse touch behaviors and spatial layout. The authors propose a需求-driven design paradigm, leveraging a virtual reality platform with haptic feedback to collect full-body social touch data across multiple scenarios. Through high-resolution contact analysis and user studies, they identify nine common social touch gestures and release an open-source dataset comprising 5,520 interactions. Building on this empirical foundation, the study provides the first quantitative guidelines for tactile skin coverage and sensor density required on humanoid robots, establishing transferable design benchmarks applicable to robots of varying morphologies.

This study addresses the limited ability of existing fingertip haptic devices to effectively discriminate critical tactile features such as edges and surfaces, which constrains the realism of interactions in virtual reality. To overcome this limitation, the authors propose a lightweight (24.3 g), wearable fingertip haptic device featuring a novel dual-motor actuation mechanism that independently renders edge and surface contact feedback. The system integrates a 6×6 flexible pressure sensor array to capture distinct pressure distributions across various contact modes. User experiments demonstrate that participants achieved an average recognition accuracy of 93% across four contact conditions—combinations of edge versus surface and light versus heavy force—with a mean response time of 2.79 seconds, significantly enhancing both haptic immersion and interaction fidelity.

This work addresses the challenge of accurate contact torque estimation in whole-body physical human–robot interaction, where performance is often degraded by friction disturbances and ambiguities in sensor data. The authors propose a multimodal approach that fuses pneumatic tactile skin with motor current-based proprioception to implicitly disentangle external contact forces from residual friction effects. By leveraging tactile cues and employing a temporal convolutional network (TCN) to model the hysteresis inherent in stick–slip transitions, the method achieves high-fidelity, smooth multi-axis contact force reconstruction from initial contact without requiring explicit friction identification. Experimental validation on a tactile-skin-integrated robotic arm demonstrates substantial improvements over unimodal baselines, exhibiting enhanced sensitivity and responsiveness under both static and dynamic contact conditions, while simultaneously enabling reliable force estimation and kinesthetic teaching.

Existing teleoperation methods for handheld robotic demonstration are limited in contact-intensive bimanual tasks due to poor hardware adaptability, low data efficacy, and the absence of realistic tactile feedback, resulting in weak demonstrability and insufficient policy robustness. This work proposes TAMEn (Tactile-Aware Manipulation Engine), introducing a cross-morphology wearable interface that enables rapid adaptation to heterogeneous grippers. It integrates dual-modality trajectory capture—combining high-fidelity motion tracking with portable VR—and incorporates a tactile-visualization-based teleoperation framework to establish a human-in-the-loop recovery mechanism, thereby forming a pyramid-structured data pipeline. The proposed framework significantly enhances demonstration repeatability, improving task success rates from 34% to 75% across diverse bimanual manipulation scenarios. To foster community advancement, the authors open-source both the hardware designs and the collected dataset.

Current robotic systems lack low-cost, scalable, and easily integrable tactile sensing solutions, limiting their performance in fine manipulation and environmental interaction. This work proposes a plug-and-play flexible piezoresistive tactile sensing module featuring a sealed tri-layer composite structure (FPC–Velostat–FPC), enabling high-consistency batch fabrication and excellent mechanical compliance. The module integrates a high-density flexible sensor array, a compact multi-channel readout circuit, low-power serial communication, and flexible printed electrodes, supporting real-time tactile signal transmission at 100 Hz across diverse form factors such as fingertip sensors and large-area tactile pads. Designed for cross-platform compatibility, the system leverages GPU-accelerated tactile simulation and vision–tactile fusion, demonstrating successful applications in contact-aware decision-making, cross-embodiment skill transfer, and sim-to-real fine-tuning tasks.

This work addresses the lack of compact, multimodal tactile sensors for dexterous manipulation by proposing a flexible tactile sensor that integrates sensing of slip velocity, six-axis force/torque, and pressure distribution within a single deformable structure. For the first time, these three sensing modalities are unified in one design, enabling simultaneous acquisition of slip state and rich multidimensional tactile information. Fabricated using standard PCB processes and rapid prototyping techniques, the sensor offers low cost and ease of manufacturing. Experimental results demonstrate its robust performance across diverse materials and both planar and curved contact scenarios, significantly enhancing the perceptual capability and adaptability of dexterous manipulation systems.