CrystalTac: 3D-Printed Vision-Based Tactile Sensor Family through Rapid Monolithic Manufacturing Technique

TL;DR

CrystalTac demonstrates that rapid monolithic manufacturing using multi-material 3D printing can produce a family of vision-based tactile sensors with varied sensing mechanisms (IMM, MDM, MFM, and multi-mechanism fusion). The work delivers five CrystalTac variants (C-Sight, C-Tac, C-SighTac, Vi-C-Tac, Vi-C-Sight) and shows substantial improvements in design flexibility and manufacturing cost, while validating performance through object and texture recognition and see-through-skin experiments. It also provides detailed analyses of sub-component feasibility, marker designs, and customization capabilities, highlighting how monolithic manufacturing can unify design and creation in VBTS development. The results indicate strong sensing performance, meaningful cost reductions with batch printing, and broad customization potential, establishing CrystalTac as a foundational template for future VBTS innovation. Overall, the study argues that monolithic manufacturing can accelerate VBTS deployment and enable versatile tactile sensing for dexterous manipulation and human–robot interaction.

Abstract

Recently, vision-based tactile sensors (VBTSs) have gained popularity in robotics systems. The sensing mechanisms of most VBTSs can be categorised based on the type of tactile features they capture. Each category requires specific structural designs to convert physical contact into optical information. The complex architectures of VBTSs pose challenges for traditional manufacturing techniques in terms of design flexibility, cost-effectiveness, and quality stability. Previous research has shown that monolithic manufacturing using multi-material 3D printing technology can partially address these challenges. This study introduces the CrystalTac family, a series of VBTSs designed with a unique sensing mechanism and fabricated through rapid monolithic manufacturing. Case studies on CrystalTac-type sensors demonstrate their effective performance in tasks involving tactile perception, along with impressive cost-effectiveness and design flexibility. The CrystalTac family aims to highlight the potential of monolithic manufacturing in VBTS development and inspire further research in tactile sensing and manipulation.

Figures (11)

• Figure 1: Typical tactile sensing mechanism of known VBTSs. A: IMM, such as GelSight and 9DTac yuan2017gelsightlin20239dtact. B: MDM, such as TacTip and ChromaTouch ward2018tactipscharff2022rapid. C/D/E: multi-mechanism fusion consisting of IMM+MDM, MDM+MFM, and IMM+MFM, such as GelSlim, Finger Vision and TIRgel taylor2022gelslimyamaguchi2016combiningzhang2023tirgel.
• Figure 2: Representative attributes of VBTS. A(Base): the external supporting structure; B(Lens): the transparent medium for camera imaging; C(Elastormer): the flexible main body; D(Marker): the physical medium for visualizing tactile information; E(Skin): the external layer for shading or protection; F(Coating): the functional layer for contact feature mapping; G(Assembly): the method of installing the aforementioned sub-components, involving various tools, workflows, and mechanisms.
• Figure 3: A: The practical feasibility of CrystalTac depends on the suitable sensor design and the setup limitations of the print materials. B: Monolithic manufacturing integrates component fabrication and assembly into a single process. C: The finished CrystalTac is ready for use after removing support structures, either through water spray or manual tools. D: CrystalTac can realise complicated structural designs.
• Figure 5: A: Setup for the object recognition using C-Tac with single-layer dot markers. (a) The marker pattern distributions change with different contact objects. (b) The marker features are effective for precise object identification. B: Setup for the object and texture hybrid recognition using Vi-C-Tac with double-layer markers. (a) By covering the fabric, the sensing of both visual and tactile features can be simultaneously evaluated. (b) Fine textures are clearly visualised, while object shape mapping relies primarily on double-layer marker patterns. (c) Both objects and textures can be identified using Vi-C-Tac.
• Figure 6: A: Setup for the see-through-skin exploration using Vi-C-Sight. (a) Pure Agilus30 Clear provides a clear view of the visual-tactile fusion feature. (b) Both the fine texture of the fabric and the geometric shape of the rigid base can be captured. B: Evaluation of CrystalTac's manufacturing cost. (a) The maximum capacity for Crystaltac using the Digit base is 48 units, compared to 64 units using a customised base. (b) As print batch increases, both the manufacturing time and cost decrease gradually until a stable level.