TouchRoller: A Rolling Optical Tactile Sensor for Rapid Assessment of Textures for Large Surface Areas

Abstract

Tactile sensing is important for robots to perceive the world as it captures the physical surface properties of the object with which it is in contact and is robust to illumination and colour variances. However, due to the limited sensing area and the resistance of their fixed surface when they are applied with relative motions to the object, current tactile sensors have to tap the tactile sensor on the target object a great number of times when assessing a large surface, i.e., pressing, lifting up, and shifting to another region. This process is ineffective and time-consuming. It is also undesirable to drag such sensors as this often damages the sensitive membrane of the sensor or the object. To address these problems, we propose a roller-based optical tactile sensor named TouchRoller, which can roll around its centre axis. It maintains being in contact with the assessed surface throughout the entire motion, allowing for efficient and continuous measurement. Extensive experiments showed that the TouchRoller sensor can cover a textured surface of 8 cm × 11 cm in a short time of 10 s, much more effectively than a flat optical tactile sensor (in 196 s). The reconstructed map of the texture from the collected tactile images has a high Structural Similarity Index (SSIM) of 0.31 on average when compared with the visual texture. In addition, the contacts on the sensor can be localised with a low localisation error, 2.63 mm in the centre regions and 7.66 mm on average. The proposed sensor will enable the fast assessment of large surfaces with high-resolution tactile sensing and the effective collection of tactile images.

Efficient Event-Based Robotic Grasping Perception using Hyperdimensional Computing

“…They processed the tactile data using Convolutional Neural Networks (CNN) for perception tasks related to clothing materials. Similarly, 11 introduced TouchRoller, a roller-based optical tactile sensor designed to efficiently measure large surface areas, providing high-resolution tactile images for texture assessment. Meanwhile, 34 demonstrated a novel design for a low-cost, high-resolution tactile sensor called DIGIT.…”

“…Moreover, traditional haptic sensing methods often employ visual sensors like Gelsight or DIGIT, which deduce object properties upon direct contact with a gel-based pad 10,11 . This contact-based process captures complex details about the object's surface, such as texture and shape, thereby enhancing grasping quality.…”

Robotic perception of object properties using tactile sensing

“…Hence, several studies have explored the integration of rotational movement into tactile sensors to enhance functionality. TouchRoller [20] was proposed to rapidly reconstruct large contact surfaces through surface rotation, while TacRot [21] utilises a rotatable surface to facilitate in-hand object manipulation. The tactile-reactive roller grasper (TRRG) [22] integrates compliant, steerable cylindrical fingertips for improved manipulation.…”

Improving the Representation and Extraction of Contact Information in Vision-based Tactile Sensors Using Continuous Marker Pattern

“…This design permits the sensor to roll in one direction, continuously acquiring data and expanding the contact area. This cylindrical structure of the vision-based tactile sensor was capable of continuously acquiring tactile data during motion for application in inspection tasks [19] [20]. However, due to their non-planar shape, whether cylindrical or generally curved, the acquired tactile information is not at a uniform depth level.…”