The field of tactile sensing and haptic interaction is rapidly advancing, with a focus on developing innovative methods for integrating tactile, language, and vision modalities. Researchers are exploring new approaches to collaborative representation learning, physics-based simulation, and sensor design to enhance the performance of tactile sensing systems. Notable developments include the introduction of sensor-aware modulators, unified bridging adapters, and biomorphic tactile sensors. These advancements have the potential to significantly improve sensor-agnostic representation learning, cross-modal alignment, and robust interaction in unstructured environments.

Some noteworthy papers in this area include: Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities, which proposes a CLIP-based tactile-language-vision collaborative representation learning method. SimTac: A Physics-Based Simulator for Vision-Based Tactile Sensing with Biomorphic Structures, which presents a physics-based simulation framework for the design and validation of biomorphic tactile sensors. Tactile Data Recording System for Clothing with Motion-Controlled Robotic Sliding, which proposes a robotic arm-based system for collecting tactile data from intact garments. Image-based Morphological Characterization of Filamentous Biological Structures with Non-constant Curvature Shape Feature, which proposes an image-based method for analyzing shape changes over time in tendrils when mechano-stimulated in different portions of their body. Multilaminate piezoelectric PVDF actuators to enhance performance of soft micro robots, which develops and characterizes multilayer PVDF actuators with parallel voltage distribution across each layer. Air-Chamber Based Soft Six-Axis Force/Torque Sensor for Human-Robot Interaction, which introduces a soft air-chamber type six-axis force/torque sensor with 16-channel barometers. Monolithic Units: Actuation, Sensing, and Simulation for Integrated Soft Robot Design, which introduces the Monolithic Unit, an actuator-lattice-sensor building block for soft robotics. Dual-Variable Force Characterisation method for Human-Robot Interaction in Wearable Robotics, which introduces a dual-variable characterisation method involving normal and tangential forces. SPHaptics: A Real-Time Bidirectional Haptic Interaction Framework for Coupled Rigid-Soft Body and Lagrangian Fluid Simulation in Virtual Environments, which presents a unified framework for real-time, bidirectional haptic interaction with rigid bodies, deformable objects, and Lagrangian fluids in virtual reality. Heterogeneous Stroke: Using Unique Vibration Cues to Improve the Wrist-Worn Spatiotemporal Tactile Display, which presents a design concept for improving the recognition accuracy of spatiotemporal tactile patterns on a wrist-worn tactile display. Funabot-Upper: McKibben Actuated Haptic Suit Inducing Kinesthetic Perceptions in Trunk, Shoulder, Elbow, and Wrist, which presents a wearable haptic suit that enables users to perceive 14 upper-body motions. Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies, which investigates a proof of concept for an artificial palpation method based on self-supervised learning.