Robotic Affection -- Opportunities of AI-based haptic interactions to improve social robotic touch through a multi-deep-learning approach

2026-05-04

AI Summary

Social robots remain hindered by the “tactile uncanny valley” when attempting emotionally expressive haptic interactions such as handshakes or soothing touches. This work proposes a neurobiologically inspired multimodal deep learning architecture that, for the first time, formulates affective touch modeling as a distributed perception task rather than a singular motor control problem. By introducing a closed-loop perception mechanism with peer-to-peer state sharing, the approach enables coordinated subtask execution. Integrating biomimetic tactile modeling with a Sim-to-Real cumulatively evolvable framework, the method facilitates interdisciplinary collaborative development and offers a novel pathway toward unified, scalable, and expressive tactile systems for social robots, thereby advancing convergent innovation across artificial intelligence, haptics, and robotics.

Abstract

Despite the advancement in robotic grasping and dexterity through haptic information, affective social touch, such as handshaking or reassuring stroking, remains a major challenge in Human-Robot-Interaction. This position paper examines current progress and limitations across artificial intelligence, haptics and robotics research, and proposes a novel multi-model architecture to address these gaps. Drawing inspiration from neurobiology, we decompose affective touch into distinct, specialized subtasks models. By treating affective touch as a distributed, closed-loop perceptual task rather than a monolithic motoric movement, we aim to overcome the "haptic uncanny valley" through a peer-to-peer, state-sharing framework. Our approach supports scalable and cumulative development within a Sim-to-Real pipeline, fostering interdisciplinary collaboration. By enabling haptics, AI, and robotics researchers to contribute independently yet coherently, we outline a pathway toward a unified, expressive system for social robotics.

Problem

• affective touch
• social robotics
• haptic interaction
• human-robot interaction
• haptic uncanny valley

Innovation

• affective touch
• multi-deep-learning
• haptic uncanny valley
• Sim-to-Real
• closed-loop perception