Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning

2026-08-02

AI Summary

This study addresses a critical gap in the literature: the absence of a unified survey on robotic learning methods that integrate force and tactile perception, particularly regarding the synthesis of multimodal sensing and multi-stage system design. To bridge this gap, the paper introduces the TF-ART categorization framework—a novel, comprehensive architecture that systematically encompasses multimodal perceptual inputs, hierarchical action generation, and reactive low-level control. By integrating heterogeneous sensor encoding, multimodal perception fusion, and action refinement mechanisms, the framework elucidates the intrinsic relationships among existing approaches and clearly maps their design logic across the perception–decision–execution pipeline. This contribution provides a holistic perspective, theoretical foundation, and practical guidance for developing intelligent systems capable of rich physical interaction.

Abstract

Physically grounded robot intelligence requires robots to perceive, reason about, and regulate their interactions with the physical world. This capability is particularly critical in contact-sensitive manipulation, where successful task execution depends not only on visual perception and motion generation, but also on force regulation and adaptive control. In this context, recent robot learning methods have made substantial progress by integrating force, tactile, vision, language, and proprioceptive sensing into learned manipulation policies. In parallel, many systems adopt multi-phase architectures that combine high-level policies, action-refinement modules, and low-level controllers to bridge semantic task understanding with reactive physical execution. Despite these advances, existing surveys have not explicitly reviewed force- and tactile-aware robot learning from a unified perspective that jointly captures multimodal sensing and multi-phase system design. This survey addresses this gap by proposing TF-ART, a Tactile/Force-Aware Robot learning Taxonomy for multimodal and multi-phase frameworks, which maps individual methods into a unified hierarchical structure. The framework characterizes how recent works organize observation modalities, encode and fuse heterogeneous sensory inputs, generate and refine actions across multiple phases, and connect learned policies to reactive robot-end control. Building on this methodological view, we further examine the task settings and infrastructure requirements of physical interaction, thereby integrating both algorithmic and practical perspectives on force- and tactile-aware robot learning.

Problem

• tactile-aware robot learning
• force-aware robot learning
• multimodal sensing
• multi-phase system design
• physical interaction

Innovation

• tactile sensing
• force-aware learning
• multimodal perception
• multi-phase architecture
• robot learning taxonomy