Bioinspired Cross-Modal Self-Adaptive Machine Intelligence for Event-Driven and Ultrahigh-Precision Underwater Grasping

Abstract

Embodied intelligent agents, which represent the future of robotics, demand precise perception and real-time decision-making capabilities to achieve natural environmental interactions. However current systems face inherent limitations in unimodal sensing and cross-modal coordination, which hinder their performance in dynamic contact-rich operations. Herein, we present a fabric-based event-driven tactile interface that features an innovative woven structure with cross-fiber electrodes. It achieves breakthroughs in sensitivity (246.3 kPa−1), pressure detection (>450 kPa), and waterproof robustness. This interface enables millisecond-level pressure/slip dual-mode feedback for self-adaptive grasping, thereby improving the dexterous manipulation of fragile or slippery objects. For underwater scenarios, a bio-inspired visual–tactile fusion (VTF) architecture leverages tactile perception to compensate for visual limitations, demonstrating a high accuracy of 97.7% in complex tasks, including underwater transparent object manipulation and recognition of similar objects. Event-driven tactile feedback is merged with visual semantics for decision-level optimization, thereby enhancing the autonomy and adaptation of humanoid machine intelligence. It creates an innovative closed-loop cross-modal perception–decision system that builds a direct link between environmental interaction and autonomous decision-making for intelligent agent development in open-world scenarios. The superior performance of the VTF architecture dynamic interaction tasks represents a crucial step toward robotic systems with advanced intelligence.