Siamese Network with Dual Attention for EEG-Driven Social Learning: Bridging the Human-Robot Gap in Long-Tail Autonomous Driving

2025-04-14

AI Summary

This work addresses two critical challenges in semi-autonomous robotic driving: the difficulty of identifying long-tail safety-critical events and insufficient human-robot cognitive synergy. To this end, we propose an EEG-based brain-computer interface framework for real-time detection of cognitive demand and safety-critical events under dynamic conditions. Methodologically, we introduce a novel EEG decoding architecture that integrates a dual-attention Siamese convolutional network with Dynamic Time Warping Barycenter Averaging (DBA), complemented by inverse source localization and integrated gradients attribution analysis to uncover perception-action coupling mechanisms in Brodmann Areas 4 and 9. We further incorporate few-shot learning to overcome decoding bottlenecks across subjects and under low-data regimes. Experimental results demonstrate 80% classification accuracy under data-scarce conditions, nearly doubling feature utilization efficiency, enabling cross-subject generalization and millisecond-level risk alerting—substantially enhancing human-robot collaborative safety in intelligent mobility systems.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robots with wheeled, quadrupedal, or humanoid forms are increasingly integrated into built environments. However, unlike human social learning, they lack a critical pathway for intrinsic cognitive development, namely, learning from human feedback during interaction. To understand human ubiquitous observation, supervision, and shared control in dynamic and uncertain environments, this study presents a brain-computer interface (BCI) framework that enables classification of Electroencephalogram (EEG) signals to detect cognitively demanding and safety-critical events. As a timely and motivating co-robotic engineering application, we simulate a human-in-the-loop scenario to flag risky events in semi-autonomous robotic driving-representative of long-tail cases that pose persistent bottlenecks to the safety performance of smart mobility systems and robotic vehicles. Drawing on recent advances in few-shot learning, we propose a dual-attention Siamese convolutional network paired with Dynamic Time Warping Barycenter Averaging approach to generate robust EEG-encoded signal representations. Inverse source localization reveals activation in Broadman areas 4 and 9, indicating perception-action coupling during task-relevant mental imagery. The model achieves 80% classification accuracy under data-scarce conditions and exhibits a nearly 100% increase in the utility of salient features compared to state-of-the-art methods, as measured through integrated gradient attribution. Beyond performance, this study contributes to our understanding of the cognitive architecture required for BCI agents-particularly the role of attention and memory mechanisms-in categorizing diverse mental states and supporting both inter- and intra-subject adaptation. Overall, this research advances the development of cognitive robotics and socially guided learning for service robots in complex built environments.

Problem

• Classifying EEG signals to detect safety-critical events in human-robot interaction
• Improving EEG signal representation for cognitive demand detection in BCI
• Enhancing cognitive robotics through attention and memory mechanisms in BCI

Innovation

• Dual-attention Siamese convolutional network for EEG
• Dynamic Time Warping Barycenter Averaging approach
• Inverse source localization for cognitive task analysis