An Empirical Evaluation of Neural and Neuro-symbolic Approaches to Real-time Multimodal Complex Event Detection

TL;DR

This paper compares neural and neuro-symbolic methods for real-time complex event detection in robots, showing neuro-symbolic models outperform neural ones especially with limited data or context.

Contribution

It provides an empirical evaluation of neural versus neuro-symbolic approaches for multimodal complex event detection, highlighting the advantages of neuro-symbolic methods.

Findings

Neuro-symbolic models outperform neural models in CE detection.

Neuro-symbolic approach requires less training data.

Neuro-symbolic models handle longer temporal contexts better.

Abstract

Robots and autonomous systems require an understanding of complex events (CEs) from sensor data to interact with their environments and humans effectively. Traditional end-to-end neural architectures, despite processing sensor data efficiently, struggle with long-duration events due to limited context sizes and reasoning capabilities. Recent advances in neuro-symbolic methods, which integrate neural and symbolic models leveraging human knowledge, promise improved performance with less data. This study addresses the gap in understanding these approaches' effectiveness in complex event detection (CED), especially in temporal reasoning. We investigate neural and neuro-symbolic architectures' performance in a multimodal CED task, analyzing IMU and acoustic data streams to recognize CE patterns. Our methodology includes (i) end-to-end neural architectures for direct CE detection from sensor embeddings, (ii) two-stage concept-based neural models mapping sensor embeddings to atomic events (AEs) before CE detection, and (iii) a neuro-symbolic approach using a symbolic finite-state machine for CE detection from AEs. Empirically, the neuro-symbolic architecture significantly surpasses purely neural models, demonstrating superior performance in CE recognition, even with extensive training data and ample temporal context for neural approaches.