Neural Associative Skill Memories for safer robotics and modelling human sensorimotor repertoires

2025-05-14

AI Summary

Robots require simultaneous acquisition of multiple motor skills, robust fault detection, and context-aware adaptive execution. Method: We propose Neural Associative Skill Memories (Neural ASMs), the first unified architecture integrating self-supervised predictive coding with energy-based neural networks. This framework jointly supports skill representation, contextual inference, implicit skill switching, online anomaly detection, and safety-triggered responses. We further introduce biologically plausible local learning rules that reproduce the speed–accuracy trade-off observed in biological motor control. Contribution/Results: Experiments demonstrate that Neural ASMs achieve skill representation quality comparable to BPTT-trained RNNs while enabling real-time, cross-behavior anomaly detection and autonomous corrective responses. The approach significantly enhances robotic safety and behavioral adaptability, and provides a novel computational modeling framework for human motor learning.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Neuro-Symbolic Learning

Application Category

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

Abstract

Modern robots face challenges shared by humans, where machines must learn multiple sensorimotor skills and express them adaptively. Equipping robots with a human-like memory of how it feels to do multiple stereotypical movements can make robots more aware of normal operational states and help develop self-preserving safer robots. Associative Skill Memories (ASMs) aim to address this by linking movement primitives to sensory feedback, but existing implementations rely on hard-coded libraries of individual skills. A key unresolved problem is how a single neural network can learn a repertoire of skills while enabling fault detection and context-aware execution. Here we introduce Neural Associative Skill Memories (ASMs), a framework that utilises self-supervised predictive coding for temporal prediction to unify skill learning and expression, using biologically plausible learning rules. Unlike traditional ASMs which require explicit skill selection, Neural ASMs implicitly recognize and express skills through contextual inference, enabling fault detection across learned behaviours without an explicit skill selection mechanism. Compared to recurrent neural networks trained via backpropagation through time, our model achieves comparable qualitative performance in skill memory expression while using local learning rules and predicts a biologically relevant speed-accuracy trade-off during skill memory expression. This work advances the field of neurorobotics by demonstrating how predictive coding principles can model adaptive robot control and human motor preparation. By unifying fault detection, reactive control, skill memorisation and expression into a single energy-based architecture, Neural ASMs contribute to safer robotics and provide a computational lens to study biological sensorimotor learning.

Problem

• How to enable robots to learn multiple sensorimotor skills adaptively
• How to unify skill learning and fault detection in one network
• How to achieve context-aware skill execution without explicit selection

Innovation

• Self-supervised predictive coding for skill learning
• Contextual inference for implicit skill recognition
• Energy-based architecture unifying fault detection and control