A Brain-Inspired Hierarchical Reasoning Framework for Cognition-Augmented Prosthetic Grasping

This paper proposes a hierarchical framework that enables reasoning across multiple levels of abstraction, from perception to high-level control. The framework relies primarily on Hyperdimensional (HD) computing, a versatile braininspired computing paradigm that can produce composite distributed representations for efficient classification and can also facilitate symbolic reasoning. We present this framework through an example use case corresponding to cognitionaugmented prosthetic grasping, where user intent is probabilistically predicted to aid the user in successfully selecting and executing the most appropriate gripping mode. Overall, this paper aims to illustrate how HD computing can constitute a mathematical formalism capable of integrating various levels of cognition under a common hierarchical framework.