A Symbolic Representation of Human Posture for Interpretable Learning and Reasoning

TL;DR

This paper introduces a symbolic, human-interpretable representation of human posture using qualitative spatial reasoning, aiming to improve interpretability in activity recognition tasks.

Contribution

It proposes a novel symbolic posture representation based on qualitative spatial reasoning, enhancing interpretability over traditional sensor-based models.

Findings

Effective as features for activity recognition

Provides two levels of detail in symbolic representation

Preliminary results show promise for interpretability

Abstract

Robots that interact with humans in a physical space or application need to think about the person's posture, which typically comes from visual sensors like cameras and infra-red. Artificial intelligence and machine learning algorithms use information from these sensors either directly or after some level of symbolic abstraction, and the latter usually partitions the range of observed values to discretize the continuous signal data. Although these representations have been effective in a variety of algorithms with respect to accuracy and task completion, the underlying models are rarely interpretable, which also makes their outputs more difficult to explain to people who request them. Instead of focusing on the possible sensor values that are familiar to a machine, we introduce a qualitative spatial reasoning approach that describes the human posture in terms that are more familiar to people. This paper explores the derivation of our symbolic representation at two levels of detail and its preliminary use as features for interpretable activity recognition.