Detecting and Accommodating Novel Types and Concepts in an Embodied Simulation Environment

TL;DR

This paper introduces methods for AI systems to quickly adapt to and recognize new object categories in an embodied simulation environment, enhancing their metacognitive capabilities.

Contribution

It presents novel techniques for rapid model expansion and novel object detection using simulation-based data, integrating these tasks into an interactive architecture.

Findings

Effective in rapidly accommodating new object categories

Successful in detecting novel object types

Demonstrates importance of motion and property data for recognition

Abstract

In this paper, we present methods for two types of metacognitive tasks in an AI system: rapidly expanding a neural classification model to accommodate a new category of object, and recognizing when a novel object type is observed instead of misclassifying the observation as a known class. Our methods take numerical data drawn from an embodied simulation environment, which describes the motion and properties of objects when interacted with, and we demonstrate that this type of representation is important for the success of novel type detection. We present a suite of experiments in rapidly accommodating the introduction of new categories and concepts and in novel type detection, and an architecture to integrate the two in an interactive system.