Detecting and Accommodating Novel Types and Concepts in an Embodied Simulation Environment
This work addresses the challenge of handling novel concepts in interactive AI systems, which is incremental as it builds on existing classification and detection methods.
The paper tackles the problem of enabling AI systems to rapidly expand classification models for new object categories and detect novel object types in an embodied simulation environment, demonstrating that motion and property representations are crucial for success in these tasks.
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.