ORACLE: Orchestrate NPC Daily Activities using Contrastive Learning with Transformer-CVAE

TL;DR

ORACLE is a novel generative model that uses contrastive learning, Transformers, and CVAE to create realistic NPC daily activity plans, enhancing immersion in digital environments by capturing human-like routines.

Contribution

This paper introduces ORACLE, a new model combining contrastive learning, Transformers, and CVAE to generate realistic indoor activity plans for NPCs, addressing data imbalance and scarcity issues.

Findings

ORACLE outperforms existing methods in generating realistic NPC activity plans.

The model effectively handles imbalanced and limited training data.

Experimental results demonstrate superior realism and diversity in generated activities.

Abstract

The integration of Non-player characters (NPCs) within digital environments has been increasingly recognized for its potential to augment user immersion and cognitive engagement. The sophisticated orchestration of their daily activities, reflecting the nuances of human daily routines, contributes significantly to the realism of digital environments. Nevertheless, conventional approaches often produce monotonous repetition, falling short of capturing the intricacies of real human activity plans. In response to this, we introduce ORACLE, a novel generative model for the synthesis of realistic indoor daily activity plans, ensuring NPCs' authentic presence in digital habitats. Exploiting the CASAS smart home dataset's 24-hour indoor activity sequences, ORACLE addresses challenges in the dataset, including its imbalanced sequential data, the scarcity of training samples, and the absence of pre-trained models encapsulating human daily activity patterns. ORACLE's training leverages the sequential data processing prowess of Transformers, the generative controllability of Conditional Variational Autoencoders (CVAE), and the discriminative refinement of contrastive learning. Our experimental results validate the superiority of generating NPC activity plans and the efficacy of our design strategies over existing methods.