Navigation Pixie: Implementation and Empirical Study Toward On-demand Navigation Agents in Commercial Metaverse

TL;DR

Navigation Pixie is an on-demand navigation agent that enhances user exploration in commercial metaverse platforms by integrating spatial metadata with language processing, validated through extensive cross-platform experiments.

Contribution

This work introduces Navigation Pixie, a novel, platform-independent navigation agent that combines spatial metadata with LLMs, and provides empirical evaluation in real-world metaverse settings.

Findings

Navigation Pixie increased dwell time and exploration in experiments.

User preferences varied between PC and VR environments.

The approach is effective across diverse commercial metaverse platforms.

Abstract

While commercial metaverse platforms offer diverse user-generated content, they lack effective navigation assistance that can dynamically adapt to users' interests and intentions. Although previous research has investigated on-demand agents in controlled environments, implementation in commercial settings with diverse world configurations and platform constraints remains challenging. We present Navigation Pixie, an on-demand navigation agent employing a loosely coupled architecture that integrates structured spatial metadata with LLM-based natural language processing while minimizing platform dependencies, which enables experiments on the extensive user base of commercial metaverse platforms. Our cross-platform experiments on commercial metaverse platform Cluster with 99 PC client and 94 VR-HMD participants demonstrated that Navigation Pixie significantly increased dwell time and free exploration compared to fixed-route and no-agent conditions across both platforms. Subjective evaluations revealed consistent on-demand preferences in PC environments versus context-dependent social perception advantages in VR-HMD. This research contributes to advancing VR interaction design through conversational spatial navigation agents, establishes cross-platform evaluation methodologies revealing environment-dependent effectiveness, and demonstrates empirical experimentation frameworks for commercial metaverse platforms.