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

2025-08-05

AI Summary

Commercial metaverse platforms lack dynamic, intent-aware personalized navigation mechanisms—especially under heterogeneous world configurations and platform constraints—rendering existing on-demand agents impractical. Method: We propose Navigation Pixie, the first lightweight, loosely coupled, on-demand navigation agent designed for real-world commercial metaverses. It integrates structured spatial metadata with large language models to enable cross-platform natural-language-guided navigation. Contribution/Results: We introduce a novel PC/VR dual-modal evaluation framework, revealing significant device-dependent navigation preferences: PC users favor proactive service invocation, whereas VR users are more influenced by social awareness. A field study with 193 real users on the Cluster platform demonstrates statistically significant improvements in session duration and unguided exploratory behavior, validating both efficacy and deployability of Navigation Pixie in production metaverse environments.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: The sharing economy

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.

Problem

• Lack dynamic navigation assistance in commercial metaverse platforms
• Challenges in implementing on-demand agents in diverse commercial settings
• Need for cross-platform evaluation of navigation agents in VR and PC

Innovation

• Loosely coupled architecture for navigation agents
• LLM-based natural language processing integration
• Cross-platform evaluation in commercial metaverse