Year: 2025
Type: conference-paper
Abstract: Advances in autonomous driving technology are expected to increase in-vehicle free time, raising demand for content recommendation services tailored to user and driving contexts (e.g., conversation atmosphere, destination). However, many existing systems rely on predefined context-sharing schemes between platform providers and service providers, which cause cross-platform incompatibility and limit context expressiveness. This paper proposes a multi-agent architecture in which platform agents infer rich contextual information from sensor data using a large language model (LLM) and communicate it via natural language to service agents. We implemented a simulator and demonstrated the system at two exhibitions, followed by user evaluations. The results indicate that the proposed architecture enables flexible context sharing, effective content recommendation, and the generation of explanations for recommendation rationales without requiring predefined context definitions. These findings contribute to the design of adaptive, platform-agnostic in-vehicle infotainment services for future autonomous vehicles.
Authors: Hiromu Ogawa, Yuta Hagio, Takashi Shoji, Shinjiro Urata, Shinji Hoshino, Yuji Ikeda, Takahiro Fukushima, Hisayuki Ohmata
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4415000215