UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 103158 - 103158

Published: April 1, 2025

Language: Английский

---

ViE-Take: A Vision-Driven Multi-Modal Dataset for Exploring the Emotional Landscape in Takeover Safety of Autonomous Driving

Research, Journal Year: 2025, Volume and Issue: 8

Published: Jan. 1, 2025

Takeover safety draws increasing attention in the intelligent transportation as new energy vehicles with cutting-edge autopilot capabilities vigorously blossom on road. Despite recent studies highlighting importance of drivers’ emotions takeover safety, lack emotion-aware datasets hinders further investigation, thereby constraining potential applications this field. To end, we introduce ViE-Take, first Vision-driven (Vision is used since it constitutes most cost-effective and user-friendly solution for commercial driver monitor systems) dataset exploring Emotional landscape Takeovers autonomous driving. ViE-Take enables a comprehensive exploration impact performance through 3 key attributes: multi-source emotion elicitation, multi-modal data collection, multi-dimensional annotations. aid use provide 4 deep models (corresponding to prevalent learning strategies) predicting different aspects (readiness, reaction time, quality). These offer benefits various downstream tasks, such recognition regulation automobile manufacturers. Initial analysis experiments conducted indicate that (a) have diverse impacts performance, some which are counterintuitive; (b) highly expressive social media clips, despite their brevity, prove effective eliciting (a foundation regulation); (c) solely vision not only feasible but also holds great potential.

Language: Английский

---

Parallel Tourism System With Foundation Models and Decentralized Autonomous Organizations

International Journal of Tourism Research, Journal Year: 2025, Volume and Issue: 27(2)

Published: March 1, 2025

ABSTRACT Tourism is a critical driver of economic growth and cultural exchange. However, traditional tourism models often struggle to address challenges such as insufficient understanding diverse travel preferences, limited capacity for personalized services, lack intelligent, convenient service solutions. In this paper, we propose virtual‐real interactive Parallel System (PTS) Smart Lifestyle Service Large Model (STLS‐LM) handle these challenges. By integrating Decentralized Autonomous Organizations (DAOs) Foundation Models (FMs) supported by Retrieval‐Augmented Generation, PTS elevates services incorporating agentic intelligence autonomous intelligence, advancing beyond AI‐powered applications. The proposed framework enables deep task requirements, precise multi‐source information sensing, functionality customization, timely public feedback adoption, forming comprehensive intelligent system that caters the evolving needs modern tourism.

Language: Английский

---

Generative artificial intelligence in intelligent transportation systems: A systematic review of applications

Frontiers of Engineering Management, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Language: Английский

---

Cognitive Reinforcement Learning: An Interpretable Decision-Making for Virtual Driver

IEEE Journal of Radio Frequency Identification, Journal Year: 2024, Volume and Issue: 8, P. 627 - 631

Published: Jan. 1, 2024

Language: Английский

---

From RAG/RAT to SAGE: Parallel Driving for Smart Mobility

IEEE Transactions on Intelligent Vehicles, Journal Year: 2024, Volume and Issue: 9(5), P. 4821 - 4825

Published: May 1, 2024

Language: Английский

---

The Emergence of the Vehicular Metaverse: A Scoping Review

Proceedings in automotive engineering, Journal Year: 2024, Volume and Issue: unknown, P. 120 - 135

Published: Nov. 19, 2024

Language: Английский

---