Survey on Human-Vehicle Interactions and AI Collaboration for Optimal Decision-Making in Automated Driving

TL;DR

The paper tackles the challenge of achieving safe, reliable automated driving by integrating human cognition into control through human-vehicle interaction (HVI) and AI collaboration. It surveys cognitive modeling approaches, decision-making methods, and the challenges of trust, communication, and adaptability in HAC. It contributes a taxonomy of HVIs and AI collaboration, a SIDA-based conceptual framework, and a generic algorithm for cognitive decision-making, offering practical guidance for designing adaptive, human-centric automated driving systems. Overall, the work underscores the importance of combining human flexibility with AI precision to handle real-world uncertainty and improve safety, efficiency, and public trust.

Abstract

The capabilities of automated vehicles are advancing rapidly, yet achieving full autonomy remains a significant challenge, requiring ongoing human cognition in decision-making processes. Incorporating human cognition into control algorithms has become increasingly important, as researchers work to develop strategies that minimize conflicts between human drivers and AI systems. Despite notable progress, many challenges persist, underscoring the need for further innovation and refinement in this field. This review covers recent progress in human-vehicle interaction (HVI) and AI collaboration for vehicle control. First, we start by looking at how HVI has evolved, pointing out key developments and identifying persistent problems. Second, we discuss the existing techniques, including methods for integrating human intuition and cognition into decision-making processes and developing systems that can mimic human behavior to enable optimal driving strategies and achieve safer and more efficient transportation. This review aims to contribute to the development of more effective and adaptive automated driving systems by enhancing human-AI collaboration.

Figures (8)

• Figure 1: Levels of Human-Machine Interaction (HMI) from coexistence to symbiosis t77.
• Figure 2: The Human-Vehicle Interaction Ecosystem, showing the interplay between cognitive inputs, AI systems, and external factors t73.
• Figure 3: A layered framework of humans-in-the-loop, AI collaboration, and control engineering in HVIs t70.
• Figure 4: Cloning the human driving pattern t75.
• Figure 5: Key challenges in human-vehicle interactions (HVIs).