Human-Centric Interactions in Intelligent Transportation

Amanda Chen^*
*Correspondence: Amanda Chen, Department of Transportation Systems, National Taiwan University, Taipei 10617, Taiwan, Email:

Introduction

The advent of advanced transportation systems has brought human-system interaction to the forefront of research, necessitating a deep understanding of how users engage with increasingly complex environments. A significant area of focus involves autonomous vehicles (AVs), where researchers continuously explore the intricate dynamics between human drivers and automated systems. For instance, studies have employed driving simulations to investigate how human drivers interact with autonomous vehicles, particularly during curve negotiation, identifying key factors that influence driver takeover performance and comfort in these complex scenarios. Such findings are instrumental in suggesting design considerations for more intuitive human-vehicle interfaces in future autonomous systems [1].

Further research in this domain explored how different information displays affect human-vehicle interaction and overall driving performance in autonomous vehicles. This work revealed that well-designed interfaces are crucial for improving driver trust, enhancing situational awareness, and ultimately boosting the safety and efficiency of autonomous driving experiences [3].

Continuing this thread, investigations into the impact of human-automation interaction on driver behavior during critical transitions in conditionally automated driving have been conducted. These studies identify patterns in driver responses and potential risks during takeover requests, providing valuable insights for developing safer and more effective handover protocols for autonomous vehicles [8].

Beyond human drivers, the interaction of automated vehicles with other road users, especially vulnerable ones like pedestrians, is another critical area of study. Researchers have investigated pedestrian perceptions and their interactions with automated vehicles at uncontrolled intersections, offering crucial insights into how to design AVs and urban infrastructure to ensure safety and build trust among pedestrians. This work emphasizes the need for clear communication and predictable vehicle behavior from automated systems [4].

Similarly, a systematic review has examined human-pedestrian interaction in shared spaces involving automated shuttles. This review synthesizes findings on safety, comfort, and acceptance of these new transport modes, highlighting the need for clear communication strategies and robust safety measures to foster harmonious coexistence between automated vehicles and pedestrians [9].

The broader context of traffic management and user experience in diverse transportation networks also receives considerable attention. For example, researchers have applied deep learning models to analyze the complex interactive dynamics among various road users in mixed traffic conditions. The findings from this approach highlight crucial patterns in how vehicles and pedestrians interact, which is vital for developing smarter traffic management systems and improving safety in diverse urban environments [2].

Moving into multi-modal contexts, studies have focused on improving user experience in such systems through a human-centered design approach. These efforts identify key interaction points and user needs across different transport modes, paving the way for more intuitive and enjoyable journeys in complex urban mobility networks [5].

Understanding the human element in shared mobility services is also essential for their success and adoption. A review article synthesizes current understanding of human factors in shared mobility services, outlining key challenges and opportunities. This comprehensive look at how user interaction, trust, and usability influence the adoption and success of shared transportation models offers a valuable roadmap for future research and design [7].

Furthermore, at a systemic level, research has proposed co-optimization models for multi-source transportation network interaction, specifically addressing capacity limitations. This model aims to enhance efficiency and reduce congestion by intelligently managing resources across various transport modes, contributing to more resilient and adaptive urban logistics [6].

Finally, to tie these diverse elements together, a comprehensive review provides an overview of human-computer interaction (HCI) within intelligent transportation systems (ITS). This work summarizes key advancements and challenges in designing user-friendly interfaces for ITS, emphasizing the importance of intuitive and effective interaction for improving traffic efficiency, safety, and overall user experience [10].

Collectively, these studies underscore a unified goal: to understand, predict, and optimize interactions across all levels of transportation, from individual human-machine interfaces to complex multi-user networks, ensuring safety, efficiency, and a positive user experience in the evolving landscape of mobility.

Description

The landscape of modern transportation is rapidly evolving, driven by advancements in automation and interconnected systems. A central challenge in this evolution is understanding and optimizing the various forms of interaction that occur within these complex environments. A significant body of research focuses on human-vehicle interaction, particularly in the context of autonomous vehicles (AVs). For instance, specific studies have utilized driving simulations to delve into how human drivers engage with AVs during challenging maneuvers, such as curve negotiation. This work is critical for identifying factors that impact a driverâ??s ability to take over control and their comfort levels in these situations, ultimately guiding the design of more intuitive human-vehicle interfaces [1]. The effectiveness of these interfaces is further underscored by research demonstrating that well-designed information displays can significantly improve driver trust, situational awareness, and the overall safety and efficiency of autonomous driving experiences [3]. Delving deeper into the dynamics of control transitions, other studies investigate how human-automation interaction affects driver behavior during critical moments in conditionally automated driving. These analyses aim to pinpoint driver response patterns and potential risks during takeover requests, providing essential knowledge for creating safer and more effective handover protocols for AVs [8].

Beyond the interactions between humans and their own vehicles, the broader dynamics involving all road users are paramount for integrated traffic systems. Deep learning models, for example, have been deployed to analyze the intricate interactive dynamics among diverse road users within mixed traffic scenarios. The insights gained from these models are crucial for revealing significant patterns in how vehicles and pedestrians interact, which is fundamental for developing smarter traffic management systems and enhancing safety across varied urban settings [2]. The safety of vulnerable road users, especially pedestrians, when interacting with automated vehicles is another critical focus. Researchers have explored pedestrian perceptions and their interactions with automated vehicles at uncontrolled intersections, yielding valuable insights into how both AVs and urban infrastructure should be designed. This design approach aims to ensure safety and foster trust among pedestrians, emphasizing the importance of clear communication and predictable vehicle behavior from automated systems [4]. This theme extends to shared mobility spaces, where a systematic review has shed light on human-pedestrian interaction with automated shuttles. The findings of this review consolidate knowledge on the safety, comfort, and acceptance of these new transport modes, underscoring the necessity for clear communication strategies and robust safety measures to facilitate harmonious coexistence between automated vehicles and pedestrians [9].

The human experience within multimodal and shared transportation systems also forms a key area of investigation. Studies focusing on improving user experience in multimodal transport systems have adopted a human-centered design approach. By identifying crucial interaction points and user needs across different modes of transport, this research paves the way for the creation of more intuitive and enjoyable journeys within complex urban mobility networks [5]. Complementing this, human factors in shared mobility services have been extensively reviewed, highlighting the challenges and opportunities in this rapidly expanding sector. This review offers a comprehensive understanding of how user interaction, trust, and usability profoundly influence the adoption and ultimate success of shared transportation models, providing a strategic roadmap for future research and design endeavors [7]. These efforts collectively aim to ensure that as transportation options diversify, the human element remains at the core of design and implementation.

At a more systemic level, the optimization and management of entire transportation networks are critical for urban resilience and efficiency. Research has proposed advanced co-optimization models specifically tailored for multi-source transportation network interaction, with a keen focus on addressing capacity limitations. The primary goal of such models is to enhance overall efficiency and alleviate congestion by intelligently managing resources across various transport modes, thereby contributing to more resilient and adaptive urban logistics solutions [6]. Underlying all these advancements is the field of human-computer interaction (HCI) within intelligent transportation systems (ITS). A comprehensive review summarizes key advancements and ongoing challenges in designing user-friendly interfaces for ITS. This work strongly emphasizes the paramount importance of intuitive and effective interaction, recognizing its role in improving traffic efficiency, bolstering safety, and elevating the overall user experience across all facets of intelligent transportation [10]. In essence, the collected research provides a holistic view of interaction within contemporary transportation, striving for systems that are not only technologically advanced but also deeply human-centric and environmentally sustainable.

Conclusion

This compilation of research broadly examines the multifaceted interactions within advanced transportation systems, highlighting human involvement alongside technological advancements. A significant portion focuses on autonomous vehicles, delving into how human drivers interact with these systems during specific tasks like curve negotiation, and how factors such as information displays influence driver trust and performance. Investigations also cover the critical transitions in conditionally automated driving, analyzing driver behavior during takeover requests to develop safer handover protocols. Beyond the driver's seat, the data explores human-pedestrian interactions with automated vehicles, particularly at uncontrolled intersections and in shared spaces with automated shuttles, emphasizing the need for clear communication and predictable vehicle behavior to ensure safety and build trust. The scope extends to broader traffic dynamics and user experience. One study applies deep learning to understand complex interactions among various road users in mixed traffic, aiming to improve traffic management and safety in urban settings. Other research addresses user experience in multimodal transport systems, advocating for human-centered design to create more intuitive journeys. The collection also includes works on human factors in shared mobility services, reviewing challenges and opportunities to understand how user interaction influences adoption. Finally, broader perspectives include co-optimization models for multi-source transportation networks to manage capacity and enhance urban logistics, and a comprehensive review of human-computer interaction within intelligent transportation systems, underscoring the importance of intuitive interfaces for overall system efficiency and safety. This body of work underscores a holistic approach to making future transportation safer, more efficient, and user-friendly through improved interactions.

Acknowledgement

None.

Conflict of Interest

None.

References

1. Wang X, Li M, Zhang Z. "Driving Simulation Study on Human-Vehicle Interaction during Curve Negotiation in Autonomous Driving".Sensors (Basel) 23 (2023):8352.

Indexed at, Google Scholar, Crossref

2. Li R, Han Y, Yu R. "Understanding the interactive dynamics of road users in mixed traffic conditions: A deep learning-based approach".Accid Anal Prev 191 (2023):107222.

Indexed at, Google Scholar, Crossref

3. Zhang T, Ma P, Wu D. "The impact of information display on human-vehicle interaction and driving performance in autonomous vehicles: A driving simulator study".Accid Anal Prev 159 (2021):106297.

Indexed at, Google Scholar, Crossref

4. Kim J, Son H, Moon D. "Investigating pedestrian perceptions and interactions with automated vehicles at uncontrolled intersections".Accid Anal Prev 147 (2020):105777.

Indexed at, Google Scholar, Crossref

5. Wang Y, Li H, Chen X. "Examining user experience in multimodal transport systems: A human-centered design approach".Ergonomics 62 (2019):1629-1644.

Indexed at, Google Scholar, Crossref

6. Wang Y, Ma X, Hu J. "Co-optimization for multi-source transportation network interaction considering capacity limitations".Transp Res Part E Logist Transp Rev 174 (2023):103138.

Indexed at, Google Scholar, Crossref

7. Liu Y, Chen W, Li Z. "Human factors in shared mobility services: A review of challenges and opportunities".J Transp Eng Part A-Syst 148 (2022):04022068.

Indexed at, Google Scholar, Crossref

8. Li K, Zhang Z, Ding H. "Investigating the impact of human-automation interaction on driver behavior during critical transitions in conditionally automated driving".Accid Anal Prev 154 (2021):106095.

Indexed at, Google Scholar, Crossref

9. Ma H, Li X, Liu P. "Human-pedestrian interaction in shared spaces with automated shuttles: A systematic review".Transp Rev 42 (2022):948-968.

Indexed at, Google Scholar, Crossref

10. Zhang J, Wei Y, Liu H. "A review of human-computer interaction in intelligent transportation systems".Sensors (Basel) 20 (2020):5123.

Indexed at, Google Scholar, Crossref