Monday, December 01, 2025


Socially compliant automated vehicles: new conceptual framework paves the way for safer mixed-traffic environments




Tsinghua University Press
Conceptual framework for developing socially compliant automated vehicles (SCAVs) 

image: 

The proposed conceptual framework integrates sensing, socially‑compliant decision‑making, safety constraints, bidirectional behavioral adaptation, and spatial‑temporal memory to guide future SCAV development.

view more 

Credit: Communications in Transportation Research





Automated vehicles (AVs) hold promise for revolutionizing transportation by improving road safety, traffic efficiency, and overall mobility. Despite the steady advancement in high-level AVs in recent years, the transition to full automation entails a period of mixed traffic, where AVs of varying automation levels coexist with human-driven vehicles (HDVs). Making AVs socially compliant and understood by human drivers is expected to improve the safety and efficiency of mixed traffic. Thus, ensuring AVs’ compatibility with HDVs and social acceptance is crucial for their successful and seamless integration into mixed traffic.

 

Researchers at Delft University of Technology (Netherlands) and RWTH Aachen University (Germany) carried out a study with a comprehensive scoping review to assess the current state of the art in developing socially compliant automated vehicles (SCAVs), identifying key concepts, methodological approaches, and research gaps. They conducted an informal expert interview to discuss the literature review results and identify critical research challenges and expectations towards SCAVs. Based on the scoping review and expert interview input, they designed a conceptual framework for the development of SCAVs and evaluated it using an online survey targeting researchers, technicians, policymakers, and other relevant professionals worldwide. The framework outlines the key capability elements necessary for SCAVs and incorporates crucial considerations across technical, social, and cultural dimensions, effectively bridging theoretical insights with practical applications to achieve socially compliant automation. The conceptual framework provides actionable insights into developing and embedding social compliance in AV systems, enabling scalable and context-sensitive deployment. It can also foster collaboration among academia, industry, and policymakers, ensuring technical innovation aligns with societal needs and regulatory standards, accelerating the path toward SCAV and further towards safe and socially inclusive automated mobility solutions.

 

The study was published on 8 September 2025, in Communications in Transportation Research.

 

“We conducted the first comprehensive scoping review to identify key concepts, methodologies, and research gaps in the emerging field of socially compliant automated driving in mixed traffic,” says Yongqi Dong, lead author and researcher at Delft University of Technology and RWTH Aachen University. “By combining this review with expert interviews and a worldwide survey, we have distilled core requirements for AVs to coexist seamlessly and predictably with human drivers through a conceptual framework.” (The conceptual framework is shown in the figure.)

 

Five methodological pillars

In reviewing 68 pivotal studies on SCAVs, the team clustered existing approaches into five main categories:

 

  • Imitation learning to clone human social driving norms
  • Reinforcement learning with utility-based models
  • Model‑based (e.g., game theory, social‑force models, and driving risk field models) generation of human-like behaviors
  • Socially‑aware trajectory prediction with social factors and machine learning
  • Optimization of social driving parameters balancing safety, comfort, and courtesy

 

Expert insights reveal critical gaps

Through informal interviews with ten AV experts across academia, industry, and government, the authors uncovered key limitations in today’s AVs:

  • Excessive conservatism, leading to inefficient traffic flow
  • Poor interpretation of implicit human cues, from hand gestures to assertive lane changes
  • Inflexibility to diverse driving cultures and styles
  • Lack of bidirectional adaptation, where AVs and human drivers dynamically adjust to each other

 

A novel conceptual framework

To address these gaps, the author team proposes a novel conceptual framework for SCAV (see Image) comprising:

  • Sensing & perception module, fusing multi-modal sensor data
  • Socially‑compliant decision‑making module, embedding social components (including culture, norms, and cues), different driving styles (e.g., aggressive, cautious, pro-social), and bidirectional behavioral adaptation mechanisms
  • Safety constraints module, a real‑time safeguard layer
  • Utility trade‑off mechanisms, balancing individual vehicles’ benefits with network‑level traffic performance
  • Bidirectional behavioral adaptation, enabling AVs to learn from and respond to human drivers’ adaptations (there will be bidirectional iterative adaptations between AVs and human drivers)
  • Spatial‑temporal memory module, continuously updating AV models with past interaction data to facilitate the long- and short-term updating of knowledge and driving rules and contribute to the implementation of bidirectional behavioral adaptation.

 

Global survey validation

An online questionnaire gathered insights from 90 experts across 29 countries. Respondents overwhelmingly endorsed the framework’s key modules, particularly the need for mutual bidirectional adaptation between AVs and human drivers, and highlighted priorities such as anticipation capability, multi-objective optimization, and spatial-temporal memory buffer integration.

 

“Our framework lays a robust foundation for both academia and industry,” concludes Bart van Arem, co‑author from Delft University of Technology. “By integrating social dynamics into AV design, we can pave the way toward mixed‑traffic environments that are safer, more efficient, socially beneficial, and widely accepted.”

 

This research marks a significant step toward realizing the promise of automated vehicles in everyday traffic, ensuring they not only drive safely but also drive in harmony with human behavior and societal expectations.

 

 

The above research is published in Communications in Transportation Research (COMMTR), which is a fully open access journal co-published by Tsinghua University Press and Elsevier. COMMTR publishes peer-reviewed high-quality research representing important advances of significance to emerging transport systems. COMMTR is also among the first transportation journals to make the Replication Package mandatory to facilitate researchers, practitioners, and the general public in understanding and advancing existing knowledge. At its discretion, Tsinghua University Press will pay the open access fee for all published papers in 2025.

Can generative AI improve vehicle trajectory prediction in car-following scenarios?



Tsinghua University Press
Overview of FollowGen. 

image: 

The proposed FollowGen framework consists of four main modules: historical feature encoding, noise scaling strategy and noise addition, car-following vehicular interaction modeling, and condition guided denoising.

view more 

Credit: Communications in Transportation Research




To answer this question, researchers from the University of Wisconsin–Madison, Tongji University, and collaborators developed FollowGen, a conditional diffusion model that integrates historical motion features and inter-vehicle interactions to generate safer and more reliable trajectory predictions for autonomous driving.

                                                              

They published their study on 16 October 2025, in Communications in Transportation Research.

 

“We introduce a scaled noise conditioning mechanism that embeds historical motion features into the forward diffusion process. This allows the model to account for motion-aware uncertainties from the beginning and generate trajectories that better align with real driving behaviors,” says Junwei You, a Ph.D. candidate studying autonomous driving and intelligent transportation.

 

Different performance across diverse driving scenarios
In the study, the research group evaluated FollowGen using multiple real-world datasets, covering both urban and highway environments. They examined car-following situations such as human-driven vehicles following each other, autonomous vehicles following humans, and humans following autonomous vehicles.

 

“This design enables the model to explicitly capture the interaction between leading and following vehicles. As a result, FollowGen delivers consistent improvements over strong baselines, particularly in terms of final displacement accuracy and reliability,” explains Haotian Shi, Associate Professor at Tongji University.

 

Visualization results show how initially chaotic scaled noise progressively evolves into accurate trajectory predictions, demonstrating the effectiveness of combining diffusion models with car-following dynamics.

 

Significant implications for autonomous driving
The findings suggest that incorporating generative AI into trajectory prediction can enhance the safety and robustness of autonomous driving systems. Beyond real-time planning, the model also offers potential applications in large-scale traffic simulation and intelligent transportation system design.

 

“Our research demonstrates that diffusion-based models are not only powerful for uncertainty modeling but can also be adapted to the unique requirements of vehicle interactions on the road. This represents an important step toward safer and more reliable autonomous vehicles,” says Sikai Chen, Assistant Professor at the University of Wisconsin-Madison.

The above research is published in Communications in Transportation Research (COMMTR), which is a fully open access journal co-published by Tsinghua University Press and Elsevier. COMMTR publishes peer-reviewed high-quality research representing important advances of significance to emerging transport systems. COMMTR is also among the first transportation journals to make the Replication Package mandatory to facilitate researchers, practitioners, and the general public in understanding and advancing existing knowledge. At its discretion, Tsinghua University Press will pay the open access fee for all published papers in 2025.

 

No comments: