🤖 AI Summary
Addressing the dual challenge of motion sickness in autonomous vehicle passengers and transportation-related carbon emissions, this paper proposes a synergistic optimization framework integrating eco-driving strategies with personalized comfort modeling. Innovatively, it introduces self-organizing maps (SOM) for the first time to jointly characterize the coupled effects of driving style on ride comfort and energy consumption. Leveraging real-world driving behavior data, it extracts multidimensional driving features to construct an interpretable comfort–eco-efficiency joint evaluation model and generates natural-language, personalized improvement recommendations. Experiments demonstrate a 57.7% improvement in mainstream comfort metrics and up to 47.1% reduction in greenhouse gas emissions—significantly outperforming baseline methods. Key contributions include: (1) an SOM-driven paradigm for modeling the coupling between ride comfort and environmental impact; (2) a data-driven framework for generating personalized, human-interpretable recommendations; and (3) a dual-objective co-optimization mechanism tailored for human–autonomous vehicle collaboration.
📝 Abstract
New challenges on transport systems are emerging due to the advances that the current paradigm is experiencing. The breakthrough of the autonomous car brings concerns about ride comfort, while the pollution concerns have arisen in recent years. In the model of automated automobiles, drivers are expected to become passengers, so, they will be more prone to suffer from ride discomfort or motion sickness. Conversely, the eco-driving implications should not be set aside because of the influence of pollution on climate and people's health. For that reason, a joint assessment of the aforementioned points would have a positive impact. Thus, this work presents a self-organised map-based solution to assess ride comfort features of individuals considering their driving style from the viewpoint of eco-driving. For this purpose, a previously acquired dataset from an instrumented car was used to classify drivers regarding the causes of their lack of ride comfort and eco-friendliness. Once drivers are classified regarding their driving style, natural-language-based recommendations are proposed to increase the engagement with the system. Hence, potential improvements of up to the 57.7% for ride comfort evaluation parameters, as well as up to the 47.1% in greenhouse-gasses emissions are expected to be reached.