Paper Type
Complete
Abstract
Motion sickness, or kinesis, is a major issue for passenger rides, especially in autonomous vehicles, affecting user experience and comfort. Software-defined Vehicles (SDVs) introduce new possibilities for mitigating motion sickness through real-time data modeling and AI-driven prediction. This paper presents Anti-Kinetosis, an SDV-based solution utilizing Vehicle Signal Specification (VSS) to access real-time vehicle dynamics, such as acceleration and angular velocity, for motion sickness prediction. The system integrates a mathematical model and two vision-based AI models to estimate kinetosis likelihood based on vehicle motion and passenger demographics. An application is containerized for cloud deployment, with an online demo using a digital twin to simulate real-world driving conditions. Future work will integrate the solution into a lab car for validation in real environments, ensuring reliable performance and practical feasibility. This study enhances passenger comfort in next-generation mobility and lays the foundation for personalized in-car experiences and further research on motion sickness mitigation.
Paper Number
1559
Recommended Citation
Cheng, Xiangwei; Burkhardt, Daniel; Slama, Dirk; and Gharsallah, Ismail, "Anti-Kinetosis: A Hybrid Analytics Approach for Motion Sickness Detection in Software-Defined Vehicles" (2025). AMCIS 2025 Proceedings. 6.
https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/6
Anti-Kinetosis: A Hybrid Analytics Approach for Motion Sickness Detection in Software-Defined Vehicles
Motion sickness, or kinesis, is a major issue for passenger rides, especially in autonomous vehicles, affecting user experience and comfort. Software-defined Vehicles (SDVs) introduce new possibilities for mitigating motion sickness through real-time data modeling and AI-driven prediction. This paper presents Anti-Kinetosis, an SDV-based solution utilizing Vehicle Signal Specification (VSS) to access real-time vehicle dynamics, such as acceleration and angular velocity, for motion sickness prediction. The system integrates a mathematical model and two vision-based AI models to estimate kinetosis likelihood based on vehicle motion and passenger demographics. An application is containerized for cloud deployment, with an online demo using a digital twin to simulate real-world driving conditions. Future work will integrate the solution into a lab car for validation in real environments, ensuring reliable performance and practical feasibility. This study enhances passenger comfort in next-generation mobility and lays the foundation for personalized in-car experiences and further research on motion sickness mitigation.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIGDSA