Paper Type
Complete
Paper Number
1888
Description
In the era of digital transformation, automotive companies are rapidly evolving towards customer integration and innovation. This study addresses a critical issue of low usage rates for the lane change assistance function in advanced driving assistance systems. While existing literature focuses on labeling lane change maneuvers in terms of appropriateness at a given moment, overlooking the frequency and classification of different lane change scenarios. This study selects and combines over 104,000 lane change events extracted from customer fleet data and applies the k-means clustering algorithm. The five distinct cluster groups indicate the categorization and frequency of different lane change scenarios. This approach is based on real customer usage data, providing practical benefits for developing customer-valued functions in semi-autonomous vehicles. The findings contribute to a new methodology for enhancing the lane change assistance function and underscore the importance of understanding specific lane change scenarios for efficient and safe driving experiences.
Recommended Citation
Micus, Christian; Hasert, Christina; Kankanhalli, Atreyi; Böhm, Markus; and Krcmar, Helmut, "DRIVING INTO THE FUTURE: REVOLUTIONIZING DRIVING ASSISTANCE FOR CUSTOMERS’ LANE CHANGE BEHAVIORS" (2024). PACIS 2024 Proceedings. 20.
https://aisel.aisnet.org/pacis2024/track19_userbeh/track19_userbeh/20
DRIVING INTO THE FUTURE: REVOLUTIONIZING DRIVING ASSISTANCE FOR CUSTOMERS’ LANE CHANGE BEHAVIORS
In the era of digital transformation, automotive companies are rapidly evolving towards customer integration and innovation. This study addresses a critical issue of low usage rates for the lane change assistance function in advanced driving assistance systems. While existing literature focuses on labeling lane change maneuvers in terms of appropriateness at a given moment, overlooking the frequency and classification of different lane change scenarios. This study selects and combines over 104,000 lane change events extracted from customer fleet data and applies the k-means clustering algorithm. The five distinct cluster groups indicate the categorization and frequency of different lane change scenarios. This approach is based on real customer usage data, providing practical benefits for developing customer-valued functions in semi-autonomous vehicles. The findings contribute to a new methodology for enhancing the lane change assistance function and underscore the importance of understanding specific lane change scenarios for efficient and safe driving experiences.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
User