TY - GEN
T1 - CarFi
T2 - 20th IEEE International Conference on Mobile Ad Hoc and Smart Systems, MASS 2023
AU - Munir, Sirajum
AU - Chen, Hongkai
AU - Fang, Shiwei
AU - Monjur, Mahathir
AU - Lin, Shan
AU - Nirjon, Shahriar
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - With the rise of hailing services, people are increasingly relying on shared mobility (e.g., Uber, Lyft) drivers to pick up for transportation. However, such drivers and riders have difficulties finding each other in urban areas as GPS signals get blocked by skyscrapers, in crowded environments (e.g., in stadiums, airports, and bars), at night, and in bad weather. It wastes their time, creates a bad user experience, and causes more CO2 emissions due to idle driving. In this paper, we explore the potential of Wi-Fi to help drivers to determine the street side of the riders. Our proposed system CarFi uses Wi-Fi CSI from two antennas placed inside a moving vehicle, and leverages signal processing and data-driven techniques for this purpose. After collecting real-world data in realistic and challenging settings by blocking the signal with other people and parked cars, we see that CarFi achieves 95.44% accuracy in rider-side determination in both line-of-sight (LoS) and non-line-of-sight (nLoS) conditions and can be run on an embedded GPU in real-time.
AB - With the rise of hailing services, people are increasingly relying on shared mobility (e.g., Uber, Lyft) drivers to pick up for transportation. However, such drivers and riders have difficulties finding each other in urban areas as GPS signals get blocked by skyscrapers, in crowded environments (e.g., in stadiums, airports, and bars), at night, and in bad weather. It wastes their time, creates a bad user experience, and causes more CO2 emissions due to idle driving. In this paper, we explore the potential of Wi-Fi to help drivers to determine the street side of the riders. Our proposed system CarFi uses Wi-Fi CSI from two antennas placed inside a moving vehicle, and leverages signal processing and data-driven techniques for this purpose. After collecting real-world data in realistic and challenging settings by blocking the signal with other people and parked cars, we see that CarFi achieves 95.44% accuracy in rider-side determination in both line-of-sight (LoS) and non-line-of-sight (nLoS) conditions and can be run on an embedded GPU in real-time.
KW - Automotive
KW - Localization
KW - Lyft
KW - self driving cars
KW - Uber
KW - Wi Fi
KW - Wi Fi CSI
UR - https://www.scopus.com/pages/publications/85178516973
U2 - 10.1109/MASS58611.2023.00072
DO - 10.1109/MASS58611.2023.00072
M3 - Conference contribution
AN - SCOPUS:85178516973
T3 - Proceedings - 2023 IEEE 20th International Conference on Mobile Ad Hoc and Smart Systems, MASS 2023
SP - 530
EP - 538
BT - Proceedings - 2023 IEEE 20th International Conference on Mobile Ad Hoc and Smart Systems, MASS 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 25 September 2023 through 27 September 2023
ER -