TY - GEN
T1 - BBEEP
T2 - 2019 CHI Conference on Human Factors in Computing Systems, CHI 2019
AU - Kayukawa, Seita
AU - Higuchi, Keita
AU - Guerreiro, João
AU - Morishima, Shigeo
AU - Sato, Yoichi
AU - Kitani, Kris
AU - Asakawa, Chieko
N1 - Funding Information:
We thank the Allegheny County Airport Authority and all study participants. This work was sponsored in part by JST CREST (JPMJCR14E1), JST AIP-PRISM (JPMJCR18ZG), NSF NRI award (1637927), NIDILRR (90DPGE0003), Uptake (CMU ML for Social Good fund) and Shimizu Corporation.
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/5/2
Y1 - 2019/5/2
N2 - We present an assistive suitcase system, BBeep, for supporting blind people when walking through crowded environments. BBeep uses pre-emptive sound notifcations to help clear a path by alerting both the user and nearby pedestrians about the potential risk of collision. BBeep triggers notifcations by tracking pedestrians, predicting their future position in real-time, and provides sound notifcations only when it anticipates a future collision. We investigate how diferent types and timings of sound afect nearby pedestrian behavior. In our experiments, we found that sound emission timing has a signifcant impact on nearby pedestrian trajectories when compared to diferent sound types. Based on these fndings, we performed a real-world user study at an international airport, where blind participants navigated with the suitcase in crowded areas. We observed that the proposed system signifcantly reduces the number of imminent collisions.
AB - We present an assistive suitcase system, BBeep, for supporting blind people when walking through crowded environments. BBeep uses pre-emptive sound notifcations to help clear a path by alerting both the user and nearby pedestrians about the potential risk of collision. BBeep triggers notifcations by tracking pedestrians, predicting their future position in real-time, and provides sound notifcations only when it anticipates a future collision. We investigate how diferent types and timings of sound afect nearby pedestrian behavior. In our experiments, we found that sound emission timing has a signifcant impact on nearby pedestrian trajectories when compared to diferent sound types. Based on these fndings, we performed a real-world user study at an international airport, where blind participants navigated with the suitcase in crowded areas. We observed that the proposed system signifcantly reduces the number of imminent collisions.
KW - Blind navigation
KW - Collision prediction
KW - Obstacle avoidance
KW - Path clearing
KW - Pedestrian detection
KW - Visual impairments
UR - http://www.scopus.com/inward/record.url?scp=85067623950&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067623950&partnerID=8YFLogxK
U2 - 10.1145/3290605.3300282
DO - 10.1145/3290605.3300282
M3 - Conference contribution
AN - SCOPUS:85067623950
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2019 - Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 4 May 2019 through 9 May 2019
ER -