Portable navigations system with adaptive multimodal interface for the blind

Lock, Jacobus, Cielniak, Grzegorz and Bellotto, Nicola (2017) Portable navigations system with adaptive multimodal interface for the blind. In: AAAI 2017 Spring Symposium - Designing the User Experience of Machine Learning Systems, 27th-29th March 2017, Stanford, CA.

25413 Lock2017.pdf
25413 Lock2017.pdf - Whole Document

Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive


Recent advances in mobile technology have the potential to radically change the quality of tools available for people with sensory impairments, in particular the blind. Nowadays almost every smart-phone and tablet is equipped with high resolutions cameras, which are typically used for photos and videos, communication purposes, games and virtual reality applications. Very little has been proposed to exploit these sensors for user localisation and navigation instead. To this end, the “Active Vision with Human-in-the-Loop for the Visually Impaired” (ActiVis) project aims to develop a novel electronic travel aid to tackle the “last 10 yards problem” and enable the autonomous navigation of blind users in unknown environments, ultimately enhancing or replacing existing solutions, such as guide dogs and white canes. This paper describes some of the key project’s challenges, in particular with respect to the design of the user interface that translate visual information from the camera to guiding instructions for the blind person, taking into account limitations due to the visual impairment and proposing a multimodal interface that embeds human-machine co-adaptation.

Keywords:active vision, co-adaptation, multimodal interface, HCI, visual impairment
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G440 Human-computer Interaction
G Mathematical and Computer Sciences > G740 Computer Vision
H Engineering > H672 Cybernetics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25413
Deposited On:26 Dec 2016 11:52

Repository Staff Only: item control page