Abstract: The ActiVis project's aim is to build a mobile guidance aid to help people with limited vision find objects in an unknown environment. This system uses bone-conduction headphones to transmit audio signals to the user and requires an effective non-visual interface. To this end, we propose a new audio-based interface that uses a spatialised signal to convey a target's position on the horizontal plane. The vertical position on the median plan is given by adjusting the tone's pitch to overcome the audio localisation limitations of bone-conduction headphones. This interface is validated through a set of experiments with blindfolded and visually impaired participants.
Abstract: Modern smartphones can provide a multitude of services to assist people with visual impairments. The cameras embedded in these mobile devices, in particular, can be useful for many tasks, like reading signs or searching for objects in unknown environments. Although previous research in computer vision has looked at ways to solve these tasks by processing the video frames of the mobile camera, very little work has been done in actively guiding the user towards specific points of interest that maximise the effectiveness of the underlying visual algorithms. In this paper, we propose a control algorithm based on a Markov Decision Process (MDP) that generates real-time instructions to guide a user searching for a target object with a smartphone's camera. The solution is part of a more general active vision application for the visually impaired. An initial implementation of the system on an Android smartphone was experimentally evaluated with sighted participants to determine the performance of the control algorithm. The results show the effectiveness of our solution and its potential application to help the visually impaired find objects in unknown environments.
Abstract: 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 and partially sighted. Nowadays almost every smart-phone and tablet is equipped with high-resolution cameras, typically used for photos, videos, 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 blind users to independently navigate in unknown environments, ultimately enhancing or replacing existing solutions such as guide dogs and white canes. This paper describes some of the project’s key challenges, in particular with respect to the design of a user interface (UI) that translates visual information from the camera to guidance instructions for the blind person, taking into account the limitations introduced by visual impairment. In this paper we also propose a multimodal UI that caters to the needs of the visually impaired that exploits human-machine progressive co-adaptation to enhance the user’s experience and improve navigation performance.
Abstract: The Solar Thermal Energy Research Group (STERG) is investigating ways to make heliostats cheaper to reduce the total cost of a concentrating solar power (CSP) plant. One avenue of research is to use unmanned aerial vehicles (UAVs) to automate and assist with the heliostat calibration process. To do this, the pose estimation error of each UAV must be determined and integrated into a calibration procedure. A computer vision (CV) system is used to measure the pose of a quadcopter UAV. However, this CV system contains considerable measurement errors. Since this is a high-dimensional problem, a sophisticated prediction model must be used to estimate the measurement error of the CV system for any given pose measurement vector. This paper attempts to train and validate such a model with the aim of using it to determine the pose error of a quadcopter in a CSP plant setting.
Abstract: Our aim is to build a navigation system for the visually impaired that uses a combination of feedback modes to guide the user to his/her destination. In this paper, we investigate the effectiveness of a spatial audio tone with a varying pitch component, played with bone-conducting headphones, in conveying the pan and tilt angles of a target to the user in a pointing task. We also wish to see how changes in the behaviour of the pitch affects a user's performance. We conducted a set of experiments with blindfolded users and found that the varying pitch component works well in conveying the tilt angle of a target. Furthermore, we were able to determine that the audio interface adheres to Fitts's Law and used it as a metric to determine which pitch setting produces the best results. We discovered a trade-off between the speed and accuracy in the pointing task, which are maximised when the tone-settings is adjusted to low and high respectively.
Available upon request from the authors
Abstract: In this paper we discuss the concept of co-adaptation between a human operator and a machine interface and we summarize its application with emphasis on two different domains, teleoperation and assistive technology. The analysis of the literature reveals that only in a few cases the possibility of a temporal evolution of the co-adaptation parameters has been considered. In particular, it has been overlooked the role of time-related indexes that capture changes in motor and cognitive abilities of the human operator. We argue that for a more effective long-term co-adaptation process, the interface should be able to predict and adjust its parameters according to the evolution of human skills and performance. We thus propose a novel approach termed progressive co-adaptation, whereby human performance is continuously monitored and the system makes inferences about changes in the users’ cognitive and motor skills. We illustrate the features of progressive co-adaptation in two possible applications, robotic telemanipulation and active vision for the visually impaired.
Abstract: The diffuse availability of mobile devices, such as smartphones and tablets, has the potential to bring substantial benefits to the people with sensory impairments. The solution proposed in this paper is part of an ongoing effort to create an accurate obstacle and hazard detector for the visually impaired, which is embedded in a hand-held device. In particular, it presents a proof of concept for a multimodal interface to control the orientation of a smartphone’s camera, while being held by a person, using a combination of vocal messages, 3D sounds and vibrations. The solution, which is to be evaluated experimentally by users, will enable further research in the area of active vision with human-in-the-loop, with potential application to mobile assistive devices for indoor navigation of visually impaired people.