Easing Wheelchair Control by Gaze-based Estimation of Intended Motion

Bartolein, Christian; Wagner, Achim; Jipp, Meike; Badreddin, Essameddin

doi:10.3182/20080706-5-kr-1001.01549

Cited by 15 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…First, natural eye-movements during keyboard control were recorded, followed by gaze data while using each of the interfaces for the virtual wheelchair keyboard control. Such demonstrations show the necessity of using natural gaze behavior as signal commands to control wheelchair navigation [Christian Bartolein et al, 2008]. Most of the aforementioned studies propose eye-based wheelchair control interfaces, which often require more effort by the user and lead to abnormal gaze behavior.…”

Section: B Gaze Control For Wheelchair Drivingmentioning

confidence: 99%

Natural Gaze Data-Driven Wheelchair

Raymond

Piccini

Subramanian

et al. 2018

Preprint

View full text Add to dashboard Cite

Abstract-Natural eye movements during navigation have long been considered to reflect planning processes and link to user's future action intention. We investigate here whether natural eye movements during joystick-based navigation of wheel-chairs follow identifiable patterns that are predictive of joystick actions. To place eye movements in context with driving intentions, we combine our eye tracking with a 3D depth camera system, which allows us to identify which eye movements have the floor as gaze target and distinguish them from other non-navigation related eye movements. We find consistent patterns of eye movements on the floor predictive of steering commands issued by the driver in all subjects. Based on this empirical data we developed two gaze decoders using supervised machine learning techniques and enabled each of these drivers to then steer the wheelchair by imagining they were using a joystick to trigger appropriate natural eye movements via motor imagery. We show that all subjects are able to navigate their wheelchair "by eye" learning it within a short time span of minutes. Our work shows that simple gazebased decoding without need for artificial user interfaces suffices to restore mobility and increasing participation in daily life.

show abstract

Section: B Gaze Control For Wheelchair Drivingmentioning

confidence: 99%

Natural Gaze Data-Driven Wheelchair

Raymond

Piccini

Subramanian

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Applying these results to control wheelchair motions, the system enhanced usability. Until now, our work has been developed for a wheelchair system using a Hidden Markov Model (HMM) [11]. We collected much of the data on a subject's gaze direction while the wheelchair moves, and the data is applied to the HMM.…”

Section: A Related Workmentioning

confidence: 99%

Wheelchair control based on a polynomial function approximating a user's gaze curve

Furuya

Alexopoulos

Badreddin

et al. 2016

2016 IEEE/SICE International Symposium on System Integration (SII)

Self Cite

View full text Add to dashboard Cite

Abstract-We propose a new wheelchair control system based on a polynomial function approximating a user's gaze curve. Conventional studies utilizing gaze data recognized three wheelchair movements: "go straight," "turn right," and "turn left." However, it was difficult for the system to assess when it should switch wheelchair motions because the user's gaze was always changing. To solve this problem, we divided "turn right" and "turn left" wheelchair movements into three groups each in order to control the wheelchair easily. Consequently, the system has to recognize seven wheelchair movements: straight, and three groups each for turning right and left. It is not sufficiency for a system to assess seven wheelchair movements by only the user's gaze. Thus, we developed a wheelchair system considering not only the user's gaze but also the angular velocity and acceleration to control wheelchair motions. We approximated the user's gaze using a polynomial function, and calculated the fine gaze angle, angular velocity and acceleration. The effectiveness of the proposed method was shown by experimental results.

show abstract

“…many approaches were proposed such as wheelesly by Holly A.Yanco et al [10] involving a graphical interface with direction commands activated by the user gaze, also Chern-Sheng LIN et al [7], proposed an optical-ty p e tracking to control powered wheelchair using a calibration algorithm for gaze estimation in real time so that they can control a nine zone divided interface. Christian Bartolein et al [11] focused on how to distinguish between relevant and non relevant gaze behavior so they can improve safety in wheelchair navigation. This was made by determining a set of gaze patterns (straight, preparing left/right, turning left/right, realigning left/right, searching left/right, and distracted left/right) which will be translated into translational and rotational velocity to initiate the wheelchair motion.…”

Section: A Gaze-based Interfacesmentioning

confidence: 99%