Authors:
Alfredo Chávez Plascencia
and
Jaroslav Rozman
Affiliation:
Brno University of Technology, Czech Republic
Keyword(s):
Assistive Technology, Sensor Fusion, Autonomous Wheelchair.
Related
Ontology
Subjects/Areas/Topics:
Human-Machine Interfaces
;
Informatics in Control, Automation and Robotics
;
Mobile Robots and Autonomous Systems
;
Robot Design, Development and Control
;
Robotics and Automation
Abstract:
This paper presents a work in progress study of a novel user-wheelchair shared control paradigm for individuals with severe motor impairments, which consists of an optimal distribution between several modes, from full user control up to autonomous driving one. To this end, a C400 Permobil wheelchair has been equipped with a control command communication interface and with a scanning laser and a RGB-D sensors to carry out the automation algorithms that are part of the robot operating system (ROS) framework. Moreover, sensor data fusion for map making based on the Bayesian method is applied to the Xtion Pro Live RGB-D camera and the Hokuyo laser sensor data readings. These latter are interpreted by a probabilistic heuristic model that abstracts
the beam into a ray casting to an occupied grid cell. Preliminary pilot tests were performed in two different room shapes. The first one in a two room laboratory with a narrow doorway, and the second one in a corridor. The former experiment was
dropped due to failure to success, whereas, the latter was a successful one. This has been tested with three different modalities; hand-joystick, tongue-joystick and autonomous modes respectively. The successful results of the second pilot-test have proven the feasibility of using a combination of autonomous and manual control of a powered wheelchair in order to continue development towards a shared-control paradigm.
(More)