Terrain Recognition for Smart Wheelchair
Research interest in robotic wheelchairs is driven in part by their potential for improving the independence and quality-of-life of persons with disabilities and the elderly. However the large majority of research to date has focused on indoor operations.
- PDF / 1,268,928 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 45 Downloads / 166 Views
Abstract. Research interest in robotic wheelchairs is driven in part by their potential for improving the independence and quality-of-life of persons with disabilities and the elderly. However the large majority of research to date has focused on indoor operations. In this paper, we aim to develop a smart wheelchair robot system that moves independently in outdoor terrain smoothly. To achive this, we propose a robotic wheelchair system that is able to classify the type of outdoor terrain according to their roughness for the comfort of the user and also control the wheelchair movements to avoid drop-off and watery areas on the road. An artificial neural network based classifier is constructed to classify the patterns and features extracted from the Laser Range Sensor (LRS) intensity and distance data. The overall classification accuracy is 97.24 % using extracted features from the intensity and distance data. These classification results can in turn be used to control the motor of the smart wheelchair. Keywords: Surface
Feature extraction Classification ANFIS LRS
1 Introduction and Motivation In recent years, millions of people around the world have exhibited mobility impairments due to aging problems. Several robotic wheelchairs possessing user-friendly interfaces and/or autonomous functions for reaching a goal have been proposed to meet the needs of an aging society [1, 4]. There are two kinds of wheelchairs that are used for the elderly or disabled people. Manual wheelchairs are widely used around the world by those who are able to control the wheelchair by hand. But it needs extra labor to control the direction of the wheel. Powered wheelchairs are more convenient to run but need a high level of attention to control the motor using a joy stick or remote control. Furthermore, such conventional control interfaces are sometimes forbidden by doctors for elderly because of safety concerns. Thus the development of powered wheelchairs that can overcome doctors’ safety concerns would be of great benefit to many. In fact, [3] found that around 3 million people could benefit from such wheelchairs. Moreover, elderly wheelchair users are often accompanied by caregivers or companions. Thus, in designing wheelchair technology it is important to consider how we can reduce the caregiver’s workload and support communication between user and caregiver [5]. Smart wheelchairs are a potential solution to these issues, which
© Springer International Publishing Switzerland 2016 D.-S. Huang et al. (Eds.): ICIC 2016, Part III, LNAI 9773, pp. 461–470, 2016. DOI: 10.1007/978-3-319-42297-8_43
462
S.A. Mamun et al.
could also have the option of granting many elderly wheelchair users the independence of controlling their wheelchairs on their own. Smart wheelchairs can be either driven by the user or computer system that can follow the caregiver’s movements to drive itself [6, 7]. Such a wheelchair follows the caregiver autonomously, by detecting the registered person in the system. But it is more important to detect the surface condi
Data Loading...
