Abstract
SUMMARYThis paper deals with the perception mode of smart wheelchairs. First we evoke the many mobility aid prototypes developed in rehabilitation robotics by considering the point of view of perception. Then we describe the localization mode of the VAHM**. We show how the odometric, ultrasound, and vision sensors are used in a complementary way in order to locate the wheelchair in its known environment. The mode of adjustment of the odometric position by the least-squared method using ultrasonic measurements is detailed. Then the use of vision to perceive the vertical segments of the environment so as to refine the orientation is presented. The results of the tests carried out on the wheelchair are given and commented.
Publisher
Cambridge University Press (CUP)
Subject
Computer Science Applications,General Mathematics,Software,Control and Systems Engineering
Reference30 articles.
1. 29. Kreutner M. and Horn O. , “Co-operation between ultrasound and monocular vision for the localization of a mobile robot,” CESA'2003, Lille, France (2003).
2. 13. Demeester E. , Nuttin M. , Vanhooydonck D. and Van Bruusel H. , “A Model-based, Probabilistic Framework for Plan Recognition in Shared Wheelchair Control: Experiments and Evaluation,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems 2003, Las Vegas, USA, pp. 1456–1461.
3. Real-time localisation of a low-cost mobile robot with poor ultrasonic data
4. 18. Diaz S. V. , Rodriguez C. A. , Diaz del Rio F. , Balcells A. C. and Muniz D. C. , “Tetranauta: A Intelligent Wheelchair for Users with very Severe Mobility Restrictions,” Proceedings of the International Conference on Control Applications, Glasgow, Scotland UK. (2002) pp. 778–783.
5. 14. Kuno Y. , Murakami Y. and Shimada N. , “User and Social Interfaces by Observing Human Faces for Intelligent Wheelchairs,” ACM International Conference, Proceeding of Workshop on Perceptive User Interfaces, Orlando, Florida, USA (2001) pp. 1–4.
Cited by
18 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献