Mobile Robot Localization Using Sonar
IEEE Transactions on Pattern Analysis and Machine Intelligence
Physically Based Simulation Model for Acoustic Sensor Robot Navigation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Monte Carlo localization for mobile robots
Artificial Intelligence
Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans
Journal of Intelligent and Robotic Systems
The Vahm Robotized Wheelchair: System Architecture and Human-Machine Interaction
Journal of Intelligent and Robotic Systems
Architectural Concepts of a Semi-autonomous Wheelchair
Journal of Intelligent and Robotic Systems
Hi-index | 0.00 |
The work described in this paper is a contribution to providing mobility aid for people with motor disability. It constitutes a part of the VAHM project which aims to design a smart powered wheelchair able to control its displacements in a known environment. Original methods established for the static localisation of the wheelchair using readings provided by a belt of 14 ultrasonic sensors is presented. This approach is based on a classical matching of occupancy grids. Yet because of the presence of the person on the wheelchair any complementary movement intended to obtain additional measures is impossible. That is why our study is centred on the search for the best way to represent ultrasound measures, to model environment and to define the matching criterion in order to mitigate the imperfections of ultrasonic sensors. The method thus developed is implemented on our prototype. Examples are given of the tests carried out in real-life conditions in a typical environment consisting of a flat recreated in our laboratory. The results obtained using real and simulated readings show that the approach is reliable and fitted to our project.