Moving Horizons Estimation for Wheelchair Trajectory Repeatability in the Home
- 273 Downloads
An advantage of Moving Horizons Estimation in contrast with the previously tested Extended Kalman Filter is presented in the context of achieving a useful form of teach/repeat for wheelchairs of severely disabled veterans within their homes. The ability to combine numerical integrals of the measured wheel rotations of the chair with chair-mounted cameras and camera-based observations of wall-mounted fiducials within a trailing, selected “window” based on the “taught” trajectory, in order to precisely and reliably repeat that trajectory, is presented. The importance and real-time feasibility of the observation-batch-selection protocol—which is applied both to the teaching data and, in real time, to the tracking data—is discussed. Experimental illustration uses the trajectory shown in https://youtu.be/7Yrc3IuXBus.
This research was supported in part by the US Department of Veterans Affairs, and in part by the Naval Center for Applied Research in Artificial Intelligence, US Office of Naval Research.
- 1.L. Fehr, E. Langbein, S. Skaar, Adequacy of power wheelchair control interfaces for persons with severe disabilities: a clinical survey. J. Rehabil. Res. Dev. 37(3), 253–260 (2000)Google Scholar
- 3.M. Perrollaz, S. Khorbotly, A. Cool, J. Yoder, E. Baumgartner, Teachless teach-repeat: toward vision-based programming of industrial robots, in Proceedings of IEEE International Conference on Robotics and Automation, St Paul, MN, USA (May 2012)Google Scholar
- 4.T. Whitworth, Fixturing for automated welding in automotive—repeatability, access, and protection are key. MetalForming 48(2) (2014)Google Scholar
- 5.H. Goldstein, Classical Mechanics, 3rd edn. (Addison Wesley, 1980), p. 16Google Scholar
- 6.A. Gelb (ed.), Applied Optimal Estimation (MIT Press), 1974Google Scholar
- 8.J.L. Junkins, C. White, J. Turner, Star pattern recognition for real-time attitude determination. J. Astronaut. Sci. 25, 251–270 (1977)Google Scholar
- 9.D. Belsley, E. Kuh, R. Welsch, The Condition Number, Regression Diagnostics: Identifying Influential Data and Sources of Collinearity (John Wiley & Sons, New York), pp. 100–104Google Scholar