Abstract | ||
---|---|---|
This paper describes an approach to surface identification in the context of mobile robotics, applicable to supervised and unsupervised learning. The identification is based on analyzing the tip acceleration patterns induced in a metallic rod, dragged along a surface that is to be identified. Eight features in time and frequency domains are used for classification. Results show that for ten type of indoor and outdoor surfaces, reliable identification can be achieved (90.0 and 94.6 percent for a 1 and 4 seconds time-window, respectively), using a non-sophisticated classifier (artificial neural network). Demonstration is done on how such a sensor and a simple control strategy can be used to guide a blind robot, using a simulation and a real differential drive robot. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ROBOT.2009.5152662 | ICRA |
Keywords | Field | DocType |
frequency domain,metallic rod,surface identification,mobile robotics,seconds time-window,non-sophisticated classifier,reliable identification,simple contact dynamic,blind robot,artificial neural network,real differential drive robot,outdoor surface,transducers,data mining,mobile robots,tactile sensors,accelerometers,acceleration,unsupervised learning,tactile sensor,testing,mobile robot | Computer vision,Accelerometer,Control engineering,Unsupervised learning,Artificial intelligence,Engineering,Robot,Classifier (linguistics),Artificial neural network,Mobile robot,Robotics,Tactile sensor | Conference |
Volume | Issue | ISSN |
2009 | 1 | 1050-4729 |
Citations | PageRank | References |
10 | 0.62 | 13 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Philippe Giguere | 1 | 45 | 4.51 |
Gregory Dudek | 2 | 2163 | 255.48 |