An Inertia-Based Surface Identification System

Jens Windau and Wei-Min Shen. An Inertia-Based Surface Identification System. In Proc. 2010 IEEE Intl. Conf. on Robotics and Automation, Anchorage, Alaska, USA, May 2010.

Download

[731.4kB pdf] 

Abstract

In many robotics applications, knowing thematerial properties around a robot is often critical for therobot�s successful performance. For example, in mobility,knowledge about the ground surface may determine the successof a robot�s gait. In manipulation, the physical properties of anobject may dictate the results of a grasping strategy. Thus, areliable surface identification system would be invaluable forthese applications. This paper presents an Inertia-BasedSurface Identification System (ISIS) based on accelerometersensor data. Using this system, a robot actively �knocks� on asurface with an accelerometer-equipped device (e.g., hand orleg), collects the accelerometer data in real-time, and thenanalyzes and extracts three critical physical properties, thehardness, the elasticity, and the stiffness, of the surface. Alookup table and k-nearest neighbors techniques are used toclassify the surface material based on a database of previouslyknown materials. This technique is low-cost and efficient incomputation. It has been implemented on the modular and selfreconfigurableSuperBot and has achieved high accuracy (95%and 85%) in several identification experiments with real-worldmaterial.

BibTeX Entry

@InProceedings{windau2010inertia-based-surfaces-identification,
  abstract	= {In many robotics applications, knowing the
material properties around a robot is often critical for the
robot�s successful performance. For example, in mobility,
knowledge about the ground surface may determine the success
of a robot�s gait. In manipulation, the physical properties of an
object may dictate the results of a grasping strategy. Thus, a
reliable surface identification system would be invaluable for
these applications. This paper presents an Inertia-Based
Surface Identification System (ISIS) based on accelerometer
sensor data. Using this system, a robot actively �knocks� on a
surface with an accelerometer-equipped device (e.g., hand or
leg), collects the accelerometer data in real-time, and then
analyzes and extracts three critical physical properties, the
hardness, the elasticity, and the stiffness, of the surface. A
lookup table and k-nearest neighbors techniques are used to
classify the surface material based on a database of previously
known materials. This technique is low-cost and efficient in
computation. It has been implemented on the modular and selfreconfigurable
SuperBot and has achieved high accuracy (95%
and 85%) in several identification experiments with real-world
material.},
  address	= {Anchorage, Alaska, USA},
  author	= {Jens Windau and Wei-Min Shen},
  booktitle	= icra-10,
  month		= may,
  title		= {An Inertia-Based Surface Identification System},
  year		= {2010}
}