This paper describes the software and hardware implementation of a mobile robotic sculpture. This work is the result of the meeting of robotics and art. The robot is able to locate people in the environment, to navigate toward them avoiding the obstacles and to approach them as a polite waiter will do. In fact, the sculpture represents a waiter and a waitress. The waiters chat among them (by play different pre recorded voice files) when wandering in the environment. Once the robot locates a person and get close to her, it asks the customer different questions like: ”Would you like a drink?”, that is the title of the sculpture. The robot development started from an idea of the artist Albano Guatti. The final shape and appearance of the statue was already determined before the design of the robot integrated in the sculpture to provide it with autonomous behaviours. Therefore, from the beginning strong constraints were posed to the possible robot mechanical structure and sensors. The robot’s main sensor an omnidirectional camera (well integrated with the artistic appearance of the statue). The omnidirectional camera was chosen with respect to classical perspective cameras to provide the robot with the feeling of being immerse in the environment thanks to the 360° field of view of the camera. The people detection software is based on two filters: a motion detection filter based on the background subtraction algorithm and a skin detection filter, based on a new skin detection filter working in a generalised colour space. The omnidirectional visual perception is coupled to an omnidirectional range sensor realized with a ring of Polaroid sonar sensors. The sonars are used to detect obstacles in the environment to avoid them and to calculate the distance of the people to be approached. The sonars data are processed using a modified VHF (Vector Field Histogram) to be robust to the intrinsic noise of these sensors. We designed and realized a simple photoresistor circuit that can light reflectivity discontinuity on the floor. This can be used to bound the working space of the robot by using a carpet as working space or by putting tape stripes on the floor bounding the working area. The hardware and software design was driven by the experience maturated in our laboratori during the Middle-Size RoboCup Competitions. Our students were able to port what they learnt in the didactical experience of the RoboCup into a commercial product realized in collaboration between the IAS-Lab of the University of Padua and IT+Robotics srl a spin-off of the University of Padua.

An interactive robotic sculpture

MENEGATTI, EMANUELE;PRETTO, ALBERTO;TONELLO, STEFANO;
2006

Abstract

This paper describes the software and hardware implementation of a mobile robotic sculpture. This work is the result of the meeting of robotics and art. The robot is able to locate people in the environment, to navigate toward them avoiding the obstacles and to approach them as a polite waiter will do. In fact, the sculpture represents a waiter and a waitress. The waiters chat among them (by play different pre recorded voice files) when wandering in the environment. Once the robot locates a person and get close to her, it asks the customer different questions like: ”Would you like a drink?”, that is the title of the sculpture. The robot development started from an idea of the artist Albano Guatti. The final shape and appearance of the statue was already determined before the design of the robot integrated in the sculpture to provide it with autonomous behaviours. Therefore, from the beginning strong constraints were posed to the possible robot mechanical structure and sensors. The robot’s main sensor an omnidirectional camera (well integrated with the artistic appearance of the statue). The omnidirectional camera was chosen with respect to classical perspective cameras to provide the robot with the feeling of being immerse in the environment thanks to the 360° field of view of the camera. The people detection software is based on two filters: a motion detection filter based on the background subtraction algorithm and a skin detection filter, based on a new skin detection filter working in a generalised colour space. The omnidirectional visual perception is coupled to an omnidirectional range sensor realized with a ring of Polaroid sonar sensors. The sonars are used to detect obstacles in the environment to avoid them and to calculate the distance of the people to be approached. The sonars data are processed using a modified VHF (Vector Field Histogram) to be robust to the intrinsic noise of these sensors. We designed and realized a simple photoresistor circuit that can light reflectivity discontinuity on the floor. This can be used to bound the working space of the robot by using a carpet as working space or by putting tape stripes on the floor bounding the working area. The hardware and software design was driven by the experience maturated in our laboratori during the Middle-Size RoboCup Competitions. Our students were able to port what they learnt in the didactical experience of the RoboCup into a commercial product realized in collaboration between the IAS-Lab of the University of Padua and IT+Robotics srl a spin-off of the University of Padua.
2006
Proc. of Workshop on Educational Robotics
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11577/1556907
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact