Color Recognition for NAO Robot Using Sugeno Fuzzy System and Evidence Theory

Thanh Long Nguyen (1) , Reda Boukezzoula (1) , Didier Coquin (1) , Stephane Perrin (1)

1 LISTIC - Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance

This paper examines the problem of recognition of col- ored objects for the NAO humanoid robot using camer- as. Based on the ability of fuzzy systems to approxi- mate any mapping, the input-output behavior between the triplet {H, S, V} and the linguistic output colors is represented by a Sugeno fuzzy system. In order to im- prove the recognition performance of the robot, more cameras are used. In this case, a decision mechanism based on the Dempster-Shafer (DS) theory is employed to resolve the conflict between cameras. The feasibility of the proposed methodology has been experimentally validated with a real-time implementation.

Mots clés: NAO robot; Sugeno fuzzy system; Dempster-Shafer; Color recognition; Information fusion

Domaines: Traitement du signal et de l'image [eess.SP]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Théorie de l'information [cs.IT]; Robotique [cs.RO]

Thanh Long Nguyen, Reda Boukezzoula, Didier Coquin, Stephane Perrin. Color Recognition for NAO Robot Using Sugeno Fuzzy System and Evidence Theory. 16th World Congress of the International Fuzzy Systems Association (IFSA), Jun 2015, Gijon, Spain. pp.1176-1183, ⟨10.2991/ifsa-eusflat-15.2015.166⟩. ⟨hal-01172051⟩