Learning Object Signiicance with an Emotion Based Process G Erald Foliot

This paper presents an emotion based process gener ating cognition through learning Two models are de scribed which investigates the possibilities of designing cognitive systems based on emotion In order to test these models through experiments we used a mobile robot simulator Webots modeling the real Khepera robot The rst proposed model is the simplest since it uses only positive and negative reinforcement signals as well as proximity sensors The robot learns to avoid obstacles based on re ex reaction and on reinforcement signals The second model relying on appraisal theory is more complex It involves the use of reinforcement signals proximity sensors and a simulated color cam era to learn in particular to associate visual stimulus with the appropriate behavior Interesting simulation results demonstrate the signi cance of this promising approach