A Situation-Aware Fear Learning (SAFEL) model for robots

详细信息    查看全文

• 作者：Caroline Rizzi^a ; ^{cr519@kent.ac.uk}Author Vitae ; Colin G. Johnson^a ; ^{C.G.Johnson@kent.ac.uk}Author Vitae ; Fabio Fabris^a ; ^{ff79@kent.ac.uk}Author Vitae ; Patricia A. Vargas^b ; ^{p.a.vargas@hw.ac.uk}Author Vitae
• 关键词：Contextual fear conditioning ; Brain Emotional Learning ; Temporal pattern ; Affective computing ; Autonomous robotics ; Amygdala and hippocampus modeling
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：19 January 2017
• 年：2017
• 卷：221
• 期：Complete
• 页码：32-47
• 全文大小：1535 K
• 卷排序：221

文摘

This work proposes a novel Situation-Aware FEar Learning (SAFEL) model for robots. SAFEL combines concepts of situation-aware expert systems with well-known neuroscientific findings on the brain fear-learning mechanism to allow companion robots to predict undesirable or threatening situations based on past experiences. One of the main objectives is to allow robots to learn complex temporal patterns of sensed environmental stimuli and create a representation of these patterns. This memory can be later associated with a negative or positive “emotion”, analogous to fear and confidence. Experiments with a real robot demonstrated SAFEL's success in generating contextual fear conditioning behavior with predictive capabilities based on situational information.