Special Issue on Skill Transfer Learning for Autonomous Robots and Human-Robot Cooperation
摘要截稿:
全文截稿: 2019-10-01
影响因子: 2.825
期刊难度:
CCF分类: 无
中科院JCR分区:
• 大类 : 计算机科学 - 2区
• 小类 : 自动化与控制系统 - 3区
• 小类 : 计算机:人工智能 - 3区
• 小类 : 机器人学 - 3区
Overview
Human and many animals usually preserve the skill knowledge learned in the past and utilize it to help future learning and problem solving. Without the ability to summarize and update skill knowledge, a robot typically needs large amounts of training samples, which may be inaccessible in rapidly-changing environments. Therefore, the skill transfer learning, which mimics the human learning process and capability, becomes an important component for autonomous robots. In addition, robots should persistently learn skill from the human demonstrations. Different from conventional machine learning, skill transfer learning focuses continuous learning process in changing conditions. Although skill transfer learning has attracted attentions from diversified communities, its cognitive mechanism and applications in autonomous robots have not been fully exploited, and many challenging problems remain unsolved.
This special issue mainly focuses on skill transfer learning for autonomous robots and human-robot cooperation, addressing both original algorithmic development and new applications of cognitive autonomous learning. We are soliciting original contributions, of leading researchers and practitioners from academia as well as industry, which address a wide range of theoretical and application issues in skill transfer learning. Topics for this special issue include, but are not limited to:
List of topics
· Theoretical foundations of skill transfer learning
· Cognitive mechanism of skill transfer learning
· Online and incremental skill learning for long-term autonomy
· Multi-modal skill acquisition and representation
· Cross-modal skill transfer
· Human-robot cooperation for skill learning
· Skill learning from human demonstrations
· Benchmark for skill transfer learning
· Evaluation criteria for skill transfer learning
· Real-world applications of skill transfer learning