A new paradigm for teaching machines to replicate the manipulation skills of humans using tactile sensing in a virtual environment

在虚拟环境中使用触觉感知来教授机器复制人类操作技能的新范例。该提案的广泛目标是研究精神运动领域的机器学习，并通过利用具有触觉感知的虚拟训练环境的演示，展示将物理约束的操作技能从人类操作员在线转移到机械手的可行性。所提出的工作在其方法和假设上是独特的，并将为从人类到机器的操作技能转移的本质提供新的见解。它将产生新的通用智能算法和方法来模拟机器中人类心理运动学习的不同阶段，包括感知、模仿、机制和复杂/公开反应。

A new paradigm for teaching machines to replicate the manipulation skills of humans using tactile sensing in a virtual environment. The broad aims of this proposal are to study machine learning in the psychomotor domain, and to show the feasibility of on line transfer of physically constrained manipulation skills from a human operator to a manipulator through demonstration utilising a virtual training environment with tactile sensing. The proposed work is unique in its approach and hypothesis, and will provide a new insight into the nature of transfer of manipulation skills from human to machine. It will produce new generic intelligent algorithms and methodologies to emulate different stages of human psychomotor learning in machine including perception, imitation, mechanism and complex/overt response.