Directions, Methods and Metrics for Mapping Human to Robot Motion with Functional Anthropomorphism:
Directions, Methods and Metrics for Mapping Human to Robot Motion with Functional Anthropomorphism:
复制标题
通过功能拟人化将人映射到机器人运动的方向、方法和指标：
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
K. Kyriakopoulos
中科院分区：
文献类型：
--
作者：
Minas Liarokapis;P. Artemiadis;Charalampos P. Bechlioulis;K. Kyriakopoulos
在这篇文章中，我们提供了方向、方法和度量，可以用来合成一个完整的框架，用于映射具有功能拟人化的人到机器人的运动。这样的映射可以用于执行从人类到具有任意运动学的机器人手臂手系统的技能转移。提出的映射方案，首先保证机器人伪影在三维空间中执行特定的功能(任务空间功能约束)，然后优化机器人运动的拟人化。通过最小化人类和机器人手臂系统配置之间的结构差异，实现了机器人运动的类人化。所提出的方法适用于广泛的应用，从自主抓取规划的演示学习，到远程或危险环境中与机械臂手系统的实时遥操作和遥操作。
In this paper we provide directions, methods and metrics that can be used to synthesize a complete framework for mapping human to robot motion with Functional Anthropomorphism. Such a mapping can be used in order to perform skill transfer from humans to robot arm hand systems with arbitrary kinematics. The mapping schemes proposed, first guarantees the execution of specific functionalities by the robotic artifact in 3D space (task space functional constraints), and then optimizes anthropomorphism of robot motion. Human-likeness of robot motion is achieved through minimization of structural dissimilarity between human and robot arm hand system configurations. The proposed methodology is suitable for a wide range of applications ranging from learn by demonstration for autonomous grasp planning, to real time teleoperation and telemanipulation with robot arm hand systems in remote or dangerous environments.