Rapidly Learning Generalizable and Robot-Agnostic Tool-Use Skills for a Wide Range of Tasks.
Rapidly Learning Generalizable and Robot-Agnostic Tool-Use Skills for a Wide Range of Tasks.
复制标题
DOI:
10.3389/frobt.2021.726463
复制
发表时间:
2021
影响因子:
3.4
通讯作者:
Scassellati B
中科院分区:
文献类型:
--
作者:
Qin M;Brawer J;Scassellati B
Many real-world applications require robots to use tools. However, robots lack the skills necessary to learn and perform many essential tool-use tasks. To this end, we present the TRansferrIng Skilled Tool Use Acquired Rapidly (TRI-STAR) framework for task-general robot tool use. TRI-STAR has three primary components: 1) the ability to learn and apply tool-use skills to a wide variety of tasks from a minimal number of training demonstrations, 2) the ability to generalize learned skills to other tools and manipulated objects, and 3) the ability to transfer learned skills to other robots. These capabilities are enabled by TRI-STAR’s task-oriented approach, which identifies and leverages structural task knowledge through the use of our goal-based task taxonomy. We demonstrate this framework with seven tasks that impose distinct requirements on the usages of the tools, six of which were each performed on three physical robots with varying kinematic configurations. Our results demonstrate that TRI-STAR can learn effective tool-use skills from only 20 training demonstrations. In addition, our framework generalizes tool-use skills to morphologically distinct objects and transfers them to new platforms, with minor performance degradation.
登录
查看更多内容
影响因子:
9.2
作者:
Kuan Fang;Zhu, Yuke;Savarese, Silvio
通讯作者:
Savarese, Silvio
影响因子:
4.3
作者:
Hoffmann, Heiko;Chen, Zhichao;Sinapov, Jivko
通讯作者:
Sinapov, Jivko
影响因子:
64.8
作者:
Burger, Benjamin;Maffettone, Phillip M.;Cooper, Andrew I.
通讯作者:
Cooper, Andrew I.
影响因子:
5.2
作者:
Gao, Wei;Tedrake, Russ
通讯作者:
Tedrake, Russ
影响因子:
9.2
作者:
Lioutikov, Rudolf;Neumann, Gerhard;Peters, Jan
通讯作者:
Peters, Jan