Incremental Semantically Grounded Learning from Demonstration
Incremental Semantically Grounded Learning from Demonstration
复制标题
从示范中渐进式基于语义的学习
DOI：
10.15607/rss.2013.ix.048
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Sarah Osentoski
中科院分区：
文献类型：
--
作者：
S. Niekum;Sachin Chitta;A. Barto;B. Marthi;Sarah Osentoski
最近机器人从演示学习的许多工作都集中在自动将连续任务演示分割成更简单、可重用的原语。然而，通常会对如何对这些原语进行排序做出强有力的假设，从而限制了数据重用的潜力。我们引入了一种新颖的方法，用于发现基于语义的原语，并逐步构建和改进可能出现各种意外情况的任务的有限状态表示。具体来说，Beta 过程自回归隐马尔可夫模型用于自动将演示分割为运动类别，然后在有限状态自动机中进一步细分为语义基础状态。在重放任务期间，数据驱动的方法用于通过交互式校正收集最需要的附加数据，然后将其用于改进有限状态自动机。总之，这允许对原语进行智能排序，以创建新颖的自适应行为，并可以根据需要逐步改进。我们使用 PR2 移动机械手演示了该技术在家具组装任务中的实用性。
Much recent work in robot learning from demonstration has focused on automatically segmenting continuous task demonstrations into simpler, reusable primitives. However, strong assumptions are often made about how these primitives can be sequenced, limiting the potential for data reuse. We introduce a novel method for discovering semantically grounded primitives and incrementally building and improving a finite-state representation of a task in which various contingencies can arise. Specifically, a Beta Process Autoregressive Hidden Markov Model is used to automatically segment demonstrations into motion categories, which are then further subdivided into semantically grounded states in a finite-state automaton. During replay of the task, a data-driven approach is used to collect additional data where they are most needed through interactive corrections, which are then used to improve the finite-state automaton. Together, this allows for intelligent sequencing of primitives to create novel, adaptive behavior that can be incrementally improved as needed. We demonstrate the utility of this technique on a furniture assembly task using the PR2 mobile manipulator.