Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning
Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning
复制标题
DOI：
--
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
M. A. Rana;Mustafa Mukadam;S. Ahmadzadeh;S. Chernova;Byron Boots
中科院分区：
文献类型：
--
作者：
M. A. Rana;Mustafa Mukadam;S. Ahmadzadeh;S. Chernova;Byron Boots
在本文中，我们提出了演示和运动规划的组合学习（CLAMP）作为技能学习和泛化技能再现的有效方法。 CLAMP 将演示学习 (LfD) 和运动规划的优势结合到一个统一的框架中。我们进行概率推理，以找到针对给定技能的最佳轨迹，并且在不同场景下也是可行的。我们使用因子图优化来加速推理。为了编码最优性，我们提供了一种基于随机动力系统的新概率技能模型。该技能模型需要最少的参数调整来学习，适合对技能约束进行编码，并允许高效的推理。初步实验结果显示了机器人初始状态和不可预见障碍的技能泛化。
In this paper, we present Combined Learning from demonstration And Motion Planning (CLAMP) as an efficient approach to skill learning and generalizable skill reproduction. CLAMP combines the strengths of Learning from Demonstration (LfD) and motion planning into a unifying framework. We carry out probabilistic inference to find trajectories which are optimal with respect to a given skill and also feasible in different scenarios. We use factor graph optimization to speed up inference. To encode optimality, we provide a new probabilistic skill model based on a stochastic dynamical system. This skill model requires minimal parameter tuning to learn, is suitable to encode skill constraints, and allows efficient inference. Preliminary experimental results showing skill generalization over initial robot state and unforeseen obstacles are presented.