Non-parametric learning for natural plan generation
Non-parametric learning for natural plan generation
复制标题
DOI：
10.1109/iros.2010.5651569
复制
发表时间：
2010-12
期刊：
影响因子：
--
通讯作者：
Ian A. Baldwin;P. Newman
中科院分区：
文献类型：
--
作者：
Ian A. Baldwin;P. Newman
我们提出了一种新的方法，通过利用专家数据来学习基于采样的运动规划器的采样分布。我们学习感兴趣的语义区域周围的样本密度的估计(在非参数设置中)，并将这些学习的分布合并到基于抽样的计划器中以产生自然计划。我们的动机是，工作空间的某些方面对计划策略有局部影响，这取决于它们在哪里和在什么地方。如果在原始特征空间中学习训练数据的密度估计是不可行的，我们利用非线性降维技术，对低维嵌入进行密度估计。然后将样本从该嵌入密度提升到原始特征空间，产生的样本仍然很接近原始分布。这项工作的一个目标是了解环境中的各种特征如何影响专家的行为--例如，人行横道、交通信号等如何影响司机。我们表明，从这些语义区域周围的专家轨迹数据学习样本分布会导致更自然的路径，这些路径明显更接近专家的路径。我们以一个虚拟的汽车机器人和一个简单的机械手为例，论证了该技术在不同场景中的可行性，并对比了语义偏向分布的规划轨迹与传统技术的差异。
We present a novel way to learn sampling distributions for sampling-based motion planners by making use of expert data. We learn an estimate (in a non-parametric setting) of sample densities around semantic regions of interest, and incorporate these learned distributions into a sampling-based planner to produce natural plans. Our motivation is that certain aspects of the workspace have a local influence on planning strategies, which is dependent both on where, and what, they are. In the event that learning the density estimate of the training data is impractical in the original feature space, we utilize a non-linear dimensionality-reduction technique and perform density estimation on a lower-dimensional embedding. Samples are then lifted from this embedded density into the original feature space, producing samples that still well approximate the original distribution. A goal of this work is to learn how various features in the environment influence the behavior of experts - for example, how pedestrian crossings, traffic signals and so on affect drivers. We show that learning sampling distributions from expert trajectory data around these semantic regions leads to more natural paths that are measurably closer to those of an expert. We demonstrate the feasibility of the technique in various scenarios for a virtual car-like robotic vehicle and a simple manipulator, contrasting the differences in planned trajectories of the semantically-biased distributions with conventional techniques.