Efficient nonparametric belief propagation for pose estimation and manipulation of articulated objects

Efficient nonparametric belief propagation for pose estimation and manipulation of articulated objects
复制标题

用于关节物体姿态估计和操纵的高效非参数置信传播

DOI:
10.1126/scirobotics.aaw4523
复制
发表时间:
2019
期刊:
影响因子:
25
通讯作者:
Jenkins, Odest Chadwicke
Jenkins, Odest Chadwicke
中科院分区:
计算机科学1区
文献类型:
--
作者:
Desingh, Karthik;Lu, Shiyang;Opipari, Anthony;Jenkins, Odest Chadwicke

文献摘要

参考文献

被引文献

相似文献

在人类环境中工作的机器人经常遇到各种各样的铰接物体,例如工具,橱柜和其他关节物体。这样的铰接对象可以采取无限数量的可能姿态,作为潜在的高维连续空间中的一个点。机器人必须感知这种连续的姿态,以将物体操纵到所需的姿态。由于其高维性和多模态的不确定性,这个问题的感知和操纵的铰接对象仍然是一个挑战。在这里,我们描述了一个因素的方法来估计关节对象的姿态,使用一种有效的方法,非参数的信念传播。我们认为输入的几何模型与关节约束和观察RGBD(红色,绿色,蓝色和深度)传感器数据。所描述的框架迭代地产生对象部分姿态信念。该问题被配制成一个成对马尔可夫随机场(MRF),其中每个隐藏节点(连续姿态变量)是一个观察到的对象部分的姿态和边缘表示部分之间的关节约束。我们描述了铰接姿态估计的“拉”的非参数信念传播(PMPNBP)的消息传递算法,并评估其收敛性能与铰接对象的场景。机器人实验证明了保持信念的必要性,以执行目标驱动的操作任务。
Robots working in human environments often encounter a wide range of articulated objects, such as tools, cabinets, and other jointed objects. Such articulated objects can take an infinite number of possible poses, as a point in a potentially high-dimensional continuous space. A robot must perceive this continuous pose to manipulate the object to a desired pose. This problem of perception and manipulation of articulated objects remains a challenge due to its high dimensionality and multimodal uncertainty. Here, we describe a factored approach to estimate the poses of articulated objects using an efficient approach to nonparametric belief propagation. We consider inputs as geometrical models with articulation constraints and observed RGBD (red, green, blue, and depth) sensor data. The described framework produces object-part pose beliefs iteratively. The problem is formulated as a pairwise Markov random field (MRF), where each hidden node (continuous pose variable) is an observed object-part’s pose and the edges denote the articulation constraints between the parts. We describe articulated pose estimation by a “pull” message passing algorithm for nonparametric belief propagation (PMPNBP) and evaluate its convergence properties over scenes with articulated objects. Robot experiments are provided to demonstrate the necessity of maintaining beliefs to perform goal-driven manipulation tasks.
通过公理场景估计进行目标导向的机器人操纵
DOI: 10.1177/0278364916683444
发表时间: 2017
期刊: The international journal of robotics research
影响因子: --
作者:
Sui, Zhiqiang;Xiang, Lingzhu;Jenkins, Odest C;Desingh, Karthik
通讯作者: Desingh, Karthik
DOI: --
发表时间: 2014
期刊: Fusion
影响因子: --
作者:
Igor Gilitschenski;G. Kurz;S. Julier;U. Hanebeck
通讯作者: U. Hanebeck
DOI: 10.1613/jair.3229
发表时间: 2011-01-01
影响因子: 5
作者:
Sturm, Juergen;Stachniss, Cyrill;Burgard, Wolfram
通讯作者: Burgard, Wolfram
用于杂乱操作的物理上合理的场景估计
DOI: 10.1109/humanoids.2016.7803404
发表时间: 2016
期刊: 2016 IEEE-RAS 16th International Conference on
影响因子: --
作者:
Desingh, Karthik;Jenkins, Odest Chadwicke;Reveret, Lionel;Sui, Zhiqiang
通讯作者: Sui, Zhiqiang
DOI: --
发表时间: 2011
期刊: International Conference on Artificial Intelligence and Statistics
影响因子: --
作者:
Le Song;A. Gretton;Danny Bickson;Yucheng Low;Carlos Guestrin
通讯作者: Carlos Guestrin