An analysis of RelaxedIK: an optimization-based framework for generating accurate and feasible robot arm motions

An analysis of RelaxedIK: an optimization-based framework for generating accurate and feasible robot arm motions
复制标题

RelaxedIK 分析:基于优化的框架,用于生成准确可行的机器人手臂运动

DOI:
10.1007/s10514-020-09918-9
复制
发表时间:
2020
期刊:
影响因子:
3.5
通讯作者:
Gleicher, Michael
Gleicher, Michael
中科院分区:
计算机科学3区
文献类型:
--
作者:
Rakita, Daniel;Mutlu, Bilge;Gleicher, Michael

文献摘要

参考文献

被引文献

相似文献

我们提出了一个实时的运动合成方法的机器人操纵器,calledRelaxedIK,这不仅能够准确地匹配末端执行器的构成目标,传统的IK解算器,但也创建平滑,可行的运动,避免关节空间的不连续性,自碰撞,和运动学奇异性。为了实现这些目标的飞行中,我们投标准的IK制定作为一个加权和非线性优化问题,这样的运动目标,除了末端效应器姿态匹配可以被编码为条款的总和。我们提出了一个规范化的程序,使我们的方法是能够有效地进行权衡,同时调和许多,并可能竞争,目标。使用这些权衡,我们的公式允许功能berelaxedwhen在冲突与其他功能被认为在给定的时间更重要。我们比较性能对一个国家的最先进的IK求解器和实时运动规划方法在几个几何和现实世界的任务7个机器人平台,从5自由度到8自由度。我们表明,我们的方法实现了运动,有效地遵循位置和方向的末端执行器的目标,而不牺牲运动的可行性,从而更成功地执行任务相比,基线方法。我们还根据经验评估了我们的求解器如何使用不同的优化求解器,梯度计算方法和目标函数中损失函数的选择。
We present a real-time motion-synthesis method for robot manipulators, calledRelaxedIK, that is able to not only accurately match end-effector pose goals as done by traditional IK solvers, but also create smooth, feasible motions that avoid joint-space discontinuities, self-collisions, and kinematic singularities. To achieve these objectives on-the-fly, we cast the standard IK formulation as a weighted-sum non-linear optimization problem, such that motion goals in addition to end-effector pose matching can be encoded as terms in the sum. We present a normalization procedure such that our method is able to effectively make trade-offs to simultaneously reconcile many, and potentially competing, objectives. Using these trade-offs, our formulation allows features to berelaxedwhen in conflict with other features deemed more important at a given time. We compare performance against a state-of-the-art IK solver and a real-time motion-planning approach in several geometric and real-world tasks on seven robot platforms ranging from 5-DOF to 8-DOF. We show that our method achieves motions that effectively follow position and orientation end-effector goals without sacrificing motion feasibility, resulting in more successful execution of tasks compared to the baseline approaches. We also empirically evaluate how our solver performs with different optimization solvers, gradient calculation methods, and choice of loss function in the objective function.
DOI: 10.15607/rss.2018.xiv.043
发表时间: 2018-06
期刊: Robotics: Science and Systems XIV
影响因子: --
作者:
D. Rakita;Bilge Mutlu;Michael Gleicher
通讯作者: D. Rakita;Bilge Mutlu;Michael Gleicher
DOI: 10.1007/978-3-030-43089-4_32
发表时间: 2017
影响因子: 1.8
作者:
Kris K. Hauser
通讯作者: Kris K. Hauser
DOI: 10.1109/38.55154
发表时间: 1990
影响因子: 1.8
作者:
A. A. Maciejewski
通讯作者: A. A. Maciejewski
DOI: 10.1109/70.56660
发表时间: 1990-06-01
期刊: IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION
影响因子: --
作者:
GOSSELIN, C;ANGELES, J
通讯作者: ANGELES, J
DOI: 10.1126/scirobotics.aaw0955
发表时间: 2019-05-29
期刊: SCIENCE ROBOTICS
影响因子: 25
作者:
Rakita, Daniel;Mutlu, Bilge;Hiatt, Laura M.
通讯作者: Hiatt, Laura M.