arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.07472cs.RO
收藏

无监督接触学习在类人机器人估计与控制中的应用

Unsupervised Contact Learning for Humanoid Estimation and Control

Computational Learning and Motor Control Lab, University of Southern California(南加州大学计算学习与运动控制实验室);Autonomous Motion Department, Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所自主运动系);New York University(纽约大学)

Nicholas Rotella, Stefan Schaal, Ludovic Righetti

摘要:

这项工作提出了一种接触状态估计的方法,使用模糊聚类学习接触概率为全,六维人形接触。训练所需的数据仅来自本体感受传感器-末端效应器接触扳手传感器和惯性测量单元(IMU)-并且该方法完全无人监督。所得到的聚类方法被用来有效地计算接触的概率在六个endeffector自由度(DoF)独立。这种基于聚类的接触概率估计器在基于运动学的基本状态估计器中进行了验证,该估计器在模拟环境中具有逼真的增加的传感器噪声,用于在粗糙,低摩擦地形上的机器人受到脚滑动和旋转的运动。利用这六个DoF接触概率估计的拟议基本状态估计器的性能比纯粹基于测量的法向力确定运动接触约束的估计器要好得多。

英文摘要:

This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑