Head and shoulders: automatic error detection in human-robot interaction
Head and shoulders: automatic error detection in human-robot interaction
复制标题
头部和肩膀：人机交互中的自动错误检测
DOI：
10.1145/3136755.3136785
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
M. Tscheligi
中科院分区：
文献类型：
--
作者：
P. Trung;M. Giuliani;Michael Miksch;Gerald Stollnberger;Susanne Stadler;Nicole Mirnig;M. Tscheligi
我们描述了一种在人机交互中自动检测错误的新方法。我们的方法是根据与错误机器人交互的人的头部和肩部运动的分类来检测错误。我们进行了一项用户研究，参与者与我们编程的机器人互动，犯下了两种类型的错误：违反社会规范和技术失败。在互动过程中，我们用Kinect v1 RGB-D摄像头记录了参与者的行为。总体而言，我们以每秒25帧的速度记录了237,998帧的数据语料库；83.48%的帧没有错误情况；16.52%的帧显示错误情况。此外，我们计算了六个不同的特征集来表示参与者的动作和他们动作的时间方面。使用这些数据，我们训练了一个规则学习器、一个朴素贝叶斯分类器和一个k近邻分类器，并用10倍交叉验证和留一交叉验证对分类器进行了评估。评估结果表明：(1)当机器人以前见过人类时，错误情况的检测工作很好；(2)当机器人与已知人类交互时，规则学习器和k-近邻分类器很好地用于自动错误检测；(3)对于未知的人类，朴素贝叶斯分类器表现最好；(4)对违反社会规范的分类表现最差；(5)使用原始数据和代表参与者相对位置的归一化特征集之间没有太大的性能差异。
We describe a novel method for automatic detection of errors in human-robot interactions. Our approach is to detect errors based on the classification of head and shoulder movements of humans who are interacting with erroneous robots. We conducted a user study in which participants interacted with a robot that we programmed to make two types of errors: social norm violations and technical failures. During the interaction, we recorded the behavior of the participants with a Kinect v1 RGB-D camera. Overall, we recorded a data corpus of 237,998 frames at 25 frames per second; 83.48% frames showed no error situation; 16.52% showed an error situation. Furthermore, we computed six different feature sets to represent the movements of the participants and temporal aspects of their movements. Using this data we trained a rule learner, a Naive Bayes classifier, and a k-nearest neighbor classifier and evaluated the classifiers with 10-fold cross validation and leave-one-out cross validation. The results of this evaluation suggest the following: (1) The detection of an error situation works well, when the robot has seen the human before; (2) Rule learner and k-nearest neighbor classifiers work well for automated error detection when the robot is interacting with a known human; (3) For unknown humans, the Naive Bayes classifier performed the best; (4) The classification of social norm violations does perform the worst; (5) There was no big performance difference between using the original data and normalized feature sets that represent the relative position of the participants.
DOI：
--
发表时间：
--
期刊：
--
影响因子：
--
作者：
Barnan Das;D. Cook;N. C. Krishnan;M. Schmitter-Edgecombe
通讯作者：
Barnan Das;D. Cook;N. C. Krishnan;M. Schmitter-Edgecombe