Multimodal real-time contingency detection for HRI
Multimodal real-time contingency detection for HRI
复制标题
HRI 的多模态实时意外事件检测
DOI：
10.1109/iros.2014.6943025
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
A. Thomaz
中科院分区：
文献类型：
--
作者：
Vivian Chu;Kalesha Bullard;A. Thomaz
我们的目标是开发能够自然地让人们参与社交交流的机器人。在本文中，我们重点关注识别人对机器人的交互请求做出响应的问题。受人类认知的启发，我们的方法是将其视为意外事件检测问题。我们提出了一个简单的判别性支持向量机 (SVM) 分类器，以与 Lee 等人之前的工作中引入的生成方法进行比较。 [1]。我们以两种方式评估这些方法。首先，通过在受控设置中收集的一组批量数据上训练三个具有多模式感觉输入的独立 SVM，我们获得的平均 F1 分数为 0.82。其次，在一个有 7 名参与者的开放式实验环境中，我们表明我们的模型能够实时执行意外事件检测，并推广到新人，最佳 F1 分数为 0.72。
Our goal is to develop robots that naturally engage people in social exchanges. In this paper, we focus on the problem of recognizing that a person is responsive to a robot's request for interaction. Inspired by human cognition, our approach is to treat this as a contingency detection problem. We present a simple discriminative Support Vector Machine (SVM) classifier to compare against previous generative methods introduced in prior work by Lee et al. [1]. We evaluate these methods in two ways. First, by training three separate SVMs with multi-modal sensory input on a set of batch data collected in a controlled setting, where we obtain an average F1 score of 0.82. Second, in an open-ended experiment setting with seven participants, we show that our model is able to perform contingency detection in real-time and generalize to new people with a best F1 score of 0.72.