Typical contact detection is based on the monitoring of a threshold value in the force and torque signals. The selection of a threshold is challenging for robots operating in unstructured or highly dynamic environments, such in a household setting, due to the variability of the characteristics of the objects that might be encountered. We propose a multimodal contact detection approach using time and frequency domain features which model the distinctive characteristics of contact events in the auditory and haptic modalities. In our approach the monitoring of force and torque thresholds is not necessary as detection is based on the characteristics of force and torque signals in the frequency domain together with the impact sound generated by the manipulation task. We evaluated our approach with a typical glass placing task in a household setting. Our experimental results show that robust contact detection (99.94% mean cross-validation accuracy) is possible independent of force/torque threshold values and suitable of being implemented for operation in highly dynamic scenarios.
翻译:典型的接触探测基于对力量和压力信号的临界值的监测。选择一个临界值对于在无结构或高度动态的环境中运行的机器人来说具有挑战性,因为可能遇到的物体的特性各不相同。我们建议采用多式接触探测方法,利用时间和频率域特征来模拟在听觉和机能模式中接触事件的独特性。在我们的方法中,对力量和压力阈值的监测是没有必要的,因为检测是基于频率域中的力和托克信号的特点以及操纵任务产生的影响声。我们用典型的玻璃在家庭环境中放置任务来评估我们的方法。我们的实验结果表明,强力接触探测(99.94%表示交叉校验精度)可能独立于强力/压力阈值,并适合在高度动态的情景下运行。