Collaborative robots are increasingly present in industry to support human activities. However, to make the human-robot collaborative process more effective, there are several challenges to be addressed. Collaborative robotic systems need to be aware of the human activities to (1) anticipate collaborative/assistive actions, (2) learn by demonstration, and (3) activate safety procedures in shared workspace. This study proposes an action classification system to recognize primitive assembly tasks from human motion events data captured by a Dynamic and Active-pixel Vision Sensor (DAVIS). Several filters are compared and combined to remove event data noise. Task patterns are classified from a continuous stream of event data using advanced deep learning and recurrent networks to classify spatial and temporal features. Experiments were conducted on a novel dataset, the dataset of manufacturing tasks (DMT22), featuring 5 classes of representative manufacturing primitives (PickUp, Place, Screw, Hold, Idle) from 5 participants. Results show that the proposed filters remove about 65\% of all events (noise) per recording, conducting to a classification accuracy up to 99,37\% for subjects that trained the system and 97.08\% for new subjects. Data from a left-handed subject were successfully classified using only right-handed training data. These results are object independent.
翻译:协作机器人越来越多地应用于工业领域,以支持人类活动。然而,为了使人机协作过程更加有效,需要解决几个挑战。协作机器人系统需要知道人类活动,以便(1)预测协作/辅助行动,(2)通过示范学习,和(3)在共享工作空间中启动安全程序。本研究提出了一个行动分类系统,以识别通过 Dynamic and Active-pixel Vision Sensor (DAVIS) 捕获的人体动作事件数据中的基本组装任务。对比并结合了几种滤波器以去除事件数据噪声。使用先进的深度学习和递归网络从连续的事件数据流中分类任务模式,以分类空间和时间特征。实验数据集是一个新颖的数据集,即制造任务数据集 (DMT22),其中包含了 5 个类别的代表性制造基本任务(拾取、放置、螺丝、保持、空闲)和 5 名参与者。结果表明,所提出的滤波器约可去除每个记录的 65\% 事件数据(噪声),从而使系统的经过训练的实验者分类准确率高达 99.37\%,对于新实验者的分类准确率为 97.08\%。仅使用右手的训练数据成功分类来自左手的参与者的数据。这些结果是物体无关的。