This paper presents an innovative feature signal transmission approach incorpo-rating block-based haptic data reduction to address time-delayed teleoperation. Numerous data reduction techniques rely on perceptual deadband (DB). In the preceding block-based approaches, the whole block within the DB is discarded. However, disregarding all signals within the DB loses too much information and hinders effective haptic signal tracking, as these signals contain valuable infor-mation for signal reconstruction. Consequently, we propose a feature signal transmission approach based on the block algorithm that aggregates samples as a unit, enabling high-quality haptic data reduction. In our proposed approach, we employ max-pooling to extract feature signals from the signals within the DB. These feature signals are then transmitted by adjusting the content of the trans-mission block. This methodology enables the transmission of more useful infor-mation without introducing additional delay, aside from the inherent algorithmic delay. Experimental results demonstrate the superiority of our approach over oth-er state-of-the-art (SOTA) methods on various assessment measures under dis-tinct channel delays.

翻译：本文提出一种创新的特征信号传输方法，融合基于块的触觉数据压缩技术，以应对时延遥操作问题。现有数据压缩技术多依赖感知死区（DB）。在先前的基于块方法中，整个DB内的数据块均被丢弃。然而，忽略DB内所有信号会损失过多信息，并阻碍有效的触觉信号跟踪——因为这些信号包含对信号重构有价值的信息。为此，我们提出一种基于块算法的特征信号传输方法，将采样点聚合为单元，实现高质量的触觉数据压缩。在该方法中，我们采用最大池化提取DB内信号的特征信号，并通过调整传输块的内容进行传输。除算法固有延迟外，该方案无需引入额外延迟即可传输更多有用信息。实验结果表明，在不同信道时延条件下，本方法在多项评估指标上均优于现有最优（SOTA）方法。