Knowledge-Based Ultra-Low-Latency Semantic Communications for Robotic Edge Intelligence

摘要

The <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sixth-generation</i> (6G) mobile networks will feature the widespread deployment of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">artificial intelligence</i> (AI) algorithms at the network edge, which provides a platform for supporting robotic edge intelligence systems. In such a system, a large-scale <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">knowledge graph</i> (KG) is operated at an edge server as a “remote brain” to guide remote robots on environmental exploration or task execution. In this paper, we present a new air-interface framework targeting the said systems, called knowledge-based robotic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">semantic communications</i> (SemCom), which consists of a protocol and relevant transmission techniques. First, the proposed robotic SemCom protocol defines a sequence of system operations for executing a given robotic task. They include identification of all task-relevant <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">knowledge paths</i> (KPs) on the KG, semantic matching between KG and object classifier, and uploading of robot’s observations for objects recognition and feasible KP identification. Next, to support <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ultra-low-latency (observation) feature transmission</i> (ULL-FT), we propose a novel transmission approach that exploits classifier’s robustness, which is measured by <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">classification margin</i>, to compensate for a high <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">bit error probability</i> (BEP) resulting from ultra-low-latency transmission (e.g., short packet and/or no coding). By utilizing the tractable <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Gaussian mixture</i> (GM) model, we mathematically derive the relation between BEP and classification margin under constraints on classification accuracy and transmission latency. The result sheds light on system requirements to support ULL-FT. Furthermore, for the case where the classification margin is insufficient for coping with channel distortion, we enhance the ULL-FT approach by studying retransmission and multi-view classification for enlarging the margin and further quantifying corresponding requirements. Finally, experiments using deep neural networks as classifier models and real datasets are conducted to demonstrate the effectiveness of ULL-FT in communication latency reduction while providing a guarantee on accurate feasible KP identification.