Enhancing intelligence in multi-agent systems with edge-assisted causal knowledge aggregation

Abstract Dynamic and uncertain environments pose major challenges for multi-agent autonomous systems, particularly in achieving robust simultaneous localization and mapping (SLAM) and efficient knowledge sharing across robots. Conventional data-driven methods often overlook underlying causal structures, resulting in spurious correlations and limited generalization. To address this, we present CASK—an edge-assisted causal knowledge aggregation framework that fuses structured causal inference with data-driven learning to improve adaptive decision-making. A key feature is a time-based normalization mechanism that ensures mapping consistency across varying operational speeds, enabling speed-independent transfer of spatial knowledge between heterogeneous agents. We validate CASK through simulations and real-world experiments using autonomous ground vehicles, a class of mobile robots. Results show substantial gains over state-of-the-art methods: up to 20% higher success at low speeds, 40% at high speeds, 50% lower trajectory deviation, and 45% fewer re-planning steps. These findings demonstrate how causal inference combined with mobile edge computing enables scalable, reliable, and generalizable autonomy in multi-agent systems.