Robot navigation in dense crowds requires understanding social cues that humans naturally use, yet existing methods struggle with real-world complexity. We investigate two questions: (1) Where do pedestrians look when navigating crowds? and (2) Can eye tracking improve robot navigation? To answer, we introduce GazeNav, an egocentric dataset collected via wearable eye trackers, featuring synchronized video, gaze, and trajectories in crowded environments. Analysis reveals that the gaze of pedestrians is closely related to the semantic presence and movement of other individuals, exhibiting distinct attention patterns across navigation behaviors. Building on this, we propose Gaze2Nav, a modular framework that first predicts human gaze to infer socially salient pedestrians, then incorporates the semantic attention into motion planning alongside visual inputs. Our method achieves 87.6% salient pedestrian prediction accuracy and reduces trajectory error by 15.4% over state-of-the-art baselines. By aligning with human gaze, our framework improves both performance and interpretability, advancing toward human-like, socially intelligent robot navigation.

Abstract Reliability evaluation of multiprocessor systems is of significant importance in the design and maintenance of multiprocessor systems. Based on edge-connectivity, more refined quantitative indicators for the reliability of multiprocessor systems have been introduced. The extra edge-connectivity and the component edge-connectivity, as two important parameters to evaluate the robustness of multiprocessor systems, are explored extensively. In this paper, we determine the $h$-extra edge-connectivity and the $(g+1)$-component edge-connectivity of the balanced complete $t$-partite graph $K_{r}^{t}$ for $t, r\geq 2$, where $1\leq h \leq \lfloor tr/2 \rfloor$ and $2\leq g \leq tr-1$.