Cities worldwide adopted lockdown policies in response to the outbreak of coronavirus disease 2019 (COVID-19), significantly influencing people's travel behavior. In particular, micro-mobility, an emerging mode of urban transport, is profoundly shaped by this crisis. However, there is limited research devoted to understanding the rapidly evolving trip patterns of micro-mobility in response to COVID-19. To fill this gap, we analyze the changes in micro-mobility usage before and during the lockdown period exploiting high-resolution micro-mobility trip data collected in Zurich, Switzerland. Specifically, docked bike, docked e-bike, and dockless e-bike are evaluated and compared from the perspective of space, time and semantics. First, the spatial and temporal analysis results uncover that the number of trips decreased remarkably during the lockdown period. The striking difference between the normal and lockdown period is the decline in the peak hours of workdays. Second, the origin-destination flows are used to construct spatially embedded networks. The results suggest that the origin-destination pairs remain similar during the lockdown period, while the numbers of trips between each origin-destination pair is reduced due to COVID-19 pandemic. Finally, the semantic analysis is conducted to uncover the changes in trip purpose. It is revealed that the proportions of Home, Park, and Grocery activities increase, while the proportions of Leisure and Shopping activities decrease during the lockdown period. The above results can help planners and policymakers better make evidence-based policies regarding micro-mobility in the post-pandemic society.

Large language models (LLMs) as autonomous agents offer a novel avenue for tackling real-world challenges through a knowledge-driven manner. These LLM-enhanced methodologies excel in generalization and interpretability. However, the complexity of driving tasks often necessitates the collaboration of multiple, heterogeneous agents, underscoring the need for such LLM-driven agents to engage in cooperative knowledge sharing and cognitive synergy. Despite the promise of LLMs, current applications predominantly center around single-agent scenarios, which limits their scope in the face of intricate, interconnected tasks. To broaden the horizons of knowledge-driven strategies and bolster the generalization capabilities of autonomous agents, we propose the $\mathsf {KoMA}$ framework consisting of the multi-agent interaction, the multi-step planning, the shared-memory, and the ranking-based reflection modules to enhance multi-agents' decision-making in complex driving scenarios. Based on the framework's generated text descriptions of driving scenarios, the multi-agent interaction module enables LLM agents to analyze and infer the intentions of surrounding vehicles based on scene information, akin to human cognition. The multi-step planning module enables LLM agents to analyze and obtain final action decisions layer by layer to ensure consistent goals for short-term action decisions. The shared memory module can accumulate collective experience to make superior decisions, and the ranking-based reflection module can evaluate and improve agent behavior with the aim of enhancing driving safety and efficiency. The $\mathsf {KoMA}$ framework not only enhances the robustness and adaptability of autonomous driving agents but also significantly elevates their generalization capabilities across diverse scenarios. Empirical results demonstrate the superiority of our approach over traditional methods, particularly in its ability to handle complex, unpredictable driving environments without extensive retraining. Project Page: https://jkmhhh.github.io/KoMA/ .