Designing efficient tools for modeling and analyzing transportation trajectories help improve various smart city services, e.g., location prediction, business recommendation and traffic forecasting. Yet with limited historical travel data, conventional tools are faced with challenges in representing the sophisticated contextual and spatiotemporal relationships inherent in transportation trajectories, while such trajectories have strong functional, geographical and time-specific characteristics. In this work, we propose an imitative transportation trajectory generation framework with multi-source urban knowledge enhancement. Specifically, we first construct Know-ST, an urban knowledge fusion framework that captures cross-domain knowledge (i.e., road network, point of interest, etc.) via tailored urban knowledge graph representation learning. The Know-ST preserves the temporal characteristics of trajectories and can continuously adapt to newly arriving trajectories. Moreover, we formulate the trajectory generation problem as a sequential imitation learning process, where an adversarially trained generator network is equipped to autonomously capture both the spatiotemporal and contextual information within individual transportation trajectories. Extensive experiments on real-world dataset show Know-ST outperforms multiple baselines under a variety of benchmarks, indicating the effectiveness of the proposed framework.

To achieve accurate and robust pose estimation in Simultaneous Localization and Mapping (SLAM) task, multisensor fusion is proven to be an effective solution and thus provides great potential in robotic applications. This paper proposes FAST-LIVO, a fast LiDAR-Inertial-Visual Odometry system, which builds on two tightly-coupled and direct odometry subsystems: a VIO subsystem and a LIO subsystem. The LIO subsystem registers raw points (instead of feature points on e.g., edges or planes) of a new scan to an incrementally-built point cloud map. The map points are additionally attached with image patches, which are then used in the VIO subsystem to align a new image by minimizing the direct photometric errors without extracting any visual features (e.g., ORB or FAST corner features). To further improve the VIO robustness and accuracy, a novel outlier rejection method is proposed to reject unstable map points that lie on edges or are occluded in the image view. Experiments on both open data sequences and our customized device data are conducted. The results show our proposed system outperforms other counterparts and can handle challenging environments at reduced computation cost. The system supports both multi-line spinning LiDARs and emerging solid-state LiDARs with completely different scanning patterns, and can run in real-time on both Intel and ARM processors. We open source our code and dataset of this work on Github22https://github.com/hku-mars/FAST-LIVO to benefit the robotics community.