Autonomous vehicle platooning improves overall energy efficiency and enhances road capacity through close-range cooperative driving. However, practical deployment under complex real-world conditions remains challenging due to sensor noise, model uncertainties, and actuator nonlinearities. This study presents a hierarchical control framework that integrates multisource sensor fusion and a controller combining longitudinal Model Predictive Control (MPC) with Lateral Feedforward-Feedback Control (LFFC) with data-driven improvement. First, a prediction-correction fusion module combines wheel odometry (ODOM), inertial measurement units (IMUs), and Global Positioning System (GPS) measurements to obtain continuous and globally consistent vehicle state estimates. Second, an MPC-LFFC-based physical controller is developed, where longitudinal MPC optimizes velocity corrections and lateral LFFC combines curvature feedforward with proportional feedback of heading and lateral errors. Third, a data-driven improvement module comprises an offline conservative Q-learning (CQL) agent that automatically calibrates controller parameters and a neural residual learning network that predicts feedforward compensation. Extensive experiments on a real-world vehicle platooning platform demonstrate that the proposed framework consistently outperforms baselines, achieving a position Root Mean Square Error (RMSE) of 0.0781 m and a 30.66% improvement in linear velocity tracking.

The last-mile delivery challenge in three-dimensional (3D) multi-floor building environments has a significant impact on logistics efficiency. Although autonomous delivery robots (ADRs) have been widely adopted to address last-mile logistics, most existing studies focus on optimizing ADR routing in simplified two-dimensional environments. Moreover, optimal layout of goods within the robot's physical containers brings another challenge. Hence, this paper formalizes the Discrete Capacity Vehicle Routing Problem with Simultaneous Delivery-Pickup and Soft Time Windows (DCVRP-SDP-STW) in a 3D environment. To achieve high-quality solutions, we propose an improved ant colony optimization algorithm that considers spatiotemporal multi-stage clustering characteristics, leading to a significant reduction in computation time. A data preprocessing framework is also developed to convert real-world architectural topologies into navigable 3D routing networks. To validate the proposed model and algorithm, we conducted a case study in Nanjing. The results show that the algorithm can improve optimization outcomes by 23% to 94% compared to pre-optimization results based on the proximity principle, which can contribute to the advancement of efficient and intelligent autonomous delivery systems.

This paper addressed the problem of highway traffic flow multivariate time series forecasting with the challenges of variate heterogeneity. To improve forecast performance without a heavy computational burden in large-scale networks, we innovatively introduced variational mode decomposition and established a decomposition-assisted multi-tasking deep learning forecasting architecture. To improve variate-specific pattern learning and mitigate pattern mixing, we proposed a novel temporal-frequency pure convolutional neural network incorporating discrete Fourier transform, deepwise convolution, and batchwise feedforward neural network. To verify the proposed model, we conducted a case study on a regional network located in Jiangsu, China. Results demonstrate strong forecast performance and efficient computation. The proposed model offers suitability toward highway operators for large-scale engineering deployment and better facilitates their managerial actions.