Min Zhao’s research while affiliated with Chongqing University and other places

Customized bus is considered an effective means to alleviate traffic congestion and reduce traffic-related environmental pollution caused by the increasing number of private cars. Exploring potential passenger information as the first stage of customized bus service has become a popular topic. Unlike manual investigation and passenger request methods, current studies utilize data mining methods to actively explore potential passengers from various historical travel data. However, the existing data mining methods only consider the spatiotemporal features of potential passengers and neglect the semantic features related to customized bus services, which play an important role in determining whether passengers are willing to use services. In this paper, we treated the exploration of potential customized bus passengers as a binary classification problem based on private car trajectory data. Then, we propose a novel data mining method, named iTrAdaboost-DTCN, which combines the strengths of deep learning and transfer learning. In detail, it integrates state-of-the-art deep neural networks by constructing a deep trajectory classification network (DTCN), which can automatically extract semantic feature representations to help improve classification accuracy. Due to the lack of city-wide labeled customized bus passenger information in practice, it also integrates instance-based transfer learning through improved TrAdaboost, which solves the learning problem of the target classification domain with limited labeled samples. Experimental results demonstrate that our method can explore potential passengers more effectively than other baseline methods. Furthermore, we apply our method to real-world scenarios and compare three travel characteristics of identified customized and non-customized bus passengers.

The tunnel entrance area usually has different velocity limitations and lane-drop bottleneck. The randomness of human-driven vehicles' (HVs') lane-change behaviors could result in vehicle slowdown and collisions, which aggravate the traffic performance of the tunnel entrance area. The use of connected and autonomous vehicles (CAVs) is a powerful tool for creating control nodes and ensuring the indirect control of HVs to mitigate the negative impacts of HV's random lanechange behaviors. Balancing the differences in the penetration rate (PR) and vehicle density between each lane provides a means to increase the PR on the lanes that have fewer CAVs while reducing the PR for lanes with higher rates. In order to achieve this purpose, this paper proposes a new decentralized hierarchical trajectory programming algorithm to compute the lane-change sequence (or lane-change decision) of CAVs. The proposed algorithm is designed based on several trajectory programming strategies, including the Lane-value based MonteCarlo Tree Search (LV-MCTS) algorithm and the Mixed Integer Linear Programming (MILP) model, which deals with the randomness of HVs' lane-change behaviors under timevarying traffic conditions. Numerical studies in a realistic traffic simulation environment show that the congestion caused by lanedrop bottleneck is improved along with the reduction of the average fuel consumption and travel time of the mixed traffic flow.

To minimize the stop-and-go behavior caused by human factors and traffic signal light constraints, this paper proposes a distributed MPC-based hierarchical cooperative control protocol for mixed vehicle groups consisting of Connected and Automated Vehicles (CAVs) and Human-driven Vehicles (HVs) in the vicinity of traffic signal lights (VTSL). Firstly, to characterize the formation pattern and mechanism of the mixed vehicle groups, the subgroup division and subgroup reorganization method is presented in the VTSL. Secondly, since human factors can affect the driving behavior of all vehicles within a subgroup, a HV model is established via considering human factors, such as the driver’s insensitivity to distance and speed of the preceding vehicle. Thirdly, to guarantee the maximum number of vehicles passing the VTSL and the minimum travel time under the traffic signal light constraints, a distributed MPC-based hierarchical cooperative control method is proposed from the Transportation Cyber-Physical System (T-CPS) perspective. Finally, the simulator experiment results indicate that the proposed control protocol is more advantageous and effective as the penetration rate of CAVs continuously increase.

Road surface detection plays a pivotal role in the realm of autonomous vehicle navigation. Contemporary methodologies primarily leverage LiDAR for acquiring three-dimensional data and utilize imagery for chromatic information. However, these approaches encounter significant integration challenges, particularly due to the inherently unstructured nature of 3D point clouds. Addressing this, our novel algorithm, specifically tailored for predicting drivable areas, synergistically combines LiDAR point clouds with bidimensional imagery. Initially, it constructs an altitude discrepancy map via LiDAR, capitalizing on the height uniformity characteristic of planar road surfaces. Subsequently, we introduce an innovative and more efficacious attention mechanism, streamlined for image feature extraction. This mechanism employs adaptive weighting coefficients for the amalgamation of the altitude disparity imagery and two-dimensional image features, thereby facilitating road area delineation within a semantic segmentation framework. Empirical evaluations conducted using the KITTI dataset underscore our methodology’s superior road surface discernment and extraction precision, substantiating the efficacy of our proposed network architecture and data processing paradigms. This research endeavor seeks to propel the advancement of three-dimensional perception technology in the autonomous driving domain.

Typical communication and detection issues in a nonideal information environment, such as sensing failure, communication and sensing delay, and packet loss, further aggravate the adverse impacts of human-driven vehicle (HV) uncertainty on a mixed vehicle platoon. To guarantee the performance of the mixed vehicle platoon featuring HVs and connected and automated vehicles under the nonideal information environment, this article proposes a platoon control strategy integrating a combined longitudinal and lateral control and message recovery. Specifically, by building the dataset associated with HV behaviors, a long short-term memory (LSTM) predictor is established to recover the problematic HV messages (i.e., position, velocity, and heading) caused by the nonideal information environment. Furthermore, based on the boundary of the HV states, an evaluation and correction (EC) method is presented to suppress the adverse impacts of prediction failures. Then, a combined longitudinal and lateral controller cooperating with the LSTM predictor and EC method is developed to enhance the stability and safety of the mixed vehicle platoon under the nonideal information environment. In a theoretical analysis, the relatedness between the asymptotic stability and string stability of the platoon and predictor accuracy is strictly proved. Finally, comparative experiments verify the effectiveness of the proposed control strategy by employing driver-in-the-loop simulations.