Space-time prism (STP) is widely applied to measure individuals' ability to reach opportunities given the resource limitations. The majority of STP models treat prism-based accessibility as binary measures, wherein all locations within a prism are assumed equally accessible while others are deemed inaccessible. Although a few STP models examined heterogeneous interiors by modeling visit probabilities within the STPs, they primarily focused on trip-level analysis and did not explore the application for accessibility measurement. This study proposes a model framework based on multi-state supernetworks for constructing and estimating the probabilistic STPs of daily activity programs. The estimation is implemented with latent class models to account for individual heterogeneities in travel and activity participation. Based on the probabilistic STPs, we suggest a space-time accessibility measurement incorporating visit probabilities. We validate the model framework using mobility trajectory data collected in the Netherlands and demonstrate that the visit probability model can effectively capture the probabilistic STP interiors and the proposed accessibility measurement can provide a comprehensive evaluation of accessibility in the presence of activity chains.

Space-time prism and accessibility incorporating monetary budget and Mobility-as-a-Service

Infrastructure-enabled autonomous driving systems have been increasingly applied in confined environments. Automated valet parking (AVP) in smart parking garages is one of the notable applications that require high-precision indoor positioning services. However, the performances of the existing wireless indoor positioning techniques, including Wi-Fi, Bluetooth, and ultra-wideband (UWB), tend to decline substantially as the working time increases and the building environment varies. In this paper, we propose a lifelong framework using crowdsourced data of fully instrumented autonomous vehicles(e.g. vehicles equipping with LiDAR), to maintain the availability and precision of indoor positioning systems. We establish a map-aided deep learning positioning correction model based on continuous data sequences, which utilizes convolution and long short-term memory (LSTM) modules to extract the spatial and temporal features of positioning errors. A local grid map generator is designed and embedded into the correction model to learn the influencing factors of errors from the building environment and facility. A deep-learning-based anomaly detector is designed to keep the lifelong stability of our framework. Based on the proposed method, we develop a lifelong UWB positioning correction system and apply it for the path tracking of AVP in a real underground parking garage. The test results show that the system can maintain positioning correction precision in the environment of varying sensor errors and reduce the positioning error by 60% and the tracking error by 40%. The study showcases an innovative infrastructure-enabled application that can accelerate the widespread use of autonomous driving systems.

The timetable of a metro system is essential for trains running safely and efficiently. For the design of a timetable, the potential power interruptions of energy supplies from the substations to the trains should be borne in mind. In case potential power interruptions occur, the backup running plan should be completed responsively to accommodate the passenger and energy demands In this study, we propose an energy supplementation strategy utilizing regenerative energy from decelerating trains in the event of power interruptions and develop a tri-objective optimization model incorporating passenger travel time, potential power interruption, and energy consumption. Particularly, for calculating regenerative energy utilization, we suggest a many-to-many energy allocation mechanism between decelerating and accelerating trains based on the real-time energy demands and supplies. A heuristic algorithm is developed to obtain a regular and cyclic timetable for minimizing passenger travel time, the potential power interruptions, and energy consumption. The suggested model and algorithm are tested based on the smart-card data collected from a bidirectional metro line in Beijing (China). The results show that the suggested approach significantly improves energy efficiency, reduces passenger waiting time, and decreases power interruption risks, compared with the currently used scheduling method.

Trajectory planning is essential for self-driving vehicles and has stringent requirements for accuracy and efficiency. The existing trajectory planning methods have limitations in the feasibility of planned trajectories and computational efficiency. This paper proposes a life-long learning framework to achieve effective and high-accuracy direct trajectory planning (DTP) tasks. Based on generative adversarial networks (GANs), this study develops a lightweight GDTP model to map the initial/final states and the control action sequence. Additionally, by embedding the GDTP into the rapidly-exploring random tree (RRT), a GDTP-RRT algorithm is further designed for long-distance and multi-stage planning tasks. Taking the tractor-trailer as an application case, we test the proposed method in multiple scenarios with varying characteristics. The experimental results show that the method can plan highly feasible trajectories in a short time, compared with the most applied algorithm – the cubic curve RRT* (CCRRT*). It is found that the tracking errors of our method are 29.1% and 44.1% lower than the CCRRT* in terms of position and heading angle. This paper provides an effective and stable vehicle trajectory planning method for complex self-driving tasks.

Space–time prism (STP) modeling for activity programs with various realizations of activity chains has been a challenging research topic. This study claims that a bidirectional search scheme in a multi-state supernetwork is capable of pinpointing the exact STP of an activity program. The correctness and search space are first analyzed for the existing two-stage bidirectional search methods originally suggested for constructing trip-based STPs. Two simultaneous bidirectional search methods are further suggested. Travel time lower bounds based on A*, landmarks, and triangular inequalities are applied in goal-directed searches to reduce the search space. The small twists in formalism over the existing methods ensure accuracy and computational efficiency. The performances of the different search methods are compared for conducting activity programs in large networks.

Space–time prism (STP), which envelops the spatial and temporal opportunities for travel and activity participation within a time frame, is a fundamental concept in time geography. Despite many variants, STPs have been mostly modeled for one flexible activity between two anchor points. This study proposes a systemic approach to construct the STP bounds of activity programs that usually include various possible realizations of activity chains. To that effect, multi-state supernetworks are applied to represent the relevant path sets of multi-activity travel patterns. A goal-directed search method in multi-state supernetworks is developed to delineate the potential space–time path areas satisfying the space–time constraints. Particularly, the approximate lower and upper STP bounds are obtained by manipulating the goal-directed search procedure utilizing landmark-based triangular inequalities and spatial characteristics. The suggested approach can in an efficient fashion find the activity state dependent bounds of STP and potential path area. The formalism of goal-directed search through multi-state supernetworks addresses the fundamental shift from constructing STPs for single flexible activities to activity programs of flexible activity chains.

Multistate supernetwork approach has been advanced recently to study multimodal, multi-activity travel behavior. The approach allows simultaneously modeling multiple choice facets pertaining to activity-travel scheduling behavior, subject to space–time constraints, in the context of full daily activity-travel patterns. In that sense, multistate supernetworks offer an alternative to constraints-based time-geographic activity-based models. To date, most research on time-geographic models and supernetworks alike has represented time and space in a deterministic fashion. To enhance the validity and realism of the scheduling process and the underlying space–time decisions, this paper pioneers incorporating time uncertainty in multistate supernetworks for activity-travel scheduling. Solutions based on the concept of the -shortest path are proposed to find the reliable activity-travel pattern with confidence level. An algorithm combining label correcting and Monte-Carlo integration is proposed to finding the-shortest paths in the presence of time window constraints. An example of a typical daily activity program is executed to demonstrate the applicability of the proposed extension.

An integrated view encompassing the networks for public and private transport modes as well as the activity programs of travelers is essential for accessibility analysis. In earlier research, the multi-state supernetwork has been put forward by the authors as a suitable technique to model the system in such an integrated fashion. An essential part of a supernetwork involving multi-modal and multi-activity is the personalized transportation network, which is an under-researched topic in the academic community. This article attempts to develop a heuristic approach to construct personalized transportation networks for an individual's activity program. In this approach, the personalized network consists of two types of network extractions from the original transportation system: public transport network and private vehicle network. Three examples are presented to illustrate that the public transport network and private vehicle network can represent an individual's attributes and be applied in large-scale applications for analyzing the synchronization of land-use and transportation systems.