This paper introduces three types of status information based on the current environmental perception and the information computing power of connected and automated vehicles (CAVs) and proposes an energy-efficient dynamic route planning algorithm without starting and stopping for the CAVs. The information types include real-time road traffic flow, traffic light and vehicle driving status (driving velocity and direction). The algorithm aims to minimize both time and energy consumption for the route. For this study, the feasibility of this energy-efficient route planning algorithm was first theoretically deduced. After introducing traffic light and driving energy consumption elements, a velocity-space-time three-dimensional network (VSTN) model was mathematically formulated to describe a dynamic route in addition to the design of the shortest route searching algorithm in VSTN. Two experimental road networks were then constructed to test and compare the energy efficiency. The first test scenario is a line road with two road conditions and various signal cycles and initial phases. The experiment shows that the cumulative energy consumption of the energy-efficient route under various scenarios is no greater than the normal route, ranging from 5.18% to 16.4%. The second test scenario involves a network located in the Jing'an district of Shanghai and is intended to verify the route searching function and energy efficiency. Compared to the traditional driving method, the new route reduces energy consumption by 10.36%. This study demonstrates that the energy efficiency does not correlate with the signal cycle or initial phase, and it appears to be random. The new algorithm proposed in this paper can be applied to dynamic route planning by CAVs and the goal of saving energy can be achieved in various road networks.
The rapid development of 5G and Artificial Intelligence (AI) has promoted the widespread application of autonomous driving in various scenarios. Currently, autonomous vehicles (AVs) can autonomously perform operations such as turning, lane changing, and acceleration in accordance with road traffic rules. It is a challenge for autonomous vehicles (AVs) to plan a series of safe and efficient trajectories on ice and snow covered road (ISCR). This paper proposes an optimal trajectory planning algorithm based on the Frenet coordinate system, which ignores the influence of road curvature and improves the quality of trajectory. Specifically, the vehicle motion is decoupled into two dimensions using the Frenet coordinate system to build lateral and longitudinal trajectory planning models, respectively. Further, according to the information on the initial and target configuration of the vehicle, the corresponding trajectory sets of horizontal and longitudinal motion were generated by sampling. Moreover, to improve the safety of autonomous vehicles (AVs) on ice and snow covered road (ISCR), the cost of driving distance and ice-obstacle distance are used as the core indicators to evaluate the trajectory planning cost, combined with the safe speed check. Simulation results show that this algorithm can plan an optimal trajectory for autonomous vehicles (AVs) that combines safety, comfort, and stability, especially on ice and snow covered road (ISCR).
Inspired by the prevailing recommendation system application, personalised travel factors are introduced into route recommendation in order to provide more human-oriented travel service. With real-time information provided by the cooperation vehicle-infrastructure systems (CVIS), four real travel factors including distance, grade, time and toll are adopted to construct a route feature vector and an individual traveler preference feature vector, respectively. A novel route recommendation model based on Pearson’s correlation coefficient is formulated. A searching algorithm of all feasible routes is designed that achieves a better balance of time and space complexity. Considering that the traveler has heterogeneity in the numerous ways of using route recommendation information and choosing a satisfactory route, individual compliance with the route recommendation is creatively proposed and used to imitate a day-to-day route choice. A specific simulation with Monte Carlo method is conducted on a test network to show the dynamic evolution features of network traffic flow.
1 October 2016 in Journal of Engineering Science and Technology Review
Optimizing the train plan for high-speed rail systems should consider both the passengers’ demands and enterprise’s benefits. The choice of the departure time period is the most important factor affecting the passenger demand distribution. In this paper, the optimization problem of a train operation plan based on time period preference is studied for a high-speed rail corridor. First, according to the travel process of the passengers, the extended service network for a high-speed rail system is established. The main factors that influence the passengers’ travel choices are analyzed, and the departure time period preference, stop time and flexible pricing strategy based on the time period preference are put forward. The generalized travel cost function, including the convenience, ticket fare and stop time costs, is constructed, and a two-level programming model is established based on the function. The upper-level planning model is formulated as a mixed 0–1 programming problem that aims at maximizing the revenue of the railway enterprise. It is mainly constrained by passenger travel demand and solved by improved genetic algorithms. The lower-level model is a user equilibrium (UE) model. The Frank–Wolfe algorithm is used to allocate multiple groups of OD (origin and destination) passenger flows to each train so that the generalized travel expenses of all the passengers with the same OD are minimized and equal. Finally, the train operation plan is solved based on the Lan-xi (Lanzhou–Xi’an) high-speed rail data, and the validity of both the model and algorithm is verified.