Spatial-Temporal Flows-Adaptive Street Layout Control Using Reinforcement Learning

Complete streets scheme makes seminal contributions to securing the basic public right-of-way (ROW), improving road safety, and maintaining high traffic efficiency for all modes of commute. However, such a popular street design paradigm also faces endogenous pressures like the appeal to a more balanced ROW for non-vehicular users. In addition, the deployment of Autonomous Vehicle (AV) mobility is likely to challenge the conventional use of the street space as well as this scheme. Previous studies have invented automated control techniques for specific road management issues, such as traffic light control and lane management. Whereas models and algorithms that dynamically calibrate the ROW of road space corresponding to travel demands and place-making requirements still represent a research gap. This study proposes a novel optimal control method that decides the ROW of road space assigned to driveways and sidewalks in real-time. To solve this optimal control task, a reinforcement learning method is introduced that employs a microscopic traffic simulator, namely SUMO, as its environment. The model was trained for 150 episodes using a four-legged intersection and joint AVs-pedestrian travel demands of a day. Results evidenced the effectiveness of the model in both symmetric and asymmetric road settings. After being trained by 150 episodes, our proposed model significantly increased its comprehensive reward of both pedestrians and vehicular traffic efficiency and sidewalk ratio by 10.39%. Decisions on the balanced ROW are optimised as 90.16% of the edges decrease the driveways supply and raise sidewalk shares by approximately 9%. Moreover, during 18.22% of the tested time slots, a lane-width equivalent space is shifted from driveways to sidewalks, minimising the travel costs for both an AV fleet and pedestrians. Our study primarily contributes to the modelling architecture and algorithms concerning centralised and real-time ROW management. Prospective applications out of this method are likely to facilitate AV mobility-oriented road management and pedestrian-friendly street space design in the near future.

Directions for Road Management Plans and Strategies for Regional Development in Aceh Besar Regency, Indonesia

Since Aceh Besar Regency has limited funds, it should focus more on road transportation services on improving existing roads. This study aims to determine the condition of existing roads, analyze the level of development of the sub-regency, analyze and develop road management plans and strategies in Aceh Besar Regency. Descriptive analysis methods, GIS, and scalogram to identify the level of development in the sub-regency and methods to get decisions about road management plans and strategies in this study used the AHP and SWOT methods. The results of the study show that the existing road conditions are around 1,644.36 KM in good condition, 330.48 KM and 387.08 KM in moderate condition, while the rest are still in a damaged condition, for the type of asphalt surface around 761.91, while the rest is still in the form of gravel and soil. The scalogram results show 3 regency are service centers (Hierarchy I), 9 regency are service sub-centers (Hierarchy II), and 11 sub-regency are hinterland areas (Hierarchy III). Based on the AHP analysis, it is found that the potential for tourism objects is more dominant in determining road handling, namely there are 5 priority sections and in the SWOT analysis using the ST (Strenght-Threats) diversification strategy (1) Road handling is carried out by the regional government of Aceh Besar Regency in developing regional potential such as regional tourism objects, markets and agriculture, (2) The government focuses on building damaged road infrastructure for smooth accessibility, (3) Aceh Besar Regency Government utilizes the private sector or investors in road handling (4) The regional government aims to maintain road quality for convenient access to all territory.

Prediction of Road Handling Cost Using Markov Chain Method in Regency Road Network

The use of budget in road management must be effective and efficient by providing the optimal pavement performance values. The problem in cost optimization of the road handling programs in West Bangka Regency is the lack of information regarding with the changes in conditions that will occur in the future due to the pattern of road handling that carried out, so that required a method that capable to predict road pavement conditions. The purpose of this study is to determine the cost of future road handling programs based on the value of road pavement conditions from the prediction results using Markov chain method. Modeling requires an initial condition vector and a Transition Probability Matrix (TPM). The main data used in the development of this model is pavement condition data and road handling history data for 2012 - 2017. The application of the Markov chain model on the road network in West Bangka Regency in the period of 2018 - 2022 shows a drastic decrease in pavement conditions, if not conducted the handling action on the road damage, with a change in the value of Good (B) condition from 63.7% in 2017 become 12.3% in 2022. Based on a simulation of a road management program during this period, produce an estimated cost of Rp. 45.338.471.000 by providing a change in the value of Good (B) conditions at the end of 2022 by 58.6%. The results of the study are expected could assist road managers in the context of the preparation of an optimal road management program.

Pengembangan Lanjutan Aplikasi Indonesia Integrated Road Management System di Direktorat Jenderal Bina Marga

Penelitian ini bertujuan untuk menjelaskan pengembangan lanjutan aplikasi Indonesia Integrated Road Management System (IRMS) di Direktorat Jenderal Bina Marga yang mendukung manajemen aset (terdiri dari jalan, jembatan, dan keselamatan pengguna) di Indonesia yang berbasis web dengan sistem pengelolaan basis data relasional (RDBMS) dan menyimpan database aplikasi, database spasial dengan memanfaatkan Sistem Informasi Geografis berbasis server untuk menyebarkan data spasial. Penelitian ini menjelaskan tahapan pengembangan aplikasi IRMS serta fitur dan modul-modul yang terdapat di dalamnya. Aplikasi IRMS juga menyimpan semua data secara terpusat (aset jalan, jembatan, kondisi, riwayat pemeliharaan, material, kepadatan lalu lintas, data tilang, dan korban kecelakaan) di Indonesia sehingga dapat melakukan analisa untuk menentukan perlakuan tingkat perbaikan jalan, memprediksi kondisi jembatan, dan mengidentifikasi lokasi rawan kecelakaan, menyusun rencana dan anggaran serta membuat rencana pencegahan sebelum terjadinya kerusakan yang parah.