urban simulation
Recently Published Documents


TOTAL DOCUMENTS

99
(FIVE YEARS 19)

H-INDEX

13
(FIVE YEARS 1)

Author(s):  
Óscar Pérez-Gil ◽  
Rafael Barea ◽  
Elena López-Guillén ◽  
Luis M. Bergasa ◽  
Carlos Gómez-Huélamo ◽  
...  

AbstractNowadays, Artificial Intelligence (AI) is growing by leaps and bounds in almost all fields of technology, and Autonomous Vehicles (AV) research is one more of them. This paper proposes the using of algorithms based on Deep Learning (DL) in the control layer of an autonomous vehicle. More specifically, Deep Reinforcement Learning (DRL) algorithms such as Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG) are implemented in order to compare results between them. The aim of this work is to obtain a trained model, applying a DRL algorithm, able of sending control commands to the vehicle to navigate properly and efficiently following a determined route. In addition, for each of the algorithms, several agents are presented as a solution, so that each of these agents uses different data sources to achieve the vehicle control commands. For this purpose, an open-source simulator such as CARLA is used, providing to the system with the ability to perform a multitude of tests without any risk into an hyper-realistic urban simulation environment, something that is unthinkable in the real world. The results obtained show that both DQN and DDPG reach the goal, but DDPG obtains a better performance. DDPG perfoms trajectories very similar to classic controller as LQR. In both cases RMSE is lower than 0.1m following trajectories with a range 180-700m. To conclude, some conclusions and future works are commented.


2022 ◽  
Vol 29 (1) ◽  
pp. 81-90
Author(s):  
Lucas Fernando Souza de Castro ◽  
Fabian Cesar Pereira Brandão Manoel ◽  
Vinicius Souza de Jesus ◽  
Carlos Eduardo Pantoja ◽  
Andre Pinz Borges ◽  
...  

The smart city systems development connected to the Internet of Things (IoT) has been the goal of several works in the multi-agent system field. Nevertheless, just a few projects demonstrate how to deploy and make the connection among the employed systems. This paper proposes an approach towards the integration of a MAS through the JaCaMo framework plus an Urban Simulation Tool (SUMO), IoT applications (Node-RED, InfluxDB, and Grafana), and an IoT platform (Konker). The integration presented in this paper applies in a Smart Parking scenario with real features, where is shown the integration and the connection through all layers, from agent level to artifacts, including real environment and simulation, as well as IoT applications. In future works, we intend to establish a methodology that shows how to properly integrate these different applications regardless of the scenario and the used tools.


2021 ◽  
Author(s):  
Yun-Tsui Chang ◽  
Aritra Pal ◽  
Jürgen Hackl ◽  
Shang-Hsien Hsieh
Keyword(s):  

2021 ◽  
Vol 2042 (1) ◽  
pp. 012078
Author(s):  
Alessandro Maccarini ◽  
Enrico Prataviera ◽  
Angelo Zarrella ◽  
Alireza Afshari

Abstract Urban Building Energy Simulation (UBES) is an efficient tool to investigate and subsequently reduce energy demand of urban areas. Nevertheless, UBES has always been a challenging task due the trade-off between accuracy, computational speed and parametrization. In order to reduce these computation and parameterization requirements, model reduction and simplification methods aim at representing building behaviour with an acceptable accuracy, but using less equations and input parameters. This paper presents the development and validation results of a simplified urban simulation model based on the ISO 13790 Standard and written in the Modelica language. The model describes the thermo-physical behaviour of buildings by means of an equivalent electric network consisting of five resistances and one capacitance. The validation of the model was carried out using four cases of the ANSI/ASHRAE Standard 140. In general, the model shows good accuracy and the validation provided values within the acceptable ranges.


Author(s):  
P. Jayasinghe ◽  
L.N. Kantakumar ◽  
V. Raghavan ◽  
G. Yonezawa

Availability of a variety of urban growth models make model selection to be an important factor in urban simulation studies. In this regard, a comparative evaluation of available urban growth models helps to choose a suitable model for the study area. Thus, we selected three open-source simulation models namely FUTURES, SLEUTH and MOLUSCE to compare in their simplest state to provide a guidance for selection of an urban growth model for Colombo. The urban extent maps of 1997, 2005, 2008, 2014 and 2019 derived from Landsat imageries were used in calibration and validation of models. Models were implemented with the minimum required data with default settings. The simulation results indicate that the estimated quantity of urban growth (148.91 km2) during 2008-2019 by FUTURES model is matching closely with observed urban growth (127.37 km2) during 2008-2019. On the other hand, the SLEUTH model showed an overestimation (250.56 km2) and MOLUSCE showed an underestimation (77.11 km2). Further, the spatial accuracy of urban growth simulation of SLEUTH (Figure of Merit = 0.26) is relatively better in comparison to FUTURES (0.20) and MOLUSCE (0.20). Considering the tradeoff between computational overheads and obtained results, FUTURES could be a good choice over SLEUTH and MOLUSCE, when these models implemented in their simplest form with minimum required datasets. As a future work, we propose the incorporation of exclusion factor for potential surface generation to mitigate the overestimation of urban areas in SLUETH.


Author(s):  
Michael Batty

AbstractThis introduction outlines a portfolio of theory and methods in the chapters that develop a basic urban science for urban informatics. Inductive and deductive methods for generating data, analytics, and urban simulation, form the focus. In this first Part of the book, the emphasis is on mobility, space-time theory, energy and infrastructure, the spatial economy, and the role of modelling in understanding and planning the smart city.


Sign in / Sign up

Export Citation Format

Share Document