An Integrated Architecture for Autonomous Vehicles Simulation. Pereira, J. L. F. Master's thesis, Faculdade de Engenharia da Universidade do Porto, June, 2011.
abstract   bibtex   
Research on autonomous vehicles has come a long way since first findings, and its software tools are increasingly acclaimed by the research community. Particularly with robotics simulators, autonomous vehicles were provided with a suitable test-bed for experimentation of new methodologies such as long-term navigation algorithms, map building and intelligent reasoning. However, when it concerns the deployment and validation of such vehicles in a larger urban traffic scenario, robotics simulators do not seem to provide the required functionality for road traffic analysis, or inter-vehicular communication infrastructure as they seem present in today�s traffic simulators. The improvement of such features is the key for the successful practical deployment of such a critical system. The main objective of this dissertation is the integration of two types of simulators, namely a robotics and a traffic simulator. This integration will enable autonomous vehicles to be deployed in a rather realistic traffic flow as an agent entity (on the traffic simulator), at the same time it simulates all its sensors and actuators (on the robotics counterpart). Also, the statistical tools available in the traffic simulator will allow practitioners to infer what kind of advantages such a novel technology will bring to our everyday�s lives. Furthermore, the current features and issues on current robotics and traffic simulators are presented and a taxonomy for selecting these simulators is proposed. An architecture for the integration of the aforementioned simulators is proposed and implemented in the light of the most desired features of such software environments. To assess the usefulness of the platform architecture towards the expected realistic simulation facility, a comprehensive system evaluation is also performed and critically reviewed, leveraging the feasibility of the integration. Further developments and future perspectives are pinpointed up in the end.
@mastersthesis{Pereira2011,
	author = {Jos� Luis Ferr�s Pereira},
	title = {An Integrated Architecture for Autonomous Vehicles Simulation},
	school = {Faculdade de Engenharia da Universidade do Porto},
	year = {2011},
	month = {June},
	abstract = {Research on autonomous vehicles has come a long way since first findings,
	and its software tools

	are increasingly acclaimed by the research community. Particularly
	with robotics simulators, autonomous

	vehicles were provided with a suitable test-bed for experimentation
	of new methodologies

	such as long-term navigation algorithms, map building and intelligent
	reasoning. However,

	when it concerns the deployment and validation of such vehicles in
	a larger urban traffic scenario,

	robotics simulators do not seem to provide the required functionality
	for road traffic analysis, or

	inter-vehicular communication infrastructure as they seem present
	in today�s traffic simulators.

	The improvement of such features is the key for the successful practical
	deployment of such a

	critical system.


	The main objective of this dissertation is the integration of two
	types of simulators, namely a

	robotics and a traffic simulator. This integration will enable autonomous
	vehicles to be deployed

	in a rather realistic traffic flow as an agent entity (on the traffic
	simulator), at the same time it

	simulates all its sensors and actuators (on the robotics counterpart).
	Also, the statistical tools

	available in the traffic simulator will allow practitioners to infer
	what kind of advantages such a

	novel technology will bring to our everyday�s lives. Furthermore,
	the current features and issues on

	current robotics and traffic simulators are presented and a taxonomy
	for selecting these simulators

	is proposed. An architecture for the integration of the aforementioned
	simulators is proposed and

	implemented in the light of the most desired features of such software
	environments.


	To assess the usefulness of the platform architecture towards the
	expected realistic simulation

	facility, a comprehensive system evaluation is also performed and
	critically reviewed, leveraging

	the feasibility of the integration. Further developments and future
	perspectives are pinpointed up

	in the end.},
	file = {:https\://sumo.dlr.de/pdf/mieec1.pdf:URL},
	keywords = {autonomous driving, SUMO, driver modelling, Universidade de Porto,
	Models},
	owner = {dkrajzew},
	timestamp = {2011.09.30}
}

Downloads: 0