Research |
|
|
|
Research Statement
|
Coordination and Cooperation Among Teams of Robots, Humans and Other Agents |
|
Pooyan Fazli's long term research goal is to develop highly heterogeneous teams of robots, humans, and other agents in order to work in dynamic multi-goal environments.
The future of robotic systems will require robots, humans and other more or less intelligent agents to work in close coordination. Robots and humans as a team must coordinate and adapt their behaviors and decision making processes with each other's requirements and expectations. In domains such as health care facilities, search and rescue, space exploration, and autonomous cars, effective collaboration between robots and humans will make the mission safer, faster, and more efficient and reliable. This is a relatively unexplored area of research in robotics systems. |
 |
Current Research
|
On Multi Robot Area Coverage |
Multi-robot area coverage is receiving considerable attention due to its applicability in different scenarios such as search and rescue operations, planetary exploration, intruder detection, environment monitoring, floor cleaning and so on. In this task a team of robots is cooperatively trying to observe or sweep an entire area, possibly containing obstacles, with their sensors or actuators. The goal is to build an efficient path for each robot which jointly ensure that every single point in the environment can be seen or swept by at least one of the robots while performing the task. If there is a need to detect some resources in the environment, area coverage guarantees finding all the resources in the target area.
|
|
|
|
Other Research Projects
|
Microsoft Robotics Studio Soccer Challenge |
Using long-term experience of leadership and supervision of RoboCup teams in Iran, Pooyan Fazli organized the Nao Soccer Simulation team of the UBC computer science department in 2007 named "UBC Thunder". The current aim of this ongoing project is to develop a dynamic task allocation mechanism in a multi-robot system using fast vision processing techniques. This team qualified for world final competitions in 2007 (Atlanta, US) and 2008 (Suzhou, China). Currently he is the leader and chief developer of the team and have been supervising and coordinating the five undergrad students which make up the team for the past year.
|
|
|
Unsupervised Categorization (Filtering) of Google Images based on Visual Consistency |
To furnish computers and their moving relatives, robots,
with object recognition skill, a number of methods have
been developed. These methods can be divided into two
groups: recognition of individual objects and recognition of
categories. Considerable progress has been made in the
recognition of individual objects under different
illumination and viewpoint conditions. Categories are more
general and difficult to deal with and learning a model for
them requires more complex representations. In recent
years extensive studies has been carried out on particular
image categories like human faces, vehicles, pedestrians,
and so on. Instead, we want to develop techniques that work
well to any category that a human can recognize. Also
while most categorization methods require manually
collecting a large sample of high quality instances of the
given object category, training a classifier on them and then
possibly evaluating it on more demanding new query
images, our project focuses on the significant challenge of
unsupervised image categorization. We have to be able to
create object categories from a collection of highly noisy
images with a very few or even no training examples. |
 |
Past Research
|
Robotics Coach Simulation |
Founder and Head of Robotics Coach Simulation Research Group at the Dept. of Computer Science, Amirkabir Univ. of Technology Responsibility: Team Leader, Chief Designer and Developer. The aim of the project was to design and implement an autonomous agent which provides advice to the other agents about how to act in the environment, using MDP and Bayesian approaches. This agent was developed and tested successfully in three different domains (including robotics soccer: Keepaway Problem) with diverse characteristics and limitations. |
 |
|
Robotics Rescue Simulation
|
Founder and Head of Robotics Rescue Simulation Research Group at the Dept. of Computer Science , Amirkabir Univ. of Technology Responsibility: Team Leader, Chief Designer and Developer. The aim of the project was to design and develop coordination algorithms that enable teams of Ambulances, Police Forces, and Fire Brigades to save as many civilians as possible and extinguish fires in a city where an earthquake has just happened. The main interest of our team in this domain was to develop and apply decision and learning techniques in a multi-agent setting using a Case-Based Reasoning (CBR) approach. We also introduced a particular knowledge representation formalism called Graph with Classified Concepts and Relations (GCR)
|
 |
Robotics Soccer Simulation
|
Founder and Head of Robotics Soccer Simulation Research Group at the Dept. of Computer Science, Amirkabir Univ. of Technology. Responsibility: Team Leader, Chief Designer and Developer. The aim of the project was to design and implement a Multi-Agent System consisting of fully autonomous and heterogeneous agents to play soccer against an opponent team. The main interest of our team in this domain was to design and develop a decision making mechanism using a Cased-Based Reasoning (CBR) approach. |
 |
 |
|||
 |
|||
Copyright @ 2012 Pooyan Fazli - Last Updated June 2012 |
