The MiPal Team

Team Leaders

Vlad Estivill-Castro portrait

Vlad Estivill-Castro

Vladimir Estivill-Castro is currently working as a Professor in the School of Information and Communication Technology, Director of MiPal and Director of the Autonomous Systems Program of the Institute for Intelligent and Integrated Systems (IIIS) at Griffith University (Australia). He is also a visiting scholar at Universitat Pompeu Fabra in Spain. His main interest are software engineering, algorithmic engineering, computational complexity, intelligent data analysis, privacy preserving data mining and knowledge discovery. Prof. Estivill-Castro holds a Ph.D. from the University of Waterloo in Canada and degrees from UNAM in Mexico. He serves in the editorial board of the Journal of Research and Practice in Information Technology, is editor in chief of the series Conferences in Research and Practice in Information Technology and serves on the editorial review board of the International Journal of Data Warehousing and Mining. He recently was awarded an ALTC citation for his to PhD supervision.

Rene Hexel portrait

Rene Hexel

Rene Hexel's research interest include Distributed Systems and Networking; Mobile Computing, Real-Time Systems, Embedded Systems Operating Systems, Network Security. Dr. Hexel has experience in fusion of distributed sensors for intelligent systems. He implemented several simulators with a modular User Graphical Interface for several of the applications of Plausible Logic on board the Sony AIBO. He has worked on wireless signals for localization and he has supervised several projects in distributed teams of robots (like role synchronization) and several Industry Affiliates Program project at MiPal.

Hector Geffner portrait

Hector Geffner

Prof. Hector Geffner's research interest are Models of reasoning, action, planning, and learning. In collaboration with others he authored the T0 Planner that translates conformant problems into classical problems; this software was the winner of the 2006 IPC Conformant Track. Other software that has chived meritorious and distinguished placements in bench-mark competitions include TP} (for Optimal Heuristic Regression Planner with Time and Resources), CPT (for Temporal POCL Planner based on Constraint Programming), HSP2.0 (for Heuristic Search Planning), and GPT (a Planner than handles uncertainty and sensing).


David-Billington portrait

David Billington

David Billington's expertise is Knowledge Representation in Artificial Intelligence, Reasoning in Artificial Agents, Non-Monotonic Logics. Dr. Billington has shown that Plausible Logic has many desirable properties, including being consistent with its facts, detecting loops in a finite number of steps, and having a fixed point semantics. With other colleagues, he has shown that Plausible Logic is very efficient, and developed an ambiguity propagating deduction mechanism. He demonstrated Plausible Logic is more powerful than Defeasible Logic because it can represent and prove disjunctive information.

Andrew-Rock portrait

Andrew Rock

Andrew Rock specializes in Functional Programming, Programming Methods, Scientific Computing. Dr. Rock developed the first implementation of Plausible Logic. The virtue is that this is the first fully implementable non-monotonic logic that recognizes infinite looping in proofs. Therefore, its algorithms always terminate. He has also lead several teams of students into the ACM Programming competition, repeatedly classifying the teams from Griffith University (above other universities in the state of Queensland) for the international rounds. In 2007, he lead the Australian Champion at the Asia Pacific Finals of the 32nd ACM International Collegiate Programming Contest. He has introduced robotics for first year-programming and for development of generic skills like problem solving.

PhD Students

Carl Lusty portrait

Carl Lusty

Currently I’m working on an extension to a pre-existing software architecture known as the Whiteboard that makes environment interaction decisions based on a combination of finite state machines and non-monotonic logic (Hexel, Rock, Estivill-Castro & Billington 2009). It is my intention to extend the Whiteboard architecture into a distributed system where behaviour decisions can be made in relation to environment observations made by both the current system as well as potentially many other systems. In the past I have worked on the Image Recognition, Motion control and behaviour design aspects of our Robocup Team as well as several iterations of Whiteboard implementations.

Fawad Riasat Raja portrait

Fawad Riasat Raja

Mr. Fawad Riasat Raja is a PhD student in the School of Information and Communication Technology, Griffith University Australia. His PhD advisors are Dr. René Hexel and Dr. David Chen. He is currently working on a communication protocol for safety critical distributed real time systems.

Mr. Fawad completed his Bachelor and Master’s Degree in Software Engineering and Computer Engineering respectively from University of Engineering and Technology Taxila, Pakistan. Before joining Griffith University he was serving as Assistant Professor in the Department of Software Engineering under the Faculty of Telecommunication and Information Engineering at University of Engineering and Technology Taxila, Pakistan. He joined the University of Engineering and Technology Taxila, Pakistan as a Lectruer in 2007 and then he was promoted to Assistant Professor in 2011.

Graduate Students

Jeremy Cade portrait

Jeremy Cade

Jeremy is currently working on a toolset allowing high level Behavior Trees to be converted into formally verified finite state machines. His primary research interest lies in the areas of Software Quality and Software Engineering practices.

Undergraduate Students

Eugene Gilmore portrait

Eugene Gilmore

My current project involves the development of a software module that allows a NAO robot to be remotely controlled through a teleoperation interface. I am interested in extending the capabilities of this interface by allowing cooperative interaction betweens the autonomous on-board behaviours of the NAO and an operator commands as well as providing more sophisticated ways of presenting information about the NAO's current environment by processing sensor information external to the NAO system. I have also worked on a number of other projects in the MiPal lab, mostly involving image processing. This includes work on image processing algorithms used as part of the MiPal labs robotic soccer playing software system used in the International RoboCup Competition. These algorithms include real-time recognition of objects observed by the NAO during play such as a ball or field lines on constrained hardware.

Dimitri Joukoff portrait

Dimitri Joukoff

The aim of the project is to develop an idempotent communication protocol over an open-loop data channel and demonstrate its functionality using a hybrid system.

The demonstration will include a PDDL based planner located on a desktop PC and a remote autonomous aerial vehicle (quadcopter) which will communicate via a wireless UDP channel.

The task for the quadcopter will be to pick-up a parcel from its pick-up point and deliver it to its destination in a closed environment. The planner will create a sequence of actions which the quadcopter will execute while sending sensor data/progress back to the planner for evaluation.

Whilst the environment will be closed, some dynamism will be allowed for (eg opening/closing of available routes).

  • The tools to be used in the development will include but not be limited to Whiteboard, ROS, guWhiteboardROSbridge, and C++.
  • Simulation tools will be made use of as appropriate.
  • PDDL and planning software will be made use of to build the problem domain/specification.
  • The code developed will be able to be compiled under Ubuntu and include unit tests to accommodate our integrated build system.
  • Final demonstration will be performed using a real quadcopter suitable to the task.