7th Plow

7th PLOW Edition (Summer 2017)

—— July 4 – 5, 2017——

The 7th PLOW edition will take place on July 4 -5, 2017 at Polytechnique Montréal, DGIGL, room L4812. The goal of this event is to introduce the participants to swarm programming, deep learning and software traceability. The students will follow hands-on lectures and labs on the challenges of programming swarms of devices, using machine learning approaches to learn and classify swarm drones behaviour while ensuring traceability of information.

A competition (PLOW challenge) will be organized to engage the students and apply the concepts learn. The competition will involve, in a simulation environment, the programming of a robot swarm, the data gathering, data modeling and accuracy evaluation as well as the collection of trace details. More in details the challenge will be making robot avoid collisions on crossroad while ensuring maximum speed. Here a sketch of a possible crossroad situation:

Breakfasts, lunches and coffee breaks will be offered by PolyMORSE members and DGIGL. For practical reasons, the maximum number of participants is limited to 50.

The event will be located in room L4812, 4th floor of Pavillons Lassonde, MacKay-Lassonde.

Lecturers

Pr. Christopher Pal

Dr. Chris Pal is an associate professor in the department of computer and software engineering at the École Polytechnique of Montreal. Prior to arriving in Montreal, he was a professor in the department of Computer Science at the University of Rochester. He has been a research scientist with the University of Massachusetts and has also been affiliated with the Interactive Visual Media Group and the Machine Learning and Applied Statistics groups at Microsoft Research. His research at Microsoft lead to three patents on image processing, computer vision and interactive multimedia.

He earned his M. Math and PhD from the University of Waterloo in Canada. During his masters research he developed methods for automated cartography and the analysis of high resolution digital aerial photography. He was also involved with a number of software engineering projects developing spatial databases for managing environmental information. His PhD research led to contributions applying probability models and optimization techniques to image, video and signal processing.

His research interest are artificial Intelligence, Computer vision and pattern recognition, computational photography, natural language processing, statistical machine learning and applications to human computer interaction.

Pr. Giovanni Beltrame

Giovanni Beltrame received the M.Sc. degree in electrical engineering and computer science from the University of Illinois, Chicago, in 2001, the Laurea degree in computer engineering from the Politecnico di Milano, Italy, in 2002, the M.S. degree in information technology from CEFRIEL, Milan, in 2002, and the Ph.D. degree in computer engineering from the Politecnico di Milano, in 2006. He worked as an engineer at the European Space Agency until 2010, and he is currently an Associate Professor at École Polytechnique de Montréal, Canada, where he directs the MIST Laboratory.
Giovanni Beltrame has published more than 60 papers in international conferences and journals, he is in the organising committee of several international conferences, and he is principal investigator on multiple projects funded by government and industry.

Pr. Giulio Antoniol

Giuliano Antoniol is professor of Software Engineering in the Department of Computer and Software Engineering of the Polytechnique Montréal where he directs the SOCCER laboratory. He worked in private companies, research institutions and universities. In 2005 he was awarded the Canada Research Chair Tier I in Software Change and Evolution. He has served in the program, organization and steering committees of numerous IEEE and ACM sponsored international conferences and workshops. His research interest include software evolution, empirical software engineering, software traceability, search based software engineering, mining software repositories and software testing.
Lab Instructors

Lab Instructors

Juliette Tibayrenc

Juliette Tibayrenc is a Master’s student in the department of Computer and Software at Polytechnique Montréal. She is also a student at the French engineering school CentraleSupélec. She has worked on projects related to autonomous quadcopters and optimal path planning. She is currently an intern at MILA where she works with a team on a project related to deep reinforcement learning and autonomous driving. Her research interests include Markov decision processes, Monte Carlo tree search, deep reinforcement learning and autonomous robots.

Ivan Svogor

Ivan Svogor is a postdoctoral fellow at the Department of computer and Software Engineering at Polytechnique Montréal. He received his PhD working with two advisors, from Chalmers University of Technology in Sweden and University of Zagreb in Croatia, he successfully defended his thesis (A framework for allocation of software components onto a heterogeneous computing systems) at the latter. This involved designing a multi-objective software component deployment scheme (demonstrated on energy and performance metrics on a heterogeneous computing platform). During his postgraduate study he received a research scholarship at Malardalen University, Sweden where he worked on component based software for heterogeneous computing platforms for underwater robotics. Currently, he is working on a project “Software Ecosystem for Swarm Robotics” in the MISTLab; and his interests involve software architecture for swarms of robots, software based energy consumption optimization, autonomous and cyber-physical systems.

Pre-requisites

Students are supposed to be familiar with object oriented programming and basic statistical modeling, although sufficient background will be provided!

Students should bring their own laptop for the lab sessions. You will be using Python, Java and Tensorflow.

Program Outline

July 4, 2017 — Room: L4812

8:30 – 10:15 Registration – Room: L4812. — For late arrival/registration please contact PLOW organizers

8:30 – 9:00 Breakfast – Room: L4812.

9:00-9:15 Welcome message by PLOW organizers

9:15-10:15 Talk by Pr. Giovanni Beltrame: Programming robot swarms

10:15-10:030 Coffee break – Room: L4812.

10:30-11:30 Talk by Pr. Giovanni Beltrame: The Buzz programming language

11:30-12:30 Talk by Pr. Christopher Pal: Deep learning in a nutshell (Part I)

12:30 – 14:00 Lunch – Ground floor of the Pavillon Lassonde.

14:00 – 15:30 Pr. Giovanni Beltrame: Swarm robotics simulation tools

15:30-16:00 Coffee break

16:00 – 17:30 Lab 1 – Hands on: the crossroad task.

17:30 – 18:00 Demo session – Participants are invited to demo their applications.

18:00 – 19:30 Poster session – finger food will be served

July 5, 2017 — Room: L4812

8:30 – 9:00 Breakfast.

9:00-10:00 Talk by Pr. Christopher Pal: deep learning in a nutshell (Part II)

10:00-10:30 Coffee break

10:30-11:30 Talk by Pr. Christopher Pal: reinforcement learning

11:30-12:30 Talk by Pr. Giulio Antoniol Traceability key concepts.

12:30 – 13:30 Lunch – Ground floor of the Pavillon Lassonde (TO BE VERIFIED).

13:30 – 17:30 Hackathon: Crossroad robot game: collision avoidance

17:30 – 17:45 Closing remarks


Important Notice

Please check the PLOW Mission page for important details such as WIFI connection and accommodation