Seminars in Artificial Intelligence and Robotics

A.A. 2013/2014

Master in Artificial Intelligence and Robotics
(Laurea Magistrale in Intelligenza Artificiale e Robotica)

Prof. Luigia Carlucci Aiello


General

6 Credits (ECTS) , Spring Semester
Schedule: Classes are on Fridays 12:00-13:30 // 14:00-15:30, Room B2
Classes start MARCH 7th. Class attendance is mandatory.

Seminars by Dr. David J Israel are cancelled. The second part of the course will take place according to the following calendar:

Seminars - Second Part

Friday May the 30th, 12 p.m. Room B2
Topic: Old and New Ways of Applying Planning in Videogames
Speakers: Stavros Vassos
Affiliation: Sapienza University of Rome


Slides

Readings:

[1] NetworkING: using Character Relationships for Interactive Narrative Generation 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2013. (pdf)

[2] Towards story-based content generation: From plot-points to maps IEEE Conference on Computational Intelligence in Games (CIG), 2013. (pdf)

NOTE: Choose one of the two papers.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Monday May the 26th, 4 p.m. Aula Magna
Topic: Named Entity Disambiguation / News Arbitrage
Speakers: Stefano Pacifico, James Hodson
Affiliation: Bloomberg


Abstract:
Stefano Pacifico - Named Entity Disambiguation
In recent years, much attention has been posed on how to identify named entities in text (e.g., Barack Obama), and how to link them unambiguously to entities contained in a given (ontological) knowledge base (e.g., Bloomberg, the former NYC mayor, or the company?). This problem is also known as Named Entity Disambiguation. In this lecture we will explore the definition of the problem, look classic approaches, and at some of the state of the art techniques used in this context.

James Hodson - News Arbitrage
News arbitrage is the gain or loss of investment opportunity due to the availability, or lack, of information between two parties. In this lecture we are going to dive into the techniques and tools that allow the construction of automatic multi-lingual translation systems that allow to exploit, or alleviate this problem.

Readings:

Topic: Named Entity Disambiguation

[1] Navigli, Roberto. "Word sense disambiguation: A survey." ACM Computing Surveys (CSUR) 41.2 (2009): 10. (pdf)

[2] Milne, David, and Ian H. Witten. "Learning to link with wikipedia." Proceedings of the 17th ACM conference on Information and knowledge management. ACM, 2008. (pdf)

[3] Hoffart, Johannes, et al. "Robust disambiguation of named entities in text." Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2011. (pdf)

[4] Hoffart, Johannes, et al. "Yago2: exploring and querying world knowledge in time, space, context, and many languages." Proceedings of the 20th international conference companion on World wide web. ACM, 2011. (pdf)

Topic: News Arbitrage

[1] Dumais, Susan, Thomas K. Landauer, and Michael L. Littman. "Automatic cross-linguistic information retrieval using latent semantic indexing." (1997). (pdf)

[2] Koo, Terry, Xavier Carreras, and Michael Collins. "Simple semi-supervised dependency parsing." (2008). (pdf)

[3] Koehn, Philipp, Franz Josef Och, and Daniel Marcu. "Statistical phrase-based translation." Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1. Association for Computational Linguistics, 2003. (pdf)

NOTE: Choose one of the papers.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Friday May the 23rd, 12 p.m. Room B2
Report on the book "Robot futures" by the Student Andea Nicastro


~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Friday May the 16th, 12 p.m. Room B2
Topic: Robotics for Healthy Aging: the relevance of user studies
Speaker: Dr. Gabriella Cortellessa
Affiliation: ISTC-CNR


Readings:

Download

[1] Palumbo, F., Barsocchi, P., Furfari, F., & Ferro, E. (2013). Aal middleware infrastructure for green bed activity monitoring. Journal of Sensors, 2013.

[2] Cesta, A., Cortellessa, G., Rasconi, R., Pecora, F., Scopelliti, M., & Tiberio, L. (2011). Monitoring elderly people with the robocare domestic environment: Interaction synthesis and user evaluation. Computational Intelligence, 27(1), 60-82.

NOTE: Choose one of the two papers.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Thursday May the 15th, 10 a.m. Aula Magna
Topic: A Cognitive Design Pattern for Collective Decisions in Distributed Systems
Speaker: Dr. Vito Trianni
Affiliation: ISTC-CNR


Abstract: In this talk, I will present the main ideas behind the development of a methodology for engineering distributed systems capable of some cognitive processing ability, such as collective decision making. I will move from theoretical studies of collective decision in distributed systems, which support the identification of the causal relationship between microscopic mechanisms and macroscopic patterns. Such theoretical understanding must be translated into formal methods and guidelines for engineering artificial systems (e.g., the interactions observed between bees during nest site selection can be distilled into a methodology for optimal decision making in swarm robotics systems). In this respect, I will introduce the concept of cognitive design patterns, that is, general solutions for the design of distributed cognitive systems, and will discuss the example of collective decisions through a simple case study.

Bio: Dr. Vito Trianni is a tenured researcher at the Institute of Cognitive Sciences and Technology of the Italian National Research Council (CNR-ISTC). He owns a Ph.D. in Applied Sciences delivered by the Université Libre de Bruxelles in 2006, and a MSc in Computer Science Engineering delivered by Politecnico di Milano in 2000. He published more than 60 papers in international journals and peer-reviewed conference proceedings, with an overall H-Index of 21 according to Google Scholar. His main research interests are in swarm intelligence and swarm robotics, and the relationship between collective behaviour and cognition. Dr. Trianni participated to some of the most successful EU projects in cognitive systems and robotics (Swarm-bots, ECAgents, Swarmanoid), and features thorough expertise, both theoretical and experimental, in the design and analysis of collective and self-organising behaviours, especially applied to swarm robotics systems. Recently, given the lack of systematic methodologies that can guide the experimental design, Dr. Trianni started to formalise an engineering approach for the synthesis of collective behaviours, through evolutionary techniques and swarm intelligence design methods. Besides engineering robotic systems, Dr. Trianni's research activities instantiate a synthetic approach to the understanding of distributed cognition in natural systems.

Readings:

Download

[1] V. Trianni, E. Tuci, K. M. Passino, and J. A. R. Marshall, "Swarm Cognition: an interdisciplinary approach to the study of self-organising biological collectives," Swarm Intelligence, vol. 5, no. 1, pp. 3-18, Dec. 2010.

[2] J. A. R. Marshall, R. Bogacz, A. Dornhaus, R. Planque, T. Kovacs, and N. R. Franks, "On optimal decision-making in brains and social insect colonies," Journal of The Royal Society Interface, vol. 6, no. 40, pp. 1065-1074, Sep. 2009.

[3] A. Reina, M. Dorigo and V. Trianni, "Towards a Cognitive Design Pattern for Collective Decision-Making," Proceedings of the Ninth International Conference on Swarm Intelligence (ANTS 2014), September 10-12 2014, Brussels, Belgium

[4] T. D. Seeley, P. K. Visscher, T. Schlegel, P. M. Hogan, N. R. Franks, and J. A. R. Marshall, "Stop Signals Provide Cross Inhibition in Collective Decision-Making by Honeybee Swarms," Science, vol. 335, no. 6064, pp. 108-111, 2012.

NOTE: Read [1] or [3], and use respectively [2] or [4] for additional information, if required.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Monday May the 12nd, 12 p.m. Aula Magna
Topic: Symbiotic Autonomous Mobile Service Robots
Speaker: Manuela Veloso
Affiliation: Carnegie Mellon University


Readings:

Silvia Coradeschi, Alessandro Saffiotti, "Symbiotic Robotic Systems: Humans, Robots, and Smart Environments," IEEE Intelligent Systems, vol. 21, no. 3, pp. 82-84, May-June 2006, doi:10.1109/MIS.2006.59 (pdf)

Rosenthal, Stephanie, Joydeep Biswas, and Manuela Veloso. "An effective personal mobile robot agent through symbiotic human-robot interaction."Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1-Volume 1. International Foundation for Autonomous Agents and Multiagent Systems, 2010. (pdf)

Veloso, Manuela, et al. "Symbiotic-autonomous service robots for user-requested tasks in a multi-floor building." In Workshop on Cognitive Assistive Systems (CAS), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-12). (pdf)

NOTE: Read the first short paper and then choose one of the other two papers.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Friday May the 9th, 12 p.m. Room B2
Topic: A.I. Scheduling, and Constraint-Satisfaction
Speaker: Amedeo Cesta
Affiliation: ISTC-CNR


Slides
Readings

NOTE: Read the survey and then choose one of the two papers.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Thursday May the 8th, 10 a.m. Aula Magna
Speaker: Dr. Khaled Kilzie
Topic: EXP(AI & ROBOTICS)
Affiliation: RAI Way


Abstract: We are seeing unprecedented technological acceleration that can change the course of history in much less time than you can imagine and what it did in the past! Artificial intelligence and Robotics are among the exponential technologies that are candidates to tow various sectors of existing and future market.

Short Bio


The class is divided into two parts:

Part 1

Prof. Joachim Hertzberg (Osnabrueck University, Institute of Computer Science, Osnabrueck, Germany)
Topics in Knowledge Representation

Calendar: For a detailed description, slides and links to further readings, see this page.

Part 2

Dr. David J Israel (Artificial Intelligence Center, SRI International, Menlo Park, California)
Topics in Machine Reading

Abstract (preliminary): After some largely methodological/quasi-historical lectures, I will talk about different approaches to AI, overall, and then with a special focus on how those approaches play out as applied to Machine Reading/Text Understanding. Only then will I talk about the more-or-less standard Natural Language Processing "pipeline" and make clear that the focus of the class will be limited to the latter stages of the pipeline -- so the course will NOT be a NLP course; rather it will focus on issues of meaning and information content that connect the aim of reading and the output of intelligent reading with issues of representation and reasoning.

Calendar:
In addition, there are some one-shot seminars that will be announced later on.