Academic exams

Interactive Empathic Virtual Coaches Based on the Social Regulatory Cycle

Long distance learning has always faced several challenges in regards to motivation and availability of opportunity for students. While the latter has seen efforts in terms of collaborative and non-traditional learning avenues, such as online courses and virtually hosted classrooms, the former still suffers due to external influences and responsibilities, which in turn lead to an increase in student’s disinterest levels. To combat these hindrances, we propose the creation of an intelligent virtual agent based on the Social Regulatory Cycle, to fill the role of a coach in a readily available mobile application. This virtual coach is capable of supporting and adapting to the needs of human students, helping them in their tasks based on their intentions, motivations and feelings. By gathering objective and subjective user data, the virtual coach is able to interpret learning situations of individual users and, with the use of a synthetic character with analogous mannerisms to those of an actual human, help them by modulating their emotional state in the context of the learning process. Preliminary evaluations performed within an online learning environment class showed users continued interest in engaging with the virtual coaches on a regular basis.

access_time February 05, 2020 at 11:00AM
place Room 2.10, IST, Taguspark
local_offer Research topics
person Candidate: Ricardo Eugénio Proença Rodrigues
supervisor_account Advisor: Prof. Carlos António Roque Martinho

Geometry Friends - A Game AI Competition

Game AI competitions are important not only for Game AI, but AI in general. These competitions usually supply different and challenging problems which can be translated into other contexts, virtual or real. They also provide with frameworks to help the research of those problems. A competition is also a way to motivate researchers to study these challenges. In this document, we present the Geometry Friends Game AI Competition. Geometry Friends is a two player cooperative physics-based puzzle platformer computer game. The concept of the game is very simple, though its solving has proven to be difficult. While the main and apparent focus of the game is cooperation, it also relies on other AI related problems such as planning, plan execution and motion control, all connected to situational awareness. All of these subjects must consider that the game must be solved in real-time. We also suggest a new set of levels, to help the participants test and train their agents on many different problems.

access_time January 30, 2020 at 10:30AM
place Room 2N7.1, IST, Taguspark
local_offer Research topics
person Candidate: Ana Rita de Castro Plácido Salta
supervisor_account Advisor: Prof. Rui Prada / Prof. Francisco Melo

An Overconstrained Approach for Multi-Objective Combinatorial Optimization


Complete methods for solving Multi-Objective Combinatorial Optimization (MOCO) problems are usually based in the classic branch and bound techniques. More recently, new constraint-based algorithms have been proposed based on the enumeration of $P$-minimal models or the enumeration of Minimal Correction Subsets (MCSs). In single-objective optimization problems such as Maximum Satisfiability (MaxSAT), several state of the art algorithms are based on over-constrained formulas that are iteratively relaxed until an optimal solution is found. In this work, we propose the first algorithm for MOCO based on over-constrained formulas. Moreover, our algorithm naturally takes advantage of incrementality commonly used in unsatisfiability-based MaxSAT algorithms.

access_time January 29, 2020 at 03:00PM
place Room E2 (Piso -1), Torre Norte, IST, Alameda
local_offer Research topics
person Candidate: João O'Neill Cortes
supervisor_account Advisor: Prof. Vasco Manquinho / Prof.ª Inês Lynce

Autonomous Vehicles Reference Model


Urban mobility as we know it today is changing. It started with the development of different non-combustion means of propulsion, such as electric motors. Then there was the appearance of ride sharing companies (using either cars, scooters, bikes and bicycles). Finally, starting with innovations like Tesla’s autopilot, urban mobility is giving its first steps towards shared autonomous vehicles. These new technologies - combined - will not only affect the environment and sustainability, but also enable the creation of new business models and significantly reduce traffic, as well as the need for parking lots, instead leading to more green spaces and other needed infrastructures. There are already a few companies around the world working on the development and testing of fully autonomous vehicles. However, the development of this technology on its own will probably not be enough. The problem is that since this mobility revolution is happening now, there is a lack of reference models for implementing an autonomous vehicle ecosystem (such as specific laws, insurance, vehicles, applications, charging stations, parking and payment systems, just to name a few) that support cities and businesses do decide to implement and take real advantage of autonomous vehicles. Therefore, developing a reference model that could easily be instantiated to any city might be a step forward in this revolution, and maybe push it forward by providing cities and businesses with a solid scientific approach to support their decision making process.

access_time January 29, 2020 at 02:00PM
place Room E5 (Piso 1), Pavilhão de Electricidade, IST, Alameda
local_offer Research topics
person Candidate: António Jorge dos Reis Pereira
supervisor_account Advisor: Prof. Miguel Leitão Bignolas Mira da Silva

Effective use of AR and VR: a literature review


Although Extended Reality technologies have enjoyed an explosion in popularity in recent years, few applications are effectively in use outside the academic or entertainment contexts. This work consists of a literature review regarding the effective integration of such technologies in the real-world. It aims to contribute with an updated view on how these technologies are being used. First, we examine existing research concerning Virtual, Augmented, and Mixed Reality applications. We also analyze which have made their way to the workflows of companies and institutions. Furthermore, we circumscribe the particular aspects of extended reality technologies that determined this applicability.

access_time January 28, 2020 at 03:30PM
place Room 0.19, Pavilhão de Informática II, IST, Alameda
local_offer Research topics
person Candidate: Nuno Filipe Verdelho Trindade
supervisor_account Advisor: Prof. Alfredo Manuel Dos Santos Ferreira Júnior

Filter by period  filter_list