# Semantic search

PrjDescription | PrjResArea | PrjTutor | PrjStudMin | PrjStudMax | |
---|---|---|---|---|---|

Exploratory data analysis by genetic feature extraction | Understanding the waves in EEG signals is an hard task and psicologists often need automatic tools to perform this task. In this project we are interested in using a genetic algorithm developed for P300 feature extraction in order to extract useful informations from Error Potentials. The project is a collaboration with the psicology department od Padua University. *B. Dal Seno, M. Matteucci, and L. Mainardi. "A genetic algorithm for automatic feature extraction in P300 detection" (http://home.dei.polimi.it/dalseno/papers/2008/ijcnn08.pdf) *B. Dal Seno, M. Matteucci, L. Mainardi, F. Piccione, and S. Silvoni. "Single-trial P300 detection in healthy and ALS subjects by means of a genetic algorithm" (http://home.dei.polimi.it/dalseno/papers/2008/grazGa08.pdf) | BioSignal Analysis | MatteoMatteucci | 1 | 2 |

Extended Kalman Filtering on Manifolds | Extended Kalman filtering is a well known technique for the estimation of the state of a dynamical system also used in robotics for localization and mapping. However in the basic formulation it assumes all variables to live in an Euclidean space while some components may span over the non-Euclidean 2D or 3D rotation group SO(2) or SO(3). It is thus possible to write tha Extended Kalman filter to operate on Lie Groups to take into account the presence of manifolds (http://www.ethaneade.org/latex2html/lie/lie.html). We are interestend in investigation this further applying it to the EKF-SLAM framework we have developed. '''''Material:''''' *papers about Manifold based optimization and space representations *C++ framework for EKF-SLAM '''''Expected outcome:''''' *An extended Kalman filter which uses this new representation '''''Required skills or skills to be acquired:''''' *Good mathematical background *C++ programming under Linux | Robotics | MatteoMatteucci SimoneCeriani DavideCucci |
1 | 2 |

Extraction | This project is aimed at removing the ontology building bottleneck, semi-automatically building an ontology starting from a set of textual documents related to a specific domain. | Machine Learning | DavideEynard MatteoMatteucci |
||

Gestures in Videogames | Analysis of gestures and facial expressions of people involved in playing a videogame (TORCS) | Affective Computing | MatteoMatteucci MaurizioGarbarino |
||

HRVCar | MatteoMatteucci | ||||

HeadsetControlForWheelChair | Study how it would be possible to control a wheelchair with a low-cost headset detecting biosignals such as NIA | BioSignal Analysis | MatteoMatteucci | ||

I.DRIVE Data Logger | This project concerns the logging of data coming from multiple sensor installed in a car. This data are used to analyze the behaviours and the reactions of the driver | MatteoMatteucci | |||

Indoor localization system based on a gyro and visual passive markers | This project aims at developing autonomous moving systems based on a gyro and passive markers | MatteoMatteucci SimoneCeriani DavideMigliore |
|||

Information geometry and machine learning | In machine learning, we often introduce probabilistic models to handle uncertainty in the data, and most of the times due to the computational cost, we end up selecting (a priori, or even at run time) a subset of all possible statistical models for the variables that appear in the problem. From a geometrical point of view, we work with a subset (of points) of all possible statistical models, and the choice of the fittest model in out subset can be interpreted as a the point (distribution) minimizing some distance or divergence function w.r.t. the true distribution from which the observed data are sampled. From this perspective, for instance, estimation procedures can be considered as projections on the statistical model and other statistical properties of the model can be understood in geometrical terms. Information Geometry (1,2) can be described as the study of statistical properties of families of probability distributions, i.e., statistical models, by means of differential and Riemannian geometry. Information Geometry has been recently applied in different fields, both to provide a geometrical interpretation of existing algorithms, and more recently, in some contexts, to propose new techniques to generalize or improve existing approaches. Once the student is familiar with the theory of Information Geometry, the aim of the project is to apply these notions to existing machine learning algorithms. Possible ideas are the study of a particular model from the point of view of Information Geometry, for example as Hidden Markov Models, Dynamic Bayesian Networks, or Gaussian Processes, to understand if Information Geometry can give useful insights with such models. Other possible direction of research include the use of notions and ideas from Information Geometry, such as the mixed parametrization based on natural and expectation parameters (3) and/or families of divergence functions (2), in order to study model selection from a geometric perspective. For example by exploiting projections and other geometric quantities with "statistical meaning" in a statistical manifold in order to chose/build the model to use for inference purposes. Since the project has a theoretical flavor, mathematical inclined students are encouraged to apply. The project requires some extra effort in order to build and consolidate some background in math, partially in differential geometry, and especially in probability and statistics. Bibliography # Shun-ichi Amari, Hiroshi Nagaoka, Methods of Information Geometry, 2000 # Shun-ichi Amari, Information geometry of its applications: Convex function and dually flat manifold, Emerging Trends in Visual Computing (Frank Nielsen, ed.), Lecture Notes in Computer Science, vol. 5416, Springer, 2009, pp. 75–102 # Shun-ichi Amari, Information geometry on hierarchy of probability distributions, IEEE Transactions on Information Theory 47 (2001), no. 5, 1701–1711. | Machine Learning | MatteoMatteucci LuigiMalago |
1 | 2 |

Integration of scanSLAM and ARToolKit in the MoonSLAM framework | The project aims at integrating the scanSLAM algorithm with the ARToolKit localization system in the MoonSLAM framework for multi sensor SLAM. | Robotics | MatteoMatteucci SimoneCeriani |
||

Interpretation of facial expressions and movements of the head | Affective Computing | MatteoMatteucci | |||

LARS and LASSO in non Euclidean Spaces | LASSO (1) and more recently LARS (2) are two algorithms proposed for linear regression tasks. In particular LASSO solves a least-squares (quadratic) optimization problem with a constrain that limits the sum of the absolute value of the coefficients of the regression, while LARS can be considered as a generalization of LASSO, that provides a more computational efficient way to obtain the solution of the regression problem simultaneously for all values of the constraint introduced by LASSO. One of the common hypothesis in regression analysis is that the noise introduced in order to model the linear relationship between regressors and dependent variable has a Gaussian distribution. A generalization of this hypothesis leads to a more general framework, where the geometry of the regression task is no more Euclidean. In this context different estimation criteria, such as maximum likelihood estimation and other canonical divergence functions do not coincide anymore. The target of the project is to compare the different solutions associated to different criteria, for example in terms of robustness, and propose generalization of LASSO and LARS in non Euclidean contexts. The project will focus on the understanding of the problem and on the implementation of different algorithms, so (C/C++ or Matlab or R) coding will be required. Since the project has also a theoretical flavor, mathematical inclined students are encouraged to apply. The project may require some extra effort in order to build and consolidate some background in math, especially in probability and statistics. Picture taken from (2) Bibliography # Tibshirani, R. (1996), Regression shrinkage and selection via the lasso. J. Royal. Statist. Soc B., Vol. 58, No. 1, pages 267-288 # Bradley Efron, Trevor Hastie, Iain Johnstone and Robert Tibshirani, Least Angle Regression, 2003 | Machine Learning | MatteoMatteucci LuigiMalago |
1 | 2 |

Low-cost IMU | Characterization of a low-cost IMU module developed by AIRLab; use of such module to extract high-level information about human behavior. | Robotics | MartinoMigliavacca MatteoMatteucci |
||

Machine Learning for Crop Weed Classification | Automatic detection of crops and weeds by using image data | Machine Learning | MatteoMatteucci | ||

MoonSLAM Reengineering | In the last three years a general framework for the implementation of EKF-SLAM algorithm has been developed at the AIRLab. After several improvements it is now time to redesign it based on the experience cumulated. The goal is to have an international reference framework for the development of EKF based SLAM algorithms with multiple sensors (e.g., lasers, odometers, inertial measurement ) and different motion models (e.g., free 6DoF motion, planar motion, ackerman kinematic, and do on). The basic idea is to implement it by using C++ templates, numerically stable techniques for Kalman filtering and investigation the use of automatic differentiation. It should be possible to seamlessly exchange motion model and sensor model without having to write code beside the motion model and the measurement equation. '''Material''' *lots of theoretical background and material *an existing (and working) C++ implementation of the framework '''Expected outcome:''' *a C++ library for the implementation of generic EKF-SLAM algorithms '''Required skills:''' *Experienced C++ programming under Linux | Robotics | MatteoMatteucci | 1 | 2 |

Multimodal GUI for driving an autonomous wheelchair | This project pulls together different Airlab projects with the aim to drive an autonomous wheelchair (LURCH - The autonomous wheelchair) with a multi modal interface (Speech Recognition, Brain-Computer Interface, etc.), through the development of key software modules. The work will be validated with live experiments. *R. Blatt et al. ''Brain Control of a Smart Wheelchair'' (http://tinyurl.com/ygldwun) | BioSignal Analysis | MatteoMatteucci SimoneCeriani DavideMigliore |
1 | 2 |

Object Recognition with Deep Boltzmann Machines | Deep Boltzmann machines for classification tasks | Robotics | MatteoMatteucci FrancescoVisin |
||

Odometric system for robots based on laser mice | We developed an odometric system for robots by combining the reading of several laser mice. The system consists of a master PIC-based board and several slave boards where the sensors employed in optical mice are located. The readings are collected on the PIC and sent on the serial port to a PC which elaborates and combines the x and y readings in order to obtain a x,y,theta estimation of the movement of the robot. The aim of the project is first to improve the current design of the PIC-based board, and realize a new working prototype, and then to implement and evaluate different algorithms able to estimate more precisely the x,y and theta odometric data from the mice readings. Experience with PIC-based systems and some experience with electronics circuits is a plus. Students are supposed to redesign the electronic board, improve the firmware of the PIC, and work on the algorithm that estimates the robot position on the PC. It would be also interesting to evaluate the possibility to embed the optimization and estimation algorithms in the firmware of the PIC in order to produce a stand-alone device. Ask the tutors of the project for extra material, such as data-sheets and other documentation. | Robotics | MatteoMatteucci LuigiMalago MarcelloRestelli |
1 | 2 |

P300 BCI | Recovery, integration and adaptation of P300 BCI (hardware and software) stubs to generate a working interface for a speller. The aim is to develop a working prototype for an ALS affected patient. | BioSignal Analysis | MatteoMatteucci | 1 | 3 |

Poit cloud SLAM with Microsoft Kinect | Simultaneous Localization and Mapping (SLAM) is one of the basic functionalities required from an autonomous robot. In the past we have developed a framework for building SLAM algorithm based on the use of the Extended Kalman Filter and vision sensors. A recently available vision sensor which has tremendous potential for autonomous robots is the Microsoft Kinect RGB-D sensor. The thesis aims at the integration of the Kinect sensor in the framework developed for the development of a point cloud base system for SLAM. '''Material:''' *Kinect sensor and libraries *A framework for multisensor SLAM *PCL2.0 library for dealing with point clouds '''Expected outcome:''' *Algorithm able to build 3D point cloud representation of the observed scene *Point clouds processing could be used to improve the accuracy of the filter as well '''Required skills or skills to be acquired:''' *Basic background in computer vision *Basic background in Kalman filtering *C++ programming under Linux | Computer Vision and Image Analysis | MatteoMatteucci | 1 | 2 |

R2P | The goal of the project is to develop a HW/SW system for rapid prototyping of robots | Robotics | AndreaBonarini MatteoMatteucci |
||

R2P IMU firmware development | We have developed the electronics of an Inertial Measurement Unit based on an ARM microcontroller to be integrated on an autonomous embedded aerial platform. The IMU has already some attitude heading reference system (AHRS) code implemented, but we are interested in: *implementing embedded algorithms for the estimation of the IMU attitude to be compared with the actual one (e.g., Kalman filter, DCM, Madgwick, etc.) *developing a, easy to use, procedure for the calibration of IMU parameters *making a comparison with commercial units using a robot arm as testbed *validate the accuracy of the IMU on a flying platform *integrate the measurements from a GPS to reduce drift and provide accurate positiong (this will make it definitely a MS thesis) '''Material''' *electronic board and eclipse based C development toolkit for ARM processors *papers describing the algorithms we are interested in implementing '''Expected outcome:''' *few different AHRS algorithms with comparative results *user-friendly procedure to calibrate the IMU *a sistem which integrated IMU and GPS to provide accurate positioning '''Required skills or skills to be acquired:''' *C programming on ARM microcontroller *background on kalman filtering and attitude estimation | Robotics | AndreaBonarini MartinoMigliavacca MatteoMatteucci |
1 | 2 |

Real-time removal of ocular artifact from EEG | In a Brain-Computer Interface (BCI) based on electroencephalogram (EEG), one of the most important sources of noise is related to ocular movements. Algorithms have been devised to cancel the effect of such artifacts. The project consists in the in the implementation in real time of an existing algorithm (or one newly developed) in order to improve the performance of a BCI. * J.R. Wolpaw et al. ''Brain-computer interfaces for communication and control'' (http://tinyurl.com/yhq27pq) * R.J. Croff, R.J. Barry. ''Removal of ocular artifact from the EEG: a review'' (http://tinyurl.com/ykk6ks9) | BioSignal Analysis | MatteoMatteucci | 1 | 2 |

Recognition of the user's focusing on the stimulation matrix | A P300-based Brain-Computer Interface (BCI) stimulates the user continuously, and the detection of a P300 designates the choice of the user. When the user is not paying attention to the interface, false positives are likely. The objective of this work is to avoid this problem; the analysis of the electroencephalogram (EEG) over the visual cortex (and possibly an analysis of P300s or of other biosignals) should tell when the user is looking at the interface | BioSignal Analysis | MatteoMatteucci | ||

RoboCom+R2P | The goal of the project is to develop a Robot equipped with collision avoidance logic. | MatteoMatteucci | |||

Robocentric MoonSLAM | Simultaneous Localization and Mapping (SLAM) is one of the basic functionalities required from an autonomous robot. In the past we have developed a framework for building SLAM algorithm based on the use of the Extended Kalman Filter and vision sensors. The actual implementation of the EKF SLAM in the framework developed uses a world-centric approach, but from the literature it is known that a robocentric approach can provide higher performances on small maps. We would like to have both implementation to compare the results in two scenarios: pure visual odometry, conditional independent submapping. '''Material''' *A framework for multisensor SLAM using the world centric approach *Papers and report about robocentric slam '''Expected outcome:''' *a fully functional robocentric version of the MoonSLAM framework '''Required skills or skills to be acquired:''' *Basic background in computer vision *Background in Kalman filtering *C++ programming under Linux | Robotics | MatteoMatteucci SimoneCeriani |
1 | 2 |

Robot Localization and Navigation With Visual Markers | Robot Localization and Navigation With Visual Markers | Robotics | MatteoMatteucci AndreaBonarini |
||

SLDR | Computer Vision and Image Analysis | MatteoMatteucci | |||

Scan Matching Odometry and Multisensor SLAM | Starting from some C/C++ code for laser scan alignment and the covariance information associated to the matching, we are interested in the development of a library for the matching and fusion of laser scans under the ROS (www.ros.org) environment. From this we are interested in the development of an odometric system based on laser scan matching and in a Simultaneous Localization and Mapping system integrating scan matching with visual SLAM. The result is a complete navigation system that fuses laser and visual information to build consisten maps in an EKF-based environment. '''Material:''' *a MS thesis which describes the scan matching algorithms *a BS thesis which implements a prototype of the system '''Expected outcome:''' *a complete system that build maps integrating laser scan and visual informtion '''Required skills or skills to be acquired:''' *Background on Kalman filtering *C++ programming under Linux | Robotics | MatteoMatteucci SimoneCeriani DavideCucci |
1 | 2 |

Self calibration of multiple odometric sensors | An odometric sensor measures the path followed by a robot in an incremental way (e.g., wheel mounted encoders, visual odometry, scan matching based odometry, etc.) . Having several odometry sensors mounted on the same platform can significantly improve the accuracy and robustness of the overall system but requires proper calibration of relative positioning and possible biases. We are interested in the development of techniques for the self calibration of a multi sensor based odometry sensor. These techniques could be inspired by classical non-linear optimization techniques used in the hand and eye problem but they could use techniques from Simultaneous Localization and Mapping. According to the setup, some information on the real position of the system may exists (i.e., external tracking system or GPS); the approach should be able to use this information as well. '''Material:''' *datasets with real data *a few odometric system implementations *C++ libraries for non linear optimization '''Expected outcome:''' *software for the self calibration of a set of odometry systems mounted on the same robot '''Required skills or skills to be acquired:''' *C++ programming under Linux | Robotics | MatteoMatteucci SimoneCeriani DavideCucci |
1 | 2 |

Sensor fusion for autonomous cars | This project concerns the logging and use of the data fusion coming from multiple sensor installed in a car. The data are used to generate the decisions and behavior of an autonomous car. | MatteoMatteucci | |||

Sound source localization for robots | MatteoMatteucci | ||||

SprayinWithBrain | AI and Robotics in agriculture | Robotics | MatteoMatteucci GiulioFontana |
||

Statistical inference for phylogenetic trees | The project will focus on the study, implementation, comparison, and analysis of different statistical inference techniques for phylogenetic trees. Phylogenetic trees (1, 2, 3) are evolutionary trees used to represent the relationships between different species with a common ancestor. Typical inference tasks concern the construction of a tree starting from DNA sequences, involving both the choice of the topology of the tree (i.e., model selection) and the values of the parameters (i.e., model fitting). The focus will be a probabilistic description of the tree, given by the introduction of stochastic variables associated to both internal nodes and leaves of the tree. The project will focus on the understanding of the problem and on the implementation of different algorithms, so (C/C++ or Matlab or R) coding will be required. Since the approach will be based on statistical models, the student is supposed to be comfortable with notions that come from probability and statistics courses. The project is thought to be extended to master thesis, according to interesting and novel directions of research that will emerge in the first part of the work. Possible ideas may concern the proposal and implementation of new algorithms, based on recent approaches to phylogenetic inference available in the literature, as in (3) and (4). In this case the thesis requires some extra effort in order to build and consolidate some background in math in oder to understand some recent literature, especially in (mathematical) statistics and, for example, in the emerging field of algebraic statistics (5). Other possible novel applications of phylogenetic trees have been proposed in contexts different from biology, as in (6). Malware (malicious software) is software designed to infiltrate a computer without the owner's informed consent. Often malwares are related to previous programs thought evolutionary relationships, i.e., new malwares appear as small mutations of previous softwares. We are interested in the use of techniques from phylogenetic trees to create a taxonomy of real world malwares. Picture taken from http://www.tolweb.org/tree/ and http://www.blogscienze.com Bibliography # Felsenstein 2003: Inferring Phylogenies # Semple and Steel 2003: Phylogenetics: The mathematics of phylogenetics # Louis J. Billera, Susan P. Holmes and and Karen Vogtmann Geometry of the space of phylogenetic trees. Advances in Applied Math 27, 733-767 (2001) # Evans, S.N. and Speed, T.P. (1993). Invariants of some probability models used in phylogenetic inference. Annals of Statistics 21, 355-377. # Lior Pachter, Bernd Sturmfels 2005, Algebraic Statistics for Computational Biology. # A. Walenstein, E-Md. Karim, A. Lakhotia, and L. Parida. Malware Phylogeny Generation Using Permutations of Code, Journal in Computer Virology, v1.1, 2005. | Machine Learning | MatteoMatteucci LuigiMalago StefanoZanero |
1 | 2 |

Stimulus tagging using aperiodic visual stimulation in a VEP-based BCI | BioSignal Analysis | MatteoMatteucci | |||

Triskar | The goal of the project is to develop an omnidirectional robot controlled via joypad. | Robotics | MatteoMatteucci | ||

Triskar+R2P | The goal of the project is to build an omnidirectional robot based on existing hardware. | MatteoMatteucci | |||

Unmanned Aerial Vehicles Visual Navigation | Visual navigation is becoming more and more important in the development of unmanned aerial vehicles (UAV). The goal of this thesis/tesina is to review in a structured way the current state of art in the field from different perspective: research teams, projects, platforms, tasks, algorithms. The latter is the most important aspect obviously and the project should provide a clear view on what is done today, and obtaining which results. Two kind of operations are of most interest: tracking of fixed and mobile targets (and how this impact on the UAV path), navigation on a geo-referenced map. Implementing one of the standard approaches on a mini unmanned aerial vehicle would be the ideal ending of the work to turn it into a thesis. '''''Material:''''' *papers from major journals and conferences *reports from research projects '''''Expected outcome:''''' *a report with a detailed review of the state of the art organized according to the main relevant aspects (to be identified during the work) *an implementation of some state of the art algorithms for tracking or navigation '''''Required skills or skills to be acquired:''''' *proficiency in english *basic understanding of computer vision *basic understanding of filtering techniques | Robotics | MatteoMatteucci | 1 | 2 |

Visual stabilization techniques for tracking with a moving camera | Target tracking in video sequences can suffer poor performances if the camera is moving (e.g, wind, hand held device, aerial tracking system). The aim of the project is to investigate the state of the art in image stabilization and registration in non static or cluttered scenes. Possible ideas to be investigated include: homography tracking or smoothing, 3D camera motion estimation, image registration and mosicing. As a by product of the work, a tool for the performance evaluation of image stabilization algorithms should be designed. '''Material''' *a huge corpus of literature on the topic *datasets to test the approach upon *C++ library for image processing and computer vision (OpenCV) '''Expected outcome:''' *software for the stabilization of videos from a moving camera showing moving objects in cluttered environments *a tool for the objective evaluation of image stabilization algorithms '''Required skills or skills to be acquired:''' *computer vision and 3D reconstruction *C++ programming under Linux | Computer Vision and Image Analysis | MatteoMatteucci | 1 | 2 |