Difference between revisions of "Robotics"

Title: 3D Indoor scene understanding and layout reconstruction for a mobile robot in collaboration with UnimiB
Description: The proposed project aims to reconstruct the 3D structural layout of an indoor environment perceived by a mobile robot. From the sensorial data, the robot should be able to reconstruct a geometrical structure of an indoor environment (e.g., an office).

Methods for indoor layout reconstruction must be significantly more tolerant to missing data than their outdoor counterparts, since environments such as offices and apartments exhibit extremely high levels of clutter, which typically results in heavy occlusions of walls and other structures of interest, large-scale artifacts, noise and missing data. The proposed work will be developed in collaboration with IRALAB, the Robotics Lab of University of Milano Bicocca.

The work will be based on an existing project, Free Your Camera (http://www.ira.disco.unimib.it/research/robotic-perception-research/free-your-camera-3d-indoor-scene-understanding-from-arbitrary-camera-motion/) and will be part of a robotic framework based on with ROS and in development at IRALAB.
Tutor: FrancescoAmigoni, MatteoLuperto
Additional Info: CFU 10 - 20 / Master of Science / Thesis

Title: Evaluation of Automatic Differentiation Techniques for Gauss-Newton based Simultaneous Localization and Mapping
Description: In Gauss-Newton non linear optimization one of the most tedious part is computing Jacobians. At the AIRLab we have developed a framework for non linear Simultaneous Localization and Mapping suitable for different motion models and measurement equations, but any time you need to change something you need to recompute the required Jacobian. Automatic differentiation is a tool for the automatic differentiation of source code either at compiling time or at runtime; we are interested in testing these techniques in the software we have developed and compare their performance with respect to (cumbersome) optimized computation.

Material

• C++ modules for Extended Kalman Filtering
• libraries for automatic differentiation (http://www.autodiff.org/)

Expected outcome: New modules implementations based on automatic differentiation A comparison between the old stuff and new approach

Required skills or skills to be acquired:

• C++ programming under Linux
  

Tutor: MatteoMatteucci
Additional Info: CFU 10 - 20 / Master of Science / Thesis

Title: Cognitive SLAM
Description: We have developed a system that is able to detect, recognize and track objects in an image taken from a low cost robot equipped with a IMU and a low cost camera. The system is capable to detect and recognize objects using a user defined fuzzy tree classifier. However the system performance is heavily dependent on high level feature extraction, such as geometric features. The problem is non trivial due to noisy low cost camera and changes in the light conditions. The aim of this project is to improve the feature extraction and description process, both in performance and quality, possible adding a more complete description or others type of features. The long term aim of the research is to have an autonomuos robot capable to create a semantic map of the envirorment, localize himself , make inference on the map, navigate into the envirorment using the objects as landmarks. No special skills are required, except basic c and object oriented programming.
Tutor: AndreaBonarini, DavideTateo
Additional Info: CFU 5 - 20 / Master of Science / Course, Thesis

Title: Designing Living Objects
Description: The aim of this activity is to investigate how one or more objects in an antropic environment (home, office, hospital) can be designed and implemented to have a character and to move, having nice interactions with people. The work to be done concerns the analysis, definition, design and implementation of at least one of these objects.
Tutor: AndreaBonarini
Additional Info: CFU 5 - 20 / Bachelor of Science, Master of Science / Thesis, Course

Title: Reengineering of a flexible framework for simultaneous localization and mapping
Description: 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
  

Tutor: MatteoMatteucci
Additional Info: CFU 20 - 20 / Master of Science / Thesis

Title: ROS_navigation_local_planner
Description: The project will be focused on the implementation of a planner and tracking algorithms for Ackermann vehicles
Tutor: MatteoMatteucci,
Additional Info: CFU 2 - 20 / Master of Science / Thesis

Title: Robot Games
Description: Projects may include the design of an interactive game on an existing or a new robot, and its evaluation. These projects allow to experiment with real mobile robots and interaction devices. Some games may be designed for disabled children. The project can be considered a MS thesis if it can produce a new game and, possibly, a new robot, and includes adapting the behavior of the robot to the player.
Tutor: AndreaBonarini
Additional Info: CFU 2 - 20 / Bachelor of Science, Master of Science / Course, Thesis

Title: A critical review on the state of the art in visual navigation for unmanned aerial vehicles
Description: 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
  

Tutor: MatteoMatteucci
Additional Info: CFU 10 - 20 / Bachelor of Science, Master of Science / Thesis