Home Research Research lines
Research lines

3D Mapping


In the mobile robotics community significant research efforts are lately focusing on
acquiring and processing information about the 3D nature of the environments found
in real world scenarios. Overcoming the limitations imposed by the 2D models is of
utmost importance regarding safe navigation but also to provide further knowledge to
be used in other robotic tasks. Fast and robust algorithms are required
for applicability to navigation.

To gather the 3D data, we use a laser scanner, employing a nodding data acquisition system mounted on both real (Nemo) and simulated robots. Our segmentation algorithm comes up from the integration of computer vision techniques, allowing for a fast separation of points corresponding to different, not necessarily planar, surfaces. The subsequent extraction of geometrical features out of each region’s points is done by means of least-squares fitting. A Maximum Incremental Probability algorithm formulated upon the Extended Kalman Filter provides 6D localization and produces a map of planar patches with a convex-hull based representation.




 

Fuzzy control

We research on fuzzy control theory in the following subtopics:

  • Fuzzy models
  • Fuzzy systems stability
  • Variable structure control
  • Fuzzy Kalman filtering

In parallel we apply the results to solve control problems in both continuous processes and mobile robotics.

 

Heuristic Search and Combinatorics

For a number of years now, ICG has been studying search procedures, a fundamental issue in AI. The approach is mainly practical, i.e. to develop efficient algorithms which reduce the average complexity of classical hard AI search problems which have, in many cases, direct applications to real life problems such as vision, planning, biocomputation etc. Interest has also extended to games (e.g. N-Queens, Sudoku), constraint satisfaction problems (CSP) and combinatorial NP-hard problems such as the maximum clique problem or the Boolean satisfiablility problem (alias SAT) both extensively studied in complexity theory. At present the landmarks of this line of research are:

A graph of 17 vertices and a maximum clique of 3
  • BB-MC : one of the best algorithms for the maximum clique problems which uses bit strings effectively to reduce complexity. BBMC has been used successfully in the geometric correspondence problem and applied to find the pose of a robot given a map of the environment and a local observation.
  • The best global search heuristic for the N-Queens problem, up to our knowledge.
  • A very efficient Sudoku solver which can solve random 25x25 giant locally minimal Sudokus instances in a few seconds.
  • A SAT algorithm which uses bit strings to efficiently compute the ‘pure literal’ rule in a DPLL search.

 

 

Man-Machine Systems


Many years of Human Factors research have shown that the development of effective, efficient, and usable interfaces requires the inclusion of the user’s perspective throughout the entire design and development process. [Unfortunately] Human-Robot  Interface development tends to be an after thought, as researchers approach the problem from an engineering perspective. Such a perspective implies that the interface is designed and developed after the majority of the robotic system design has been completed. The goal of this line of research is to develop robotic systems usable for humans.
A user interface provides the means by which humans and machines interact. Another term for user interface is a man-machine interface (MMI). The MMI includes all the components that the user encounters. The components include the input language, output language and interaction protocol. The term ”human-computer interaction” was adopted in the mid-1980’s, and it describes a field of study that deals with all aspects of interaction between participants and computers. Human-Computer Interaction (HCI) is defined by the Association for Computing Machinery (ACM) Special Interest Group on Computer-Human Interaction (SIGCHI) as ”a discipline concerned with the design, evaluation, and implementation of interactive computing systems for human use and with the study of the major phenomenon surrounding them”.

Initially, human-robot interfaces began in the form of robotic-arms tele-operation, limited by the lack of sensing and intelligence; in this first stage, the robot was just seen as an extension of the operator body. As computational capabilities increased, research advances were made in sensing, artificial intelligence, computer graphics, etc. This drastically changed the HRI system, from a master-slave system to collaborative systems. Such an HRI system should improve the mission or task results because it benefits from the capabilities of the artificial agent and the human. This system should bring four advantages to the simple master-slave telesystem:
  1. Improve both the speed and quality of the operator’s problem-solving performance;
  2. reduce cognitive fatigue by managing the presentation of information;
  3. maintain low communication bandwidths associated with semi-autonomous control by requesting only the relevant sensory data from the remote;
  4. improve efficiency by reducing the need for supervision so that the operator can perform other tasks; and
  5. support the incremental evolution of telesystems to full autonomy
 

Swarm Robotics

Swarm

 
More Articles...
  • «
  •  Start 
  •  Prev 
  •  1 
  •  2 
  •  Next 
  •  End 
  • »
Page 1 of 2