The aim of the research is to develop a method of design and implementation of intelligent service robots. It has been established that in order to execute the tasks formerly exclusively performed by humans, such a system requires sensors corresponding to human senses such as sight and perception of force as well as appropriate processing algorithms. In this project we focus on developing the algorithms and the technology necessary for creating a working robotic system, able to locate and classify objects, generate an appropriate plan of approaching those objects and, in the final phase, their classification and manipulation using appropriate tool assuming that the object have internal degrees of freedom.

1. T. Winiarski, M. Węgierek, D. Seredyński, W. Dudek, K. Banachowicz, and C. Zieliński
   EARL – Embodied Agent-Based Robot Control Systems Modelling Language
   Electronics, vol. 9, no. 2-379, 2020
   [ BIB | DOI | abstract | URL ]

   @article{earl2020-twiki,
     author = {Winiarski, Tomasz and Węgierek, Maciej and Seredyński, Dawid and Dudek, Wojciech and Banachowicz, Konrad and Zieliński, Cezary},
     title = {{EARL -- Embodied Agent-Based Robot Control Systems Modelling Language}},
     journal = {Electronics},
     year = {2020},
     volume = {9},
     number = {2 - 379},
     issn = {2079-9292},
     article-number = {379},
     doi = {10.3390/electronics9020379},
     projects = {GrantMeDeRo,EARL},
     twiki = {journal},
     url = {https://www.mdpi.com/2079-9292/9/2/379}
   }
   

   The paper presents the Embodied Agent-based Robot control system modelling Language (EARL). EARL follows a Model-Driven Software Development approach (MDSD), which facilitates robot control system development. It is based on a mathematical method of robot controller specification, employing the concept of an Embodied Agent, and a graphical modelling language: System Modelling Language (SysML). It combines the ease of use of SysML with the precision of mathematical specification of certain aspects of the designed system. It makes the whole system specification effective, from the point of view of the time needed to create it, conciseness of the specification and the possibility of its analysis. By using EARL it is possible to specify systems both with fixed and variable structure. This was achieved by introducing a generalised system model and presenting particular structures of the system in terms of modelling block configurations adapted by using instances. FABRIC framework was created to support the implementation of EARL-based controllers. EARL is compatible with component based robotic middlewares (e.g., ROS and Orocos).

2. T. Kornuta, C. Zieliński, and T. Winiarski
   A universal architectural pattern and specification method for robot control system design
   Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 68, no. 1, pp. 3–29, 2020
   [ BIB | DOI | abstract | URL ]

   @article{kornuta-bpan-2020-twiki,
     author = {Kornuta, Tomasz and Zieliński, Cezary and Winiarski, Tomasz},
     journal = {Bulletin of the Polish Academy of Sciences: Technical Sciences},
     title = {A universal architectural pattern and specification method for robot control system design},
     year = {2020},
     number = {1},
     pages = {3-29},
     volume = {68},
     doi = {10.24425/bpasts.2020.131827},
     projects = {GrantMeDeRo,GrantRobREx},
     howpublished = {online},
     keywords = {Autonomous Agents, Control Architectures and Programming, service robots, Range Sensing, Recognition, Grasping},
     twiki = {journal},
     url = {http://journals.pan.pl/Content/115154/PDF/01_03-29_01163_Bpast.No.68-1_28.02.20_K_OK_TeX.pdf}
   }
   

   The paper presents a universal architectural pattern and an associated specification method that can be applied in the design of robot control systems. The approach describes the system in terms of embodied agents and proposes a multi-step decomposition enabling precise definition of their inner structure and operation. An embodied agent is decomposed into effectors, receptors, both real and virtual, and a control subsystem. Those entities communicate through communication buffers. The activities of those entities are governed by FSMs that invoke behaviours formulated in terms of transition functions taking as arguments the contents of input buffers and producing the values inserted into output buffers. The method is exemplified by applying it to the design of a control system of a robot executing one of the most important tasks for a service robot, i.e. picking up, by a position-force controlled robot, an object located using an RGB-D image acquired from a Kinect. Moreover in order to substantiate the universality of the presented approach we present how classical, known from the literature, robotic architectures can be expressed as systems composed of one or more embodied agents.

3. C. Zieliński and M. Figat
   Robot System Design Procedure Based on a Formal Specification
   in Recent Advances in Automation, Robotics and Measuring Techniques, 2016, vol. 440, pp. 511–522
   [ BIB | DOI | abstract | URL ]

   @inproceedings{zielinski:2016-automation-twiki,
     author = {Zieliński, Cezary and Figat, Maksym},
     booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
     title = {{Robot System Design Procedure Based on a Formal Specification}},
     year = {2016},
     editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
     note = {Zielinski},
     pages = {511-522},
     publisher = {Springer},
     series = {Advances in Intelligent Systems and Computing (AISC)},
     volume = {440},
     doi = {10.1007/978-3-319-29357-8_45},
     projects = {GrantMeDeRo},
     owner = {tkornut},
     timestamp = {2015.10.30},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/specification.pdf}
   }
   

   This paper presents a robot control system design procedure based on a formal specification. The specification describes both the structure and the activities of a robot system in a formal manner. Using this specification the code of the robot system controller can be produced. The paper shows how. Moreover it has been shown that the complexity of the robot control system is concentrated in two of its elements: transition functions and the structure of the FSM. The reduction of the complexity of transition functions simultaneously increases the number of states of the FSM and vice versa, so it is up to the designer of the system to choose the adequate complexity level of this pair.

4. A. Wujek and T. Winiarski
   Automated Drawing Recognition and Reproduction with a Multisensory Robotic Manipulation System
   in Recent Advances in Automation, Robotics and Measuring Techniques, 2016, vol. 440, pp. 423–433
   [ BIB | DOI | abstract | URL | VIDEO ]

   @inproceedings{wujek:automation-2016-twiki,
     author = {Wujek, Anna and Winiarski, Tomasz},
     booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
     title = {{Automated Drawing Recognition and Reproduction with a Multisensory Robotic Manipulation System}},
     year = {2016},
     editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
     pages = {423-433},
     publisher = {Springer},
     series = {Advances in Intelligent Systems and Computing (AISC)},
     volume = {440},
     doi = {10.1007/978-3-319-29357-8_38},
     projects = {GrantMeDeRo},
     owner = {tkornut},
     timestamp = {2015.10.30},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/15-automated-drawing-recognition.pdf},
     video = {https://vimeo.com/170228609}
   }
   

   Article presents a multisensory robotic system, that is reproducing contour drawings. Initially the system detects a sheet of paper with a reference drawing, determines contours of the drawing, and then draws contour image on a blank sheet of paper. The reproduction conserves features of the original drawing - shapes, location and scale. The system was created with usage of an embodied agent theory. In this article two main parts of a designed system are presented - vision module (virtual receptor) and control subsystem. System is verified on a modified industrial manipulator acting as a service robot with an eye in hand camera and a force/torque sensor mounted in the wrist.

5. T. Winiarski, W. Kasprzak, M. Stefańczyk, and M. Walęcki
   Automated inspection of door parts based on fuzzy recognition system
   in 21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2016, 2016, pp. 478–483
   [ BIB | DOI | abstract | URL ]

   @inproceedings{mmar_winiarski_automated-2016-twiki,
     author = {Winiarski, Tomasz and Kasprzak, Włodzimierz and Stefańczyk, Maciej and Walęcki, Michał},
     booktitle = {21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2016},
     title = {{Automated inspection of door parts based on fuzzy recognition system}},
     year = {2016},
     pages = {478--483},
     publisher = {IEEE},
     doi = {10.1109/MMAR.2016.7575182},
     projects = {GrantMeDeRo},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/mmar_winiarski_automated.pdf}
   }
   

   The article presents a comprehensive strategy of door parts (locks, handles, doorplates etc.) examination as a paradigm of active sensing. It covers the whole process – from segmentation, through initial hypothesis generation based on fuzzy inference, to final recognition and precise localization of the keyholes in a robot base coordinate system. The strategy is a preliminary stage of a door locks opening procedure. The image analysis process is divided into three steps. First, an initial region of interest is localized using a RGB-D low resolution camera mounted on the robot’s head. It is then categorized, based on its properties, as a lock, handle, doorplate etc. Finally it is inspected using 2D camera mounted on the robot’s arm. Thanks to the preliminary localization with the head camera the robot can look at the point of interest at sight, without time-consuming thorough inspection of the whole door. The whole system was formally specified as an embodied agent. For that purpose a system modeling language was used to specify embodied agent subsystems behaviors. The proposed strategy is verified experimentally using Velma prototype service robot.

6. D. Seredyński, K. Banachowicz, and T. Winiarski
   Graph–based potential field for the end–effector control within the torque–based task hierarchy
   in 21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2016, 2016, pp. 645–650
   [ BIB | DOI | abstract | URL | VIDEO ]

   @inproceedings{mmar_seredynski_graph-2016-twiki,
     author = {Seredyński, Dawid and Banachowicz, Konrad and Winiarski, Tomasz},
     booktitle = {21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2016},
     title = {{Graph–based potential field for the end–effector control within the torque–based task hierarchy}},
     year = {2016},
     pages = {645--650},
     publisher = {IEEE},
     doi = {10.1109/MMAR.2016.7575212},
     projects = {GrantMeDeRo},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/mmar_seredynski_graph.pdf},
     video = {https://vimeo.com/139385788}
   }
   

   In the article, a reactive torque–based hierarchical task–space control for a robot with multiple redundant DOFs is presented that is suitable to plan, validate and execute a humanoid upper-body motion in human oriented environment. The strategy consists of: (i) joint limit avoidance, (ii) self–collision avoidance using repulsive force fields with additional environment collision avoidance, (iii) end–effector task with a specified discrete potential field with tricubic interpolation and (iv) a posture task on the lowest priority. The proposed approach is verified for Velma – a robot with a humanoid upper-body.

7. D. Seredyński, M. Stefańczyk, K. Banachowicz, B. Świstak, V. Kutia, and T. Winiarski
   Control system design procedure of a mobile robot with various modes of locomotion
   in 21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2016, 2016, pp. 490–495
   [ BIB | DOI | abstract | URL | VIDEO ]

   @inproceedings{mmar_seredynski_control-2016-twiki,
     author = {Seredyński, Dawid and Stefańczyk, Maciej and Banachowicz, Konrad and Świstak, Bartosz and Kutia, Vitalii and Winiarski, Tomasz},
     booktitle = {21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2016},
     title = {{Control system design procedure of a mobile robot with various modes of locomotion}},
     year = {2016},
     pages = {490--495},
     publisher = {IEEE},
     doi = {10.1109/MMAR.2016.7575184},
     projects = {GrantMeDeRo},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/mmar_seredynski_control.pdf},
     video = {https://www.youtube.com/watch?v=lnnb9ZKDu4M}
   }
   

   In this article the design procedure of a control system of a mobile robot with various modes of locomotion has been considered. The procedure is based on an embodied agent theory and focuses on the agent behaviours and transitions between them. The procedure was introduced to speed up and organize the whole controller development process. The effectiveness of the proposed approach is proved through control system development and experimental verification of the custombuilt Lynx mobile robot with vertical and horizontal modes of locomotion.

8. T. Kornuta and M. Laszkowski
   Perception subsystem for object recognition and pose estimation in RGB-D images
   in Recent Advances in Automation, Robotics and Measuring Techniques, 2016, vol. 440, pp. 597–607
   [ BIB | DOI | abstract | URL ]

   @inproceedings{Kornuta:2016_automation_perception-twiki,
     author = {Kornuta, Tomasz and Laszkowski, Michał},
     booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
     title = {{Perception subsystem for object recognition and pose estimation in RGB-D images}},
     year = {2016},
     editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
     pages = {597-607},
     publisher = {Springer},
     series = {Advances in Intelligent Systems and Computing (AISC)},
     volume = {440},
     doi = {10.1007/978-3-319-29357-8_52},
     projects = {GrantMeDeRo},
     owner = {tkornut},
     timestamp = {2015.10.30},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/rgbd-grasping.pdf}
   }
   

   RGB-D sensors have become key components of all kind of robotic systems. In this paper we present a perception subsystem for object recognition and pose estimation in RGB-D images. The system is able to recognize many objects at once, disregarding whether they belong to one or many classes. Next to the detailed description of the principle of the system operation we present several off-line and on-line experiments validating the system, including verification in the task of picking up recognized objects with IRp-6 manipulator.

9. T. Winiarski, K. Banachowicz, M. Walęcki, and J. Bohren
   Multibehavioral position–force manipulator controller
   in 21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2016, 2016, pp. 651–656
   [ BIB | DOI | abstract | URL ]

   @inproceedings{mmar_winiarski_multibehavioral-2016-twiki,
     author = {Winiarski, Tomasz and Banachowicz, Konrad and Walęcki, Michał and Bohren, Jonathan},
     booktitle = {21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2016},
     title = {{Multibehavioral position–force manipulator controller}},
     year = {2016},
     pages = {651--656},
     publisher = {IEEE},
     doi = {10.1109/MMAR.2016.7575213},
     projects = {GrantMeDeRo},
     twiki = {article},
     url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/mmar_winiarski_multibehavioral.pdf}
   }
   

   In the article the whole process of a manipulator controller development is presented. The controller is designed for the execution of various benchmark tasks in the field of service robotics. Initially, a set of system behaviors is presented as the base of the universal controller structure. For that purpose the embodied agent theory and the System Modeling Language are utilized. The execution and switching between the behaviors relies on a particular algorithm. The control system is verified on a two arm robotic system that consists of position-controlled industrial manipulators and a number of extra force/torque sensors and cameras.

10. T. Winiarski, K. Banachowicz, and D. Seredyński
    Two mode impedance control of Velma service robot redundant arm
    in Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics., 2015, vol. 351, pp. 319–328
    [ BIB | DOI | abstract | URL ]

    @inproceedings{winiarski2015automation-twiki,
      author = {Winiarski, Tomasz and Banachowicz, Konrad and Seredyński, Dawid},
      booktitle = {Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics.},
      title = {{Two mode impedance control of Velma service robot redundant arm}},
      year = {2015},
      editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
      pages = {319--328},
      publisher = {Springer},
      series = {Advances in Intelligent Systems and Computing (AISC)},
      volume = {351},
      doi = {10.1007/978-3-319-15847-1_31},
      projects = {GrantMeDeRo},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/14-velma-two-mode-aut.pdf}
    }
    

    The previous research on reactive torque control of redundant arms led to conclusion, that initial arm kinematic configuration is vital for task executed with the use of Cartesian impedance control. To provide that, in the article the control system is proposed with the two following modes of impedance control of redundant manipulators: Joint space and Cartesian space. For this purpose the system was treated as embodied agent with two behaviors of its Virtual Effector (hardware abstraction layer). Each behavior has been decomposed to several components described by automatons and communicate asynchronously with upper layers of the control system. The whole system has been finally verified on real manipulator.

11. T. Winiarski and K. Banachowicz
    Automated generation of component system for the calibration of the service robot kinematic parameters
    in 20th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2015, 2015, pp. 1098–1103
    [ BIB | DOI | abstract | URL ]

    @inproceedings{winiarskimmar2015-twiki,
      author = {Winiarski, Tomasz and Banachowicz, Konrad},
      booktitle = {20th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2015},
      title = {Automated generation of component system for the calibration of the service robot kinematic parameters},
      year = {2015},
      pages = {1098--1103},
      publisher = {IEEE},
      doi = {10.1109/MMAR.2015.7284032},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2015/velma-calibration-2015.pdf},
      projects = {GrantMeDeRo},
      twiki = {article}
    }
    

    In the article we propose a fast and cheap strategy of service robot kinematic parameters calibration. Our method is based on sensors (cameras in particular) that are already mounted on the robot and inexpensive markers, that are easy to fix on the robot arms. We developed the method to compute the impact of manipulator velocity on markers localization error in camera image. Thanks to our method, the calibration data acquisition can be significantly shortened, because a certain, acceptable marker detection error threshold can be introduced that allows to acquire the data with non-zero velocity of the manipulator. Additionally, we propose a method of automatic component based data acquisition system generation, based on the embodied agent theory and tree like kinematic model representation of the robot. Our model is suitable for the most of service robots. The same model forms the base for an automatic generation of measure functions for cost functions used in the optimization process to find the optimal set of model parameters. The whole approach has been verified experimentally using Velma service robot.

12. T. Kornuta, T. Winiarski, and C. Zieliński
    Specification of abstract robot skills in terms of control system behaviours
    in Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics., 2015, vol. 351, pp. 139–152
    [ BIB | DOI | abstract | URL ]

    @inproceedings{Kornuta:2015_Automation_grasping-twiki,
      author = {Kornuta, Tomasz and Winiarski, Tomasz and Zieliński, Cezary},
      booktitle = {Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics.},
      title = {{Specification of abstract robot skills in terms of control system behaviours}},
      year = {2015},
      editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
      note = {Zielinski},
      pages = {139--152},
      publisher = {Springer},
      series = {Advances in Intelligent Systems and Computing (AISC)},
      volume = {351},
      affiliation = {Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland},
      doi = {10.1007/978-3-319-15847-1_14},
      projects = {GrantMeDeRo},
      owner = {tkornuta},
      timestamp = {2014.12.10},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2015/14-grasp-skill-specification.pdf}
    }
    

    Robotic systems possess diverse effectors and receptors influencing their capabilities. For this reason description of robot tasks in a human-understandable form, being strict and abstracting the hardware limitations at the one hand, yet enabling straightforward transformation into robot actions at the other, has been elusive. Herein we propose a method of specification of tasks in terms of abstract object-level relations. This approach imposes the introduction of manipulation primitives modifying those relations by influencing object parameters. To narrow the scope of research in this paper we focus on one of the most elementary robot skills: grasping. We decompose the robot control system using the embodied agent-based methodology, define a set of required behaviours and express the skill as a sequence of those behaviours. To enable the future automatic translation from specification to code, we developed a formal specification of the introduced concepts.

13. T. Winiarski, K. Banachowicz, and D. Seredyński
    Multi-sensory Feedback Control in Door Approaching and Opening
    in Intelligent Systems’2014, 2015, vol. 323, pp. 57–70
    [ BIB | DOI | abstract | URL | VIDEO ]

    @inproceedings{winiarski2014is-twiki,
      author = {Winiarski, Tomasz and Banachowicz, Konrad and Seredyński, Dawid},
      booktitle = {Intelligent Systems'2014},
      title = {Multi-sensory Feedback Control in Door Approaching and Opening},
      year = {2015},
      editor = {Filev, D. and Jabłkowski, J. and Kacprzyk, J. and Krawczak, M. and Popchev, I. and Rutkowski, L. and Sgurev, V. and Sotirova, E. and Szynkarczyk, P. and Zadrozny, S.},
      volume = {323},
      series = {Advances in Intelligent Systems and Computing},
      pages = {57-70},
      publisher = {Springer International Publishing},
      doi = {10.1007/978-3-319-11310-4_6},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2015/14-door-is.pdf},
      projects = {GrantMeDeRo},
      isbn = {978-3-319-11309-8},
      keywords = {service robot; impedance control; tactile sensing},
      language = {English},
      twiki = {inbook},
      video = {https://vimeo.com/114881804}
    }
    

    In the article the robotic system behavior is investigated for the complex door opening task. The system consists of the 7-DOF KUKA LWR4+ manipulator, which is controlled in an impedance way and the BarrettHand gripper, which is controlled in a position way. The system utilizes multi-sensory feedback. The visual feedback is used to roughly localize door and to plan a door approach trajectory. The tactile feedback detects the contact with the door, and handle and determines an exact contact position with the handle. The system does not form a grip in a door opening stage, but the contact between the robot and the door is maintained by the gripper’s fingers (with intrinsic backlash), which are pushing the handle from its one side. This concept allows to open the door when there are obstacles in the neighborhood of the handle (e.g. door jamb or frame), which make the grip impossible.

14. M. Stefańczyk and T. Kornuta
    Handling of asynchronous data flow in robot perception subsystems
    in Simulation, Modeling, and Programming for Autonomous Robots, 2014, vol. 8810, pp. 509–520
    [ BIB | DOI | abstract | URL ]

    @inproceedings{Stefanczyk:2014_discode_simpar,
      author = {Stefańczyk, Maciej and Kornuta, Tomasz},
      booktitle = {Simulation, Modeling, and Programming for Autonomous Robots},
      title = {Handling of asynchronous data flow in robot perception subsystems},
      year = {2014},
      volume = {8810},
      series = {Lecture Notes in Computer Science},
      pages = {509-520},
      publisher = {Springer},
      doi = {10.1007/978-3-319-11900-7_43},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/discode.pdf},
      projects = {GrantMeDeRo},
      isbn = {978-3-319-11899-4},
      keywords = {discode},
      owner = {tkornuta},
      timestamp = {2014.07.17},
      twiki = {inbook}
    }
    

    Robot perception subsystems typically form complex networks, with boxes representing computations and arrows presenting the exchanged data. Taking into account that data acquired from robot sensors may arrive with different frequencies, as well as that computations may by performed on different processor cores, a problem of handling of asynchronous data flows appears. Hence appropriate tools facilitating the implementation are highly demanded. In this article we propose a solution to the aforementioned problem, enabling the activation of a conditional behaviour of a given computational block, depending on the presence of data in its input buffers. Theoretical considerations led to the implementation of these mechanisms in a component-oriented framework for development of robot perception subsystems: DisCODe. Operation of the solution was verified on an exemplary perception subsystem using RGB-D camera.

15. M. Stefańczyk and T. Kornuta
    Akwizycja obrazów RGB-D: metody
    Pomiary – Automatyka – Robotyka PAR, vol. 18, no. 1, pp. 82–90, 2014
    [ BIB | DOI | abstract | URL ]

    @article{Stefanczyk:2014_par_rgbd_metody,
      author = {Stefańczyk, Maciej and Kornuta, Tomasz},
      journal = {Pomiary -- Automatyka -- Robotyka PAR},
      title = {{Akwizycja obrazów RGB-D: metody}},
      year = {2014},
      note = {Acquisition of RGB-D images: methods (in Polish)},
      number = {1},
      pages = {82--90},
      volume = {18},
      doi = {10.14313/PAR_203/82},
      projects = {GrantMeDeRo},
      owner = {tkornuta},
      timestamp = {2014.01.25},
      twiki = {journal},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/13-rgbd-metody.pdf}
    }
    

    Dwuczęściowy artykuł poświęcono czujnikom umożliwiającym akwizycję chmur punktów oraz map głębi. W poniższej, pierwszej części uwagę skupiono na trzech głównych metodach pomiarowych: stereowizji, świetle strukturalnym oraz pomiarze czasu lotu wiązki jako tych, które sa najpowszechniej stosowane w robotyce. Poza zasadą działania każdej z metod przeanalizowano także ich właściwości, złożoność obliczeniową oraz potencjalne zastosowania.

16. T. Kornuta, M. Laszkowski, A. Wilkowski, Ł. Żmuda, and K. Katerżawa
    Rozpoznawanie obiektów w obrazach RGB-D: generacja modeli obiektów
    in XIII Krajowa Konferencja Robotyki – Postępy robotyki, 2014, vol. 194, no. 1, pp. 277–286
    [ BIB | abstract | URL ]

    @inproceedings{Kornuta:2014_kkr_generacja-twiki,
      author = {Kornuta, Tomasz and Laszkowski, Michał and Wilkowski, Artur and Żmuda, Łukasz and Katerżawa, Karol},
      booktitle = {XIII Krajowa Konferencja Robotyki -- Postępy robotyki},
      title = {{Rozpoznawanie obiektów w obrazach RGB-D: generacja modeli obiektów}},
      year = {2014},
      editor = {Tchoń, K. and Zieliński, Cezary},
      note = {{Recognition of objects in RGB-D images: generation of models of objects (in Polish)}},
      number = {1},
      pages = {277--286},
      series = {Prace Naukowe – Elektronika},
      volume = {194},
      conference = {kkr13},
      projects = {GrantMeDeRo},
      lang = {pl},
      owner = {tkornuta},
      timestamp = {2014.02.11},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/rozpoznawanie-obiektow-modele-kkr13.pdf}
    }
    

    Czujniki RGB-D zwracające obrazy kolorowe wraz ze skojarzonymi mapami głębi otwierają nowe możliwości w percepcji robotów. W dwuczęściowym artykule skupiono uwagę na rozpoznawaniu obiektów w obrazach zwracanych przez tego typu urządzenia. W poniższej, pierwszej części skupiono uwagę na generacji modeli obiektów trójwymiarowych. Zaprezentowano stworzone stanowisko do akwizycji różnych widoków obiektów oraz omówiono proces tworzenia modeli poprzez łączenie tych widoków. Ideę jego działania oparto o przekształcenie obrazu RGB-D do postaci chmury punktów oraz ekstrakcję cech. Stworzone modele wykorzystywane są następnie do rozpoznawania konkretnych instancji obiektów z wykorzystaniem metod probabilistycznych, czemu poświęcono druga część artykułu.

17. C. Zieliński and T. Kornuta
    Diagnostic Requirements in Multi-robot Systems
    in Intelligent Systems in Technical and Medical Diagnostics, vol. 230,
    Springer, 2014, pp. 345–356 [ BIB | DOI | abstract | URL ]

    @incollection{zielinski2014diagnostic,
      author = {Zieliński, Cezary and Kornuta, Tomasz},
      title = {Diagnostic Requirements in Multi-robot Systems},
      booktitle = {Intelligent Systems in Technical and Medical Diagnostics},
      publisher = {Springer},
      year = {2014},
      volume = {230},
      series = {Advances in Intelligent Systems and Computing (AISC)},
      pages = {345--356},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/2014_dps_diagnostics.pdf},
      doi = {10.1007/978-3-642-39881-0_29},
      projects = {GrantMeDeRo},
      isbn = {978-3-642-39880-3},
      owner = {tkornuta},
      timestamp = {2013.10.03},
      twiki = {inbook},
      note = {Zielinski}
    }
    

    The paper presents a generic robot control architecture facilitating the collection of data for the purpose of diagnostics. Each robot within the system is treated as an embodied agent composed of effectors, receptors and a control system. Its behaviour is described in terms of transition functions and: initial, terminal and error conditions. Data within such systems can be collected at the control system sampling rate, thus both continuous monitoring and event driven one are possible.

18. M. Stefańczyk and M. Walęcki
    Localization of essential door features for mobile manipulation
    in Recent Advances in Automation, Robotics and Measuring Techniques, 2014, vol. 267, pp. 487–496
    [ BIB | DOI | abstract | URL ]

    @inproceedings{stefanczyk2014localization-twiki,
      author = {Stefańczyk, Maciej and Walęcki, Michał},
      booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
      title = {Localization of essential door features for mobile manipulation},
      year = {2014},
      editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
      volume = {267},
      series = {Advances in Intelligent Systems and Computing (AISC)},
      pages = {487--496},
      publisher = {Springer},
      doi = {10.1007/978-3-319-05353-0_46},
      url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/13-door-rec-aut.pdf},
      projects = {GrantMeDeRo},
      twiki = {inbook}
    }
    

    In this paper, we present a control system of a robot actively detecting and labeling door features, such as handle, lock or door plate. System is described using agent-based approach, with clear division into control, effector and receptor subsystems, with most important parts deeply explained. Presented approach supplements gap between door detection and opening algorithms, giving a robot the ability to take more actions, like recognizing room number or opening door lock.

19. M. Stefańczyk, M. Walęcki, K. Banachowicz, and T. Winiarski
    Robot usługowy Velma – projekt i konstrukcja głowy
    in XIII Krajowa Konferencja Robotyki – Postępy robotyki, 2014, vol. 2, pp. 451–460
    [ BIB | abstract | URL ]

    @inproceedings{stefanczyk2014robotkkr13-twiki,
      author = {Stefańczyk, Maciej and Walęcki, Michał and Banachowicz, Konrad and Winiarski, Tomasz},
      booktitle = {XIII Krajowa Konferencja Robotyki -- Postępy robotyki},
      title = {{Robot usługowy Velma -- projekt i konstrukcja głowy}},
      year = {2014},
      pages = {451--460},
      volume = {2},
      conference = {kkr13},
      projects = {GrantMeDeRo},
      lang = {pl},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/velma-glowa-kkr13.pdf}
    }
    

    Robot usługowy Velma jest nową konstrukcją, powstającą w Zespole Programowania Robotów i Systemów Rozpoznających Politechniki Warszawskiej. W niniejszym artykule uwaga skupiona jest na projekcie i konstrukcji jego głowy. Proces powstawania głowy omówiono kompleksowo, zaczynając od analizy istniejących konstrukcji oraz specyfikacji wymagań. Z nich wynika zastosowana konstrukcja mechaniczna oraz wykorzystywany układ sensoryczny, których sterowanie opisane zostało dodatkowo w sposób formalny. Działanie zbudowanego urządzenia zostało już częściowo zweryfikowane aplikacyjnie.

20. T. Kornuta, K. Katerżawa, and M. Laszkowski
    Rozpoznawanie obiektów w obrazach RGB-D: wnioskowanie probabilistyczne
    in XIII Krajowa Konferencja Robotyki – Postępy robotyki, 2014, vol. 194, no. 1, pp. 287–296
    [ BIB | abstract | URL ]

    @inproceedings{Kornuta:2014_kkr_wnioskowanie-twiki,
      author = {Kornuta, Tomasz and Katerżawa, Karol and Laszkowski, Michał},
      booktitle = {XIII Krajowa Konferencja Robotyki -- Postępy robotyki},
      title = {{Rozpoznawanie obiektów w obrazach RGB-D: wnioskowanie probabilistyczne}},
      year = {2014},
      editor = {Tchoń, K. and Zieliński, Cezary},
      note = {{Recognition of objects in RGB-D images: probabilistic inference (in Polish)}},
      number = {1},
      pages = {287--296},
      series = {Prace Naukowe – Elektronika},
      volume = {194},
      conference = {kkr13},
      projects = {GrantMeDeRo},
      lang = {pl},
      owner = {tkornuta},
      timestamp = {2014.02.11},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/rozpoznawanie-obiektow-wnioskowanie-kkr13.pdf}
    }
    

    Czujniki RGB-D zwracające obrazy kolorowe wraz ze skojarzonymi mapami głębi otwierają nowe możliwości w percepcji robotów. W dwuczęściowym artykule skupiono uwagę na rozpoznawaniu obiektów w obrazach zwracanych przez tego typu urządzenia. W poniższej, pierwszej części skupiono uwagę na generacji modeli obiektów trójwymiarowych. Zaprezentowano stworzone stanowisko do akwizycji różnych widoków obiektów oraz omówiono proces tworzenia modeli poprzez łączenie tych widoków. Ideę jego działania oparto o przekształcenie obrazu RGB-D do postaci chmury punktów oraz ekstrakcję cech. Stworzone modele wykorzystywane są następnie do rozpoznawania konkretnych instancji obiektów z wykorzystaniem metod probabilistycznych, czemu poświęcono druga część artykułu.

21. T. Winiarski and K. Banachowicz
    Sterowanie redundantnym systemem dwuramiennym z aktywnym korpusem
    in XIII Krajowa Konferencja Robotyki – Postępy robotyki, 2014, vol. 2, pp. 433–442
    [ BIB | abstract | URL ]

    @inproceedings{winiarski-sterowanie-dr-kkr13-twiki,
      author = {Winiarski, Tomasz and Banachowicz, Konrad},
      booktitle = {XIII Krajowa Konferencja Robotyki -- Postępy robotyki},
      title = {{Sterowanie redundantnym systemem dwuramiennym z aktywnym korpusem}},
      year = {2014},
      pages = {433--442},
      volume = {2},
      conference = {kkr13},
      projects = {GrantMeDeRo},
      lang = {pl},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/sterowanie-systemem-dwuramiennym-kkr13.pdf}
    }
    

    Artykuł prezentuje systemem sterowania redundantego robota dwuramiennego z aktywnym korpusem. Do projektu wybrano manipulatory KUKA-LWR4+ oraz korpus o dwóch aktywnych stopniach swobody. Sterownik robota oparto o podejście agentowe oraz sterowanie impedancyjne. Uwzględnia ono typową definicję zadania w przestrzeni zewnętrznej, korektę postury, ograniczenia manipulatorów w przestrzeni konfiguracyjnej oraz specyficzną konstrukcją korpusu sterowanego admitancyjnie i prądowo.

22. T. Winiarski and M. Walęcki
    Motor cascade position controllers for service oriented manipulators
    in Recent Advances in Automation, Robotics and Measuring Techniques, 2014, vol. 267, pp. 533–542
    [ BIB | DOI | abstract | URL ]

    @inproceedings{winiarski2014automation-twiki,
      author = {Winiarski, Tomasz and Walęcki, Michał},
      booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
      title = {{Motor cascade position controllers for service oriented manipulators}},
      year = {2014},
      editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
      pages = {533--542},
      publisher = {Springer},
      series = {Advances in Intelligent Systems and Computing (AISC)},
      volume = {267},
      doi = {10.1007/978-3-319-05353-0_50},
      projects = {GrantMeDeRo},
      twiki = {inbook},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/13-con-aut.pdf}
    }
    

    In the article a method is proposed to achieve some advantages of impedance control in the manipulators without direct torque controllers in joints, that is with indirect position–force control, position controlled joints and force–torque sensor in the wrist. The method is applicable to robots with backdrivable gears, where the external force exerted on the links causes the joints movement. The approach improves safety behaviour of a manipulator without the need for major changes in the hardware nor building a new robot, which is very important especially from the point of view of research systems.

23. T. Winiarski and K. Banachowicz
    Opening a door with a redundant impedance controlled robot
    Robot Motion & Control (RoMoCo), 9th Workshop on, pp. 221–226, 2013
    [ BIB | DOI | abstract | URL ]

    @article{Winiarski:2013_RoMoCo-twiki,
      author = {Winiarski, Tomasz and Banachowicz, Konrad},
      title = {Opening a~door with a~redundant impedance controlled robot},
      journal = {Robot Motion \& Control (RoMoCo), 9th Workshop on},
      year = {2013},
      pages = {221--226},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/door-romoco-2013.pdf},
      conference = {romoco13},
      doi = {10.1109/RoMoCo.2013.6614612},
      editor = {K.~Kozłowski},
      projects = {GrantMeDeRo},
      twiki = {article}
    }
    

    Opening a door with a robotic manipulator equipped with a gripper, is a vital problem in service robotics research. This paper presents an approach to opening a cabinet door with an impedance controlled 7-DOF redundant manipulator. A control system is developed that considers redundancy in order to maximise the manipulation capabilities of the manipulator whilst avoiding reaching the joints limits. The control strategy is based on automatically estimating the kinematic parameters of the door. All conducted experiments were based on the assumption that the manipulator pulls a handle and opens a door using a single finger.

24. T. Kornuta and Ł. Żmuda
    Specification of the structure and behaviours of a robotic system able to determine object convexity
    in 18th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2013, 2013, pp. 350–355
    [ BIB | DOI | abstract | URL ]

    @inproceedings{kornuta2013specification,
      author = {Kornuta, Tomasz and Żmuda, Łukasz},
      booktitle = {18th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2013},
      title = {Specification of the structure and behaviours of a~robotic system able to determine object convexity},
      year = {2013},
      pages = {350-355},
      publisher = {IEEE},
      doi = {10.1109/MMAR.2013.6669932},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/2013_mmar_tkornuta_behaviour_selection.pdf},
      projects = {GrantMeDeRo},
      owner = {tkornuta},
      timestamp = {2013.10.03},
      twiki = {article}
    }
    

    The paper focuses on the problem of design of robotic controllers able to perform complex service tasks. The proposed approach, rooted in the embodied agent concept, enables the definition of both the structure and behaviour of the system. The supplementing each other mathematical and graphical notations along with the multi-level decomposition enable the specification of the system in details facilitating its implementation. The approach is validated on a non-trivial task of determination of object convexity. The presented results of experimental verification prove both the correctness of the designed system and the usefulness of the approach.

25. D. Seredyński and T. Winiarski
    Robot mobilny o zmiennym sposobie lokomocji –- wyniki badań
    Pomiary Automatyka Robotyka, vol. 17, no. 7–8, pp. 107–115, 2013
    [ BIB | abstract | URL ]

    @article{rys-badania-13-eng-twiki,
      author = {Seredyński, Dawid and Winiarski, Tomasz},
      journal = {Pomiary Automatyka Robotyka},
      title = {{Robot mobilny o~zmiennym sposobie lokomocji –- wyniki badań}},
      year = {2013},
      note = {Mobile robot with two modes of locomotion -- experimental results (in~Polish)},
      number = {7--8},
      pages = {107--115},
      volume = {17},
      projects = {GrantMeDeRo},
      twiki = {journal},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/rys_badania-13.pdf}
    }
    

    W artykule przedstawiono opis badań, jakie przeprowadzono na robocie mobilnym Ryś, który może poruszać się w dwóch trybach lokomocji: dynamicznie stabilnym oraz statycznie stabilnym. Robot może zmieniać tryb ruchu przez automatyczny manewr wstawania do pionu.

26. T. Winiarski and D. Seredyński
    Robot mobilny o zmiennym sposobie lokomocji – system sterowania
    Pomiary Automatyka Robotyka, vol. 17, no. 5, pp. 93–99, 2013
    [ BIB | abstract | URL ]

    @article{rys-sterowanie-13-eng-twiki,
      author = {Winiarski, Tomasz and Seredyński, Dawid},
      journal = {Pomiary Automatyka Robotyka},
      title = {{Robot mobilny o~zmiennym sposobie lokomocji – system sterowania}},
      year = {2013},
      note = {Mobile robot with two modes of locomotion -- control system (in~Polish)},
      number = {5},
      pages = {93--99},
      volume = {17},
      projects = {GrantMeDeRo},
      twiki = {journal},
      url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/rys_sterowanie-13.pdf}
    }
    

    W artykule przedstawiono opis systemu sterowania robota mobilnego o dwóch współosiowych kołach, mogącego poruszać się w dwóch trybach lokomocji: dynamicznie stabilnym oraz statycznie stabilnym. Robot może zmieniać tryb ruchu przez automatyczny manewr wstawania do pionu. System sterowania stanowią kaskady regulatorów PID.