Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yevheniy Dmytriyev has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Brain–Computer Interface and Hand-Guiding Control in a Human–Robot Collaborative Assembly Task

    by Yevheniy Dmytriyev, Federico Insero, Marco Carnevale, Hermes Giberti

    Collaborative robots (Cobots) are compact machines programmable for a wide variety of tasks and able to ease operators’ working conditions. They can be therefore adopted in small and medium enterprises, characterized by small production batches and a multitude of different and complex tasks. To develop an actual collaborative application, a suitable task design and a suitable interaction strategy between human and cobot are required. The achievement of an effective and efficient communication strategy between human and cobot is one of the milestones of collaborative approaches, which can be based on several communication technologies, possibly in a multimodal way. In this work, we focus on a cooperative assembly task. A brain–computer interface (BCI) is exploited to supply commands to the cobot, to allow the operator the possibility to switch, with the desired timing, between independent and cooperative modality of assistance. The two kinds of control can be activated based on the brain commands gathered when the operator looks at two blinking screens corresponding to different commands, so that the operator does not need to have his hands free to give command messages to the cobot, and the assembly process can be sped up. The feasibility of the proposed approach is validated by developing and testing the interaction in an assembly application. Cycle times for the same assembling task, carried out with and without the cobot support, are compared in terms of average times, variability and learning trends. The usability and effectiveness of the proposed interaction strategy are therefore evaluated, to assess the advantages of the proposed solution in an actual industrial environment.


  • On cobot programming in industrial tasks: a test case

    by Yevheniy Dmytriyev, Marco Carnevale, Hermes Giberti, Giovanni Todeschini

    Collaborative robots open the way to new applications where industrial robots currently cannot be used. They are perfect for craft, non-industrial environments or schools, and to people who don't know how to program robots, like artists, designers, or students. A simplified end-user programming of the cobots allows a more flexible deployment of these machines. Originally, they were developed to contain the effort, the complexity and the cost of the robotic solutions, allowing the adoption of robots specially by small and medium-sized enterprises. However, when a cobot has to be used in an industrial environment some issues arise. This article presents an industrial application that uses a collaborative robot. The focus is on the use of the latest methods for cobot programming and on how to deal with their limitations and advantages when exploiting them in an industrial application.


  • Trajectory Planning for Contact-Based Robotic Applications by Use of a 3D Stereo Depth Camera

    by Ahmed Magdy Ahmed Zaki, Yevheniy Dmytriyev, Kevin Castelli, Marco Carnevale, Hermes Giberti

    In this paper a robotic solution is introduced to automate the generation of trajectories in contact-based industrial operations, through the use of a 3D stereo depth camera. The 3D camera is used to detect the workpiece features like color, depth, position and orientation, and the trajectory to be followed by the tool contact point is then generated only based on this information. A force sensor is then used to guarantee a constant contact force between the robot end-effector and the workpiece, and to adjust possible errors in the generated trajectory. The system performance, on curvilinear non-flat workpiece, is validated through glue deposition application in footwear manufacturing.


  • Mechanical Design and Development of a Continuous Rotational Variable Stiffness Actuator

    by Kevin Castelli, Marco Gavioli, Yevheniy Dmytriyev, Hermes Giberti

    One of the major issue concerning the coexistence of a human being and a robot is the interaction between a high stiffness object and a softer body part, especially if the impact is characterized by a high energy transmission. Expected or fortuitous collisions can be either managed using control strategies or mechanical elements such as SEA (Serial Elastic Actuators) or VSA (Variable Stiffness Actuators). This article deals with the design of an original prototype of a Continuous Rotation Variable Stiffness Actuator (CR-VSA). The solution proposed is made of two main functional subsystems: motor-reducer group and a variable stiffness equipment. The latter is formed by four steel foils whose length is defined by an actuated slider; the longer the beam, the lower the stiffness. The foils connect the rotation of the output to the one of the speed reducer, a cycloidal drive; encoders measure the angular coordinates to compute the position of the output shaft and the torque applied. A working prototype of this CR-VSA has been manufactured using rapid prototyping and low-cost solutions; ROS (Robot Operating System) has been used to implement the control strategy. This paper shows the design phase and the results achieved by the prototype built.


  • Brain computer interface for human-cobot interaction in industrial applications

    by Yevheniy Dmytriyev, Ahmed Magdy Ahmed Zaki, Marco Carnevale, Federico Insero, Hermes Giberti

    In the recent years, the industry has seen the introduction of the collaborative robots (or “cobots”), designed to interact with human workers in a shared environment. However, the involvement of the cobots in industrial applications is still strongly influenced by the strategies for non-collaborative robotic cells. The researchers are working frantically to find solutions to improve the interactions between the cobot and the operator, simplifying the communication and the programming work. This paper proposes a task-based algorithm which allows a fluid interaction, via biosignals of a Brain Compute Interface (BCI), as an enabling strategy of the collaborative workstations. The goal is to provide an implementation method of the BCI devices for industrial applications in order to make the cobots easy to use and interact with. The proposed solution is tested on an experimental setup which uses the Steady-State Visual Evoked Potential (SSVEP) response signal to drive machine commands to a collaborative robotic arm.


  • Open Access

    A Feasibility Study of a Robotic Approach for the Gluing Process in the Footwear Industry

    by Kevin Castelli, Ahmed Magdy Ahmed Zaki, Yevheniy Dmytriyev, Marco Carnevale, Hermes Giberti

    Manufacturing processes in the shoe industry are still characterized to a large extent by human labour, especially in small and medium craft enterprises. Even when machinery is adopted to support manufacturing operations, in most cases an operator has to supervise or carry out the task. On the other hand, craft footwear industries are called to respond to continuous challenges to face the globalization effects, so that a rapid adaptability to customer needs is required. The industry 4.0 paradigms, which are taking place in the industrial environments, represent an excellent opportunity to improve the efficiency and quality of production, and a way to face international competitors. This paper analyses and proposes a robotic cell to automatize the process of glue deposition on shoe upper, which exploits a new means of depositing the glue compared to State-of-Art applications. While the latter mainly adopt glue gun spraying systems or pneumatic syringes, the proposed robotic cell is based on an extrusion system for the deposition of molten material originally in the form of a filament, similar to all extent to those adopted for Fused Deposition Modeling (FDM). Two cell solutions are designed and tested. In the former the extruder is the robot end effector and the shoe upper is grounded to the cell frame. In the second, being the reciprocal, the shoe last is clamped to the robot wrist and the extruder is fixed to the cell frame. The peculiarities of the two solutions are pointed out and compared in terms of cell layout, hardware, programming software and possibility to develop collaborative applications. A self developed slicing software allows designing the trajectories for glue deposition based on the CAD model of the shoe upper, also allowing driving the inclination of the extruder nozzle with respect to the vectors normal to the upper surface. Both the proposed cell layouts permit to achieve good quality and production times. The solution with the mobile extruder is able to deposit glue at highest end-effector speed (up to 200 mm/s). On the other hand, the solution with the mobile shoe upper and fixed extruder seems to be more appropriate to enhance collaborative applications.