Effective Functioning of a Mixed Heterogeneous Team in a Collaborative Robotic System

The study describes a collaborative robot (cobot) as one of the types of intelligent robotics and its distinctive features compared to other types of robots. The paper presents a collaborative robotic system as a single complex system in which actors of different types – cobots and human workers – perform collaborative actions to achieve a common goal. Elements of a collaborative robotic system, as well as processes and entities that directly influence it are represented. The key principles of Human-Robot Collaboration are described. A collaborative robotic system is analyzed both as a multi-agent system and as a mixed team, whose members are heterogeneous actors. The relevance of the work lies in a weak level of research on issues of formation of mixed teams of people and cobots and distribution of tasks in such teams, taking into account features of these two types of participants and requirements of their safe collaboration. This work focused on a formation of mixed teams of elements of a single complex human-cobot system, the distribution of tasks among the members of such teams, taking into account the need to minimize costs for its participants and the heterogeneity of the team. As part of the study, the problem of forming a mixed heterogeneous team of people and cobots, and distribution of work among its members, as well as the corresponding mathematical description are presented. Specific cases of the problem, including different cost functions of different types of participants, a limited activity of the team’s members, the dependence of the cost function of the participants of one type on the number of participants of another type, as well as an arbitrary number of works assigned to the team’s members are considered.

Robust scalable reversible strong adhesion by gecko-inspired composite design

Bio-inspired reversible adhesion has significant potential in many fields requiring flexible grasping and manipulation, such as precision manufacturing, flexible electronics, and intelligent robotics. Despite extensive efforts for adhesive synthesis with a high adhesion strength at the interface, an effective strategy to actively tune the adhesion capacity between a strong attachment and an easy detachment spanning a wide range of scales has been lagged. Herein, we report a novel soft-hard-soft sandwiched composite design to achieve a stable, repeatable, and reversible strong adhesion with an easily scalable performance for a large area ranging from ∼1.5 to 150 cm2 and a high load ranging from ∼20 to 700 N. Theoretical studies indicate that this design can enhance the uniform loading for attachment by restraining the lateral shrinkage in the natural state, while facilitate a flexible peeling for detachment by causing stress concentration in the bending state, yielding an adhesion switching ratio of ∼54 and a switching time of less than ∼0.2 s. This design is further integrated into versatile grippers, climbing robots, and human climbing grippers, demonstrating its robust scalability for a reversible strong adhesion. This biomimetic design bridges microscopic interfacial interactions with macroscopic controllable applications, providing a universal and feasible paradigm for adhesion design and control.

Programmable self-propelling actuators enabled by a dynamic helical medium

Rotation-translation conversion is a popular way to achieve power transmission in machinery, but it is rarely selected by nature. One unique case is that of bacteria swimming, which is based on the collective reorganization and rotation of flagella. Here, we mimic such motion using the light-driven evolution of a self-organized periodic arch pattern. The range and direction of translation are altered by separately varying the alignment period and the stimulating photon energy. Programmable self-propelling actuators are realized via a specific molecular assembly within a photoresponsive cholesteric medium. Through rationally presetting alignments, parallel transports of microspheres in customized trajectories are demonstrated, including convergence, divergence, gathering, and orbital revolution. This work extends the understanding of the rotation-translation conversion performed in an exquisitely self-organized system and may inspire future designs for functional materials and intelligent robotics.

Accelerated HOG+SVM for object recognition

Fast track article for IS&T International Symposium on Electronic Imaging 2021: Intelligent Robotics and Industrial Applications using Computer Vision 2021 proceedings.

Towards large-scale evaluation of mental stress and biomechanical strain in manufacturing environments using 3D-referenced gaze and wearable-based analytics

Fast track article for IS&T International Symposium on Electronic Imaging 2021: Intelligent Robotics and Industrial Applications using Computer Vision 2021 proceedings.