The aim of this study was to develop a physical activity advisory system supporting the correct implementation of sport exercises using inertial sensors and machine learning algorithms. Specifically, three mobile sensors (tags), six stationary anchors and a system-controlling server (gateway) were employed for 15 scenarios of the series of subsequent activities, namely squats, pull-ups and dips. The proposed solution consists of two modules: an activity recognition module (ARM) and a repetition-counting module (RCM). The former is responsible for extracting the series of subsequent activities (so-called scenario), and the latter determines the number of repetitions of a given activity in a single series. Data used in this study contained 488 three defined sport activity occurrences. Data processing was conducted to enhance performance, including an overlapping and non-overlapping window, raw and normalized data, a convolutional neural network (CNN) with an additional post-processing block (PPB) and repetition counting. The developed system achieved satisfactory accuracy: CNN + PPB: non-overlapping window and raw data, 0.88; non-overlapping window and normalized data, 0.78; overlapping window and raw data, 0.92; overlapping window and normalized data, 0.87. For repetition counting, the achieved accuracies were 0.93 and 0.97 within an error of ±1 and ±2 repetitions, respectively. The archived results indicate that the proposed system could be a helpful tool to support the correct implementation of sport exercises and could be successfully implemented in further work in the form of web application detecting the user’s sport activity.

The monitoring and early avoidance of collisions in a workspace shared by collaborative robots (cobots) and human operators is crucial for assessing the quality of operations and tasks completed within manufacturing. A gap in the research has been observed regarding effective methods to automatically assess the safety of such collaboration, so that employees can work alongside robots, with trust. The main goal of the study is to build a new method for recognising collisions in workspaces shared by the cobot and human operator. For the purposes of the research, a research unit was built with two UR10e cobots and seven series of subsequent of the operator activities, specifically: (1) entering the cobot’s workspace facing forward, (2) turning around in the cobot’s workspace and (3) crouching in the cobot’s workspace, taken as video recordings from three cameras, totalling 484 images, were analysed. This innovative method involves, firstly, isolating the objects using a Convolutional Neutral Network (CNN), namely the Region-Based CNN (YOLOv8 Tiny) for recognising the objects (stage 1). Next, the Non-Maximum Suppression (NMS) algorithm was used for filtering the objects isolated in previous stage, the k-means clustering method and Simple Online Real-Time Tracking (SORT) approach were used for separating and tracking cobots and human operators (stage 2) and the Convolutional Neutral Network (CNN) was used to predict possible collisions (stage 3). The method developed yields 90% accuracy in recognising the object and 96.4% accuracy in predicting collisions accuracy, respectively. The results achieved indicate that understanding human behaviour working with cobots is the new challenge for modern production in the Industry 4.0 and 5.0 concept.

This paper deals with the real-time trajectory generation problem for two cooperating mobile robots moving the common rigid object. The holonomic constraints resulting from a closed kinematic chain and the dynamics of such a system are considered. Two methods of generation sub-optimal trajectories allowing for mechanical and control limitations and collision avoidance conditions are proposed. The first solution is based on a leader-follower approach, in the second one the robotic system is treated as a whole mechanism. In both cases, the trajectories are generated in order to avoid singularities and they are scaled to satisfy control constraints. Advantages and disadvantages of both presented approaches are discussed. A computer example involving two mobile manipulators consisting of nonholonomic platform (2,0) class and planar 3-DOF holonomic manipulator is presented.

SUMMARY: This paper presents a method of planning a sub-optimal trajectory for a mobile manipulator subject to mechanical and control constraints. The path of the end-effector is defined as a curve that can be parameterised by any scaling parameter—the reference trajectory of a mobile platform is not needed. Constraints connected with the existence of mechanical limits for a given manipulator configuration, collision avoidance conditions and control constraints are considered. Nonholonomic constraints in a Pfaffian form are explicitly incorporated to the control algorithm. To avoid manipulator singularities, the motion of the robot is planned in order to maximise the manipulability measure.

This paper presents the usage of holonomic mobile humanoid manipulators to carry out autonomous tasks in industrial environments, according to the smart factory concept and the Industry 4.0 philosophy. The problem of transporting lengthy objects, taking into account mechanical limitations, the conditions for avoiding collisions, as well as the dexterity of the manipulator arms was considered. The primary problem was divided into three phases, leading to three different types of robotic tasks. In the proposed approach, the pseudoinverse Jacobian method at the acceleration level to solve each of the tasks was used. The redundant degrees of freedom were used to satisfy secondary objectives such as robot kinetic energy, the maximization of the manipulability measure, and the fulfillment mechanical and collision-avoidance limitations. A computer example involving a mobile humanoid manipulator, operating in an industrial environment, illustrated the effectiveness of the proposed method.

A method of planning collision-free trajectory for a mobile manipulator tracking a line section path is presented. The reference trajectory of a mobile platform is not needed, mechanical and control constraints are taken into account. The method is based on a penalty function approach and a redundancy resolution at the acceleration level. Nonholonomic constraints in a Pfaffian form are explicitly incorporated to the control algorithm. The problem is shown to be equivalent to some point-to-point control problem whose solution may be easier determined. The motion of the mobile manipulator is planned in order to maximise the manipulability measure, thus to avoid manipulator singularities. A computer example involving a mobile manipulator consisting of a nonholonomic platform (2,0) class and a 3 DOF RPR type holonomic manipulator operating in a three-dimensional task space is also presented.