Mechanical systems (as belt conveyors) used in the mining industry, especially in deep underground mines, must be supervised on a regular basis. Unfortunately, they require high power and are spatially distributed over a large area. Till now, some elements of the conveyor (drive units) have been monitored 24 h/day using SCADA systems. The rest of the conveyor is inspected by maintenance staff. To minimize the presence of humans in harsh environments, we propose a mobile inspection platform based on autonomous UGV. It is equipped with various sensors, and in practice it is capable of collecting almost the same information as maintenance inspectors (RGB image, sound, gas sensor, etc.). Till now such experiments have been performed in the lab or in the mine, but the robot was controlled by the operator. In such a scenario the robot is able to record data, process them and detect, for example, an overheated idler. In this paper we will introduce the general concept of an automatic robot-based inspection for underground mining applications. A framework of how to deploy the inspection robot for automatic inspection (3D model of the tunnel, path planing, etc.) are defined and some first results from automatic inspection tested in lab conditions are presented. Differences between the planned and actual path are evaluated. We also point out some challenges for further research.

An orienting platform is a mechanism which allows rotation of a spatial object without translational motion of that object. In this work, we study a parallel platform with one passive nonholonomic spherical joint and two series of spherical, actuated prismatic and universal joints (the platform is also known in literature as an (nS)-2SPU wrist). To solve the control and motion planning problems, an analytic approach is used. The design of practical stabilization and tracking algorithm is based on transverse functions and a method for motion planning respecting mechanical singularities is derived from endogenous configuration space approach. It is shown that the system is controllable and locally equivalent to the chained form system. Then, the stabilization, tracking, and motion planning algorithms are proposed. Results are verified with computer simulations. A combination of the open-loop motion planning algorithm and the closed-loop tracking provide a tool for designing a motion planning algorithm respecting mechanical singularities and robust to input disturbances.

In the paper a problem of analyzing surgeon's right hand wrist trajectory during laparoscopic operation is considered. Based on the results of the analysis detection algorithms to recognize six motions are developed. The motions can be considered as primitives of a surgery from the human scrub nurse point of view. In the analysis, to represent motions the third order polynomials are used. The two proposed algorithms are based on Kohonen maps and boosted decision trees. The performance of the algorithms is tested on surgical operation data.

The continuous inverse kinematic problem amounts to computing a configuration of a mobile manipulator capable of producing a prescribed trajectory in the taskspace. By adopting a control system representation of kinematics of the mobile manipulator this problem is made equivalent to the problem of exact or asymptotic output tracking that may be solved by the dynamic extension algorithm. We study the continuous inverse kinematic problem for a mobile manipulator comprising a 3 DOF RTR manipulator mounted on a kinematic car type mobile platform. Our main result is a continuous asymptotic inverse kinematics algorithm employing dynamic state feedback. The performance of this inversion algorithm has been examined in computer simulations.

This work continues our study on the control synthesis for multiple mobile robot systems (MMRS). We assume a hybrid approach that comprises the supervisory control level, based on a discrete event model of MMRS, and the robot control level, based on a continuous time model of the robot motion. Our objective is to further develop the control concept towards its implementation in a real-world application – a testbed for a fleet of six laboratory robots. In the first part of the paper, we develop a methodology of the supervisory control synthesis, that employs the Petri net formalism and formally ensures the required logics of MMRS operation, as well as propose a relevant architecture of the supervisor. The second part is focused on the low-level robot control and control procedures enabling modification of the robot motion according to the supervisor’s decisions. A simulation case is presented that illustrates the operation of the system.

The automatic inspection of belt conveyors gathers increasing attention in the mining industry. The utilization of mobile robots to perform the inspection allows increasing the frequency and precision of inspection data collection. One of the issues that needs to be solved is the location of inspected objects, such as, for example, conveyor idlers in the vicinity of the robot. This paper presents a novel approach to analyze the 3D LIDAR data to detect idler frames in real time with high accuracy. Our method processes a point cloud image to determine positions of the frames relative to the robot. The detection algorithm utilizes density histograms, Euclidean clustering, and a dimension-based classifier. The proposed data flow focuses on separate processing of single scans independently, to minimize the computational load, necessary for real-time performance. The algorithm is verified with data recorded in a raw material processing plant by comparing the results with human-labeled objects. The proposed process is capable of detecting idler frames in a single 3D scan with accuracy above 83%. The average processing time of a single scan is under 22 ms, with a maximum of 75 ms, ensuring that idler frames are detected within the scan acquisition period, allowing continuous operation without delays. These results demonstrate that the algorithm enables the fast and accurate detection and localization of idler frames in real-world scenarios.