Human identification and tracking using ultra-wideband-vision data fusion in unstructured environments

<p class="Abstract">Nowadays, the importance of working in changing and unstructured environments such as logistics warehouses through the cooperation between Automated Guided Vehicles (AGV) and the operator is increasingly demanded. The challenge addressed in this article aims to solve two crucial functions of autonomy: operator identification, and tracking. These tasks are necessary to enable an AGV to follow the selected operator along his path. This paper presents an innovative, accurate, robust, autonomous, and low-cost operator real-time tracking system, leveraging the inherent complementarity of the uncertainty regions (2D ellipses) between ultra-wideband (UWB) transceivers and cameras. The test campaign shows how the UWB system has higher uncertainty in the angular direction. In contrast, in the case of the vision system, the uncertainty is predominant along the radial coordinate. Due to the nature of the data, a sensor fusion demonstrates improvement in the accuracy and goodness of the final tracking.</p>

Cathlab department diagnostic reference levels and trigger values analysis

Background This study aims to assess the examination dose values in interventional cardiology procedures to establish diagnostic reference levels and analyse number of procedures that exceed trigger values. Methods Data about the procedure type, operator identification, procedure access, patient characteristics (gender, age and weight), fluoroscopy time (min), Kerma Area Product - PKA (Gy.cm2), was retrospectively collected, for a period of 12 months. Patients were categorised in three weight groups: low ( &lt; 65 kg), standard (65–75kg) and high ( &gt; 75 kg). Results he majority of the 2540 examinations were diagnostic procedures (65%) and the more common access was via the right radial artery (92%). Significant differences (P &lt; 0.05) in fluoroscopy time and PKA values, between procedure access, patient weight group and type of procedure were found. The trigger level of PKA ( &gt; 300Gy.cm2) value was exceeded in 0.5% of the procedures, lower than the incidence found in the literature. The local DRL values for diagnostic and therapeutical procedures were respectively 39 and 111 Gy.cm2, in line with values published in the literature. Conclusions The dose distribution is in line with the ones found in the literature. The percentage of patients that exceed one of trigger levels is lower when compared with the literature, however a patient follow-up plan should be established.

Intelligent Machine Operator Identification to Develop Damage-Reducing Operating Strategies for Mobile Machines

Mobile machines are exposed to a multitude of influencing factors, such as the working task, the operator and the environmental conditions. This leads to a broad spectrum of load collectives for the machine components. In many cases it is difficult to influence the working task and the environmental conditions under the objective function of achieving the required work goals optimally while at the same time minimizing the component load. The operation of the machine offers a more evident degree of freedom to minimize the component damage. With control systems adapted to the operator, the external environmental conditions and the working task, which instructs the operator to a less damaging operating behaviour or override the damage-initiating control signals, the loads and damage can be reduced. An explicit operator identification is the basis for such control approaches. This paper presents a method for machine operator identification (MOI) based on Hidden Markov Models (HMM). Through a parameter influence analysis and a combination with operation state recognition (OSR), a machine operator can be successfully identified among others. To create and validate the method, measurement data from 150 work cycles of seven different operators are analysed. Based on the MOI, a method for an operator-specific damage reduction using adaptive control strategies is developed. The results and limits of this strategy are presented and discussed by means of a complete machine simulation, considering the traction drive and function drives (working hydraulics), a multi-body simulation and the driving dynamics. The conclusion is made by considering predictive operating strategies to avoid damage-intensive operating points.