DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment

Recent advancements in deep learning techniques have accelerated the growth of robotic vision systems. One way this technology can be applied is to use a mobile robot to automatically generate a 3D map and identify objects within it. This paper addresses the important challenge of labeling objects and generating 3D maps in a dynamic environment. It explores a solution to this problem by combining Deep Object Pose Estimation (DOPE) with Real-Time Appearance-Based Mapping (RTAB-Map) through means of loose-coupled parallel fusion. DOPE's abilities are enhanced by leveraging its belief map system to filter uncertain key points, which increases precision to ensure that only the best object labels end up on the map. Additionally, DOPE's pipeline is modified to enable shape-based object recognition using depth maps, allowing it to identify objects in complete darkness. Three experiments are performed to find the ideal training dataset, quantify the increased precision, and evaluate the overall performance of the system. The results show that the proposed solution outperforms existing methods in most intended scenarios, such as in unilluminated scenes. The proposed key point filtering technique has demonstrated an improvement in the average inference speed, achieving a speedup of 2.6× and improving the average distance to the ground truth compared to the original DOPE algorithm.

Synthesizing Rolling Bearing Fault Samples in New Conditions: A Framework Based on a Modified CGAN

Bearings are vital components of rotating machines that are prone to unexpected faults. Therefore, bearing fault diagnosis and condition monitoring are essential for reducing operational costs and downtime in numerous industries. In various production conditions, bearings can be operated under a range of loads and speeds, which causes different vibration patterns associated with each fault type. Normal data are ample as systems usually work in desired conditions. On the other hand, fault data are rare, and in many conditions, there are no data recorded for the fault classes. Accessing fault data is crucial for developing data-driven fault diagnosis tools that can improve both the performance and safety of operations. To this end, a novel algorithm based on conditional generative adversarial networks (CGANs) was introduced. Trained on the normal and fault data on actual fault conditions, this algorithm generates fault data from normal data of target conditions. The proposed method was validated on a real-world bearing dataset, and fault data were generated for different conditions. Several state-of-the-art classifiers and visualization models were implemented to evaluate the quality of the synthesized data. The results demonstrate the efficacy of the proposed algorithm.

A Critical Analysis of Industrial Human-Robot Communication and Its Quest for Naturalness Through the Lens of Complexity Theory

Human-robot communication is one of the actively researched fields to enable efficient and seamless collaboration between a human and an intelligent industrial robotic system. The field finds its roots in human communication with the aim to achieve the “naturalness” inherent in the latter. Industrial human-robot communication pursues communication with simplistic commands and gestures, which is not representative of an uncontrolled real-world industrial environment. In addition, naturalness in communication is a consequence of its dynamism, typically ignored as a design criterion in industrial human-robot communication. Complexity Theory-based natural communication models allow for a more accurate representation of human communication which, when adapted, could also benefit the field of human-robot communication. This paper presents a perspective by reviewing the state of human-robot communication in industrial settings and then presents a critical analysis of the same through the lens of Complexity Theory. Furthermore, the work identifies research gaps in the aforementioned field, fulfilling which, would propel the field towards a truly natural form of communication. Finally, the work briefly discusses a general framework that leverages the experiential learning of data-based techniques and naturalness of human knowledge.

Comprehensive review of conventional and state-of-the-art detection methods of Cryptosporidium

Cryptosporidium is a critical waterborne protozoan pathogen found in water resources that have been a major cause of death and serious illnesses worldwide, costing millions of dollars annually for its detection and treatment. Over the past several decades, substantial efforts have been made towards developing techniques for the detection of Cryptosporidium. Early diagnostic techniques were established based on the existing tools in laboratories, such as microscopes. Advancements in fluorescence microscopy, immunological, and molecular techniques have led to the development of several kits for the detection of Cryptosporidium spp. However, these methods have several limitations, such as long processing times, large sample volumes, the requirement for bulky and expensive laboratory tools, and the high cost of reagents. There is an urgent need to improve these existing techniques and develop low-cost, portable and rapid detection tools for applications in the water quality industry. In this review, we compare recent advances in nanotechnology, biosensing and microfluidics that have facilitated the development of sophisticated tools for the detection of Cryptosporidium spp.Finally, we highlight the advantages and disadvantages, of these state-of-the-art detection methods compared to current analytical methodologies and discuss the need for future developments to improve such methods for detecting Cryptosporidium in the water supply chain to enable real-time and on-site monitoring in water resources and remote areas.

Portable on-chip colorimetric biosensing platform integrated with a smartphone for label/PCR-free detection of Cryptosporidium RNA

Cryptosporidium, a protozoan pathogen, is a leading threat to public health and the economy. Herein, we report the development of a portable, colorimetric biosensing platform for the sensitive, selective and label/PCR-free detection of Cryptosporidium RNA using oligonucleotides modified gold nanoparticles (AuNPs). A pair of specific thiolated oligonucleotides, complementary to adjacent sequences on Cryptosporidium RNA, were attached to AuNPs. The need for expensive laboratory-based equipment was eliminated by performing the colorimetric assay on a micro-fabricated chip in a 3D-printed holder assembly. A smartphone camera was used to capture an image of the color change for quantitative analysis. The detection was based on the aggregation of the gold nanoparticles due to the hybridization between the complementary Cryptosporidium RNA and the oligonucleotides immobilized on the AuNPs surface. In the complementary RNA's presence, a distinctive color change of the AuNPs (from red to blue) was observed by the naked eye. However, in the presence of non-complementary RNA, no color change was observed. The sensing platform showed wide linear responses between 5 and 100 µM with a low detection limit of 5 µM of Cryptosporidium RNA. Additionally, the sensor developed here can provide information about different Cryptosporidium species present in water resources. This cost-effective, easy-to-use, portable and smartphone integrated on-chip colorimetric biosensor has great potential to be used for real-time and portable POC pathogen monitoring and molecular diagnostics.

Micron-sized particle separation with standing surface acoustic wave-Experimental and numerical approaches

Traditional cell/particle isolation methods are time-consuming and expensive and can lead to morphology disruptions due to high induced shear stress. To address these problems, novel lab-on-a-chip-based purification methods have been employed. Among various methods introduced for the separation and purification of cells and synthetics particles, acoustofluidics has been one of the most effective methods. Unlike traditional separation techniques carried out in clinical laboratories based on chemical properties, the acoustofluidic process relies on the physical properties of the sample. Using acoustofluidics, manipulating cells and particles can be achieved in a label-free, contact-free, and highly biocompatible manner. To optimize the functionality of the platform, the numerical study should be taken into account before conducting experimental tests to save time and reduce fabrication expenses. Most current numerical studies have only considered one-dimensional harmonic standing waves to simulate the acoustic pressure distribution. However, one-dimensional simulations cannot calculate the actual acoustic pressure distribution inside the microchannel due to its limitation in considering longitudinal waves. To address this limitation, a two-dimensional numerical simulation was conducted in this study. Our numerical simulation investigates the effects of the platform geometrical and operational conditions on the separation efficiency. Next, the optimal values are tested in an experimental setting to validate these optimal parameters and conditions. This work provides a guideline for future acoustofluidic chip designs with a high degree of reproducibility and efficiency.

Low-Cost Graphene-Based Digital Microfluidic System

In this work, the laser-scribing technique was used as a low-cost, rapid and facile method for fabricating digital microfluidic (DMF) systems. Laser-scribed graphene (LSG) electrodes are directly synthesized on flexible substrates to pattern the DMF electrode arrays. This facilitates the DMF electrodes’ fabrication process by eliminating many microfabrication steps. An electrowetting test was performed to investigate the effectiveness of the LSG DMF electrodes in changing the contact angles of droplets. Different DMF operations were successfully performed using the proposed LSG DMF chips in both open and closed DMF systems. The quality and output resolution were examined to assess the performance of such patterned electrodes in the DMF systems. To verify the efficacy of the LSG DMF chips, a one-step direct assay for the detection of Legionellapneumophila deoxyribonucleic acid (DNA) was performed on the chip without the need for any washing step. The high specificity in distinguishing a single-nucleotide mismatch was achieved by detecting target DNA concentrations as low as 1 nM. Our findings suggest that the proposed rapid and easy fabrication method for LSG DMF electrodes offers a great platform for low-cost and easily accessible point-of-care diagnostic devices.

Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review

Autonomous vehicles (AV) are expected to improve, reshape, and revolutionize the future of ground transportation. It is anticipated that ordinary vehicles will one day be replaced with smart vehicles that are able to make decisions and perform driving tasks on their own. In order to achieve this objective, self-driving vehicles are equipped with sensors that are used to sense and perceive both their surroundings and the faraway environment, using further advances in communication technologies, such as 5G. In the meantime, local perception, as with human beings, will continue to be an effective means for controlling the vehicle at short range. In the other hand, extended perception allows for anticipation of distant events and produces smarter behavior to guide the vehicle to its destination while respecting a set of criteria (safety, energy management, traffic optimization, comfort). In spite of the remarkable advancements of sensor technologies in terms of their effectiveness and applicability for AV systems in recent years, sensors can still fail because of noise, ambient conditions, or manufacturing defects, among other factors; hence, it is not advisable to rely on a single sensor for any of the autonomous driving tasks. The practical solution is to incorporate multiple competitive and complementary sensors that work synergistically to overcome their individual shortcomings. This article provides a comprehensive review of the state-of-the-art methods utilized to improve the performance of AV systems in short-range or local vehicle environments. Specifically, it focuses on recent studies that use deep learning sensor fusion algorithms for perception, localization, and mapping. The article concludes by highlighting some of the current trends and possible future research directions.

Parametric study on the geometrical parameters of a lab-on-a-chip platform with tilted planar electrodes for continuous dielectrophoretic manipulation of microparticles

Advances in lab-on-a-chip (LOC) devices have led to significant improvements in the on-chip manipulation, separation, sorting, and isolation of particles and cells. Among various LOC-based approaches such as inertia-based methods, acoustophoresis, and magnetophoresis, the planar-slanted-electrode dielectrophoresis (DEP) method has demonstrated great potential as a label-free, cost-effective, and user-friendly approach. However, the devices built based on this method suffer from low flow throughput compared to devices functioning based on other LOC-based manipulation approaches. In order to overcome this obstacle, the geometrical parameters of these types of DEP-based devices must be studied to increase the effectiveness of DEP manipulation. With the consideration of both numerical and experimental studies, this paper studies the geometrical factors of a LOC platform consisting of tilted planar electrodes with the goal of achieving higher throughput in continuous manipulation of polystyrene particles. COMSOL Multiphysics software was used to study the effect of the electrodes geometry on the induced electric field. The simulation results show that by increasing the electrode's width and decreasing the electrode's spacing, higher DEP force is generated. Furthermore, the experimental outcomes indicated that lower channel height, higher voltage, and larger particle size resulted in the most improvement to DEP manipulation. Additionally, the experimental results demonstrated that slanted electrodes with an angle of 8° with respect to the direction of flow provide a more effective configuration.

High Throughput Screening of Cell Mechanical Response Using a Stretchable 3D Cellular Microarray Platform

Cells in vivo are constantly subjected to multiple microenvironmental mechanical stimuli that regulate cell function. Although 2D cell responses to the mechanical stimulation have been established, these methods lack relevance as physiological cell microenvironments are in 3D. Moreover, the existing platforms developed for studying the cell responses to mechanical cues in 3D either offer low-throughput, involve complex fabrication, or do not allow combinatorial analysis of multiple cues. Considering this, a stretchable high-throughput (HT) 3D cell microarray platform is presented that can apply dynamic mechanical strain to cells encapsulated in arrayed 3D microgels. The platform uses inkjet-bioprinting technique for printing cell-laden gelatin methacrylate (GelMA) microgel array on an elastic composite substrate that is periodically stretched. The developed platform is highly biocompatible and transfers the applied strain from the stretched substrate to the cells. The HT analysis is conducted to analyze cell mechano-responses throughout the printed microgel array. Also, the combinatorial analysis of distinct cell behaviors is conducted for different GelMA microenvironmental stiffnesses in addition to the dynamic stretch. Considering its throughput and flexibility, the developed platform can readily be scaled up to introduce a wide range of microenvironmental cues and to screen the cell responses in a HT way.

Graphene-Coated Spandex Sensors Embedded into Silicone Sheath for Composites Health Monitoring and Wearable Applications

This study presents a low-cost, tunable, and stretchable sensor fabricated based on spandex (SpX) yarns coated with graphene nanoplatelets (GnP) through a dip-coating process. The SpX/GnP is wrapped into a stretchable silicone rubber (SR) sheath to protect the conductive layer against harsh conditions, which allows for fabricating washable wearable sensors. Dip-coating parameters are optimized to obtain the maximum GnP coating rate. The covering sheath is tailored to achieve high stretchability beyond the sensing limit of 104% for SpX/GnP/SR sensors. Adjustable sensitivity is attained by manipulating SpX immersion times broadening its application for a wide range of strains: Gauge factors as high as two orders of magnitude are achieved at tensile strains greater than ≈40%. The fabricated sensors are tested for two applications: First, the SpX/GnP sensors are integrated into composite fabrics (with no negative impact on the structural integrity of the part) for screening the yarn displacements, resin flow, solidification during the hot press forming process, and structural health monitoring under mechanical loads with minimal cross-sensitivity to temperature/humidity. Second, the capability of SpX/GnP/SP sensors in detection of a wide range of bodily motions (from the joint motion to arterial blood pressure) is demonstrated.

Portable device for the detection of colorimetric assays

In this work, a low-cost, portable device is developed to detect colorimetric assays for in-field and point-of-care (POC) analysis. The device can rapidly detect both pH values and nitrite concentrations of five different samples, simultaneously. After mixing samples with specific reagents, a high-resolution digital camera collects a picture of the sample, and a single-board computer processes the image in real time to identify the hue-saturation-value coordinates of the image. An internal light source reduces the effect of any ambient light so the device can accurately determine the corresponding pH values or nitrite concentrations. The device was purposefully designed to be low-cost, yet versatile, and the accuracy of the results have been compared to those from a conventional method. The results obtained for pH values have a mean standard deviation of 0.03 and a correlation coefficient R2 of 0.998. The detection of nitrites is between concentrations of 0.4-1.6 mg l-1, with a low detection limit of 0.2 mg l-1, and has a mean standard deviation of 0.073 and an R2 value of 0.999. The results represent great potential of the proposed portable device as an excellent analytical tool for POC colorimetric analysis and offer broad accessibility in resource-limited settings.

Portable device for the detection of colorimetric assays

In this work, a low-cost, portable device is developed to detect colorimetric assays for in-field and point-of-care (POC) analysis. The device can rapidly detect both pH values and nitrite concentrations of five different samples, simultaneously. After mixing samples with specific reagents, a high-resolution digital camera collects a picture of the sample, and a single-board computer processes the image in real time to identify the hue-saturation-value coordinates of the image. An internal light source reduces the effect of any ambient light so the device can accurately determine the corresponding pH values or nitrite concentrations. The device was purposefully designed to be low-cost, yet versatile, and the accuracy of the results have been compared to those from a conventional method. The results obtained for pH values have a mean standard deviation of 0.03 and a correlation coefficient R² of 0.998. The detection of nitrites is between concentrations of 0.4-1.6 mg l^-1, with a low detection limit of 0.2 mg l^-1, and has a mean standard deviation of 0.073 and an R² value of 0.999. The results represent great potential of the proposed portable device as an excellent analytical tool for POC colorimetric analysis and offer broad accessibility in resource-limited settings.

3D Printing-Based Integrated Water Quality Sensing System

The online and accurate monitoring of drinking water supply networks is critically in demand to rapidly detect the accidental or deliberate contamination of drinking water. At present, miniaturized water quality monitoring sensors developed in the laboratories are usually tested under ambient pressure and steady-state flow conditions; however, in Water Distribution Systems (WDS), both the pressure and the flowrate fluctuate. In this paper, an interface is designed and fabricated using additive manufacturing or 3D printing technology-material extrusion (Trade Name: fused deposition modeling, FDM) and material jetting-to provide a conduit for miniaturized sensors for continuous online water quality monitoring. The interface is designed to meet two main criteria: low pressure at the inlet of the sensors and a low flowrate to minimize the water bled (i.e., leakage), despite varying pressure from WDS. To meet the above criteria, a two-dimensional computational fluid dynamics model was used to optimize the geometry of the channel. The 3D printed interface, with the embedded miniaturized pH and conductivity sensors, was then tested at different temperatures and flowrates. The results show that the response of the pH sensor is independent of the flowrate and temperature. As for the conductivity sensor, the flowrate and temperature affect only the readings at a very low conductivity (4 µS/cm) and high flowrates (30 mL/min), and a very high conductivity (460 µS/cm), respectively.

Droplet sensing by measuring the capacitance between coplanar electrodes in a digital microfluidic system

In this paper, we report a novel method of droplet sensing in a two-plate digital microfluidic system (DMS) based on coplanar capacitance measurement. The total capacitance between the two adjacent electrodes on the lower plate depends on the position of the droplet. Both numerical and experimental results show that the capacitance is maximal at the midpoint between two electrodes. The value of maximum capacitance increases with the volume of the droplet. Further, the measured capacitance is a function of the gaps between the electrodes as well as the plates. This new method of droplet sensing adds to the functionality of DMSs by allowing single plate measurement.

Capacitance-based droplet position estimator for digital microfluidic devices

Digital microfluidic (DMF) devices manipulate minuscule droplets through basic fluidic operations including droplet transport, mixing and splitting commonly known as the building blocks for complete laboratory analyses on a single device. A DMF device can house various chemical species and confine chemical reactions within the volume of a droplet much like a micro-reactor. The automation of fluidic protocols requires a feedback controller whose sensor is capable of locating droplets independent of liquid composition (or previous knowledge of liquid composition). In this research, we present an estimator that tracks the continuous displacement of a droplet between electrodes of a DMF device. The estimator uses a dimensionless ratio of two electrode capacitances to approximate the position of a droplet, even, in the domain between two adjacent electrodes. This droplet position estimator significantly enhances the control precision of liquid handling in DMF devices compared to that of the techniques reported in the literature. It captures the continuous displacement of a droplet; valuable information for a feedback controller to execute intricate fluidic protocols including droplet positioning between electrodes, droplet velocity and acceleration control. We propose a state estimator for tracking the continuous droplet displacement between two adjacent electrodes. The dimensionless nature of this estimator means that any droplet composition can be sensed. Thus, no calibration for each chemical species within a single DMF device is required. We present theoretical and experimental results that demonstrate the efficacy of the position estimator in approximating the position of the droplet in the interval between two electrodes.

In situ characterization of microdroplet interfacial properties in digital microfluidic systems

Real-time characterization of digital microfluidic lab-on-a-chip devices is important for biological and chemical applications in which the properties of the microdroplet are time variant. In this paper, a method for in situ characterization of microdroplet interfacial properties is introduced. The proposed characterization method relies on two submodules, namely the contact angle and capacitance sampling submodules, in a digital microfluidic system. In the contact angle measurement submodule, the microdroplet profile is acquired and an accurate contact angle is determined. In the capacitance sampling submodule, the capacitance of the system is measured by means of an activation voltage signal. For verification purposes, the results obtained from the proposed method are compared to the Lippmann-Young equation. The results are in excellent agreement with previously reported values. Finally, the proposed submodules are used to characterize the interfacial properties of a microdroplet containing an aqueous solution of bovine serum albumin (BSA) in which adsorption is a predominant effect. The results show the temporal behaviour of both microdroplet interfacial properties and dielectric characteristics.

Decision making under uncertainty--an example for seismic risk management

Decision-making techniques are used to select the "best" alternatives under multiple and often conflicting criteria. Multicriteria decision making (MCDM) necessitates to incorporate uncertainties in the decision-making process. The major thrust of this article is to extend the framework proposed by Yager for multiple decisionmakers and fuzzy utilities (payoffs). In addition, the concept of expert credibility factor is introduced. The proposed approach is demonstrated for an example of seismic risk management using a heuristic hierarchical structure. A step-by-step formulation of the proposed approach is illustrated using a hypothetical example and a three-story reinforced concrete building.