High-level Processing Research Articles

Reaching the top of Bloom’s Taxonomy: an innovative pilot program for preclinical undergraduate and medical school students to create curricula for STEMM outreach/service-learning programs

Bloom’s Taxonomy is an andragogical tool that classifies educational objectives, learning activities, and assessments into distinct levels of cognitive thinking. Preclinical medical sciences educators aim to promote higher-order thinking in their curricula to help students develop clinical decision-making skills and foster deep learning. However, many courses and curricula remain focused on lower levels of Bloom’s Taxonomy because they are easier to implement and assess. Meanwhile, many service-learning opportunities for medical students focus on developing affective faculties over higher-level cognitive processing of curricular material. We describe a model program in which undergraduate pre-medical education (UPE) and undergraduate medical education (UPE/UME) students at Boston University Charles River Campus (BU CRC) and Boston University Aram V. Chobanian & Edward Avedisian School of Medicine (BU Chobanian & Avedisian SOM) simultaneously engaged in service-learning and the Create level of Bloom’s Taxonomy by developing a supplementary high school (HS) medical science curriculum based on content and instructional models from their preclinical courses. Activities such as mock patient cases, simulated patient interviews, and physical examination training contributed toward a HS curriculum that promotes healthy habits; increases community public health self-efficacy; sparks interest in Science, Technology, Engineering, Math and Medicine (STEMM) concepts; and educates about medical careers through engaging lessons and activities focused on human anatomy and physiology.

Dynamic 3D Point Cloud Sequences as 2D Videos.

Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant challenges to effective and efficient processing. Existing deep point cloud sequence modeling approaches imitate the mature 2D video learning mechanisms by developing complex spatio-temporal point neighbor grouping and feature aggregation schemes, often resulting in methods lacking effectiveness, efficiency, and expressive power. In this paper, we propose a novel generic representation called Structured Point Cloud Videos (SPCVs). Intuitively, by leveraging the fact that 3D geometric shapes are essentially 2D manifolds, SPCV re-organizes a point cloud sequence as a 2D video with spatial smoothness and temporal consistency, where the pixel values correspond to the 3D coordinates of points. The structured nature of our SPCV representation allows for the seamless adaptation of well-established 2D image/video techniques, enabling efficient and effective processing and analysis of 3D point cloud sequences. To achieve such re-organization, we design a self-supervised learning pipeline that is geometrically regularized and driven by self-reconstructive and deformation field learning objectives. Additionally, we construct SPCV-based frameworks for both low-level and high-level 3D point cloud sequence processing and analysis tasks, including action recognition, temporal interpolation, and compression. Extensive experiments demonstrate the versatility and superiority of the proposed SPCV, which has the potential to offer new possibilities for deep learning on unstructured 3D point cloud sequences.

Navigating Uncertainty: The Role of Mood and Confidence in Decision-Making Flexibility and Performance

Dealing with uncertainty is a pivotal skill for adaptive decision-making across various real-life contexts. Cognitive models suggest that individuals continuously update their knowledge based on past choices and outcomes. Traditionally, uncertainty has been linked to negative states such as fear and anxiety. Recent evidence, however, highlights that uncertainty can also evoke positive emotions, such as surprise, interest, excitement, and enthusiasm, depending on one’s task expectations. Despite this, the interplay between mood, confidence, and learning remains underexplored. Some studies indicate that self-reported mood does not always align with confidence, as these constructs evolve on different timescales. We propose that mood influences confidence, thereby enhancing decision flexibility—defined as the ability to switch effectively between exploration and exploitation. This increased flexibility is expected to improve task performance by increasing accuracy. Our findings support this hypothesis, revealing that confidence modulates exploration/exploitation strategies and learning rates, while mood affects reward perception and confidence levels. These findings indicate that metacognition entails a dynamic balance between exploration and exploitation, integrating mood states with high-level cognitive processes.

Evaluation of impact of lean management practices on dairy business performance

Purpose This research was initiated by motivation from a real business problem that delves into lean management practices in dairy farm operations. It investigates how lean management practices can be applied as an improvement strategy in the dairy business to evaluate its impact on performance, where profitability is a decisive factor. Design/methodology/approach Based on the qualitative design, a 5-phase action research methodology was used in this study, where multiple data collection sources were used, including focus group discussions, on-site observation or Gemba walks and process mapping. The impact is evaluated by comparing the key performance measures with the same period before and after research. Findings The research revealed that lean management practices can significantly improve dairy business performance. It explained vital aspects of lean management practices and their sequence with examples of first-hand applications. It explained, how lean management practices were applied in dairy farm operations. Furthermore, the research resulted in significant benefits, in terms of quality, cost and profitability. Practical implications This research was conducted in a real business setting in the field environment, to improve dairy business performance. It was a distinctive application of lean management practices to solve a national problem. This could be used as a road map to bring continuous improvement at the national level to improve the performance of food value chains. Originality/value This research is unique because it addresses the methodological, population and empirical gaps in dairy farm operations. It adds value to the existing knowledge base by sharing best practices, developed and implemented for the first time to the best of our knowledge, like high-level process mapping and performance measures at different levels. Furthermore, the solutions can be simulated in related farm operations to bring breakthrough improvements in dairy business performance.

Alterations in center-surround contrast suppression in patients with major depressive disorder

Previous pattern electroretinogram studies indicate reduced retinal contrast gain in patients with a major depressive disorder (MDD) which may contribute to alterations in visual perception. In line, psychophysical investigations reported elevated contrast thresholds in MDD. This study aims to gain insights into higher-level processing of visual information in MDD by evaluating contrast suppression. We examined contrast suppression of 21 MDD patients and 23 healthy controls (HC) using four different stimulus conditions (spatial frequencies 6.3 and 12.6 cpd at 30% and 60% background contrast) in a psychophysical test. Participants were instructed to adjust perceived contrasts between two vertical target patches, embedded in a horizontally or vertically oriented grid background. With finer stimulus gratings, MDD patients exhibited less contrast suppression compared to HC, particularly when the stimulus contrast was high (p = 0.006; MDD vs. HC = − 45%). Contrast suppression in the HC group was significantly reduced for the coarse compared to the fine grating, while contrast suppression scores in MDD did not change with the spatial properties of the stimulus. The reduced contrast suppression in patients with MDD supports the hypothesis of altered dopaminergic neurotransmission and could be attributed to alterations in the retinal receptive fields or in dysfunctional adaptation mechanisms in depression.

High-level visual prediction errors in early visual cortex.

Perception is shaped by both incoming sensory input and expectations derived from our prior knowledge. Numerous studies have shown stronger neural activity for surprising inputs, suggestive of predictive processing. However, it is largely unclear what predictions are made across the cortical hierarchy, and therefore what kind of surprise drives this up-regulation of activity. Here, we leveraged fMRI in human volunteers and deep neural network (DNN) models to arbitrate between 2 hypotheses: prediction errors may signal a local mismatch between input and expectation at each level of the cortical hierarchy, or prediction errors may be computed at higher levels and the resulting surprise signal is broadcast to earlier areas in the cortical hierarchy. Our results align with the latter hypothesis. Prediction errors in both low- and high-level visual cortex responded to high-level, but not low-level, visual surprise. This scaling with high-level surprise in early visual cortex strongly diverged from feedforward tuning. Combined, our results suggest that high-level predictions constrain sensory processing in earlier areas, thereby aiding perceptual inference.

Divided Attention Has Limited Effects on Speech Sensorimotor Control.

When vowel formants are externally perturbed, speakers change their production to oppose that perturbation both during the ongoing production (compensation) and in future productions (adaptation). To date, attempts to explain the large variability across individuals in these responses have focused on trait-based characteristics such as auditory acuity, but evidence from other motor domains suggests that attention may modulate the motor response to sensory perturbations. Here, we test the extent to which divided attention impacts sensorimotor control for supralaryngeal articulation. Neurobiologically healthy speakers were exposed to random (Experiment 1) or consistent (Experiment 2) real-time auditory perturbation of vowel formants to measure online compensation and trial-to-trial adaptation, respectively. In both experiments, participants completed two conditions: one with a simultaneous visual distractor task to divide attention and one without this secondary task. Divided visual attention slightly reduced online compensation, but only starting > 300 ms after vowel onset, well beyond the typical duration of vowels in speech. Divided attention had no effect on adaptation. The results from both experiments suggest that the use of sensory feedback in typical speech motor control is a largely automatic process unaffected by divided visual attention, suggesting that the source of cross-speaker variability in response to formant perturbations likely lies within the speech production system rather than in higher-level cognitive processes. Methodologically, these results suggest that compensation for formant perturbations should be measured prior to 300 ms after vowel onset to avoid any potential impact of attention or other higher-order cognitive factors.

The effect of covert visual attention on pupil size during perceptual fading

Pupil size is modulated by various cognitive factors such as attention, working memory, mental imagery, and subjective perception. Previous studies examining cognitive effects on pupil size mainly focused on inducing or enhancing a subjective experience of brightness or darkness (for example by asking participants to attend to/memorize a bright or dark stimulus), and then showing that this affects pupil size. Surprisingly, the inverse has never been done; that is, it is still unknown what happens when a subjective experience of brightness or darkness is eliminated or strongly reduced even though bright or dark stimuli are physically present. Here, we aim to answer this question by using perceptual fading, a phenomenon where a visual stimulus gradually fades from visual awareness despite its continuous presentation. The study contains two blocks: Fading and Non-Fading. In the Fading block, participants were presented with black and white patches with a fuzzy outline that were presented at the same location throughout the block, thus inducing strong perceptual fading. In contrast, in the Non-Fading block, the patches switched sides on each trial, thus preventing perceptual fading. Participants covertly attended to one of the two patches, indicated by a cue, and reported the offset of one of a set of circles that are displayed on top. We hypothesized that pupil size will be modulated by covert visual attention in the Non-Fading block, but that this effect will not (or to a lesser extent) arise in the Fading block. We found that covert visual attention to bright/dark does modulate pupil size even during perceptual fading (Fading block), but to a lesser extent than when the perceptual experience of brightness/darkness is preserved (Non-Fading block). This implies that pupil size is always modulated by covert attention, but that the effect decreases as subjective experience of brightness or darkness decreases. In broader terms, this suggests that cognitive modulations of pupil size reflect a mixture of high-level and lower-level visual processing.

Perceived duration of visual stimuli contracts due to crowding.

Recent research on duration perception suggests that duration encoding is not a single general process but involves several separate processes, some of which are specific to visual modality. Moreover, different functional aspects of visual processing can influence duration perception in distinct ways. One of the most important functions of the visual system is to identify and recognize features, shapes, and objects. However, it is still unclear whether and how computations related to these processes affect duration perception. To clarify this issue, we used a spatial crowding phenomenon, which allows the dissociation of low-level feature extraction from high-level processes such as object recognition. We created letter and vernier stimuli matched for their low-level properties but different in their discriminability due to spatial crowding. Here, we show that stimuli that became more difficult to discriminate appeared shorter in duration (data collected in 2019-2023). This difference in perceived duration could not be explained by low-level stimulus properties, cognitive bias due to discriminability, or perceived stimulus onsets or offsets. These results suggest the existence of time-sensitive structures specific to visual processing of features, shapes, and objects that is affected by crowding. These findings support the notion of distributed timing mechanisms in the visual system. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

The impact of interword spacing on inference processing during text reading: Evidence from eye movements

ABSTRACT Removing interword spacing has been shown to disrupt lower-level oculomotor processes and word identification during text reading. However, the impact of these disruptions on higher-level processes remains unclear. To examine the influence of spacing on inferential processing, we monitored eye movements while participants read spaced and unspaced passages that were strongly or weakly constrained toward an inference. Removing spaces disrupted reading fluency, as evidenced by longer reading times, longer fixation durations, reduced skipping, and shorter saccades. We also observed the effects of inferential constraint for spaced passages as characterized by longer reading times, more regressions, and longer regression-path durations for weakly than strongly constrained passages. However, these constraint effects were absent for unspaced passages, suggesting that removing spaces disrupts inferential processing. Our results are consistent with models of reading and discourse processing that assume that higher-level reading processes depend on the quality of lexical representations developed at earlier, word-level reading stages.

Does vibrotactile biofeedback for postural control interfere with cognitive processes?

BackgroundDirectional vibrotactile biofeedback for balance control can be instructed in the form of Repulsive (to move in the opposite direction of vibrations) or Attractive (to move in the direction of vibrations) stimulus encodings. However, which of these encodings is less cognitively demanding and poses less interference with high-level cognitive processes of conflict resolution remains unresolved.MethodsIn two between-subject studies with 30 (16 females) and 35 (23 females) healthy young adults, respectively, we investigated the cognitive load of Attractive and Repulsive vibrotactile biofeedback on 1) working memory (Study I) and 2) cognitive conflict resolution (Study II). Both studies also examined the effectiveness of both feedback stimulus encodings on balance control during quiet standing with eyes closed.ResultsBoth Attractive and Repulsive vibrotactile biofeedback increased balance stability (reduced trunk sway variability) in both the working memory and the conflict resolution study (Study I and II, respectively) with a greater increase of stability for the Repulsive encoding during multitasking demanding cognitive conflict resolution (Study II). Cognitive costs, measured in terms of the Linear Integrated Speed-Accuracy Score (LISAS), were greater for the Attractive encoding during multitasking with working memory demands. When cognitive conflict resolution was required as a secondary cognitive task, both stimulus encodings increased cognitive costs equally.ConclusionsThe effects of instructed Repulsive and Attractive stimulus encodings for the response-related interpretation of vibrotactile biofeedback of body sway were contrasted with respect to cognitive processing demands and balance stabilisation benefits. Both encodings improved balance stability but at certain cognitive costs. Regarding interference with specific high-level cognitive processes, however, a distinction has to be made between both encodings. Repulsive feedback encoding seems to cause less cognitive costs on working memory load and slightly greater stabilisation when cognitive conflict resolution is required. These results are discussed in the context of the known benefits of avoidance actions on cognitive control.

EEG Responses to the Number of Objects in Partially Occluded and Uncovered Scenes.

Perceptual completion is ubiquitous when estimating properties such as the shape, size, or number of objects in partially occluded scenes. Behavioral experiments showed that the number of hidden objects is underestimated in partially occluded scenes compared with an estimation based on the density of visible objects and the amount of occlusion. It is still unknown at which processing level this (under)estimation of the number of hidden objects occurs. We studied this question using a passive viewing task in which observers viewed a game board that was initially partially occluded and later was uncovered to reveal its hidden parts. We simultaneously measured the electroencephalographic responses to the partially occluded board presentation and its uncovering. We hypothesized that if the underestimation is a result of early sensory processing, it would be observed in the activities of P1 and N1, whereas if it is because of higher level processes such as expectancy, it would be reflected in P3 activities. Our data showed that P1 amplitude increased with numerosity in both occluded and uncovered states, indicating a link between P1 and simple stimulus features. The N1 amplitude was highest when both the initially visible and uncovered areas of the board were completely filled with game pieces, suggesting that the N1 component is sensitive to the overall Gestalt. Finally, we observed that P3 activity was reduced when the density of game pieces in the uncovered parts matched the initially visible parts, implying a relationship between the P3 component and expectation mismatch. Overall, our results suggest that inferences about the number of hidden items are reflected in high-level processing.

Bridging the Gap: The Synergy of AI, Data Integration, and Data Science in Driving Innovation

The intersection of Artificial Intelligence (AI), Data Integration, and Data Science is fundamentally rewriting the definition of how businesses collaborate and differentiate. In this article, we will discuss how the triple convergence of these three fields facilitates one another to provide valuable insights, decision-making optimization, and any high-level process automation. In turn, AI relies on data to deliver predictive analytics and automate decision-making, while Data Integration ensures diverse raw data is brought together in a way that makes it possible. Data Science: Utilizing sophisticated, statistical, and computational methods to extract actionable insights. Collectively they deliver a compelling stack that enables organizations to unleash the power of their data, ensure operational efficiency and drive competitive advantage in the market. Outlining the convergence of both technologies, this paper describes core challenges, advantages and future impact, presenting a pathway for organizations planning to leverage the two digitally transformative phenomena.

Expectation generation and its effect on subsequent pain and visual perception.

Bayesian accounts of perception, such as predictive processing, suggest that perceptions integrate expectations and sensory experience, and thus assimilate to expected values. Furthermore, more precise expectations should have stronger influences on perception. We tested these hypotheses in a paradigm that manipulates both the mean value and the precision of cues within-person. Forty-five participants observed cues-presented as ratings from 10 previous participants-with varying cue means, variances (precision), and skewness across trials. Participants reported expectations regarding the painfulness of thermal stimuli or the visual contrast of flickering checkerboards. Subsequently, similar cues were each followed by a visual or noxious thermal stimulus. While perceptions assimilated to expected values in both modalities, cues' precision mainly affected visual ratings. Furthermore, behavioral and computational models revealed that expectations were biased towards extreme values in both modalities, and towards low-pain cues specifically. fMRI analysis revealed that the cues affected systems related to higher-level affective and cognitive processes-including assimilation to the cue mean in a neuromarker of endogenous contributions to pain and in the nucleus accumbens, and activity consistent with aversive prediction-error-like encoding in the periaqueductal gray during pain perception-but not systems related to early perceptual processing. Our findings suggest that predictive processing theories should be combined with mechanisms such as selective attention to better fit empirical findings, and that expectation generation and its perceptual effects are mostly modality-specific and operate on higher-level processes rather than early perception.

Time scale analysis of enzymatic reduction of uric acid in a microfluidic biomedical device

Time Scale Analysis (TSA) is an investigative tool used in engineering design to identify locations in processes that should be a focus of Process Intensification (PI). Furthermore, TSA points to process variables and parameters that could be used to advance and measure PI improvement. However, TSA cannot suggest any specific design solution to intensify process performance. Instead, design engineers should use their fundamental knowledge and creative intelligence to specify detailed design transformations. TSA will then provide a specific quantitative measure of the improvement. TSA implementation improves an explicitly defined process performance, thus helping achieve process intensification goals. TSA is based on first principles, and it utilizes Characteristic Times (CT) such as diffusion, mean residence, and reaction times to improve an existing process. In this study, we specifically consider microfluidic biomedical devices. To illustrate the genesis of CT and TSA, we start by developing a mathematical model of an enzymatic degradation process in a biomedical device called iCore based on mass, momentum, and kinetic equations. After introducing user-defined scaling parameters, we extract CTs pertinent to the enzymatic degradation of uric acid in this microfluidic biomedical device. Diffusion coefficients, microchannel architectural characteristics, enzyme loading, hydrogel thickness, and characteristic parameters of enzyme kinetics are the parameters and process variables incorporated in this analysis. Finally, we compared the extracted CTs with a COMSOL Multiphysics parametric study to demonstrate how time scale analysis as a design tool and adjusting design parameters, such as diffusion coefficient, hydrogel layer thickness, substrate concentration, and enzyme concentration, can enhance the enzymatic reaction process without a need for complex computational modeling. It is crucial to recognize that pertinent CTs can be determined by understanding the type and nature of the observed process, previous experience, published data, and other foundational engineering design work. There is no need for mathematical modeling and numerical simulations to identify and acknowledge the CTs relevant and essential to the observed process; in this work, we only illustrate the principal origin of CTs via a detailed mathematical model of the process, as previously reported by Jovanovic et al. Therefore, in a routine application of TSA, it is important to remember that mathematical modeling and detailed numerical simulations are not necessary. This is a very comforting fact when TSA is deployed as a tool in higher-level process design functions. The investigations on how best to apply TSA in these higher level design functions such as Process Intensification, scale-up/numbering-up, change of device architecture, change of operating conditions, change of process feed characteristics, change of material physical and chemical properties, parametric optimization of the system for various objective functions, and techno-economic analysis, are yet to be studied and reported.

Functional role of area 8A in the posterior dorsolateral frontal region of the human brain: A single case study.

Area 8A has traditionally been considered to be the frontal eye field (FEF), i.e. the area for the motor production of eye movements. However, recent research has shown that the FEF lies posteriorly in premotor area 6. Research in macaque monkeys has demonstrated that, in contrast to premotor area 6, which is involved in the production of motor actions, area 8A is implicated in the cognitive allocation of attention to stimuli based on instruction cues. The aim of the present study was to elucidate the specific cognitive role of area 8A by examining a unique patient with a lesion restricted to area 8A, i.e. sparing the premotor cortex. This right-handed male patient underwent neuropsychological assessment and testing on two conditional associative-learning tasks: the motor hand conditional associative-learning task (MCALT) assessing the selection of motor actions based on instruction cues and the visual conditional associative-learning task (VCALT) assessing the selection of visual stimuli based on instruction cues. The patient's performance on the VCALT was significantly impaired compared to control subjects, but performance on the MCALT and on an Eye Movement Control Task was preserved. The present study provides evidence that area 8A is critical for the cognitive process regulating the allocation of attention to different stimuli in the environment, but not in the production of eye movements. These findings enhance understanding of the functional organization of the posterior dorsolateral frontal region in the human brain and suggest a specialized role of area 8A in high-level cognitive processes.

Process Mapping to Support the Implementation of a Regional Strategy to Address the Opioid Epidemic.

To address the opioid epidemic in Kansas City, Missouri, local health systems sought to implement a referral to peer recovery coaches (PRCs) for clients presenting with opioid use disorder. Client referrals were made primarily through health system emergency departments, where PRCs met clients to facilitate linkages to recovery support for up to twelve months. This study aimed to evaluate and improve program implementation with process mapping at three local health systems. Using a five-phase conceptual framework and three development and implementation domains, providers, administrators, and PRCs were interviewed to identify the process for recognizing clients with opioid use disorders and referring them to PRCs. Serial meetings were held to validate the process maps at three health systems and a distillation of key processes was created to guide future analyses and implementation efforts. A detailed process map for each health system was developed, from which a high-level process map was created to support future implementation efforts. Health system-specific process maps varied, although conceptually coherent elements were identified across each system to diagram a recovery ecosystem to support client referrals to PRCs. By systematically assessing the implementation of the same program across different health systems, critical steps, along with their barriers and facilitators, were identified that can be used to understand the processes of care associated with outcomes and to guide future implementation efforts.

Slow but flexible or fast but rigid? Discrete and continuous processes compared

A tradeoff exists when dealing with complex tasks composed of multiple steps. High-level cognitive processes can find the best sequence of actions to achieve a goal in uncertain environments, but they are slow and require significant computational demand. In contrast, lower-level processing allows reacting to environmental stimuli rapidly, but with limited capacity to determine optimal actions or to replan when expectations are not met. Through reiteration of the same task, biological organisms find the optimal tradeoff: from action primitives, composite trajectories gradually emerge by creating task-specific neural structures. The two frameworks of active inference – a recent brain paradigm that views action and perception as subject to the same free energy minimization imperative – well capture high-level and low-level processes of human behavior, but how task specialization occurs in these terms is still unclear. In this study, we compare two strategies on a dynamic pick-and-place task: a hybrid (discrete-continuous) model with planning capabilities and a continuous-only model with fixed transitions. Both models rely on a hierarchical (intrinsic and extrinsic) structure, well suited for defining reaching and grasping movements, respectively. Our results show that continuous-only models perform better and with minimal resource expenditure but at the cost of less flexibility. Finally, we propose how discrete actions might lead to continuous attractors and compare the two frameworks with different motor learning phases, laying the foundations for further studies on bio-inspired task adaptation.

No evidence for unconscious initiation and following of arithmetic rules: A replication study.

The field of consciousness studies has yielded various-sometimes contradicting-accounts regarding the function of consciousness, ranging from denying it has such function to claiming that any high-level cognitive function requires consciousness. Empirical findings supporting both accounts were reported, yet some of them have been recently revisited based on failures to replicate. Here, we aimed at replicating a remarkable finding reported by Ric and Muller (2012); participants were able to follow an unseen instruction, integrate it with a subsequently presented pair of unseen digits, and accordingly either add the digits (resulting in a priming effect), or simply represent them. This finding thus demonstrates unconscious task-switching, temporal integration (involving mental chaining), and arithmetic operation. Finding such high-level processes in the absence of awareness is of pivotal importance to our understanding of consciousness, as it challenges prominent theories in the field (e.g., the global neuronal workspace). Accordingly, in light of the self-correction wave in psychological science in general and in the field of consciousness studies in particular, we report here a preregistered replication aimed at testing the reproducibility of this finding, while also better controlling for subjects' awareness of both the instruction and the digits. Across two highly powered experiments, our results failed to replicate the original effect. We, therefore, conclude that the current evidence does not support the claim that arithmetic operations (specifically, addition) can be flexibly initiated without awareness, in line with the current arguments for a more limited scope of unconscious processing. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

5G-Cloud-based real-time robotic part repairing for advanced manufacturing via computer vision

In this paper, we delve into the transformative capabilities of 5G wireless communication technology within the realm of robotics, particularly in the context of advanced manufacturing. Leveraging the power of computer vision and cloud/edge computing, we unveil the boundless possibilities that this technology heralds. Leveraging the ultra-reliable low latency communication (uRLLC) of 5G, we establish a distributed system showcasing its potential to revolutionize industrial processes. Additionally, to validate our framework, we developed a testbed tailored for real-world applications, focusing on milling operations using an industrial robot. Through high-level lidar data processing, we identify defects and create toolpaths, seamlessly to execute milling tasks. This research highlights 5G’s potential to redefine industrial processes while elucidating operational requirements for achieving uRLLC. Empirical testing underscores the benefits of 5G-robotics integration, enhancing efficiency and innovation in advanced manufacturing.