Robust Task Research Articles

A Cross-Scale and Illumination Invariance-Based Model for Robust Object Detection in Traffic Surveillance Scenarios

Robust object detection methods in traffic surveillance scenarios often encounters challenges due to large-scale deformations and illumination variations in outdoor scenes. To enhance the tolerance of such methods against these variations, we design a cross-scale and illumination-invariant detection model (CSIM) based on the You Only Look Once (YOLO) architecture. A main cause of false detection in large-scale detection tasks is the inconsistency between various feature scales. To address this issue, we introduce an adaptive cross-scale feature fusion model to ensure the consistency of the constructed feature pyramid. To overcome the influence of uneven light, we build an illumination-invariant chromaticity space on the CSIM model, which is independent of the correlated color temperature. In addition, we adopt spatial attention modules, K-means clustering and the Mish activation function for further model optimization. The obtained experimental results show that the proposed CSIM produces excellent detection results for addressing the challenges derived from large-scale deformations and the illumination changes encountered during traffic surveillance. Compared with state-of-the-art object detection methods on public datasets, our proposed model has achieved competitive results in robust object detection tasks in traffic surveillance scenarios.

Towards Robust Task Assignment in Mobile Crowdsensing Systems

Mobile Crowdsensing (MCS), which assigns outsourced sensing tasks to volunteer workers, has become an appealing paradigm to collaboratively collect data from surrounding environments. However, during actual task implementation, various unpredictable disruptions are usually inevitable, which might cause a task execution failure and thus impair the benefit of MCS systems. Practically, via reactively shifting the pre-determined assignment scheme in real time, it is usually impossible to develop reassignment schemes without a sacrifice of the system performance. Against this background, we turn to an alternative solution, i.e., proactively creating a robust task assignment scheme offline. In this work, we provide the first attempt to investigate an important and realistic RoBust Task Assignment (RBTA) problem in MCS systems, and try to strengthen the assignment scheme's robustness while minimizing the workers' traveling detour cost simultaneously. By leveraging the workers' spatiotemporal mobility, we propose an assignment-graph-based approach. Firstly, an assignment graph is constructed to locally model the assignment relationship between the released MCS tasks and available workers. And then, under the framework of evolutionary multi-tasking, we devise a population-based optimization algorithm, namely EMTRA, to effectively achieve adequate Pareto-optimal schemes. Comprehensive experiments on two real-world datasets clearly validate the effectiveness and applicability of our proposed approach.

Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this challenge. We extend meta-RL to broad non-parametric task distributions which have never been explored before, and also achieve state-of-the-art results in non-stationary and out-of-distribution tasks. Specifically, MoSS consists of a task inference module and a policy module. We utilize the Gaussian mixture model for task representation to imitate the parametric and non-parametric task variations. Additionally, our online adaptation strategy enables the agent to react at the first sight of a task change, thus being applicable in non-stationary tasks. MoSS also exhibits strong generalization robustness in out-of-distributions tasks which benefits from the reliable and robust task representation. The policy is built on top of an off-policy RL algorithm and the entire network is trained completely off-policy to ensure high sample efficiency. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.

An uncertainty-tolerant robust distributed control strategy for building cooling water systems considering measurement uncertainties

Distributed control is receiving increasing attention in the domain of building heating, ventilation, and air-conditioning (HVAC) systems, due to its charactristics of high generality, scalability and flexibility. However, the existing studies rarely took the impacts of measurement uncertainties into consideration which are common and inevitable in HVAC systems. It would cause the distributed control strategies fail to achieve the desired optimization performance. This paper therefore proposes an uncertainty-tolerant robust strategy to reduce the impacts of measurement uncertainties on the performance of distributed control of building cooling water systems. Firstly, the uncertain parameters are modeled as probability distributions determined by sensor biases and measurement noises. An improved adaptive Monte-Carlo method is then presented to estimate the expected performance (i.e., the expected optimization objective) under multiple measurement uncertainties. Finally, a multi agent-based structure is proposed for HVAC systems to perform the robust distributed control task. Research results indicate that the proposed strategy can achieve similar optimal control results as the ideal uncertainty-free strategy in the presence of measurement uncertainties. The average deviation of optimal control results is reduced from 0.55 K to 0.28 K in comparisons to the conventional distributed control strategy without considering measurement uncertainties. The deviation of optimal control results can still be within 0.6 K even when the degree of measurement uncertainty is nearly 30%.

Fuzzy-Based Robust Precision Consensus Tracking for Uncertain Networked Systems With Cooperative–Antagonistic Interactions

In bipartite consensus tracking (BCT) tasks for nonlinear multiagent systems, stochastic disturbances and actuator faults are regarded as essential factors that hamper effective controller formulation and tracking precision improvement. To address these difficulties, we design an improved finite-time performance function (FTPF) for a fuzzy fault-tolerant distributed cooperative control scheme to achieve finite-time robust precision BCT tasks for nonlinear multiagent systems. The parameter selection range of the improved FTPF is relaxed, which renders systems to achieve better transient performance. Benefitting from stochastic Lyapunov stability theory, it is shown that all signals of systems are semi-global uniformly ultimately bounded in probability, and bipartite consensus errors can satisfy the arbitrary precision with probability in the predefined time. Finally, to verify its effectiveness, the proposed control scheme is applied to BCT tasks of a group of vehicles, which manifests anticipated control performance under various uncertainties.

Robust Task Scheduling for Heterogeneous Robot Teams Under Capability Uncertainty

This article develops a stochastic programming framework for multiagent systems, where task decomposition, assignment, and scheduling problems are simultaneously optimized. The framework can be applied to heterogeneous mobile robot teams with distributed subtasks. Examples include pandemic robotic service coordination, explore and rescue, and delivery systems with heterogeneous vehicles. Owing to their inherent flexibility and robustness, multiagent systems are applied in a growing range of real-world problems that involve heterogeneous tasks and uncertain information. Most previous works assume one fixed way to decompose a task into roles that can later be assigned to the agents. This assumption is not valid for a complex task where the roles can vary and multiple decomposition structures exist. Meanwhile, it is unclear how uncertainties in task requirements and agent capabilities can be systematically quantified and optimized under a multiagent system setting. A representation for complex tasks is proposed: agent capabilities are represented as a vector of random distributions, and task requirements are verified by a generalizable binary function. The conditional value at risk is chosen as a metric in the objective function to generate robust plans. An efficient algorithm is described to solve the model, and the whole framework is evaluated in two different practical test cases: capture-the-flag and robotic service coordination during a pandemic (e.g., COVID-19). Results demonstrate that the framework is generalizable, is scalable up to 140 agents and 40 tasks for the example test cases, and provides low-cost plans that ensure a high probability of success.

Risk-Aware Contextual Learning for Edge-Assisted Crowdsourced Live Streaming

This paper proposes an edge-assisted crowdsourced live video transcoding approach where the transcoding capabilities of the edge transcoders are unknown and dynamic. The resilience and trustworthiness of highly unstable transcoders in decision making are characterized with mean-variance-based measures to avoid making highly risky decisions. The risk level of each device’s situation is assessed and two upper confidence bounds of the variance of transcoding performance are presented. Based on the derived bounds and by leveraging the contextual information of devices, two risk-aware contextual learning schemes are developed to efficiently estimate the transcoding capabilities of the edge devices. Combining context awareness and risk sensitivity, a novel transcoding task assignment and viewer association algorithm is proposed. Simulation results demonstrate that the proposed algorithm achieves robust task offloading with superior network utility performance as compared to the linear upper confidence bound and the risk-aware mean-variance upper confidence bound-based algorithms. In particular, an epoch-based task assignment strategy is designed to reduce the task switching costs incurred in assigning the same transcoding task to different transcoders over time. This strategy also reduces the computational time needed. Numerical results confirm that this strategy achieves up to 86.8% switching costs reduction and 92.3% computational time reduction.

General figure and face-specific closure ability: predictors of trait-autism?

Little research has examined the association between general figure closure speed, a stratum I ability within the Cattell-Horn-Carroll (CHC) model of intelligence, and face-specific closure ability; an important consideration, as some research suggests face processing is independent of other abilities. Additionally, figure closure ability (general and face) may correlate negatively with trait-autism, due to theorised autism-related difficulties in global processing. Therefore, in addition to developing a psychometrically robust short-form Mooney face detection task, we administered the Gestalt Figure Completion Test and the Autism Spectrum Quotient to a sample of 263 general community adults. We found convergent validity between face-specific and general figure closure ability (r = .44, 95%CI:[.30, .58]). Furthermore, based on a latent variable model, general figure closure ability was directly, and face-specific figure closure ability indirectly, negatively associated with trait-autism (i.e., nonverbal communication). We conclude that face detection ability evidences convergent validity with general figure closure ability and can be measured reliably in less than four minutes. Finally, a general, rather than face-specific, figure closure process may tap more directly into autism-like nonverbal communication ability, supporting the notion that global processing abilities of non-face objects may better reflect the requirements to ‘fill in the gaps’ in social contexts.

A shallow hybrid classical–quantum spiking feedforward neural network for noise-robust image classification

Deep Convolutional Neural Network (CNN)-based image classification systems are often susceptible to noise interruption, i.e., minor image noise may significantly impact the outcome. On the contrary, classical Spiking Neural Network (SNN) is known for handling noisy data due to the stochastic and temporal behaviour of the spiking neuron signals. However, it is not always feasible to train the weights of the classical SNN due to stochastic and non-differentiable spiking signals. Recent applications of quantum machine learning to stochastic modelling have predicted that quantum computing would prove to be a significant advantage, hence catapulting the study of quantum and neuromorphic computing to a new level of development. Motivated by these observations, this paper introduces a shallow hybrid classical–quantum spiking feedforward neural network referred to as Spiking Quantum Neural Network (SQNN) for dealing with a robust image classification task in the presence of noise and adversarial attacks. The proposed SQNN offers the inherent capabilities of processing unforeseen noisy test images due to its spatial and temporal information. An efficient variational quantum circuit training with the help of a standard back-propagation algorithm obviates the classical Spiking Time-Dependent Plasticity (STDP) and Spike-Prop algorithms, which are often found inefficient in training the feedforward SNN. The proposed SQNN is extensively tested and benchmarked on the PennyLane Quantum Simulator. Experimental results show that the proposed SQNN model supersedes the feedforward SNN (SFNN), Random Quantum Neural Networks (RQNN), AlexNet and ResNet-18 on unseen test images with added noise from the FashionMNIST, MNIST, KMNIST, CIFAR10, and ImageNet datasets.

Machine understanding and deep learning representation

Practical ability manifested through robust and reliable task performance, as well as information relevance and well-structured representation, are key factors indicative of understanding in the philosophical literature. We explore these factors in the context of deep learning, identifying prominent patterns in how the results of these algorithms represent information. While the estimation applications of modern neural networks do not qualify as the mental activity of persons, we argue that coupling analyses from philosophical accounts with the empirical and theoretical basis for identifying these factors in deep learning representations provides a framework for discussing and critically evaluating potential machine understanding given the continually improving task performance enabled by such algorithms.

Robust Motor Imagery Tasks Classification Approach Using Bayesian Neural Network

The development of Brain-Computer Interfaces based on Motor Imagery (MI) tasks is a relevant research topic worldwide. The design of accurate and reliable BCI systems remains a challenge, mainly in terms of increasing performance and usability. Classifiers based on Bayesian Neural Networks are proposed in this work by using the variational inference, aiming to analyze the uncertainty during the MI prediction. An adaptive threshold scheme is proposed here for MI classification with a reject option, and its performance on both datasets 2a and 2b from BCI Competition IV is compared with other approaches based on thresholds. The results using subject-specific and non-subject-specific training strategies are encouraging. From the uncertainty analysis, considerations for reducing computational cost are proposed for future work.

Humanoid Loco-Manipulations Using Combined Fast Dense 3D Tracking and SLAM With Wide-Angle Depth-Images

To efficiently achieve complex humanoid loco-manipulation tasks in industrial contexts, we propose a combined vision-based tracker-localization interplay integrated as part of a task-space whole-body optimization control. To achieve good perception complementarity between manipulation and localization, a new fast dense 3D model-based tracking using wide-angle depth image is developed and used in conjunction with a simultaneous localization and mapping software. Our approach allows humanoid robots, targeted for industrial manufacturing, to manipulate and assemble large-scale objects while walking. It is assessed with experiments consisting in rolling and assembling in an unwinder a heavy and wide bobbin using bimanual grasping and bipedal locomotion at a time. This experimental use-case is found in some large-scale manufacturing where bobbins are enrolled with various materials (cables, papers, rubbers, etc.). The same experiments are made using two different humanoid robots of the same family. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper aims at deploying humanoid robots in large-scale manufacturing industries. We consider non-added value tasks related to transporting large tools or objects such as large bobbins by means of locomanipulation skills, similarly to human workers. We developed a task-space control framework that has been successfully applied in the aircraft industry. In the frame of a current collaboration with other major industrial sectors, we enhanced our control framework to interplay between SLAM and visual tracking to realize robust loco-manipulation tasks. Our approach can be applied and ported to any humanoid robot or bi-manual wheeled mobile robots with minor programming effort as the software is made open. Preliminary experiments with two different humanoids and use-cases suggest that our approach is feasible. In future research, we will address the problem of performance to reach at least human-speed in the execution of locomanipulation tasks in large-scale industry and automation contexts.

Iterative Rectifying Methods for Nonrepetitive Continuous-Time Learning Control Systems.

To implement iterative learning control (ILC), one of the most fundamental hypotheses is the strict repetitiveness (i.e., iteration-independence) of the controlled systems, especially of their plant models. This hypothesis, however, results in difficulties of developing theoretic analysis methods and promoting practical applications for ILC, especially in the presence of continuous-time systems, which is the motivation of the current paper to cope with robust tracking problems of continuous-time ILC systems subject to nonrepetitive (i.e., iteration-dependent) uncertainties. Based on integrating an iterative rectifying mechanism, continuous-time ILC can effectively address the ill effects of the multiple nonrepetitive uncertainties that arise from the system models, initial states, load and measurement disturbances, and desired references. Furthermore, a robust convergence analysis method is presented for continuous-time ILC by combining a contraction mapping-based method and a system equivalence transformation method. It is disclosed that regardless of continuous-time ILC systems with zero or nonzero system relative degrees, the robust tracking tasks in the presence of nonrepetitive uncertainties can be accomplished, together with the boundedness of all the system trajectories being ensured. Two examples are included to verify the validity of our robust tracking results for nonrepetitive continuous-time ILC systems.

Bimanual telemanipulation with force and haptic feedback through an anthropomorphic avatar system

Robotic teleoperation is a key technology for a wide variety of applications. It allows sending robots instead of humans in remote, possibly dangerous locations while still using the human brain with its enormous knowledge and creativity, especially for solving unexpected problems. A main challenge in teleoperation consists of providing enough feedback to the human operator for situation awareness and thus create full immersion, as well as offering the operator suitable control interfaces to achieve efficient and robust task fulfillment. We present a bimanual telemanipulation system consisting of an anthropomorphic avatar robot and an operator station providing force and haptic feedback to the human operator. The avatar arms are controlled in Cartesian space with a direct mapping of the operator movements. The measured forces and torques on the avatar side are haptically displayed to the operator. We developed a predictive avatar model for limit avoidance which runs on the operator side, ensuring low latency. The system was successfully evaluated during the ANA Avatar XPRIZE competition semifinals. In addition, we performed in lab experiments and carried out a small user study with mostly untrained operators.

ENTROPY BASED GREEDY UNSUPERVISED FEATURE SELECTION METHOD USING ROUGH SET THEORY FOR CLASSIFICATION

Feature selection technique attempts to select and remove irrelevant features while ensuring that an informative subset of features remains in the dataset. The performance of a classifier often depends on the feature subset used for the robust classification task. In the medical and healthcare application domain, classification accuracy plays a vital role. The higher level of false negatives in medical diagnosis systems may raise the risk of patients not employing the necessary treatment they need. In this article, we have proposed an unsupervised feature selection method that underlines the concepts of rough set theory for the task of classification of high-dimensional datasets. Experiments are carried out on seven public domain healthcare and life science related datasets. The obtained experimental results justify the significance of the proposed method over five other state-of-the-art feature selection methods.

Optimal k-means clustering using artificial bee colony algorithm with variable food sources length

&lt;span&gt;Clustering is a robust machine learning task that involves dividing data points into a set of groups with similar traits. One of the widely used methods in this regard is the k-means clustering algorithm due to its simplicity and effectiveness. However, this algorithm suffers from the problem of predicting the number and coordinates of the initial clustering centers. In this paper, a method based on the first artificial bee colony algorithm with variable-length individuals is proposed to overcome the limitations of the k-means algorithm. Therefore, the proposed technique will automatically predict the clusters number (the value of k) and determine the most suitable coordinates for the initial centers of clustering instead of manually presetting them. The results were encouraging compared with the traditional k-means algorithm on three real-life clustering datasets. The proposed algorithm outperforms the traditional k-means algorithm for all tested real-life datasets.&lt;/span&gt;

Robust Task Allocation for Multiple Cooperative Robotic Vehicles Considering Node Position Uncertainty

Robust Task Allocation for Multiple Cooperative Robotic Vehicles Considering Node Position Uncertainty

Identifying Irregular Financial Operations Using Accountant Comments and Natural Language Processing Techniques

Finding not typical financial operations is a complicated task. The difficulties arise not only due to the sophisticated actions of fraudsters but also because of the large number of financial operations performed by business companies. This is especially true for large companies. It is highly desirable to have a tool to reduce the number of potentially irregular operations significantly. This paper presents an implementation of NLP-based algorithms to identify irregular financial operations using comments left by accountants. The comments are freely written and usually very short remarks used by accountants for personal information. Implementation of content analysis using cosine similarity showed that identification of the type of operation using the comments of accountants is very likely. Further comment content analysis and financial data analysis showed that it could be expected to reduce the number of potentially suspicious operations significantly: analysis of more than half a million financial records of Dutch companies enabled the identification of 0.3% operations that may be potentially suspicious. This could make human financial auditing easier and more robust task.

Robust visualization of trajectory data

Abstract The analysis of movement trajectories plays a central role in many application areas, such as traffic management, sports analysis, and collective behavior research, where large and complex trajectory data sets are routinely collected these days. While automated analysis methods are available to extract characteristics of trajectories such as statistics on the geometry, movement patterns, and locations that might be associated with important events, human inspection is still required to interpret the results, derive parameters for the analysis, compare trajectories and patterns, and to further interpret the impact factors that influence trajectory shapes and their underlying movement processes. Every step in the acquisition and analysis pipeline might introduce artifacts or alterate trajectory features, which might bias the human interpretation or confound the automated analysis. Thus, visualization methods as well as the visualizations themselves need to take into account the corresponding factors in order to allow sound interpretation without adding or removing important trajectory features or putting a large strain on the analyst. In this paper, we provide an overview of the challenges arising in robust trajectory visualization tasks. We then discuss several methods that contribute to improved visualizations. In particular, we present practical algorithms for simplifying trajectory sets that take semantic and uncertainty information directly into account. Furthermore, we describe a complementary approach that allows to visualize the uncertainty along with the trajectories.

Accurate semantic segmentation of RGB-D images for indoor navigation

We introduce an approach of semantic segmentation to detect various objects for the mobile robot system “ROSWITHA” (RObot System WITH Autonomy). Developing a semantic segmentation method is a challenging research field in machine learning and computer vision. The semantic segmentation approach is robust compared with the other traditional state-of-the-art methods for understanding the surroundings. Semantic segmentation is a method that presents the most information about the object, such as classification and localization of the object on the image level and the pixel level, thus precisely depicting the shape and position of the object in space. In this work, we experimented with verifying the effectiveness of semantic segmentation when used as an aid to improving the performance of robust indoor navigation tasks. To make the output map of semantic segmentation meaningful, and enhance the model accuracy, points cloud data were extracted from the depth camera, which fuses the data originated from RGB and depth stream to improve the speed and accuracy compared with different machine learning algorithms. We compared our modified approach with the state-of-the-art methods and compared the results when trained with the available dataset NYUv2. Moreover, the model was then trained with the customized indoor dataset 1 (three classes) and dataset 2 (seven classes) to achieve a robust classification of the objects in the dynamic environment of Frankfurt University of Applied Sciences laboratories. The model attains a global accuracy of 98.2%, with a mean intersection over union (mIoU) of 90.9% for dataset 1. For dataset 2, the model achieves a global accuracy of 95.6%, with an mIoU of 72%. Furthermore, the evaluations were performed in our indoor scenario.