High-level Tasks Research Articles

Enhancing the work engagement of frontline nurses during the COVID-19 pandemic: the mediating role of affective commitment and perceived organizational support

BackgroundOverload and anxiety were common phenomena among frontline nurses during the pandemic. Understanding the potential pathway for fostering engagement in high-stress working conditions can provide evidence of targeted intervention to facilitate nurses’ well-being and safety practices. This study aims to investigate the level of nurses’ work engagement during nucleic acid collection tasks in the COVID-19 pandemic and identify its potential antecedents.MethodsA cross-sectional design was adopted. A sample of 824 nurses who engaged in nucleic acid collection tasks completed an online self-report questionnaire between 1 March and 31 May 2022. Descriptive and path analyses were utilized to analyse the interrelationships among anxiety, perceived workload, affective commitment, perceived organizational support and work engagement. This study was conducted and reported under the guidelines for Strengthening the Reporting of Observational Studies in Epidemiology.ResultsThe results showed that frontline nurses engaged in such tasks reported high levels of anxiety and task load and low levels of work engagement. Path analysis identified anxiety symptoms, perceived workload, perceived organizational support, and affective commitment as associated with work engagement, and among these factors, perceived organizational support and affective commitment played key roles in mediating the relationship of anxiety, workload and work engagement in high-stress working conditions.ConclusionsAffective commitment and perceived organizational support were associated with frontline nurses’ level of work engagement during the COVID-19 pandemic; these two variables might explain how engagement is generated in high-anxiety and high-workload situations. When healthcare organizations give more attention to frontline nurses’ physical and psychological conditions and are able to innovatively motivate affective commitment and facilitate organizational support, nurses’ work engagement in high-level tasks may increase, thus enhancing work safety and personal well-being.

Signal temporal logic synthesis under Model Predictive Control: A low complexity approach

In this paper, we focus on the challenging problem of model predictive control (MPC) for dynamics systems with high-level tasks formulated as signal temporal logic (STL). The state-of-art for STL synthesis mainly suffers from limited scalability with respect to the complexity of the task and the planning horizon, hindering the real-time implementation of MPC. This work tackles this issue by STL formula reformulation and input blocking. Specifically, simplifications are applied on disjunctive STL (sub)formulae recursively in the framework of MPC to limit formula size. We show that the simplified STL can be reformulated into mixed integer linear programming (MILP) constraints with a modifiable number of binary variables being required. The move blocking scheme is then employed to further reduce problem complexity by fixing input variables to be constant over several time intervals. In order to trade off the control performance and computational load, a blocking structure design with on-line correction is proposed. The extension of the proposed STL-MPC algorithm to uncertain systems is achieved through STL constraint tightening. Simulations and experiments show the effectiveness of the proposed algorithm.

Sim2Real Neural Controllers for Physics-Based Robotic Deployment of Deformable Linear Objects

Deformable linear objects (DLOs), such as rods, cables, and ropes, play important roles in daily life. However, manipulation of DLOs is challenging as large geometrically nonlinear deformations may occur during the manipulation process. This problem is made even more difficult as the different deformation modes (e.g., stretching, bending, and twisting) may result in elastic instabilities during manipulation. In this paper, we formulate a physics-guided data-driven method to solve a challenging manipulation task—accurately deploying a DLO (an elastic rod) onto a rigid substrate along various prescribed patterns. Our framework combines machine learning, scaling analysis, and physical simulations to develop a physics-based neural controller for deployment. We explore the complex interplay between the gravitational and elastic energies of the manipulated DLO and obtain a control method for DLO deployment that is robust against friction and material properties. Out of the numerous geometrical and material properties of the rod and substrate, we show that only three non-dimensional parameters are needed to describe the deployment process with physical analysis. Therefore, the essence of the controlling law for the manipulation task can be constructed with a low-dimensional model, drastically increasing the computation speed. The effectiveness of our optimal control scheme is shown through a comprehensive robotic case study comparing against a heuristic control method for deploying rods for a wide variety of patterns. In addition to this, we also showcase the practicality of our control scheme by having a robot accomplish challenging high-level tasks such as mimicking human handwriting, cable placement, and tying knots.

Web Platform for Interconnecting Body Sensors and Improving Health Care

The Internet of Things (IoT) is a paradigm in which smart objects actively collaborate among them and with other physical and virtual objects available in the Web in order to perform high-level tasks for the benefit of end-users. In the e-health scenario, these communicating smart objects can be body sensors that enable a continuous real-time monitoring of vital signs of patients. Data produced by such sensors can be used for several purposes and by different actors, such as doctors, patients, relatives, and health care centers, in order to provide remote assistance to users. However, major challenges arise mainly in terms of the interoperabil- ity among several heterogeneous devices from a variety of manufacturers. In this context, we introduce Eco Health (Ecosystem of Health Care Devices), a Web middleware platform for connecting doctors and patients using attached body sensors, thus aiming to provide improved health monitoring and diagnosis for patients. This platform is able to integrate information obtained from heterogeneous sensors in order to provide mechanisms to monitor, process, visualize, store, and send notifications regarding patients’ conditions and vital signs at real-time by using Internet standards. In this paper, we present blueprints of our proposal to Eco Health and its logical architecture and implementation, as well as an e-health motivational scenario where such a platform would be useful.

Vital information is only worth one thumbnail: Towards efficient human pose estimation

In pursuit of impressive performance, existing DCNN-based approaches of human pose estimation usually use massive networks and large-size images to train a deep model. When applying these deep based methods in real-time systems, current works try to compress the deep network by reducing the number of layers and channels, but such approaches are complex and poorly generalized since they require elaborate design of small-scale network structures. Based on the fact that large-size images contain redundant information, in this paper, we explore the influence of image-size on system complexity and propose a novel framework called ThumbPose to accelerate and compress deep models by inferring on thumbnail representations in the task of human pose estimation. In our framework, we first propose a style supervised online downscaler to reduce an input image into a thumbnail image. Furthermore, a training strategy of dual-branch auto-encoding is designed to obtain effective and accurate thumbnail representation in a knowledge distillation manner, which is further used to maintain the performance of thumbnail images as the original-size input images. For heat-map based human pose estimation, ThumbPose is an orthogonal and implementation-friendly method, that can not only compress and accelerate the inference network but also obtain an image downscaler in a supervised manner that can be used in other high-level tasks (e.g. detection, segmentation, etc. in practical applications). Extensive experiments on MS COCO dataset demonstrate the effectiveness of our proposed method, and ThumbPose achieves superior performance (＋ 1.3% AP and ＋ 0.7% AR) with negligible additional cost (<0.2 GFLOPs) compared to previous state-of-the-art methods when using small-size images as inputs. Moreover, experiments on MPII show that our model achieves higher accuracy (＋ 0.2% Mean@0.5) with minimal computation (2.5 GFLOPs) compared to superior lightweight models obtained by the network compression methods.

A method for understanding and digitizing manipulation activities using programming by demonstration in robotic applications

Robots are flexible machines, where the flexibility is achieved, mainly, by the re-programming of the robotic system. To fully exploit the potential of robotic systems, an easy, fast, and intuitive programming methodology is desired. By applying such methodology, robots will be open to a wider audience of potential users (i.e. SMEs, etc.) since the need for a robotic expert in charge of programming the robot will not be needed anymore. This paper presents a Programming by Demonstration approach dealing with high-level tasks taking advantage of the ROS standard. The system identifies the different processes associated to a single-arm human manipulation activity and generates an action plan for future interpretation by the robot. The system is composed of five modules, all of them containerized and interconnected by ROS. Three of these modules are in charge of processing the manipulation data gathered by the sensors system, and converting it from the lowest level to the highest manipulation processes. In order to do this transformation, a module is used to train the system. This module generates, for each operation, an Optimized Multiorder Multivariate Markov Model, that later will be used for the operations recognition and process segmentation. Finally, the fifth module is used to interface and calibrate the system. The system was implemented and tested using a dataglove and a hand position tracker to capture the operator’s data during the manipulation. Four users and five different object types were used to train and test the system both for operations recognition and process segmentation and classification, including also the detection of the locations where the operations are performed.

Real-Time Online Goal Recognition in Continuous Domains via Deep Reinforcement Learning.

The problem of goal recognition involves inferring the high-level task goals of an agent based on observations of its behavior in an environment. Current methods for achieving this task rely on offline comparison inference of observed behavior in discrete environments, which presents several challenges. First, accurately modeling the behavior of the observed agent requires significant computational resources. Second, continuous simulation environments cannot be accurately recognized using existing methods. Finally, real-time computing power is required to infer the likelihood of each potential goal. In this paper, we propose an advanced and efficient real-time online goal recognition algorithm based on deep reinforcement learning in continuous domains. By leveraging the offline modeling of the observed agent's behavior with deep reinforcement learning, our algorithm achieves real-time goal recognition. We evaluate the algorithm's online goal recognition accuracy and stability in continuous simulation environments under communication constraints.

우리나라와 미국 교과서의 사각형의 성질 과제 비교

In order to derive implications for the reasoning tasks presented in Korean textbooks, this study classified tasks of the proposition of quadrilateral unit in Korean and U.S. textbooks into type of proof-related reasoning, analyzed them according to the level of reasoning and argument competency demands. In addition, detailed characteristics according to each level were examined for tasks of the types of DA, IC and MC that accounted for the majority. As a result of the analysis, low-level tasks were presented at a high rate in both countries, but the proportion of high-level tasks was higher in U.S. textbooks. Additionally, opportunities to develop reasoning and argument competency were provided at a limited level for each type of reasoning. This tendency could be clearly confirmed based on the detailed characteristics of reasoning tasks related to the proposition of quadrilateral unit in Korea, examined by the type of reasoning. Therefore Korean textbooks need to provide opportunities to learn high-level reasoning, to present tasks at various levels according to each type of reasoning furthermore, and to reconsider how to develop and transform tasks of various levels for each reasoning type in terms of element and the chain of inference.

Bio-inspired XYW parallel pathway edge detection network

Edge detection is of critical importance for middle-level and high-level tasks in computer vision. Existing edge detection methods usually use VGG16 as the encoding network and achieve exceptional performance through transfer learning, which has the characteristics of high parameters and high computational cost. Researchers have implemented edge detection by designing decoding networks. Unlike existing methods, this paper is inspired by the effective mechanisms of edge detection in the parallel pathway of biological vision and proposes a new lightweight encoding–decoding structure for edge detection networks, which we refer to as XYW-Net. In the encoding network, we drew inspiration from the receptive field properties of X-type cells, Y-type cells, and W-type cells involved in the parallel pathway, and developed more meticulous convolutional models. Based on the structure of the parallel pathway, the three cell modules are combined into a novel encoding network and excellent feature extraction performance is obtained. Within the decoding network, this paper draws inspiration from the feature integration ability of the inferotemporal cortex (IT) and introduces a novel feature integration module to constitute the decoding network. Experiments show that the proposed network in this paper obtains the Optimal Dataset Scale (ODS) = 0.812 on the BSDS500 dataset with only 0.79 M parameters. Additionally, the model has exhibited outstanding ODS performance on various publicly available edge detection datasets, including NYUD, BIPEDv1, and Multicue. Moreover, future research could concentrate on implementing more efficient antagonistic mechanisms and devising networks grounded in higher-level visual cortical mechanisms. This could further augment the performance and efficiency of edge detection networks. We encourage researchers to delve into these directions within the field. The codes are available at https://github.com/PXinTao/XYW-Net.

Symmetric Graph-Based Visual Question Answering Using Neuro-Symbolic Approach

As the applications of robots expand across a wide variety of areas, high-level task planning considering human–robot interactions is emerging as a critical issue. Various elements that facilitate flexible responses to humans in an ever-changing environment, such as scene understanding, natural language processing, and task planning, are thus being researched extensively. In this study, a visual question answering (VQA) task was examined in detail from among an array of technologies. By further developing conventional neuro-symbolic approaches, environmental information is stored and utilized in a symmetric graph format, which enables more flexible and complex high-level task planning. We construct a symmetric graph composed of information such as color, size, and position for the objects constituting the environmental scene. VQA, using graphs, largely consists of a part expressing a scene as a graph, a part converting a question into SPARQL, and a part reasoning the answer. The proposed method was verified using a public dataset, CLEVR, with which it successfully performed VQA. We were able to directly confirm the process of inferring answers using SPARQL queries converted from the original queries and environmental symmetric graph information, which is distinct from existing methods that make it difficult to trace the path to finding answers.

Understanding How In-Visualization Provenance Can Support Trade-off Analysis.

In domains such as agronomy or manufacturing, experts need to consider trade-offs when making decisions that involve several, often competing, objectives. Such analysis is complex and may be conducted over long periods of time, making it hard to revisit. In this paper, we consider the use of analytic provenance mechanisms to aid experts recall and keep track of trade-off analysis. We implemented VisProm, a web-based trade-off analysis system, that incorporates in-visualization provenance views, designed to help experts keep track of trade-offs and their objectives. We used VisProm as a technology probe to understand user needs and explore the potential role of provenance in this context. Through observation sessions with three groups of experts analyzing their own data, we make the following contributions. We first, identify eight high-level tasks that experts engaged in during trade-off analysis, such as locating and characterizing interest zones in the trade-off space, and show how these tasks can be supported by provenance visualization. Second, we refine findings from previous work on provenance purposes such as recall and reproduce, by identifying specific objects of these purposes related to trade-off analysis, such as interest zones, and exploration structure (e.g., exploration of alternatives and branches). Third, we discuss insights on how the identified provenance objects and our designs support these trade-off analysis tasks, both when revisiting past analysis and while actively exploring. And finally, we identify new opportunities for provenance-driven trade-off analysis, for example related to monitoring the coverage of the trade-off space, and tracking alternative trade-off scenarios.

An Accurate and Efficient Supervoxel Re-Segmentation Approach for Large-Scale Point Clouds Using Plane Constraints

The accurate and efficient segmentation of large-scale urban point clouds is crucial for many higher-level tasks, such as boundary line extraction, point cloud registration, and deformation measurement. In this paper, we propose a novel supervoxel segmentation approach to address the problem of under-segmentation in local regions of point clouds at various resolutions. Our approach introduces distance constraints from boundary points to supervoxel planes in the merging stage to enhance boundary segmentation accuracy between non-coplanar supervoxels. Additionally, supervoxels with roughness above a threshold are re-segmented using random sample consensus (RANSAC) to address multi-planar coupling within local areas of the point clouds. We tested the proposed method on two publicly available large-scale point cloud datasets. The results show that the new method outperforms two classical methods in terms of boundary recall, under-segmentation error, and average entropy in urban scenes.

Automatic Model-Based Dataset Generation for High-Level Vision Tasks of Autonomous Driving in Haze Weather

Improving the performance of high-level computer vision tasks in adverse weather (e.g., haze) is highly critical for autonomous driving safety. However, collecting and annotating training sets for various high-level tasks in haze weather is expensive and time-consuming. To address this issue, we propose a novel haze generation model called HazeGEN by coupling the variational autoencoder (VAE) and the generative adversarial network (GAN) to automatically generate annotated datasets. The proposed HazeGEN leverages a shared latent space assumption based on an optimized encoder-decoder architecture, which guarantees high fidelity in the cross-domain image translations. To ensure that the generated image can truly facilitate high-level vision task performance, a semi-supervised learning strategy is developed for HazeGEN to efficiently learn the useful knowledge from both the real-world images (with unsupervised losses) and the synthetic images generated following the atmosphere scattering model (with supervised losses). Extensive experiments and ablation studies demonstrate that training the model with our generated haze dataset greatly improves accuracy in high-level tasks such as semantic segmentation and object detection. Furthermore, one important but under-exploited issue is investigated to find out whether the developed dataset can be a good substitute for the real ones. Results show that the generated dataset has the most similar performance to the real-world collected haze dataset on multiple challenging industrial scenarios compared with prior works.

An Object SLAM Framework for Association, Mapping, and High-Level Tasks

Object SLAM is considered increasingly significant for robot high-level perception and decision-making. Existing studies fall short in terms of data association, object representation, and semantic mapping and frequently rely on additional assumptions, limiting their performance. In this paper, we present a comprehensive object SLAM framework that focuses on object-based perception and object-oriented robot tasks. First, we propose an ensemble data association approach for associating objects in complicated conditions by incorporating parametric and nonparametric statistic testing. In addition, we suggest an outlier-robust centroid and scale estimation algorithm for modeling objects based on the iForest and line alignment. Then a lightweight and object-oriented map is represented by estimated general object models. Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching. Finally, we suggest an object-driven active exploration strategy to achieve autonomous mapping in the grasping scenario. A range of public datasets and real-world results in mapping, augmented reality, scene matching, relocalization, and robotic manipulation have been used to evaluate the proposed object SLAM framework for its efficient performance.

Robot task programming in complex task scenarios based on spatio-temporal constraint calculus

PurposeRobots face fundamental challenges in achieving reliable and stable operations for complex home service scenarios. This is one of the crucial topics of robotics methods to imitate human beings’ advanced cognitive characteristics and apply them to solve complex tasks. The purpose of this study is to enable robots to have the ability to understand the scene and task process in complex scenes and to provide a reference method for robot task programming in complex scenes.Design/methodology/approachThis paper constructs a task modeling method for robots in complex environments based on the characteristics of the perception-motor memory model of human cognition. In the aspect of episodic memory construction, the task execution process is included in the category of qualitative spatio-temporal calculus. The topology interaction of objects in a task scenario is used to define scene attributes. The task process can be regarded as changing scene attributes on a time scale. The qualitative spatio-temporal activity graphs are used to analyze the change process of the object state with time during the robot task execution. The tasks are divided according to the different values of scene attributes at different times during task execution. Based on this, in procedural memory, an object-centered motion model is developed by analyzing the changes in the relationship between objects in the scene episode by analyzing the scene changes before and after the robot performs the actions. Finally, the task execution process of the robot is constructed by alternately reconstructing episodic memory and procedural memory.FindingsTo verify the applicability of the proposed model, a scenario where the robot combines the object (one of the most common tasks in-home service) is set up. The proposed method can obtain the landscape of robot tasks in a complex environment.Originality/valueThe robot can achieve high-level task programming through the alternating interpretation of scenarios and actions. The proposed model differs from traditional methods based on geometric or physical feature information. However, it focuses on the spatial relationship of objects, which is more similar to the cognitive mechanism of human understanding of the environment.

Mechanisms of sensorimotor adaptation in a hierarchical state feedback control model of speech.

Upon perceiving sensory errors during movements, the human sensorimotor system updates future movements to compensate for the errors, a phenomenon called sensorimotor adaptation. One component of this adaptation is thought to be driven by sensory prediction errors-discrepancies between predicted and actual sensory feedback. However, the mechanisms by which prediction errors drive adaptation remain unclear. Here, auditory prediction error-based mechanisms involved in speech auditory-motor adaptation were examined via the feedback aware control of tasks in speech (FACTS) model. Consistent with theoretical perspectives in both non-speech and speech motor control, the hierarchical architecture of FACTS relies on both the higher-level task (vocal tract constrictions) as well as lower-level articulatory state representations. Importantly, FACTS also computes sensory prediction errors as a part of its state feedback control mechanism, a well-established framework in the field of motor control. We explored potential adaptation mechanisms and found that adaptive behavior was present only when prediction errors updated the articulatory-to-task state transformation. In contrast, designs in which prediction errors updated forward sensory prediction models alone did not generate adaptation. Thus, FACTS demonstrated that 1) prediction errors can drive adaptation through task-level updates, and 2) adaptation is likely driven by updates to task-level control rather than (only) to forward predictive models. Additionally, simulating adaptation with FACTS generated a number of important hypotheses regarding previously reported phenomena such as identifying the source(s) of incomplete adaptation and driving factor(s) for changes in the second formant frequency during adaptation to the first formant perturbation. The proposed model design paves the way for a hierarchical state feedback control framework to be examined in the context of sensorimotor adaptation in both speech and non-speech effector systems.

Joint data and feature augmentation for self-supervised representation learning on point clouds

To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly produce sufficient transferability to high-level tasks on different datasets. Besides, augmentations on point clouds may also change underlying semantics. To address the issues, we propose a simple but efficient augmentation fusion contrastive learning framework to combine data augmentations in Euclidean space and feature augmentations in feature space. In particular, we propose a data augmentation method based on sampling and graph generation. Meanwhile, we design a data augmentation network to enable a correspondence of representations by maximizing consistency between augmented graph pairs. We further design a feature augmentation network that encourages the model to learn representations invariant to the perturbations using an encoder perturbation. We comprehensively conduct extensive object classification experiments and object part segmentation experiments to validate the transferability of the proposed framework. Experimental results demonstrate that the proposed framework is effective to learn the point cloud representation in a self-supervised manner, and yields state-of-the-art results in the community. The source code is publicly available at: https://github.com/VCG-NJUST/AFSRL.

No-reference shadow detection quality assessment via reference learning and multi-mode exploring

Shadow detection is a common computer vision task that identifies the location of shadows. It has been used as a key primitive for many high-level tasks such as object segmentation and video tracking. Due to the complexity and variety of shadows, it is challenging to design a one-size-fits-all shadow detection algorithm in real-world scenarios. Instead, it is often necessary in practice to pick the best shadow detection algorithm for a particular vision application. While shadow detection algorithms can be assessed by comparing the detected shadow with the ground truth, such ground truth is often unavailable in real-world vision systems consistently generating new data. In this paper, we propose a no-reference shadow detection quality assessment network (NSDQA-Net) to rank shadow detection algorithms without needing the ground truth. For a given image, the proposed assessment network first learns a reference map that compensates the false positives and false negatives of multiple input shadow detection algorithms. The reference map, as well as the original image and the input shadow detection results, are then used to regress the quality scores of the shadow detection methods. Our framework supports the assessment of one, two, or multiple algorithms in a single run, making it easier for deployment in practical scenarios. Experiments results show that the proposed network achieves optimal accuracy in no-reference shadow detection assessment. Relying on it for adaptive algorithm selection also improves the performance of shadow detection using a fixed algorithm on benchmark datasets.

MODEL-AGNOSTIC META-LEARNING FOR RESILIENCE OPTIMIZATION OF ARTIFICIAL INTELLIGENCE SYSTEM

Context. The problem of optimizing the resilience of artificial intelligence systems to destructive disturbances has not yet been fully solved and is quite relevant for safety-critical applications. The task of optimizing the resilience of an artificial intelligence system to disturbing influences is a high-level task in relation to efficiency optimization, which determines the prospects of using the ideas and methods of meta-learning to solve it. The object of current research is the process of meta-learning aimed at optimizing the resilience of an artificial intelligence system to destructive disturbances. The subjects of the study are architectural add-ons and the meta-learning method which optimize resilience to adversarial attacks, fault injection, and task changes.&#x0D; Objective. Stated research goal is to develop an effective meta-learning method for optimizing the resilience of an artificial intelligence system to destructive disturbances.&#x0D; Method. The resilience optimization is implemented by combining the ideas and methods of adversarial learning, fault-tolerant learning, model-agnostic meta-learning, few-shot learning, gradient optimization methods, and probabilistic gradient approximation strategies. The choice of architectural add-ons is based on parameter-efficient knowledge transfer designed to save resources and avoid the problem of catastrophic forgetting.&#x0D; Results. A model-agnostic meta-learning method for optimizing the resilience of artificial intelligence systems based on gradient meta-updates or meta-updates using an evolutionary strategy has been developed. This method involves the use of tuner and metatuner blocks that perform parallel correction of the building blocks of a original deep neural network. The ability of the proposed approach to increase the efficiency of perturbation absorption and increase the integral resilience indicator of the artificial intelligence system is experimentally tested on the example of the image classification task. The experiments were conducted on a model with the ResNet-18 architecture, with an add-on in the form of tuners and meta-tuners with the Conv-Adapter architecture. In this case, CIFAR-10 is used as a base set on which the model was trained, and CIFAR-100 is used as a set for generating samples on which adaptation is performed using a few-shot learning scenarios. We compare the resilience of the artificial intelligence system after pre-training tuners and meta-tuners using the adversarial learning algorithm, the fault-tolerant learning algorithm, the conventional model-agnostic meta-learning algorithm, and the proposed meta-learning method for optimizing resilience. Also, the meta-learning algorithms with meta-gradient updating and meta-updating based on the evolutionary strategy are compared on the basis of the integral resilience indicator.&#x0D; Conclusions. It has been experimentally confirmed that the proposed method provides a better resilience to random bit-flip injection compared to fault injection training by an average of 5%. Also, the proposed method provides a better resilience to Ladversarial evasion attacks compared to adversarial training by an average of 4.8%. In addition, an average 4.8% increase in the resilience to task changes is demonstrated compared to conventional fine-tuning of tuners. Moreover, meta-learning with an evolutionary strategy provides, on average, higher values of the resilience indicator. On the downside, this meta-learning method requires more iterations.

The Task Decomposition and Dedicated Reward-System-Based Reinforcement Learning Algorithm for Pick-and-Place

This paper proposes a task decomposition and dedicated reward-system-based reinforcement learning algorithm for the Pick-and-Place task, which is one of the high-level tasks of robot manipulators. The proposed method decomposes the Pick-and-Place task into three subtasks: two reaching tasks and one grasping task. One of the two reaching tasks is approaching the object, and the other is reaching the place position. These two reaching tasks are carried out using each optimal policy of the agents which are trained using Soft Actor-Critic (SAC). Different from the two reaching tasks, the grasping is implemented via simple logic which is easily designable but may result in improper gripping. To assist the grasping task properly, a dedicated reward system for approaching the object is designed through using individual axis-based weights. To verify the validity of the proposed method, wecarry out various experiments in the MuJoCo physics engine with the Robosuite framework. According to the simulation results of four trials, the robot manipulator picked up and released the object in the goal position with an average success rate of 93.2%.