Search results

Autonomous robots must be able to understand long-term manipulation tasks described by humans and perform task analysis and planning based on the current environment in a variety of scenes, such as daily manipulation and industrial assembly. However, both classical task and motion planning algorithms and single data-driven learning planning methods have limitations in practicability, generalization and interpretability. The purpose of this work is to overcome the limitations of the above methods and achieve generalized and explicable long-term robot manipulation task planning.

The authors propose a planning method for long-term manipulation tasks that combines the advantages of existing methods and the prior cognition brought by the knowledge graph. This method integrates visual semantic understanding based on scene graph generation, regression planning based on deep learning and multi-level representation and updating based on a knowledge base.

The authors evaluated the capability of this method in a kitchen cooking task and tabletop arrangement task in simulation and real-world environments. Experimental results show that the proposed method has a significantly improved success rate compared with the baselines and has excellent generalization performance for new tasks.

The authors demonstrate that their method is scalable to long-term manipulation tasks with varying complexity and visibility. This advantage allows their method to perform better in new manipulation tasks. The planning method proposed in this work is meaningful for the present robot manipulation task and can be intuitive for similar high-level robot planning.

The purpose of this paper is to present a novel automatic planning and coordinated control method of redundant dual‐arm space robot for inner space‐station operation based on multiple sensors information by stages.

In order to improve the coordinated control capability of dual‐arm robot system, a four‐layer hierarchical control structure is designed based on the theory of centralization and decentralization. At the high‐level planning of dual‐arm system, a task decomposition strategy based on task knowledge and a task allocation strategy in terms of the robotic capability are proposed, respectively. Moreover, a control method by stages based on the information of multiple sensors is introduced to object recognition, task planning, path planning and trajectory planning. Finally, a 3D simulation and experiment of screwing nut and bolt are implemented on a dual‐arm robot system, and the feasibility and applicability of this control strategy are verified.

The automatic planning can be accomplished by means of sensors information by stages, and by this method, the autonomy and intelligence of dual‐arm space robot system can be further improved.

A new automatic planning strategy integrated with multiple sensors information by stages is proposed, and can be implemented on a dual‐arm robot system for inner space‐station operations. This method specializes in heterogeneous dual‐arm robot system.

A task decomposition strategy based on task knowledge and a task allocation strategy in terms of the robotic capability are proposed, respectively. Moreover, a control method by stages based on the information of multiple sensors is introduced to object recognition, task planning, path planning and trajectory planning of dual‐arm robot system.

This paper aims to innovatively propose to improve the efficiency of satellite observation and avoid the waste of satellite resources, a genetic algorithm with entropy operator (GAE) of synthetic aperture radar (SAR) satellites’ task planning algorithm.

The GAE abbreviated as GAE introduces the entropy value of each orbit task into the fitness calculation of the genetic algorithm, which makes the orbit with higher entropy value more likely to be selected and participate in the remaining process of the genetic algorithm.

The simulation result shows that in a condition of the same calculate ability, 85% of the orbital revisit time is unchanged or decreased and 30% is significantly reduced by using the GAE compared with traditional task planning genetic algorithm, which indicates that the GAE can improve the efficiency of satellites’ task planning.

The GAE is an optimization of the traditional genetic algorithm. It combines entropy in thermodynamics with task planning problems. The algorithm considers the whole lifecycle of task planning and gets the desired results. It can greatly improve the efficiency of task planning in observation satellites and shorten the entire task execution time. Then, using the GAE to complete SAR satellites’ task planning is of great significance in reducing satellite operating costs and emergency rescue, which brings certain economic and social benefits.

This paper aims to introduce the human arm movement primitive (HAMP) to express and plan the motions of anthropomorphic arms. The task planning method is established for the minimum task cost and a novel human-like motion planning method based on the HAMPs is proposed to help humans better understand and plan the motions of anthropomorphic arms.

The HAMPs are extracted based on the structure and motion expression of the human arm. A method to slice the complex tasks into simple subtasks and sort subtasks is proposed. Then, a novel human-like motion planning method is built through the selection, sequencing and quantification of HAMPs. Finally, the HAMPs are mapped to the traditional joint angles of a robot by an analytical inverse kinematics method to control the anthropomorphic arms.

For the exploration of the motion laws of the human arm, the human arm motion capture experiments on 12 subjects are performed. The results show that the motion laws of human arm are reflected in the selection, sequencing and quantification of HAMPs. These motion laws can facilitate the human-like motion planning of anthropomorphic arms.

This study presents the HAMPs and a method for selecting, sequencing and quantifying them in human-like style, which leads to a new motion planning method for the anthropomorphic arms. A similar methodology is suitable for robots with anthropomorphic arms such as service robots, upper extremity exoskeleton robots and humanoid robots.

The product family assembly line (PFAL) is a mixed model-assembly line, which is widely used in mass customization and intelligent manufacturing. The purpose of this paper is to study the problem of PFAL, a flexible (evolution) planning method to respond to product evolution for PFAL, to focus on product data analysis and evolution planning method.

The evolution balancing model for PFAL is established and an improved NSGA_II (INSGA_II) is proposed. From the perspective of data analysis, dynamic characteristics of PFAL are researched and analyzed. Especially the tasks, which stability is considered, can be divided into a platform and individual task. In INSGA_II algorithm, a new density selection and a decoding method based on sorting algorithms are proposed to compensate for the lack of traditional algorithms.

The effectiveness and feasibility of the method are validated by an example of PFAL evolution planning for a family of similar mechanical products. The optimized efficiency is significantly improved using INSGA_II proposed in this paper and the evolution planning model proposed has a stronger ability to respond to product evolution, which maximizes business performance over an effective period of time.

The assembly line designers and managers in discrete manufacturing companies can obtain an optimal solution for PFAL planning through the evolution planning model and INSGA-II proposed in this paper. Then, this planning model and optimization method have been successfully applied in the production of small wheel loaders.

This paper justifies the need for moving indirect production planning costing in the book manufacturing industry toward direct production planning costing. Principles of activity based costing are utilized to accomplish this feat. This paper develops a methodology to break down the various tasks required in planning a job for production in the book manufacturing industry and to apply time measurement to these activities. These time measurements can then be used to individually cost the planning process of any book manufacturing company. The methodology is tested and justified through extensive data collection and application in a major book manufacturing firm. Thus, this industry can now effectively apply cost to activities of the planning process for each individual job as a direct cost, rather than an indirect one.

This chapter is aimed at contributing to the question of how institutional reforms affect multi-level governance (MLG) capacities and thus the performance of public task fulfillment with a particular focus on the local level of government in England, France, and Germany.

Drawing on concepts of institutional evaluation, we analytically distinguish six dimensions of impact assessment: vertical coordination; horizontal coordination; efficiency/savings; effectiveness/quality; political accountability/democratic control; equity of service standards. Methodologically, we rely on document analysis and expert judgments that could be gleaned from case studies in the three countries and a comprehensive evaluation of the available secondary data in the respective national and local contexts.

Institutional reforms in the intergovernmental setting have exerted a significant influence on task fulfillment and the performance of service delivery. Irrespective of whether MLG practice corresponds to type I or type II, task devolution (decentralization/de-concentration) furthers the interlocal variation and makes the equity of service delivery shrink. There is a general tendency of improved horizontal/MLG type I coordination capacities, especially after political decentralization, less in the case of administrative decentralization. However, decentralization often entails considerable additional costs which sometimes overload local governments.

The distinction between multi-purpose territorial organization/MLG I and single-purpose functional organization/MLG II provides a suitable analytical frame for institutional evaluation and impact assessment of reforms in the intergovernmental setting. Furthermore, comparative research into the relationship between MLG and institutional reforms is needed to reveal the explanatory power of intervening factors, such as the local budgetary and staff situation, local policy preferences, and political interests in conjunction with the salience of the transferred tasks.

The findings provide evidence on the causal relationship between specific types of (vertical) institutional reforms, performance, and task-related characteristics. Policy-makers and government actors may use this information when drafting institutional reform programs and determining the allocation of public tasks in the intergovernmental setting.

In general, the euphoric expectations placed upon decentralization strategies in modern societies cannot straightforwardly be justified. Our findings show that any type of task transfer to lower levels of government exacerbates existing disparities or creates new ones. However, the integration of tasks within multi-functional, politically accountable local governments may help to improve MLG type I coordination in favor of local communities and territorially based societal actors, while the opposite may be said with regard to de-concentration and the strengthening of MLG type II coordination.

The chapter addresses a missing linkage in the existing MLG literature which has hitherto predominantly been focused on the political decision-making and on the implementation of reforms in the intergovernmental settings of European countries, whereas the impact of such reforms and of their consequences for MLG has remained largely ignored.

This study explores how a hospital works, which is important for further enhancing hospital performance. Following the introduction of a Hospital Planning Centre (HPC), changes are explored in a hospital in terms of integration (the coordination and alignment of tasks), differentiation (the extent to which tasks are segmented into subsystems), rules, coordination mechanisms and hospital performance.

A case study was conducted examining the hospital’s social network, rules, coordination mechanisms and performance both before and after the introduction of the HPC. All planning and execution tasks for surgery patients were studied using a naturalistic inquiry and mixed-method approach.

After the introduction of the HPC, the overall network structure and coordination mechanisms and coordination mechanisms remained largely the same. Integration and certain rules changed for specific planning tasks. Differentiation based on medical discipline remained. The number of local rules decreased and hospital-wide rules increased, and these remained largely in people’s minds. Coordination mechanisms remained largely unchanged, primarily involving mutual adjustment and standardization of work both before and after the introduction of the HPC. Overall, the hospital’s performance did not change substantially. The findings suggest that integration seems to “emerge” instead of being designed. Hospitals could benefit, we argue, from a more conscious system-wide approach that includes collective learning and information sharing.

This exploratory study provides in-depth insight into how a hospital works, yielding important knowledge for further research and the enhancement of hospital performance.

Building information modelling (BIM) and radio frequency identification (RFID) technologies have been extensively explored to improve supply chain visibility and coordination of material flow processes, particularly in the pursuit of Industry 4.0. It remains challenging, however, to effectively use these technologies to enable the precise and reliable coordination of material flow processes. This paper aims to propose a new workflow designed to include the use of detailed look-ahead plans when using BIM and RFID technologies, which can accurately track and match both the dynamic site needs and supply status of materials.

The new workflow is designed according to lean theory and is modeled using business process modeling notation. To digitally support the workflow, an integrated BIM-RFID database system is constructed that links information on material demands with look-ahead plans. The new workflow is then used to manage material flows in the erection of an office building with prefabricated columns. The performance of the new workflow is compared with that of a traditional workflow, using discrete event simulations. The input for the simulations was derived from expert opinion in semi-structured interviews.

The new workflow enables contractors to better observe on-site status and differences between the actual and planned material requirements, as well as to alert suppliers if necessary. The simulation results indicate that the new workflow has the potential to reduce the duration of the material flow processes by 16.1% compared with the traditional workflow.

The new workflow is illustrated using a real-world-like situation with input data based on expert opinion. Although the workflow shows potential, it should be tested on a real-world site.

The new workflow allows project participants to combine detailed near-term look-ahead plans with BIM and RFID technologies to better manage material flow processes. It is particularly useful for the management of engineer-to-order components considering the dynamic site progress.

The research improves on existing research focused on using BIM and RFID technologies to improve material flow processes by showing how the workflow can be adapted to use detailed look-ahead plans. It reinforces data-driven construction material management practices through improved visibility and reliability in planning and control of material flow processes.

Health care is an example of an organization where the needs of potential clients are much greater than the capabilities of the service delivery system. The implementation of any medical procedure, as well as the provision of any service, just like the manufacturing of any product, can be decomposed into a series of tasks. The purpose of this paper is to propose a model for measuring the effectiveness of quality assurance tasks in health-care delivery processes.

The authors analyze a system of factors that affect the implementation of tasks in a process. In their considerations, they have focused on four areas of science that describe conditions that are related to the implementation of tasks: Scheduling as a methodology for allocating resources to perform tasks; Capacity planning as a methodology for assigning values to given resources expressed by the number of tasks that can be executed with the resources; Queueing theory, used as a methodology for describing phenomena in which not all planned tasks are performed within the prescribed specification limits; and Quality management, as a methodology to ensure appropriate conditions for completing tasks (CCTs), where CCT is a representation of parameters of casual relationship between variables.

The authors show that the effectiveness of executing any scheduled tasks in the process is determined by the difference between the capacity of resources allocated (at a given time interval) and the number of tasks planned to be carried out at that time. The CCT conditions determine the level of capacity of the fixed amount of resources. It is shown that their deviation from the reference CCT specification may cause the nominally correct amount of resources be either too small (causing queue formation and longer wait time in hospitals) or too large to contribute to the waste in the system by creating idle capacity.

The scope of application of the model is wide. It covers tasks performed with different degrees of uncertainties regarding the capacity of resources. It applies in all areas of health care where unlike manufacturing, the services delivered and the tasks performed in the health-care delivery system are seldom identical. Every patient is treated differently than the one waiting next in line. The workloads are pre-arranged in the order they are needed and completed in accordance with the FI-FO (first in-first out) principle. The model presented in this paper makes it possible to better understand the mechanism of effectiveness and efficiency improvement and the role of humans as a specific carrier of capacity.

As most of the health-care organizations are still stuck in the soft side of quality assurance, there has been little research conducted to test the applicability of well-known productions/operation management methodologies and theories benefitting health-care systems. The formulation of a reference point of CCT in this study is to serve as a stabilizing control point with the same connotation as that of a central reference line in the statistical process control chart. The correct capacity planning is needed to determine with a high degree of probability of success in implementation of all tasks to assure quality all the time.