Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 54 for “"TASK DECOMPOSITION"”.

  1. Accelerating Learning Robot Manipulation Tasks by Using Curriculum Learning and Task Decomposition

    … high-dimensional continuous robotic control tasks. The DRL methods provide a new learning paradigm that enables a robot to learn a policy end-to-end through trial-and-error with little prior knowledge. This dissertation utilizes deep reinforcement learning to solve several fundamental robotic …

    kings Repository record for Accelerating Learning Robot Manipulation Tasks by Using Curriculum Learning and Task Decomposition (opens in a new tab) Download PDF for Accelerating Learning Robot Manipulation Tasks by Using Curriculum Learning and Task Decomposition (opens in a new tab)

  2. Hierarchical task decomposition and execution for robot manipulation task using a wrist force sensor

    … 560 robot arm and its original controller. A task decomposition methodology has been developed that enables a mechanical assembly task to be subdivided into a series of executable subtasks. By applying this methodology to the assembly of a hydraulic gear pump, a library of special purpose, …

    ubc Repository record for Hierarchical task decomposition and execution for robot manipulation task using a wrist force sensor (opens in a new tab) Download PDF for Hierarchical task decomposition and execution for robot manipulation task using a wrist force sensor (opens in a new tab)

  3. A Distributed Q-learning Classifier System for task decomposition in real robot learning problems

    … on a mobile robot for the study of complex task decomposition in real robot learning environments. The Distributed Q-learning Classifier System (DQLCS) is evolved from the standard Learning Classifier System (LCS) proposed by J.H. Holland. Two of the limitations of the standard LCS are its …

    vt Repository record for A Distributed Q-learning Classifier System for task decomposition in real robot learning problems (opens in a new tab)

  4. The Effects of Job Characteristics and Task Decomposition on the Estimation of the Dollar-Value of Performance

    The purpose of this research was to investigate the influence of job characteristics and structuring aids on the accuracy and acceptance of managers' estimates of the standard deviation of job performance in dollars (i.e., SDy). The job characteristics consisted of critical incidents of work …

    odu Repository record for The Effects of Job Characteristics and Task Decomposition on the Estimation of the Dollar-Value of Performance (opens in a new tab)

  5. Curriculum learning in reinforcement learning for multi-step manipulation tasks

    … promise in robotic manipulation, yet multi-step tasks remain a persistent challenge due to sparse rewards and inefficient exploration. Multi-step manipulation tasks often require precise sequential interactions that are difficult for RL agents to learn effectively. To address this challenge, task …

    texas Repository record for Curriculum learning in reinforcement learning for multi-step manipulation tasks (opens in a new tab)

  6. Exploring the Transfer from Drills to Skills in Elite Freestyle Swimming

    Practice tasks that decompose the skill into smaller components are routinely prescribed by coaches to improve biomechanical qualities for efficient and fast swimming. Such practice tasks are typically referred to as drills and prescribed within part-whole training approaches. The Representative …

    vu-aus Download PDF for Exploring the Transfer from Drills to Skills in Elite Freestyle Swimming (opens in a new tab)

  7. Automating Hierarchical Task Network Learning

    Automating Hierarchical Task Network (HTN) learning is essential for reducing the knowledge engineering burden in automated planning systems. Traditional HTN learning techniques, like HTN-MAKER, face challenges related to scalability, efficacy, and the need for manual input. This dissertation fully …

    maryland Repository record for Automating Hierarchical Task Network Learning (opens in a new tab)

  8. Slaugytojų saviveiksmingumas ir sąmoninga praktika klinikinėje veikloje /

    … only sometimes, in complex situations, use the task decomposition principle (4.95±0.94). The greater the nurses' work experience, the more nurses consciously maintain the congruence of Goals and activities (r=0.226; p=0.037). Nurses' self-efficacy is higher than average (32.08±4.85). Nurses' …

    vilnius Repository record for Slaugytojų saviveiksmingumas ir sąmoninga praktika klinikinėje veikloje / (opens in a new tab)

  9. Telerobotic Sensor-based Tool Control Derived From Behavior-based Robotics Concepts

    … { page: Section1; }</p> <p>Teleoperated task execution for hazardous environments is slow and requires highly skilled operators. Attempts to implement telerobotic assists to improve efficiency have been demonstrated in constrained laboratory environments but are not being used in the …

    utk-theses Repository record for Telerobotic Sensor-based Tool Control Derived From Behavior-based Robotics Concepts (opens in a new tab)

  10. COGNITIVE MODELING FOR HUMAN FACTORS TESTING: DEVELOPING A STRUCTURED TASK ANALYSIS FRAMEWORK FOR DESIGNERS

    … root causes of use error. Existing Cognitive Task Analysis (CTA) methods offer structured approaches for modeling cognition, but these methods were designed for experts with a background in cognitive sciences. These methods also lack standardized syntax for describing the tasks, a discrete …

    maryland Repository record for COGNITIVE MODELING FOR HUMAN FACTORS TESTING: DEVELOPING A STRUCTURED TASK ANALYSIS FRAMEWORK FOR DESIGNERS (opens in a new tab)

  11. Ant Colony Optimisation for Multi-Uncrewed Ground Vehicle Mission Planning

    … of mission planning are NP-hard and include task allocation, scheduling, and motion planning. Swarm Optimisation Algorithms (SOAs) have attracted increasing attention due to their superiority in addressing NP-hard problems. This thesis contributes a comprehensive evaluation of SOAs, design of …

    unsw Repository record for Ant Colony Optimisation for Multi-Uncrewed Ground Vehicle Mission Planning (opens in a new tab)

  12. Evaluation of alternative idea generation techniques in audit fraud risk assessments.

    … giving additional brainstorming guidelines and task decomposing (in addition to the original brainstorming guidelines), improve performance compared to having only the original brainstorming guidelines. Both the additional brainstorming guidelines and the task decomposition treatments generated …

    unsw Repository record for Evaluation of alternative idea generation techniques in audit fraud risk assessments. (opens in a new tab)

  13. A GENERAL ALGORITHM FOR DETERMINING LIKELIHOOD RATIOS IN CASCADED INFERENCE

    In cascaded inference tasks there is not a direct logical connection between an observable event (datum) and the hypothesis of interest. Instead there is interposed at least one logical reasoning stage, consisting of intervening variables or intermediate event states. This paper is concerned with …

    rice Repository record for A GENERAL ALGORITHM FOR DETERMINING LIKELIHOOD RATIOS IN CASCADED INFERENCE (opens in a new tab)

  14. Knowledge intensive natural language generation with revision

    … Two problems with this architecture are poor task decomposition and the lack of interaction between conceptual and stylistic decisions making. A revision architecture operating in a knowledge intensive environment is proposed as a means to deal with these two problems. In a revision system. …

    vt Repository record for Knowledge intensive natural language generation with revision (opens in a new tab)

  15. TASK ASSIGNMENT IN VARIABLE CAPACITY DRONE SWARMS USING DYNAMICALLY STABLE MATCHING

    … to efficiently allocate system resources through task decomposition and subtask assignment. As the general task assignment problem is nondeterministic polynomial-time hard, approximation techniques must be employed to derive near-optimal solutions in a timely manner. Currently, auction and …

    nps Repository record for TASK ASSIGNMENT IN VARIABLE CAPACITY DRONE SWARMS USING DYNAMICALLY STABLE MATCHING (opens in a new tab)

  16. Evaluating modular neuroevolution in robotic keepaway soccer

    Keepaway is a simpler subtask of robot soccer where three `keepers' attempt to keep possession of the ball while a `taker' tries to steal it from them. This is a less complex task than full robot soccer, and lends itself well as a testbed for multi-agent systems. This thesis does a comprehensive …

    texas Repository record for Evaluating modular neuroevolution in robotic keepaway soccer (opens in a new tab)

  17. The Impact Of Experience Replay Buffers On Catastrophic Forgetting Within Proximal Policy Optimization

    … the effects of catastrophic forgetting via task decomposition, rehearsal, and layered learning. However, critical agent knowledge is still susceptible to being driven out of these agents with state-of-the-art techniques. This research explores how prioritized experience replay buffers impact …

    ucf Repository record for The Impact Of Experience Replay Buffers On Catastrophic Forgetting Within Proximal Policy Optimization (opens in a new tab)

  18. Applying failure modes, effects, and criticality analysis and human reliability analysis techniques to improve safety design of work process in Singapore Armed Forces

    … They include vague categorization to guide task decomposition, a generic 5-M factor hazard identification method, and insufficient resolution to prioritize risks. This thesis studies two alternative risk assessment techniques: Process Failure Modes, Effects, and Criticality Analysis (PFMECA) …

    nps Repository record for Applying failure modes, effects, and criticality analysis and human reliability analysis techniques to improve safety design of work process in Singapore Armed Forces (opens in a new tab)

  19. A Constraints-Led Approach to Acquiring the Power Clean

    … common method involves explicit instruction and task decomposition. However, contemporary skill acquisition theory is in conflict with this explicit and reductionist approach. Through three case studies the examination of individualised task constraints were used to reshape the state space of the …

    auckland-tech Repository record for A Constraints-Led Approach to Acquiring the Power Clean (opens in a new tab)

  20. COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS

    … However, they struggle with compositional tasks in reasoning and planning. In those tasks, evidence is scattered across multiple sources and needs to be considered together simultaneously or connected in a multi-step process to solve the task. This thesis addresses the compositionality by …

    nus Repository record for COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS (opens in a new tab) Download file for COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS (opens in a new tab)

Page 1 of 3