Explore the vast range of titles available.

This paper presents a novel object transportation method using deep reinforcement learning (DRL) and the task space decomposition (TSD) method. Most previous studies on DRL-based object transportation worked well only in the specific environment where a robot learned how to transport an object. Another drawback was that DRL only converged in relatively small environments. This is because the existing DRL-based object transportation methods are highly dependent on learning conditions and training environments; they cannot be applied to large and complicated environments. Therefore, we propose a new DRL-based object transportation that decomposes a difficult task space to be transported into simple multiple sub-task spaces using the TSD method. First, a robot sufficiently learned how to transport an object in a standard learning environment (SLE) that has small and symmetric structures. Then, a whole-task space was decomposed into several sub-task spaces by considering the size of the SLE, and we created sub-goals for each sub-task space. Finally, the robot transported an object by sequentially occupying the sub-goals. The proposed method can be extended to a large and complicated new environment as well as the training environment without additional learning or re-learning. Simulations in different environments are presented to verify the proposed method, such as a long corridor, polygons, and a maze.

In real-world applications, multiple robots need to be dynamically deployed to their appropriate locations as teams while the distance cost between robots and goals is minimized, which is known to be an NP-hard problem. In this paper, a new framework of team-based multi-robot task allocation and path planning is developed for robot exploration missions through a convex optimization-based distance optimal model. A new distance optimal model is proposed to minimize the traveled distance between robots and their goals. The proposed framework fuses task decomposition, allocation, local sub-task allocation, and path planning. To begin, multiple robots are firstly divided and clustered into a variety of teams considering interrelation and dependencies of robots, and task decomposition. Secondly, the teams with various arbitrary shape enclosing intercorrelative robots are approximated and relaxed into circles, which are mathematically formulated to convex optimization problems to minimize the distance between teams, as well as between a robot and their goals. Once the robot teams are deployed into their appropriate locations, the robot locations are further refined by a graph-based Delaunay triangulation method. Thirdly, in the team, a self-organizing map-based neural network (SOMNN) paradigm is developed to complete the dynamical sub-task allocation and path planning, in which the robots are dynamically assigned to their nearby goals locally. Simulation and comparison studies demonstrate the proposed hybrid multi-robot task allocation and path planning framework is effective and efficient.

We conduct three behavioral laboratory experiments to compare newsvendor order decisions placed directly to order decisions submitted in a decomposed way by soliciting point forecasts, uncertainty estimates, and service-level decisions. Decomposing order decisions in such a way often follows from organizational structure and can lead to performance improvements compared with ordering directly. However, we also demonstrate that if the critical ratio is below 50%, or if the underlying demand uncertainty is too high, task decomposition may not be preferred to direct ordering. Under such conditions, decision makers are prone to set service levels too high or to suffer from excessive random judgment error, which reduces the efficacy of task decomposition. We further demonstrate that if accompanied by decision support in the form of suggested quantities, task decomposition becomes the better-performing approach to newsvendor decision making more generally. Decision support and task decomposition therefore appear as complementary methods to improve decision performance in the newsvendor context. This paper was accepted by Serguei Netessine, operations management .

To address the challenges of low efficiency and high redundancy in massive data acquisition within the Power Internet of Things (PIoT), existing systems suffer from redundant acquisition and resource waste due to insufficient identification of overlapping regions, while traditional scheduling mechanisms struggle to balance task priorities with dynamic scenario requirements. This paper proposes a data acquisition task decomposition and scheduling method optimized through overlapping data analysis. Initially, hash functions are employed to rapidly identify overlapping regions in target data clusters, with a “hyperlink anchoring” mechanism implemented to eliminate redundant data acquisition. Subsequently, a task decomposition model centered on total cost minimization is formulated, prioritizing the allocation of tasks with maximum overlapping regions to optimize resource distribution strategies. Finally, a multi-dimensional dynamic priority scheduling model is developed, integrating task criticality and temporal characteristics to dynamically adjust execution sequences, ensuring high-value tasks achieve priority completion. Case study results demonstrate that the proposed method improves task efficiency by 18.7% compared to baseline methods, while maintaining operational effectiveness under high-load scenarios.

Cognitive scientists have discovered normative and heuristic principles that capture human subgoal preferences when partitioning problems into smaller ones. However, it remains unclear where such preferences come from and why they tend to be both effective and efficient. In this work, we study the processes through which these preferences may be implicitly encoded over learning as learners improve towards optimal traversals. We build on the graph-based environments from prior work and use neural networks as model learners to test if learning shortest-path traversal can lead to human-like path decomposition. We find that simple transformer models develop a preference for paths containing nodes that occur frequently on the shortest paths, consistent with human subgoal preferences found in prior work. This preference is observed when models solve shortest path traversals for unseen problems in both known graphs and new graphs, demonstrating that human-like subgoal preferences can arise without requiring explicit preference computation or exhaustively searching over all possible paths. The same preference does not emerge when models learn to perform random or Hamiltonian traversals. Our findings are robust across several transformer variants as well as recurrent neural networks, suggesting they depend more on the data distribution than the network architecture.

Large language models (LLMs) have shown remarkable capabilities in solving complex tasks. Recent work has explored decomposing such tasks into subtasks with independent contexts. However, some contextually related subtasks may encounter information loss during execution, leading to redundant operations or execution failures. To address this issue, we propose a training-free framework with an interaction mechanism, which enables a subtask to query specific information or trigger certain actions in completed subtasks by sending requests. To implement interaction, we introduce a subtask trajectory memory to enable the resumption of completed subtasks upon receiving interaction requests. Additionally, we propose a new action during execution, which generates a concise and precise description of the execution process and outcomes of a subtask, to assist subsequent subtasks in determining interaction targets and requests. Our framework achieves 46.0% and 52.6% success rates on WebShop and HotpotQA, outperforming the strong baselines by 1.0 and 2.6 absolute percentage points, respectively.

As the number and variety of remote sensing satellites continue to grow, user demands are becoming increasingly complex and diverse. Concurrently, there is an escalating requirement for timeliness in satellite observations, thereby augmenting the complexity of task processing and resource allocation. In response to these challenges, this paper proposes an innovative method for dynamic task planning in multi-source remote sensing satellite cooperative observations tailored to complex scenarios. In the task processing phase, this study develops a preprocessing model suitable for various types of targets, enabling the decomposition of complex scenes into multiple point targets for independent satellite observation, thereby reducing the complexity of the problem. In the resource allocation phase, a dynamic task planning algorithm for multi-satellite cooperative observation is designed to achieve dynamic and optimized scheduling of the processed point targets, catering to the needs of multi-source remote sensing satellites. Empirical validation demonstrated that this method effectively implements dynamic adjustment plans for point targets, comprehensively optimizing the number of observation targets, computation time, task priority, and satellite resource utilization, significantly enhancing the dynamic observation efficiency of remote sensing satellites.

Decomposing complex real-world tasks into simpler subtasks and devising a subtask execution plan is critical for humans to achieve effective decision-making. However, replicating this process remains challenging for AI agents and naturally raises two questions: 1) How to extract discriminative knowledge representation from priors? 2) How to develop a rational plan to decompose complex problems? To address these issues, we introduce a groundbreaking framework that incorporates two main contributions. First, our multiple-encoder and individual-predictor regime goes beyond traditional architectures to extract nuanced task-specific dynamics from datasets, enriching the feature space for subtasks. Second, we innovate in planning by introducing a top-K subtask planning tree generated through an attention mechanism, which allows for dynamic adaptability and forward-looking decision-making. Our framework is empirically validated against challenging benchmarks BabyAI including multiple combinatorially rich synthetic tasks (e.g., GoToSeq, SynthSeq, BossLevel), where it not only outperforms competitive baselines but also demonstrates superior adaptability and effectiveness in complex task decomposition.

With the continuous emergence of intelligent network applications and complex tasks for mobile terminals, the traditional single computing model often fails to meet the greater requirements of computing and network technology, thus promoting the formation of a new computing power network architecture, of ‘cloud, edge and end’ three-level heterogeneous computing. For complex divisible computing tasks in the network, task decomposition and offloading help to realize a distributed execution of tasks, thus reducing the overall running time and improving the utilization of fragmented resources in the network. However, in the process of task decomposition and offloading, there are problems, such as there only being a single method of task decomposition; that too large or too small decomposition granularity will lead to an increase in transmission delay; and the pursuit of low-delay and low-energy offloading requirements. Based on this, a complex divisible computing task decomposition and offloading scheme is proposed. Firstly, the computational task is decomposed into multiple task elements based on code partitioning, and then a density-peak-clustering algorithm with an improved adaptive truncation distance and clustering center (ATDCC-DPC) is proposed to cluster the task elements into subtasks based on the task elements themselves and the dependencies between the task elements. Secondly, taking the subtasks as the offloading objects, the improved Double Deep Q-Network subtask offloading algorithm (ISO-DDQN) is proposed to find the optimal offloading scheme that minimizes the delay and energy consumption. Finally, the proposed algorithms are verified by simulation experiments, and the scheme in this paper can effectively reduce the task delay and energy consumption and improve the service experience.

Complex task crowdsourcing (CTC) integrates distributed talent, knowledge, and ideas into innovation via the web; however, task decomposition remains a critical challenge. While existing studies focus primarily on workflow management for specific tasks, they leave a gap in decomposing more complex, creative tasks, which are characterized by the absence of objective ground truths, nonlinear dependencies, and non-sequential processes. To address this gap, we propose a novel integrated task decomposition framework for CTC that comprises three interconnected components. First, primary decomposition considers knowledge reuse by identifying similar past task decomposition schemes to inform the initial breakdown. Second, modifications to the scheme are guided by work breakdown structure (WBS)-based principles, which also serve as a foundation when no prior knowledge is available. Third, to enhance executability, a task package model is proposed to combine subtasks that share common resources, thereby reducing coordination costs and avoiding waste of workers’ capabilities. To solve this model, we develop an improved non-dominated sorting genetic algorithm (NSGA-II) to generate the final decomposition scheme. A case study from ZBJ.COM validates the feasibility and effectiveness of the proposed framework. Experimental results demonstrate that, compared to baseline algorithms, the improved NSGA-II better balances conflicting objectives and generates non-dominated solution sets with higher diversity and more uniform distribution.