Task Planning Research Articles

Research on construction and task planning of police equipment support system based on background of anti-terrorism operation

Research on construction and task planning of police equipment support system based on background of anti-terrorism operation

PLACEMENT PREDICTION SYSTEM USING MACHINE LEARNING

Engineering students are not sure what they want to study after graduation. Students are confused by the many options offered by universities such as postgraduate admissions, and factors such as salaries and different jobs worsen the situation. There is no reliable platform that allows students to predict outcomes from the beginning of engineering and take action to bridge the gap and create a better future. Students studying in engineering faculties need to know where they stand compared to others and what kind of placement they will get. Training and workshops are available when students enter their final year, but these are not useful for students to plan their future studies. Student placement is one of the most important goals of the school. Schools work hard to accommodate students. The aim is to predict the current year's student placement by analyzing the data students have collected from previous years. Prediction of student performance is an important part of the study because today all student development is directly related to the student's success in tests and activities. Therefore, there are many situations where it is necessary to predict student performance, for example, identifying students who are not performing well and taking steps to improve them. There is no platform for girls to review their current work and highlight their strengths. . Currently, there are platforms that are not trained on real and complete data and cannot learn from error prediction, which reduces accuracy in the long run. Our goal is to create one. To ensure the results are acceptable, the model will be trained on real data and a large number of positive and negative results will be obtained. The model proposes an algorithm to estimate the model. Information is collected by the school where the prediction will be made, using the necessary information before the process or by examining the historical data of the previous year's students, and the placement of the current students is predicted and helps to improve the placement percentage of the students. institute. Keywords: task planning, task prediction, data decision making, machine learning algorithms, prediction prediction, student prediction, good study, student learning results, pre-process data, learning results.

Synchronous planning of initial and target positions of redundant space manipulator based on deterministic configuration tree

Planning the operating position of redundant space manipulators (RSMs) can effectively improve the performance of manipulators while improving the quality of on-orbit servicing (OOS) is of great significance. For RSM, OOS with synchronous planning of initial and target positions (ITPs) has many combinations of positions or configurations, making it difficult to apply existing methods directly. To address this problem, this study proposes a method for synchronous planning ITPs of RSMs based on a deterministic configuration tree (DCT). First, the planning area is divided into grids, with the global performance analyzed utilizing self-motion manifolds. Then, a DCT is constructed based on the analysis results of global performance. Finally, a position planning strategy of pre-planning, rewiring, and regrowth is proposed to achieve synchronized planning of the ITP of the RSM on the DCT. This method is conducted alternately in operational space and joint space. The gridding and regrowth process in operational space avoids the considerable calculation required by gridding in high-dimensional joint space and improves the efficiency of position planning. In joint space pre-planning and rewiring, the ITP is optimized with the constraint of motion planning results while position planning is realized. The simulation experiment results of the 3-degree-of-freedom (DOF) planar RSM, 4-DOF RSM, and 7-DOF RSM indicate that the proposed method reduces time consumption by 34.81%, 18.15%, and 16.26% compared to conventional methods. Furthermore, energy consumption is reduced by 30.68%, 16.93%, and 15.64%, respectively. A typical ITPs synchronous planning task is also simulated, and the results also show that this planning method can effectively optimize the ITPs and reduce energy consumption.

Repeated context-specific actions disrupt feedforward adjustments in motor commands in younger and older adults.

The flexibility of the motor system to adjust a planned action before or during the execution of the movement in response to sensory information is critical for preventing errors in motor control. As individuals age, this function declines, leading to an increased incidence of motor errors. Although sensory processing and cognitive decline are known contributors to this impairment, here, we test the hypothesis that repetition of context-specific planned actions interferes with the adjustment of feedforward motor commands. Younger and older participants were instructed to grasp and lift a T-shaped object with a concealed, off-sided center of mass and minimize its roll through anticipatory force control, relying predominantly on predictive model-driven planning (i.e., sensorimotor memories) developed through repeated lifts. We selectively manipulate the number of trial repeats with the center of mass on one side before switching it to the other side of the T-shaped object. The results showed that increasing the number of repetitions improved performance in manipulating an object with a given center of mass but led to increased errors when the object's center of mass was switched. This deleterious effect of repetition on feedforward motor adjustment was observed in younger and older adults. Critically, we show these effects on an internal model-driven motor planning task that relies predominantly on sensorimotor memory, with no differences in sensory inputs from the repetition manipulation. The findings indicate that feedforward motor adjustments are hampered by repetitive stereotyped planning and execution of motor behavior.NEW & NOTEWORTHY Adjusting planned actions in response to sensory stimuli degrades with age contributing to increased incidence of errors ranging from clumsy spills to catastrophic falls. Multiple factors likely contribute to age-related motor inflexibility, including sensory- and cognition-supporting system declines. Here, we present compelling evidence for repetition to disrupt feedforward adjusting of motor commands in younger and older adults, which suggests increases in stereotypy as a deleterious potentiator of motor control errors.

Застосування ArcGIS для оптимізації військового планування

The purpose of the article is to substantiate the advantages of using this software in comparison with a paper map. Theoretical justification of practical software studies. In modern conditions of military conflict, where strategic management and decision-making determine the effectiveness of actions on the battlefield, the use of advanced technologies becomes an integral part of the functioning of the Armed Forces. One of the key areas of innovation in this context is the use of geographic information systems (GIS), which provide unit commanders with the means to obtain, analyze, and use spatial information. This article is intended to review the practical experience of using GIS in the Armed Forces, particularly focusing on important aspects related to unit management. The basis of our research is the experience and use of the ArcGIS geoinformation system, which was used in the military. The main advantages and capabilities of this system from the point of view of the unit commander are considered, as well as how these technologies can improve leadership and interaction on the battlefield. Method. Methods of analysis of key system functions, including ArcMap, ArcScene, and other modules, were used to understand their potential for unit management. A comparison with paper maps was made: a comparative analysis of the effectiveness of the implementation of regulations on paper topographic maps and in ArcGIS software. Methods of systematization and generalization of scientific information: the advantages of 3D Visualization are highlighted, the study of ArcScene capabilities to improve understanding of the terrain in a three-dimensional format, details and advantages of using special tools for military analysis and management. The results. As a result of the study of the use of the ArcGIS geoinformation system by the unit commander, it was established that the implementation of ArcGIS significantly accelerates a number of actions related to the deployment of artillery, the time required to hit an unplanned target is reduced. Tactical planning is improved: the use of Military Tools for ArcGIS allows the commander to effectively manage and control the actions of his units and the enemy, the creation of tactical symbols and artificial maps simplifies the planning of tasks and responding to unexpected circumstances. The use of 3D Visualization in ArcScene allows you to get a three-dimensional overview of the area, improving the perception of the commander of the unit of the situation. Built-in functions such as centering and zooming in on the target make it easy to monitor objects in real time. The obtained results indicate the great potential and advantages of using the ArcGIS geographic information system in military management, which can lead to an increase in the efficiency and success of military operations. The scientific novelty is that although the ArcGIS software is in service with many NATO countries and is being implemented in the Armed Forces of Ukraine, it is determined that only this program should be used in the Armed Forces of Ukraine for digital maps and direct research that would determine the advantages of this product and analyze there are no particularities of application. The main focus of the research is on the features of ArcGIS application. The components of ArcGIS were identified, their analysis and prospects in the military sector were carried out. Practical meaning. As a result of the study of the use of the geographic information system ArcGIS by the commander of the unit, a significant potential for improving operational management and decision-making in the conditions of military operations was revealed. The use of ArcGIS allows you to speed up actions, improve tactical planning, provide three-dimensional visualization of the terrain and optimize geodetic calculations. The obtained results confirm the importance and necessity of using modern geoinformation tools in the military leadership to ensure the efficiency and success of military operations.

ARCHITECTURE OF RESIDENTIAL BUILDINGS IN ASTANA 30-s-50s XX CENTURY

The study of the architecture of residential buildings is of great scientific interest, and the topic of housing always remains one of the most relevant in the development of society. The article analyzes the features of the formation of the architecture of residential buildings in Astana in the period from 1936 to 1954, which developed under the influence of socio-economic factors, political decisions, architectural and urban planning tasks of the first half of the 20th century. The study involves the use of a method of analysis, study and field survey of residential buildings in Astana of the 1930s-1950s. The article is based on documents collected by the author in 2014-2015 from the funds of the National Archive of the Republic of Kazakhstan, the State Archive of the city of Astana, the archive of the real estate center in the city of Astana, as well as materials from field surveys and photographic recordings of residential buildings. The theoretical foundation for the study was the works of Kazakh scientists: B.A. Glaudinova, M.G. Seydalina, A.S. Karpykova, T.K. Basenova, B.U. Kuspangalieva, K.I. Samoilova, K.G. Tokzhumanova, etc. As a result of the study, three periods of formation and development of the architecture of residential buildings in Astana were identified: pre-war (1936-1940s); war period (1941-1945); post-war period (1946-1953). Within the established periods, the characteristic features of the architecture of residential buildings in the city are determined: urban planning solutions for residential development, typological methods of housing construction and architectural style.

Automated mission planning for aerial large‐scale power plant thermal inspection

AbstractClose‐range aerial inspection of large‐scale industrial facilities such as power plants is complex. It is characterized by a few areas suitable for safe landing, many obstacles, complicated radio communication, and so forth. The paper presented a new offline approach for automated mission planning in such conditions. It is based on novel concepts of ‐shaped flight profile and safe altitude map. These concepts reduce the mission planning task to a multiple traveling salesmen problem on a two‐dimensional map, which is solved using rapidly exploring random tree and genetic algorithms. A computational fluid dynamics‐based local turbulence map concept was proposed to avoid turbulence zones during inspection flights. As an advantage, this map can be generated at least 6.8× faster than the known approaches. Our new multicopter flight time prediction model provides an error of less than 10% in most cases and significantly outperforms those implemented in commercial mission planning software. All the proposed solutions were verified during a 2400‐MW power plant inspection. Our algorithms managed to plan to visit all the inspection points in six routes, approximately 15 min long each. This mission set has a comparable overall duration but better safety and even battery usage compared with the routes planned by a qualified operator. Moreover, the designed aerial inspection system provides higher quality images than manually from the ground using a thermal camera with two times higher sensitivity and equipped with more advanced optics. To our knowledge, this research is the first to report the successful implementation of autonomous unmanned aerial vehicle‐based power equipment diagnostics on a large‐scale thermal power plant.

Path Planning Method for Manipulators Based on Improved Twin Delayed Deep Deterministic Policy Gradient and RRT*

This paper proposes a path planning framework that combines the experience replay mechanism from deep reinforcement learning (DRL) and rapidly exploring random tree star (RRT*), employing the DRL-RRT* as the path planning method for the manipulator. The iteration of the RRT* is conducted independently in path planning, resulting in a tortuous path and making it challenging to find an optimal path. The setting of reward functions in policy learning based on DRL is very complex and has poor universality, making it difficult to complete the task in complex path planning. Aiming at the insufficient exploration of the current deterministic policy gradient DRL algorithm twin delayed deep deterministic policy gradient (TD3), a stochastic policy was combined with TD3, and the performance was verified on the simulation platform. Furthermore, the improved TD3 was integrated with RRT* for performance analysis in two-dimensional (2D) and three-dimensional (3D) path planning environments. Finally, a six-degree-of-freedom manipulator was used to conduct simulation and experimental research on the manipulator.

Research on Robot Path Planning Technology Combining Ant Algorithm and DWA Algorithm

Path planning is an important problem in the field of robotics, the main purpose of which is to plan the best path to avoid obstacles during the robot's action, so as to realize the robot's autonomous action. However, the traditional path planning algorithm often cannot deal with the situation of multiple dynamic obstacles, which makes the application of the robot in the actual scene is greatly limited. To solve this problem, a path planning algorithm based on ant colony algorithm and dynamic window method is proposed in this paper. This fusion algorithm can not only obtain the global optimal path by using the global known information, but also cope with the unknown dynamic obstacles to avoid collision. It can better complete the path planning task in the actual situation with superior performance, improve the safety of the robot during the execution of the task, and ensure the subsequent execution efficiency.

Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning

This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems that have been studied in the AI planning literature and explore the effect of an LLM on those tasks. We empirically demonstrate how the performance of an LLM contrasts with combinatorial search (CS) – an approach that has been traditionally used to solve model space tasks in planning, both with the LLM in the role of a standalone model space reasoner as well as in the role of a statistical signal in concert with the CS approach as part of a two-stage process. Our experiments show promising results suggesting further forays of LLMs into the exciting world of model space reasoning for planning tasks in the future.

Generalized Planning in PDDL Domains with Pretrained Large Language Models

Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.

A Goal Interaction Graph Planning Framework for Conversational Recommendation

Multi-goal conversational recommender system (MG-CRS) which is more in line with realistic scenarios has attracted a lot of attention. MG-CRS can dynamically capture the demands of users in conversation, continuously engage their interests, and make recommendations. The key of accomplishing these tasks is to plan a reasonable goal sequence which can naturally guide the user to accept the recommended goal. Previous works have demonstrated that mining the correlations of goals from the goal sequences in the dialogue corpus is helpful for recommending the goal that the user is interested in. However, they independently model correlations for each level of goal (i.e., goal type or entity) and neglect the order of goals appear in the dialogue. In this paper, we propose a goal interaction graph planning framework which constructs a directed heterogeneous graph to flexibly model the correlations between any level of goals and retain the order of goals. We design a goal interaction graph learning module to model the goal correlations and propagate goal representations via directed edges, then use an encoder and a dual-way fusion decoder to extract the most relevant information with the current goal from the conversation and domain knowledge, making the next-goal prediction fully exploit the prior goal correlations and user feedback. Finally we generate engaging responses based on the predicted goal sequence to complete the recommendation task. Experiments on two benchmark datasets show that our method achieves significant improvements in both the goal planning and response generation tasks.

On the Computational Complexity of Plan Verification, (Bounded) Plan-Optimality Verification, and Bounded Plan Existence

In this paper we study the computational complexity of several reasoning tasks centered around the bounded plan existence problem. We do this for standard classical planning and hierarchical task network (HTN) planning and each for a grounded and a lifted representation. Whereas bounded plan existence complexity is known for classical planning, it has not yet been studied for HTN planning. For plan verification, results were available for both formalisms except for the lifted HTN planning. We will present lower and upper bounds of the complexity of plan verification in lifted HTN planning and provide novel insights into its grounded counterpart, in which we show that verification is not just NP-complete in the general case, but already for a severely restricted special case. Finally, we show the complexity concerning verifying the optimality of a given plan and discuss its connection to the bounded plan existence problem.

Symbolic Reasoning Methods for AI Planning

Planning is the act of deliberative thinking before acting. It is based on a symbolic model of the world and the options to act in it, usually defined in function-free first-order logic. The task is to find a sequence of actions (a plan) that leads from a given current state to a desired goal state. The basic, purely physical description may be augmented with a partially ordered grammar-like structure (a Hierarchical Task Network or HTN), which can describe expert knowledge, or practical, legal, or operational requirements. In this talk, I will survey a variety of methods for automatically deriving plans using symbolic methods for planning -- from both my past and future research. These symbolic methods -- in some sense -- translate planning problems into other, simpler symbolic representations and reason over them to find plans. As a basis for these methods, I will firstly introduce relevant theoretical results on planning. First, I will discuss the expressive power of planning formalisms (ECAI'14, ICAPS'16) and second, the computational complexity of HTN planning and related tasks such as HTN plan verification, plan modification, and plan recognition (ICAPS'15, ICAPS'16). Based on these theoretical results, I will develop why SAT-based HTN planning is possible and how it can be implemented. To this end, I will survey several of my publications at top-tier conferences, including papers at ICAPS'17, AAAI'18, AAAI'19, IJCAI'19, AAAI'20, and ICAPS'21 -- in which I developed an highly SAT-based planner for HTN problems including the ability to find optimal plans as well as the grounding as a preprocessing step. Here I will also give an outlook on future developments and new ideas that I propose for SAT-based planning -- including the exploitation of structures in plan (e.g.\ landmarks or operator-counting constraints). Next, I will present the idea of expressing lifted classical planning as SAT (ICAPS'22). The resulting planner LiSAT was the first lifted SAT-based planner -- and proved highly efficient and outperformed all other lifted planners at the time of publication. Notably, LiSAT was the first planner (lifted or grounded) and still is the only one to solve the challenging OrganicSynthesis benchmark -- and could even prove optimality for all plans. I will also outline future ideas to further improve the efficiency of LiSAT. Lastly, I introduce the notion of planning with symbolic symbolic representations (AAAI'21 and ICAPS'23). Here one uses Binary Decision Diagrams to encode large sets of states efficiently. For expressing the additional structure encoded by HTNs, I show how BDDs can be suitably integrated into finite automata. Based on this representation, an efficient and optimal planning algorithm can be derived. Additionally, I show how this algorithm can be extended to also cover oversubscription planning.

Task Planning for Object Rearrangement in Multi-Room Environments

Object rearrangement in a multi-room setup should produce a reasonable plan that reduces the agent's overall travel and the number of steps. Recent state-of-the-art methods fail to produce such plans because they rely on explicit exploration for discovering unseen objects due to partial observability and a heuristic planner to sequence the actions for rearrangement. This paper proposes a novel task planner to efficiently plan a sequence of actions to discover unseen objects and rearrange misplaced objects within an untidy house to achieve a desired tidy state. The proposed method introduces several innovative techniques, including (i) a method for discovering unseen objects using commonsense knowledge from large language models, (ii) a collision resolution and buffer prediction method based on Cross-Entropy Method to handle blocked goal and swap cases, (iii) a directed spatial graph-based state space for scalability, and (iv) deep reinforcement learning (RL) for producing an efficient plan to simultaneously discover unseen objects and rearrange the visible misplaced ones to minimize the overall traversal. The paper also presents new metrics and a benchmark dataset called MoPOR to evaluate the effectiveness of the rearrangement planning in a multi-room setting. The experimental results demonstrate that the proposed method effectively addresses the multi-room rearrangement problem.

Dealing with Numeric and Metric Time Constraints in PDDL3 via Compilation to Numeric Planning

This paper studies an approach to planning with PDDL3 constraints involving mixed propositional and numeric conditions, as well as metric time constraints. We show how the whole PDDL3 with instantaneous actions can be compiled away into a numeric planning problem without PDDL3 constraints, enabling the use of any state-of-the-art numeric planner that is agnostic to the existence of PDDL3. Our solution exploits the concept of regression. In addition to a basic compilation, we present an optimized variant based on the observation that it is possible to make the compilation sensitive to the structure of the problem to solve; this can be done by reasoning on the interactions between the problem actions and the constraints. The resulting optimization substantially reduces the size of the planning task. We experimentally observe that our approach significantly outperforms existing state-of-the-art planners supporting the same class of constraints over known benchmark domains, settling a new state-of-the-art planning system for PDDL3.

Novelty vs. Potential Heuristics: A Comparison of Hardness Measures for Satisficing Planning

Classical planning considers a given task and searches for a plan to solve it. Some tasks are harder to solve than others. We can measure the 'hardness' of a task with the novelty width and the correlation complexity. In this work, we compare these measures. Additionally, we introduce the river measure, a new measure that is based on potential heuristics and therefore similar to the correlation complexity but also comparable to the novelty width. We show that the river measure is upper bounded by the correlation complexity and by the novelty width +1. Furthermore, we show that we can convert a planning task with a polynomial blowup of the task size to ensure that a heuristic of dimension 2 exists that gives rise to backtrack-free search.

Learning Domain-Independent Heuristics for Grounded and Lifted Planning

We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we present the first method for learning domain-independent heuristics with only the lifted representation of a planning task. We also provide a theoretical analysis of the expressiveness of our models, showing that some are more powerful than STRIPS-HGN, the only other existing model for learning domain-independent heuristics. Our experiments show that our heuristics generalise to much larger problems than those in the training set, vastly surpassing STRIPS-HGN heuristics.

რისკების რაოდენობრივი შეფასების მაჩვენებელთა სისტემა და მათი ეკონომიკური ეფექტიანობის შეფასების მეთოდები

The mathematical models of the company's optimal risk management mechanism ensure the maximum efficiency of the activity at the level of risk acceptable to the enterprise. Classification of risks into operational risk and interest risk is given. One of the possible options for determining the tasks of optimal planning of the enterprise is presented, which includes restrictions on the values of operational effect (OE) (OR). The OE (two) indicator is considered as a limitation, the normative value of which can be considered as a given value during planning. It is a multidimensional linear optimal planning problem with linear constraints. Its size is determined by the number of product types in the enterprise. We have formulated original economic-mathematical models of the distribution type, which are used to create the optimal production plan of the enterprise. In order to minimize the interest risk, we have used the duration indicator analysis method. Duration represents the elasticity of the price of a financial instrument (in this case the present value of a stream of payments) with respect to the interest rate (discount rate) and is therefore a measure of the risk of the price of the instrument changing when the interest rate changes.

Performance Task Mapping for Collaboration

As the main project, performance tasks call for broader cooperation among learning areas. This study mapped out the performance tasks assigned to students at the University of Baguio Senior High School and the common enhanced learning competencies for possible collaboration. Through a qualitative design, a semi-structured interview guide was used to gather data from 13 writers of learning modules in Grade 11 academic strands during the first semester of the school year 2022-2023. An analysis of the learning modules, course syllabi, and curriculum guides was conducted to support responses from interviews. The findings showed that the performance tasks were plans, creative presentations, and analytical documents. Simultaneously, the most common essential learning competencies were geared toward developing life and career skills, followed by learning and innovation skills. An action plan for collaborative tasks was prepared as the output of the study.