Search

Autonomous systems such as space‐ or underwater‐exploration robots or elderly people assistance robots often include an artificial intelligence (AI) planner as a component. Starting from the initial state of a system, an AI planner automatically generates sequential plans to reach final states that satisfy user‐specified goals. Generating plans having a minimum number of intermediate steps or taking the least time to execute is usually strongly desired, as these plans exhibit minimal costs. Unfortunately, testing if an AI planner generates optimal plans is almost impossible because the expected cost of these plans is usually unknown. Based on mutation adequacy test suite selection, this article proposes a novel metamorphic testing framework for detecting the lack of optimality in AI planners. The general idea is to perform a systematic but non‐exhaustive state space exploration from the initial state and to select mutant‐adequate states to instantiate new planning tasks as follow‐up test cases. We then check a metamorphic relation between the automatically generated solutions of the AI planner for these new test cases and the cost of the initial plan. We implemented this metamorphic testing framework in a tool called MorphinPlan. Our experimental evaluation shows that MorphinPlan can detect non‐optimal behaviour in both mutated AI planners and off‐the‐shelf, configurable planners. It also shows that our proposed mutation adequacy test selection strategy outperforms three alternative test generation and selection strategies, including both random state selection and random walks through the state space in terms of mutation scores. [ABSTRACT FROM AUTHOR]

Deep learning methods have recently emerged as a mechanism for generating embeddings of planning states without the need to predefine feature spaces. In this work, we advocate for an automated, cost-effective and interpretable approach to extract representative features of planning states from high-level language. We present a technique that builds up on the objects type and yields a generalization over an entire planning domain, enabling to encode numerical state and goal information of individual planning tasks. The proposed representation is then evaluated in a task for learning heuristic functions for particular domains. A comparative analysis with one of the best current sequential planner and a recent ML-based approach demonstrate the efficacy of our method in improving planner performance. [ABSTRACT FROM AUTHOR]

We study a planning problem based on Plotting, a tile-matching puzzle video game published by Taito in 1989. The objective of this turn-based game is to remove a target number of coloured blocks from a grid by sequentially shooting blocks into the same grid. Plotting features complex transitions after every shot: various blocks are affected directly, while others can be indirectly affected by gravity. We consider modelling and solving Plotting from two perspectives. The puzzle is naturally cast as an AI Planning problem and we first discuss modelling the problem using the Planning Domain Definition Language (PDDL). We find that a model in which planning actions correspond to player actions is inefficient with a grounding-based state-of-the-art planner. However, with a more fine-grained action model, where each change of a block is a planning action, solving performance is dramatically improved. We also describe two lifted constraint models, able to capture the inherent complexities of Plotting and enabling the application of efficient solving approaches from SAT and CP. Our empirical results with these models demonstrates that they can compete with, and often exceed, the performance of the dedicated planning solvers, suggesting that the richer languages available to constraint modelling can be of benefit when considering planning problems with complex changes of state. CP and SAT solvers solved almost all of the largest and most challenging instances within 1 hour, whereas the best planning approach solved approximately 30%. Finally, the flexibility provided by the constraint models allows us to easily curate interesting levels for human players. [ABSTRACT FROM AUTHOR]

SH is an open-source and domain-independent system for Hierarchical Task Network (HTN) planning, a branch of Artificial Intelligence Planning and Scheduling. SH adopts a modular architectural design that enables flexibility, extensibility, and maintainability. The planning system supports representing complex planning problems and offers various capabilities, including problem parsing, problem grounding, plan generation, and integration, making SH suitable for addressing real-world challenges. The combination of these features puts SH in a unique position, offering researchers and practitioners the power to adopt and tailor SH to meet their specific requirements coming from real-world applications.

Industry 4.0 smart production systems comprise industrial systems and subsystems that need to be integrated in such a way that they are able to support high modularity and reconfigurability of all system components. In today's industrial production, manufacturing execution systems (MESs) and supervisory control and data acquisition (SCADA) systems are typically in charge of orchestrating and monitoring automated production processes. This article explicates an MES architecture that is capable of autonomously composing, verifying, interpreting, and executing production plans using digital twins and symbolic planning methods. To support more efficient production, the proposed solution assumes that the manufacturing process can be started with an initial production plan that may be relatively inefficient but quickly found by an AI. While executing this initial plan, the AI searches for more efficient alternatives and forwards better solutions to the proposed MES, which is able to seamlessly switch between the currently executed plan and the new plan, even during production. Further, this on-the-fly replanning capability is also applicable when newly identified production circumstances/objectives appear, such as a malfunctioning robot, material shortage, or a last-minute change to a customizable product. Another feature of the proposed MES solution is its distributed operation with multiple instances. Each instance can interpret its part of the production plan, dedicated to a location within the entire production site. All of these MES instances are continuously synchronized, and the actual global or partial (i.e., from the instance perspective) progress of the production is handled in real-time within one common digital twin. This article presents three main contributions: (i) an execution system that is capable of switching seamlessly between an original and a subsequently introduced alternative production plan, (ii) on-the-fly AI-powered planning and replanning of industrial production integrated into a digital twin, and (iii) a distributed MES, which allows for running multiple instances that may depend on topology or specific conditions of a real production plant. All of these outcomes are demonstrated and validated on a use-case utilizing an Industry 4.0 testbed, which is equipped with an automated transport system and several industrial robots. While our solution is tested on a lab-sized production system, the technological base is prepared to be scaled up to larger systems. [ABSTRACT FROM AUTHOR]

Copyright of Automatisierungstechnik is the property of De Gruyter and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cyber security systems generally have the phenomena of passive defense and low-efficiency early warnings. Aiming at the above problems, this study proposes a real-time warning and plans an AI defense strategy for a cyber security system aided by a security ontology. First, we design a security defense ontology that integrates attack graphs, general purpose and domain-specific knowledge bases, and on this basis, we (1) develop an ontology-driven method of early warnings of real-time attacks, which supports non-intrusive scanning attack detection and (2) combine artificial intelligence planning and bounded rationality to recommend and automatically execute defense strategies in conventional defense scenarios. A case study has been performed, and the results indicate that: (1) the proposed method can quickly analyze network traffic data for real-time warnings, (2) the proposed method is highly feasible and has the ability to implement defense strategies autonomously, and (3) the proposed method performs the best, with a 5.4–11.4% increase in defense effectiveness against the state-of-the-art counterparts considering the APT29 attack. Overall, the proposed method holds the potential to increase the defense effectiveness against cyberattacks under high computing resource constraints. [ABSTRACT FROM AUTHOR]

Deep learning (DL) is a branch of machine learning that uses deep neural networks (DNNs) to extract knowledge from raw data. DL techniques have been used successfully in many intelligence domains, such as general approximation, computer vision, pattern recognition, and many more. Planning problems with small search space can be solved by exhaustive exploration of the search space, whereas the big search space of some problems exposes the search space explosion due to computational limitations. This subject motivates us to propose an approach using DL techniques for solving such planning problems. The proposed approach tries to learn the knowledge about the application order of actions, before solving the given (main) planning problem. Actually, it reduces the size of the given planning problem such that it can be solved by exhaustive exploration of the search space. After solving the reduced problem successfully, a DNN is learned from the explored search space. The proposed approach then employs the learned DNN to solve the given planning problem. The proposed approach deals with the planning problems specified through graph transformations language because of its superiorities compared to planning domain definition languages. The main contribution of the proposed approach is that it uses DL techniques, for the first time, to solve planning problems specified through graph transformations. Based on experimental results, the proposed approach outperforms state-of-the-art techniques in terms of execution speed, accuracy, and generating short-length plans with the exploration of lower states. [ABSTRACT FROM AUTHOR]

A service robot needs integration of symbolic reasoning for high-level task planning and geometric computation for low-level motion planning to provide services in an everyday human-living environment. For this purpose, one may develop individual modules for object recognition, knowledge inference, task planning, and motion planning, which requires a system that integrates them to provide services autonomously. In this paper, we propose a combined task-motion planning system implemented using existing open-source libraries. We implemented an action library module that specifies the relationship between the compound actions that are modeled in an AI planning language to enable abstract reasoning and the primitive actions that can be geometrically verified its feasibility. This serves as an interface between the two levels by providing a rule in which a compound action sequence obtained from task planning at the symbolic level is decomposed into a primitive action sequence capable of motion planning at the geometric level. In addition, we defined the relationship between the two types of actions in a hierarchical structure and added conditional clauses according to the task states, so that primitive actions that need to be additionally performed are automatically added to the action sequence during decomposition. This procedure enables the robot to successfully perform the task in response to an unintended change in the environment. We establish a task domain where a robot delivers an object to a human user in unexpected situations and verify the proposed method under dynamic simulation environments. [ABSTRACT FROM AUTHOR]

The technology which could make our lives prosper within the four walls could also help to create our own corner of nature nourish. In this paper, we propose a smart gardening system that utilizes the concept of the Internet of Things (IoT) [1]. The major goal of this project is to reduce water consumption when gardening and to maintain the garden remotely. Important plant data, like temperature, relative humidity, and soil moisture, are continuously stored in a relational database in this gardening system. Artificial Intelligence (AI) based planning [2] is used for watering the plants at regular intervals and providing appropriate illumination in the garden area for aesthetics and overall plant growth. Our proposed system reduces the effort due to manual intervention by around 59.3%. The real-time sensor status can be monitored which in turn allows the end-users of the garden to control the surrounding conditions optimal for plant growth, using the Telegram application. A plant recognition model has been introduced in this system, where a Convolutional Neural Network (CNN) [3] based deep learning algorithm classifies the plant categories with 95% accuracy. Moreover, an 98% accurate, deep learning-based, plant health identification model integrated with this gardening system also informs the end-user about the health of the plant.

In sustainable agriculture, intercropping systems represent a valuable approach. These systems involve placing mutually beneficial plant types in close proximity to each other, with the goal of exploiting biodiversity to reduce pesticide and water usage, as well as improve soil nutrient utilization. Despite its potential, the optimization of intercropping systems has received limited attention in previous studies. One of the first steps in the design of an intercropping system is the solution of the crop planting layout problem, which involves meeting crop demand while maximizing positive interactions between adjacent plants. We perform a complexity analysis of this problem and solve it through constraint programming, an artificial intelligence technique, which relies on automated reasoning, constraint propagation and search heuristics. To this aim, we present two constraint programming models based on integer variables and interval variables, respectively. Through a computational study on real-life instances, we examine the impact of different modelling approaches on the difficulty of solving the crop planting layout problem with standard constraint programming solvers. This research work has also provided the groundwork for a sowing robotic arm (under development), aiming to automate intercropping systems and assist farm workers. • We study the Crop Planting Layout Problem. • We perform complexity analysis and use an Artificial Intelligence solving method. • We present two constraint programming models with integer and interval variables. • The computational tests show that our models scale up to 8 species and 1080 plants. [ABSTRACT FROM AUTHOR]

Virtual reality simulation has had a significant impact on training of psychomotor surgical skills, yet there is still a lack of work on its use to teach surgical decision making. This is particularly noteworthy given the recognized importance of decision making in achieving positive surgical outcomes. With the objective of filling this gap, we have developed a system for teaching surgical decision making in the field of endodontics, by integrating a virtual reality simulation environment with a conversational intelligent tutor. This work presents SDMentor (Surgical Decision-making Mentor) – the first intelligent tutoring system for teaching surgical decision making. In this paper we focus on presenting the intelligent tutoring component of the training system. The design of the system and the teaching approaches are driven by information gained from an observational study of clinical teaching sessions. The tutoring system represents surgical actions and the procedure using a variant of the planning domain definition language (PDDL). Tutorial interaction places emphasis on teaching the rationale for decisions, as well as aspects of situation awareness. We evaluated the quality of the tutorial content by comparing it with tutorial feedback from ten experienced human tutors. We had three expert dental instructors rate the appropriateness of the tutorial feedback given by the human tutors as well as SDMentor over 20 scenarios. Bayesian analysis showed that tutoring interventions of SDMentor were significantly better than interventions by human tutors. To determine whether the expert scores may have been influenced by raters' knowledge of whether interventions came from human tutors or SDMentor, we carried out a type of Turing test. Results show that the expert raters were able to correctly guess which interventions came from SDMentor only 15% of the time, compared to a random baseline accuracy of 9%. [ABSTRACT FROM AUTHOR]

The technology which could make our lives prosper within the four walls could also help to create our own corner of nature nourish. In this paper, we propose a smart gardening system that utilizes the concept of the Internet of Things (IoT) [1]. The major goal of this project is to reduce water consumption when gardening and to maintain the garden remotely. Important plant data, like temperature, relative humidity, and soil moisture, are continuously stored in a relational database in this gardening system. Artificial Intelligence (AI) based planning [2] is used for watering the plants at regular intervals and providing appropriate illumination in the garden area for aesthetics and overall plant growth. Our proposed system reduces the effort due to manual intervention by around 59.3%. The real-time sensor status can be monitored which in turn allows the end-users of the garden to control the surrounding conditions optimal for plant growth, using the Telegram application. A plant recognition model has been introduced in this system, where a Convolutional Neural Network (CNN) [3] based deep learning algorithm classifies the plant categories with 95% accuracy. Moreover, an 98% accurate, deep learning-based, plant health identification model integrated with this gardening system also informs the end-user about the health of the plant. [ABSTRACT FROM AUTHOR]

This study proposes a Task and Motion Planning (TAMP) method with symbolic decisions embedded in a bilevel optimization. This TAMP method exploits the discrete structure of sequential manipulation for long-horizon and versatile tasks in dynamic environments. At the symbolic planning level, we propose a scalable decision-making method for long-horizon manipulation tasks using the Planning Domain Definition Language (PDDL) with causal graph decomposition. At the motion planning level, we devise a trajectory optimization (TO) approach based on the Differential Dynamic Programming (DDP) and Alternating Direction Method of Multipliers (ADMM), suitable for solving constrained, large-scale nonlinear optimization in a distributed manner. Distinct from conventional geometric motion planners, our approach generates highly dynamic manipulation motions by incorporating the full robot and object dynamics. Furthermore, in lieu of a hierarchical planning approach, we solve a holistically integrated bilevel optimization problem involving costs from both the low-level TO and the high-level search. Simulation and experimental results demonstrate dynamic manipulation for long-horizon object sorting tasks in clutter and on a moving conveyor belt.

Flexible control strategies are required in industrial scenarios to coordinate the actions of mobile manipulators (e.g., robots and humans). Temporal planning approaches can be used as such control strategies because they can generate those actions for the agents that must be executed to reach the goals, from any given state of the world. To deploy such approaches, planning models must be formulated. Although available in the literature, these models are not generic enough such that they can be easily transferred to new use cases. In this work, a generic industrial scenario is derived from real scenarios. For this scenario, a generic planning problem is developed. To demonstrate their generality, the two constructs are configured for a new scenario, where custom grippers are assembled. Lastly, a validation methodology is developed for the generic planning problem. The results show that the generic industrial scenario and the generic planning problem can be easily instantiated for new use cases, without any new modelling. Further, the proposed validation methodology guarantees that these planning problems are complete enough to be used in industrial use cases. The generic scenario, the planning problems, and the validation methodology are proposed as standards for use when deploying temporal planning in industrial scenarios with mobile manipulators. [ABSTRACT FROM AUTHOR]

Effective deployment of multi-robot teams requires solving several interdependent problems at varying levels of abstraction. Specifically, heterogeneous multi-robot systems must answer four important questions: what (task planning), how (motion planning), who (task allocation), and when (scheduling). Although there are rich bodies of work dedicated to various combinations of these questions, a fully integrated treatment of all four questions lies beyond the scope of the current literature, which lacks even a formal description of the complete problem. In this article, we address this absence, first by formalizing this class of multi-robot problems under the banner Simultaneous Task Allocation and Planning with Spatiotemporal Constraints (STAP-STC), and then by proposing a solution that we call Graphically Recursive Simultaneous Task Allocation, Planning, and Scheduling (GRSTAPS). GRSTAPS interleaves task planning, task allocation, scheduling, and motion planning, performing a multi-layer search while effectively sharing information among system modules. In addition to providing a unified solution to STAP-STC problems, GRSTAPS includes individual innovations both in task planning and task allocation. At the task planning level, our interleaved approach allows the planner to abstract away which agents will perform a task using an approach that we refer to as agent-agnostic planning. At the task allocation level, we contribute a search-based algorithm that can simultaneously satisfy planning constraints and task requirements while optimizing the associated schedule. We demonstrate the efficacy of GRSTAPS using detailed ablative and comparative experiments in a simulated emergency-response domain. Results of these experiments conclusively demonstrate that GRSTAPS outperforms both ablative baselines and state-of-the-art temporal planners in terms of computation time, solution quality, and problem coverage. [ABSTRACT FROM AUTHOR]

AI (artificial intelligence) planning is an important branch of artificial intelligence. Planning decomposition is an important topic of intelligent planning research, which plays a key role in improving planning speed and reducing the scale of planning expansion. The decomposition algorithm in intelligent planning is studied extensively and deeply, and the development history is introduced comprehensively. This paper expounds and analyzes the general forms of planning decomposition, and classifies the planning decomposition from various situations, in which key methods and popular applications of planning decomposition are mainly introduced. The main contents and advantages of the decomposition method are introduced from the aspects of traditional methods, abstraction levels, constraint satisfaction problems, sub-objective ordering, etc. Application areas include improvements in planning algorithms, multi-agent systems, software test-case generation, large Markov decision processes, etc. This paper summarizes the problems and deficiencies of the existing planning decomposition, and analyzes the future direction.

With the progress of web technologies, web services with abundant functionalities, such as video transmission, location, navigation, etc., are becoming more and more pervasive. Automatic web service composition aims to automatically combine selected elementary web services from a finite service set by matching the input and output parameters given an initial state and a goal state. Considering the end-to-end Quality-of-Service(QoS) of each web service, the service composition problem becomes an optimization problem to find the optimal solution. This paper maps this problem to an automatic planning problem and proposes Q-Graphplan based on the classical graphplan, an efficient planner for solving classical planning problems. First, we construct a planning graph based on the dependency relationships of the web services and extract essential heuristics according to the reachability analysis. Second, we convert this planning graph to a directed path generation graph. Finally, we extract the optimal solution from the path generation graph using a backward A* algorithm with the heuristics of the planning graph. Furthermore, our approach avoids redundancies when constructing the planning graph and improves the searching effectiveness in extracting solution. We conduct experiments on the WSC-2009 dataset to compare performance against present approaches, and the results show the efficiency and effectiveness of our proposed approach.

Many areas of computer science require answering questions about reachability in compactly described discrete transition systems. Answering such questions effectively requires techniques to be able to do so without building the entire system. In particular, heuristic search uses lower-bounding ("admissible") heuristic functions to prune parts of the system known to not contain an optimal solution. A prominent technique for deriving such bounds is to consider abstract transition systems that aggregate groups of states into one. The key question is how to design and represent such abstractions. The most successful answer to this question are pattern databases, which aggregate states if and only if they agree on a subset of the state variables. Merge-and-shrink abstraction is a new paradigm that, as we show, allows to compactly represent a more general class of abstractions, strictly dominating pattern databases in theory. We identify the maximal class of transition systems, which we call factored transition systems, to which merge-and-shrink applies naturally, and we show that the well-known notion of bisimilarity can be adapted to this framework in a way that still guarantees perfect heuristic functions, while potentially reducing abstraction size exponentially. Applying these ideas to planning, one of the foundational subareas of artificial intelligence, we show that in some benchmarks this size reduction leads to the computation of perfect heuristic functions in polynomial time and that more approximate merge-and-shrink strategies yield heuristic functions competitive with the state of the art. [ABSTRACT FROM AUTHOR]

Flexible control strategies are required in industrial scenarios to coordinate the actions of mobile manipulators (e.g., robots and humans). Temporal planning approaches can be used as such control strategies because they can generate those actions for the agents that must be executed to reach the goals, from any given state of the world. To deploy such approaches, planning models must be formulated. Although available in the literature, these models are not generic enough such that they can be easily transferred to new use cases. In this work, a generic industrial scenario is derived from real scenarios. For this scenario, a generic planning problem is developed. To demonstrate their generality, the two constructs are configured for a new scenario, where custom grippers are assembled. Lastly, a validation methodology is developed for the generic planning problem. The results show that the generic industrial scenario and the generic planning problem can be easily instantiated for new use cases, without any new modelling. Further, the proposed validation methodology guarantees that these planning problems are complete enough to be used in industrial use cases. The generic scenario, the planning problems, and the validation methodology are proposed as standards for use when deploying temporal planning in industrial scenarios with mobile manipulators.

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Traffic signal control is widely used at intersection to improve its operation efficiency. However, the existing signal control systems cannot satisfy the control requirements under unsaturated, saturated, and oversaturated conditions, which will induce queue spillover, even network deadlock. A signal Cooperative Control method with traffic Supply and Demand (CCSD) on a single intersection is put forward to maximize the efficiency and avoid queue spillover by the cooperation between traffic supply and demand. A general CCSD control framework is constructed by the control relationship description and discrete-time statespace equations. Furthermore, the uniform matrix description of CCSD is put forward under the framework to fast solve the problem by matrix calculation. An artificial intelligence planning model on CCSD is established by an objective function compromising between throughput and fairness to satisfy the control requirements under dynamic unknown traffic environment. CCSD is compared with the Webster method and capacity-aware back-pressure (CABP) control in the experiments by both the simulation data and investigation data under unsaturated, saturated, and oversaturated conditions. The results show that CCSD is superior to CABP control and the Webster method in the throughput, the number of stops, and stop time, and can avoid the queue spillover. Accordingly, CCSD can be used to improve the efficiency and avoid queue spillover at intersection under all traffic conditions.

America's critical infrastructure is becoming “smarter”and increasingly dependent on highly specialized computers called industrial control systems (ICS). Networked ICS components now called the industrial Internet of Things (IIoT) are at the heart of the “smart city”, controlling critical infrastructure, such as CCTV security networks, electric grids, water networks, and transportation systems. Without the continuous, reliable functioning of these assets, economic and social disruption will ensue. Unfortunately, IIoT are hackable and difficult to secure from cyberattacks. This leaves our future smart cities in a state of perpetual uncertainty and the risk that the stability of our lives will be upended. The Local government has largely been absent from conversations about cybersecurity of critical infrastructure, despite its importance. One reason for this is public administrators do not have a good way of knowing which assets and which components of those assets are at the greatest risk. This is further complicated by the highly technical nature of the tools and techniques required to assess these risks. Using artificial intelligence planning techniques, an automated tool can be developed to evaluate the cyber risks to critical infrastructure. It can be used to automatically identify the adversarial strategies (attack trees) that can compromise these systems. This tool can enable both security novices and specialists to identify attack pathways. We propose and provide an example of an automated attack generation method that can produce detailed, scalable, and consistent attack trees-the first step in securing critical infrastructure from cyberattack.

Abstract In the last decade, many approaches to automated service composition have been proposed. However, most of them do not fully exploit the opportunities offered by the Internet of Services (IoS). In this article, we focus on the dynamicity of the execution environment, that is, any change occurring at run-time that might affect the system, such as changes in service availability, service behavior, or characteristics of the execution context. We indicate that any IoS-based application strongly requires a composition framework that supports for the automation of all the phases of the composition life cycle, from requirements derivation, to synthesis, deployment and execution. Our solution to this ambitious problem is an AI planning-based composition framework that features abstract composition requirements and context-awareness. In the proposed approach most human-dependent tasks can be accomplished at design time and the few human intervention required at run time do not affect the system execution. To demonstrate our approach in action and evaluate it, we exploit the ASTRO-CAptEvo framework, simulating the operation of a fully automated IoS-based car logistics scenario in the Bremerhaven harbor.