Search

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.

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.

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.

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.

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.

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.

Synthesizing plans for a deformable object to transit from initial observations to goal observations, both of which are represented by high-dimensional data (namely “raw” data), is challenging due to the difficulty of learning abstract state representations of raw data and transition models of continuous states and continuous actions. Even though there have been some approaches making remarkable progress regarding the planning problem, they often neglect actions between observations and are unable to generate action sequences from initial observations to goal observations. In this paper, we propose a novel algorithm framework, namely AGN. We first learn a state-abstractor model to abstract states from raw observations, a state-generator model to generate raw observations from states, a heuristic model to predict actions to be executed in current states, and a transition model to transform current states to next states after executing specific actions. After that, we directly generate plans for a deformable object by performing the four models. We evaluate our approach in continuous domains and show that our approach is effective with comparison to state-of-the-art algorithms.

This paper describes an algorithm for semantic decomposition. For that we surveys languages used to enrich contextual information with semantic descriptions. Such descriptions can be e.g. applied to enable reasoning when collecting vast amounts of information. In particular, we focus on the elements of the languages that make up their semantic. To do so, we compare the expressiveness of the well-known languages OWL, PDDL and MOF with a theory from linguistic called the Natural Semantic Metalanguage. We then analyze how the semantic of the language is build up and describe how semantic decomposition based on the semantic primes can be used for a so called mental lexicon. This mental lexicon can be used to reason upon semantic service description in the research domain of service match making.

This paper focuses on to propose how to use the techniques of Planning in Artificial Intelligence in conjunction with Ontological Reasoning in t-learning environments, in order to i) achieve automating processes such as, the presentation and adaption of the Learning Objects or the educational applications (composed of Learning Object); ii) address the differences of terms and meanings that can occur between multiple viewers, finally, iii) allow reuse of learning objects in different contexts