Artificial Intelligence Planning Research Articles

Supporting Upper Elementary Students in Learning AI Concepts with Story-Driven Game-Based Learning

Artificial intelligence (AI) is quickly finding broad application in every sector of society. This rapid expansion of AI has increased the need to cultivate an AI-literate workforce, and it calls for introducing AI education into K-12 classrooms to foster students’ awareness and interest in AI. With rich narratives and opportunities for situated problem solving, story-driven game-based learning offers a promising approach for creating engaging and effective K-12 AI learning experiences. In this paper, we present our ongoing work to iteratively design, develop, and evaluate a story-driven game-based learning environment focused on AI education for upper elementary students (ages 8 to 11). The game features a science inquiry problem centering on an endangered species and incorporates a Use-Modify-Create scaffolding framework to promote student learning. We present findings from an analysis of data collected from 16 students playing the game's quest focused on AI planning. Results suggest that the scaffolding framework provided students with the knowledge they needed to advance through the quest and that overall, students experienced positive learning outcomes.

Digital workflow for printability checking and prefabrication in robotic construction 3D printing based on Artificial Intelligence planning

This paper introduces an innovative digital workflow for printability checking and prefabrication in robotic construction 3D printing based on Artificial Intelligence (AI) planning techniques. The proposed method generates operational sequences for a robotic manipulator tasked with concrete 3D printing by utilizing Planning Domain Definition Language (PDDL) 2.1-based AI planners. The planned sequences consider diverse geometry specifications, aligning with printability checks and prefabrication requisites. The sequences can then be executed in a robotic simulation environment, allowing operators to assess the 3D printing process in every aspect before real-world deployment, and potentially avoiding costly mistakes and the waste of resources. Compared to existing methods, the use of AI planning makes our approach more modular and easy to adapt across a variety of robotic platforms, diverse designs, materials, and printing conditions; and it is released as open-source software to the benefit of the community. The proposed method was tested by processing objects with multiple geometries and a varying number of printing layers, and by employing two different PDDL planners. Results prove the viability of the approach but also hint at possible scalability limitations for complex geometries that involve a large number of edges to be printed.

Mirage: cyber deception against autonomous cyber attacks in emulation and simulation

AbstractAs the capabilities of cyber adversaries continue to evolve, now in parallel to the explosion of maturing and publicly-available artificial intelligence (AI) technologies, cyber defenders may reasonably wonder when cyber adversaries will begin to also field these AI technologies. In this regard, some promising (read: scary) areas of AI for cyber attack capabilities are search, automated planning, and reinforcement learning. As such, one possible defensive mechanism against future AI-enabled adversaries is that of cyber deception. To that end, in this work, we present and evaluate Mirage, an experimentation system demonstrated in both emulation and simulation forms that allows for the implementation and testing of novel cyber deceptions designed to counter cyber adversaries that use AI search and planning capabilities.

AI Think with Me, Or Think for Me?

This research aims to study and analyze strategies for the strategic application of artificial intelligence in marketing by developing a framework that guides artificial intelligence planning strategies in marketing systematically and can be followed up by making decisions about service strategies at the J&T Company. The research locus is the object and source of data from the place being researched so that the information obtained can provide accurate data and truth in research. J&T Cargo is a technologically innovative express company under the auspices of the J&T Group. The locus of this research was carried out at: Marketing manager, HR manager and marketing expert team. The qualitative approach carried out through the data analysis technique used is the Manual Data Analysis Procedure (MDAP) by Rofiah, (2022), from the results of interviews accompanied by triangulation of sources, methods and theories it can be concluded that artificial intelligence for marketing strategies at J&T Cargo is used to determine preferences. Various Consumer Segments; Micro Segment Customers; Target Cause Marketing Outreach; Identify the Best Target; Refining Customer Based Perception Maps; Positioning Slogan; Psychographic Consumer Segmentation; Tourism Consumer Segment; New Customer Promotion Target; Target Digital Consumers; Target Customers Based on Brand with the aim of monitoring local market developments, so that in this business J&T Cargo is not left behind compared to other competitors. This paper also contributes to strategic marketing research by providing a systematic and rigorous approach to identifying research gaps that bridge strategic marketing practice research and artificial intelligence.

Argument Schemes and a Dialogue System for Explainable Planning

Artificial Intelligence (AI) is being increasingly deployed in practical applications. However, there is a major concern whether AI systems will be trusted by humans. To establish trust in AI systems, there is a need for users to understand the reasoning behind their solutions. Therefore, systems should be able to explain and justify their output. Explainable AI Planning is a field that involves explaining the outputs, i.e., solution plans produced by AI planning systems to a user. The main goal of a plan explanation is to help humans understand reasoning behind the plans that are produced by the planners. In this article, we propose an argument scheme-based approach to provide explanations in the domain of AI planning. We present novel argument schemes to create arguments that explain a plan and its key elements and a set of critical questions that allow interaction between the arguments and enable the user to obtain further information regarding the key elements of the plan. Furthermore, we present a novel dialogue system using the argument schemes and critical questions for providing interactive dialectical explanations.

Performance evaluation of an AI-based preoperative planning software application for automatic selection of pedicle screws based on computed tomography images.

Recent neurosurgical applications based on artificial intelligence (AI) have demonstrated its potential in surgical planning and anatomical measurement. We aimed to evaluate the performance of an AI planning software application on screw length/diameter selection and insertion accuracy in comparison with freehand surgery. A total of 45 patients with 208 pedicle screw placements on thoracolumbar segments were included in this analysis. The novel AI planning software was developed based on a deep learning model. AI-based pedicle screw placements were selected on the basis of preoperative computed tomography (CT) data, and freehand surgery screw placements were observed based on postoperative CT data. The performance of AI pedicle screw placements was evaluated on the components of screw length, diameter, and Gertzbein grade in comparison with the results achieved by freehand surgery. Among 208 pedicle screw placements, the average screw length/diameters selected by the AI model and used in freehand surgery were 48.65 ± 5.99 mm/7.39 ± 0.42 mm and 44.78 ± 2.99 mm/6.1 ± 0.27 mm, respectively. Among AI screw placements, 85.1% were classified as Gertzbein Grade A (no cortical pedicle breach); among free-hand surgery placements, 64.9% were classified as Gertzbein Grade A. The novel AI planning software application could provide an accessible and safe pedicle screw placement strategy in comparison with traditional freehand pedicle screw placement strategies. The choices of pedicle screw dimensional parameters made by the model, including length and diameter, may provide potential inspiration for real clinical discretion.

Frontmatter

This volume contains the papers accepted for presentation at ICAPS 2023, the Thirty-Third International Conference on Automated Planning and Scheduling, to be held in Prague, Czech Republic, July 8-13, 2023. The annual ICAPS conference series was formed in 2003 through the merger of two pre-existing biennial conferences, the International Conference on Artificial Intelligence Planning and Scheduling (AIPS) and the European Conference on Planning (ECP). ICAPS continues the traditional high standards of AIPS and ECP as an archival forum for new research in the field of automated planning and scheduling.

Artificial intelligence in local government services: Public perceptions from Australia and Hong Kong

Despite the exponential growth in the popularity of artificial intelligence (AI), our knowledge on the public perception of AI, especially in the context of local government services, is still limited. To bridge this gap, this study aims to provide empirical evidence and insights into public perceptions concerning the use of AI in local government services. Our methodological approach involves collecting data via an online survey from the residents of three major Australian cities—i.e., Sydney, Melbourne, Brisbane—and Hong Kong (n = 850), and performing statistical analyses. We found that: (a) Ease of using AI is significantly and positively influenced by attitude towards AI; (b) Attitude towards AI significantly and positively influences perceived usefulness of AI in local government services; (c) AI is seen useful in resource management and to improve delivery of service, reduction of cost to provide urban-service, improvement of public safety, and monitoring the effectiveness of strategies to manage environmental crisis, and; (d) AI is more positively perceived by Australians in comparison to Hong Kongers, indicating the impact of contextual and cultural differences. The research findings inform local government authorities—e.g., urban policymakers, managers, and planners—on their AI policy, planning and implementation decisions.

A Contrastive Plan Explanation Framework for Hybrid System Models

In artificial intelligence planning, having an explanation of a plan given by a planner is often desirable. The ability to explain various aspects of a synthesized plan to an end user not only brings in trust on the planner but also reveals insights of the planning domain and the planning process. Contrastive questions such as “Why action A instead of action B?” can be answered with a contrastive explanation that compares properties of the original plan containing A against the contrastive plan containing B. In this article, we explore a set of contrastive questions that a user of a planning tool may raise and propose a re-model and re-plan framework to provide explanations to such questions. Earlier work has reported this framework on planning instances for discrete problem domains described in the Planning Domain Definition Language (PDDL) and its variants. In this article, we propose an extension for planning instances described by PDDL+ for hybrid systems that portray a mix of discrete-continuous dynamics. Specifically, given a mixed discrete-continuous system model in PDDL+ and a plan describing the set of desirable actions on the same to achieve a destined goal, we present a framework that can integrate contrastive questions in PDDL+ and synthesize alternate plans. We present a detailed case study on our approach and propose a comparison metric to compare the original plan with the alternate ones.

Transforming Experimental Cobot Cell to Industrial Realization – an Ethical AI Approach

Collaborative Robot (cobot) cells are getting more and more integrative building blocks of Cyber Physical Enterprises. These cells integrate the advantages of human workers with the special capabilities of robots in a safe manner. Cobots need advanced, in many cases artificial intelligence (AI) based control systems to harmonize the collaborative activities. When transferring/transforming experimental setups into industrial application, not only technological and business related, but also ethical aspects have to be taken into consideration. The paper introduces a novel workflow supporting this transformation and presents its application in a case-study of a cobot cell which uses advanced sensing, symbolic AI planning and mixed reality techniques for planning and explaining visually the operation of the cell. The work which takes the responsible artificial intelligence (RAI) approach combines the actual relevant AI standards with the explicit requirements of industrial practitioners.

Towards Real-Time Warning and Defense Strategy AI Planning for Cyber Security Systems Aided by Security Ontology

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.

Investigating a visual interface for elementary students to formulate AI planning tasks

Recent years have seen the rapid adoption of artificial intelligence (AI) in every facet of society. The ubiquity of AI has led to an increasing demand to integrate AI learning experiences into K-12 education. Early learning experiences incorporating AI concepts and practices are critical for students to better understand, evaluate, and utilize AI technologies. AI planning is an important class of AI technologies in which an AI-driven agent utilizes the structure of a problem to construct plans of actions to perform a task. Although a growing number of efforts have explored promoting AI education for K-12 learners, limited work has investigated effective and engaging approaches for delivering AI learning experiences to elementary students. In this article, we propose a visual interface to enable upper elementary students (grades 3-5, ages 8-11) to formulate AI planning tasks within a game-based learning environment. We present our approach to designing the visual interface as well as how the AI planning tasks are embedded within narrative-centered gameplay structured around a Use-Modify-Create scaffolding progression. Further, we present results from a study of upper elementary students using the visual interface. We discuss how the Use-Modify-Create approach supported student learning as well as discuss the misconceptions and usability issues students encountered while using the visual interface to formulate AI planning tasks.

Prospective Clinical Integration of AI Based Treatment Planning Tool for Whole Breast Radiation Therapy (WBRT): A Single Institution's Three-Year Experience

<h3>Purpose/Objective(s)</h3> Artificial intelligence (AI) has shown promising results of treatment planning in well-controlled retrospective environment. However, its clinical acceptability and long-term robustness has not been widely investigated. We report the prospective clinical results of AI-based whole breast/chest wall radiation therapy (WBRT) planning tool. We evaluated the 3-year overall performance and the progression of AI tool's acceptance among human planners. <h3>Materials/Methods</h3> In-house AI based WBRT treatment planning tool using random forest was commissioned for clinic since 2019. A total of 1151 patients have been planned with AI tool by Dec 2021, and all were included in this study. The AI tool is seamlessly integrated with clinical planning workflow and treatment planning system (TPS) – AI automatically generates fluence maps, which are used for final dose calculation in TPS (AI plan). The planner evaluates the plan quality and attempts to improve by manually modifying fluence if deemed necessary before physician's approval (final plan). The manual modification value (MMV) of each beamlet is the difference between fluence maps in AI and final plans. The manually modified beamlets were located and correlated to the dosimetry quality enhancement of the final plan over AI plan. In the longitudinal dimension, MMV also tracks the adaptation of human planner towards AI tools over 3 years. A regression model captures planner's frequency of editing AI plans over time. If the planner becomes more acceptive of the AI over time, the regression trend line will be significantly different from zero. <h3>Results</h3> Table 1 shows the dosimetric endpoints, as well as mean MMV of the entire patient population. No statistical significance was observed between the AI and final plans in PTV coverage and OAR sparing (Mood's median test), except V105% (reduced in final plan by 18.4 cc, <i>p</i>< 0.001). Spatially, irradiated lung region received most frequent editing, while skin flash region received minimum editing. Among all 12 planners, the number of cases planned ranged from 13 to 150. The max mean absolute MMV of a single planner was 5.0% (planned 131 cases) and minimum was 0.8% (planned 38 cases). Ten out of 12 planners showed a significantly decreasing editing AI plans with yearly mean MMV of 4.0%, 2.3% and 0.8% for 2019, 2020 and 2021 respectively, indicating improving acceptability/trust over time (<i>p</i><0.001). <h3>Conclusion</h3> This 3-year study demonstrated robustness of AI planning and steady improvement in acceptability by planners over time. It also revealed key areas towards human planner's preference that can be adopted in future AI tools.

Commissioning of an Artificial Intelligence (AI) Tool for Automated Head and Neck Intensity Modulated Radiation Therapy (IMRT) Treatment Planning

<h3>Purpose/Objective(s)</h3> Radiation treatment planning for head and neck (HN) cancers is challenging due to complex anatomy and labor-intensive inverse optimization. Recently we developed an Artificial Intelligence (AI) tool to generate IMRT plans for bilateral planning target volumes (PTVs) with promising results in both plan quality and efficiency. In this study, we describe the clinical commissioning process of this tool. <h3>Materials/Methods</h3> The AI tool was interfaced to the commercial treatment planning system (TPS) in the clinical environment. Essential information about patient anatomy was collected through vendor-supported scripts and transmitted to a designated workstation. This workstation was configured to perform AI core functions to avoid modification and burden on TPS workstations. The AI-generated optimal fluence maps were then imported into TPS for leaf sequencing, dose calculation, and optional fine-tuning. Planners could examine the plan dose and make further adjustments as clinically needed. The workflow and performance were evaluated and validated by experienced physicians and physicists specializing in HN treatment. Training, validation, and testing datasets of the AI tool consisted of 200, 16, and 15 retrospective cases. The commissioning dataset of the AI tool used 36 recent cases of various disease sites in HN. The commissioning AI plans were evaluated based on the corresponding clinical plans regarding critical dose-volume endpoints and 3D dose distributions. All plans were normalized to 44Gy covering 95% of PTV. Wilcoxon signed-rank tests were performed with a significance level of 0.05. <h3>Results</h3> The average AI planning time was 10 to 15min per case with default settings from start to finish. The dose distributions were comparable to clinical plans with slightly better dose conformity and slightly worse but acceptable dose heterogeneity and maximum dose. OAR sparing was comparable. <h3>Conclusion</h3> The AI planning tool for HN was commissioned in our clinic. The commissioning process demonstrates outstanding performance and robustness of the AI tool and provides sufficient validation and confidence for clinical use. Table. Statistics of dosimetric endpoints (median ± std) of the 36 commissioning cases.

A Review of Plan-Based Approaches for Dialogue Management

Dialogue systems deliver a more natural mean of communication between humans and machines when compared to traditional systems. Beyond input/output components that understand and generate natural language utterances, the core of a dialogue system is the dialogue manager. The aim of the dialogue manager is to mimic all cognitive aspects related to a natural conversation and it is responsible for identifying the current state of the dialogue and for deciding the next action to be taken by a dialogue system. Artificial intelligence (AI) planning is one of the techniques available in the literature for dialogue management. In a dialogue system, AI planning deals with the action selection problem by treating each utterance as an action and by choosing the actions that get closer to the dialogue goal. This work aims to provide a systematic literature review (SLR) that investigates recent contributions to plan-based dialogue management. This SLR aims at answering research questions concerning: (i) the types of AI planning exploited for dialogue management; (ii) the planning characteristics that justify its adoption in dialogue system; (iii) and, the challenges posed on the development of plan-based dialogue managers. The present SLR was performed by querying four scientific repositories, followed by a manual search on works from the most eminent authors in the field. Further works that were cited by the retrieved papers were also considered for inclusion. Our final corpus is composed of forty works, including only works published since 2014. The results indicate that AI planning is still an emerging strategy for dialogue management. Although AI planning can offer a strong contribution to dialogue systems, especially to those that require predictability, some relevant challenges might still limit its adoption. Our results contributed to discussions in the field and they highlight some research gaps to be addressed in future studies.

An Automatic Planning-Based Attack Path Discovery Approach from IT to OT Networks

With the convergence of IT and OT networks, more opportunities can be found to destroy physical processes by cyberattacks. Discovering attack paths plays a vital role in describing possible sequences of exploitation. Automated planning that is an important branch of artificial intelligence (AI) is introduced into the attack graph modeling. However, while adopting the modeling method for large-scale IT and OT networks, it is difficult to meet urgent demands, such as scattered data management, scalability, and automation. To that end, an automatic planning-based attack path discovery approach is proposed in this paper. At first, information of the attacking knowledge and network topology is formally represented in a standardized planning domain definition language (PDDL), integrated into a graph data model. Subsequently, device reachability graph partitioning algorithm is introduced to obtain subgraphs that are small enough and of limited size, which facilitates the discovery of attack paths through the AI planner as soon as possible. In order to further cope with scalability problems, a multithreading manner is used to execute the attack path enumeration for each subgraph. Finally, an automatic workflow with the assistance of a graph database is provided for constructing the PDDL problem file for each subgraph and traversal query in an interactive way. A case study is presented to demonstrate effectiveness of attack path discovery and efficiency with the increase in number of devices.

Assessing the Robustness and Performance of Artificial Intelligence Powered Planning Tools in Clinical Settings

Artificial intelligence (AI) driven tools have been maturing in automating the radiation treatment planning process. To prepare for clinical deployment of these tools, it is essential to understand their robustness in clinical scenarios. This study works to fill the existing gap between research initiated and clinically ready AI tools by investigating a clinical assessment approach based on phantom design and planning complexity simulation. The hypothesis is that AI tool assessment program provides more clinically relevant and comprehensive evaluations beyond typical model validation studies.A cylindrical digital phantom was designed in the treatment planning system with an axial diameter of 30 cm and length of 18 cm. The phantom contains key structures involved in pancreas SBRT including the PTV25Gy, PTV33Gy, C-loop, stomach, bowel and liver with their base shape and volume representing the average of 100 clinical SBRT patients. Phantom cases were synthesized to mimic real-life anatomical variations and overlaps through displacement, expansion, and rotation of PTVs and OARs. This study involved a total of 32 simulated cases to test a broad range of planning scenarios. A previously developed deep learning based automatic planning tool was assessed in this study. This AI tool is composed of two deep neural networks (NNs) which predict beam dose and fluence maps sequentially. The goal of treatment planning was to deliver 25 Gy to PTV25 and 33 Gy to PTV33 in 5 fractions via simultaneous integral boost (SIB) while limiting luminal OAR max dose to below 29 Gy. The AI-plan's quality was analyzed against the clinical evaluation criteria, which include PTV V100%, luminal OAR max dose using Dmax and D0.03cc. The passing rate of key clinical criteria were collected to quantify overall robustness.For all scenarios, the mean PTV25 V25Gy of the AI plans was 96.7% while mean PTV33 V33 Gy was 82.2%. Large variation (16.3%) in PTV33 V33 Gy was observed due to anatomical variations, i.e., proximity of luminal structures to PTV33. Mean max dose was 28.55, 27.68, and 24.63 Gy for the C-loop, bowel and stomach respectively. Using D0.03cc as a surrogate for max dose, the value was 28.03, 27.12, and 23.84 Gy for the same respective structures. A max dose constraint of 29 Gy was achieved for 81.3% cases for the C-loop and stomach, and 78.1% for the bowel. Using D0.03cc as a surrogate for max dose, the passing rate was 90.6% for the C-loop and 81.3% for both the bowel and stomach.The results showed promising robustness of AI planning tool for pancreas SBRT, providing important evidence of its readiness for clinical implementation. The established approach could guide the robustness testing and other clinical assessments of AI based treatment planning tools in general, which is an important component for safe clinical implementation.

Arranging test tubes in racks using combined task and motion planning

The paper develops a robotic manipulation system to meet the pressing needs for handling a large number of test tubes in clinical examination and replace or reduce human labor. It presents the technical details of the system, which separates and arranges test tubes in racks with the help of 3D vision and artificial intelligence (AI) planning. The developed system only requires a person to put a rack with mixed and non-arranged tubes in front of a robot. The robot autonomously performs recognition, reasoning, planning, manipulation, etc., and returns a rack with separated and arranged tubes. The system is simple-to-use, and there are no requests for expert knowledge in robotics. We expect such a system to play an important role in helping managing bulky examination samples. We also hope similar systems could be extended to other clinical manipulation like handling mixers and pipettes in the future.

Parallel best-first search algorithms for planning problems on multi-core processors

The multiplication of computing cores in modern processor units permits revisiting the design of classical algorithms to improve computational performance in complex application domains. Artificial Intelligence planning is one of those applications where large search spaces require intelligent and more exhaustive search control. In this paper, parallel planning algorithms, derived from best-first search, are proposed for shared memory architectures. The parallel algorithms, based on the asynchronous work pool paradigm, maintain good thread occupancy in multi-core CPUs. All algorithms use one ordered global list of states stored in shared memory from where they select nodes for expansion. A parallel best-first search algorithm that develops new states with depth equal to one is proposed first. Then, we propose an extension of this parallel algorithm that features a diversification strategy in order to escape local minima. We study and analyse a set of computational experiments for problems that come from the International Planning Competition and real-world industry applications. The empirical evaluation shows that the parallel algorithms solve most of the domains efficiently without incurring higher solutions costs. In those problems with partial results, we highlight the potential shortcomings of the proposed approaches for promising future directions.

Game AI Planning Analytics: The Case of Three First-Person Shooters

We present a general framework for Game Artificial Intelligence Planning (AIP) Analytics. The objective is to provide analytic tools to study and improve AIP components and their use in video-games. Extraction and formatting of AI data is first described and discussed. Then AIP metrics are listed with examples and illustrations from three popular First-Person Shooters: F.E.A.R. (2005), KillZone 3 (2011) and Transformers 3: Fall of Cybertron (2012). The patterns we discovered in our study clearly show the AIP component is called more often by the game over the years.