Search

The development of domain-independent planners within the AI planning community is leading to “off-the-shelf” technology that can be used in a wide range of applications. Moreover, it allows a modular approach—in which planners and domain knowledge are modules of larger software applications—that facilitates substitutions or improvements of individual modules without changing the rest of the system. This approach also supports the use of reformulation and configuration techniques, which transform how a model is represented in order to improve the efficiency of plan generation. In this article, we investigate how the performance of domain-independent planners is affected by domain model configuration, i.e. the order in which elements are ordered in the model, particularly in the light of planner comparisons. We then introduce techniques for the online and offline configuration of domain models, and we analyse the impact of domain model configuration on other reformulation approaches, such as macros.

Reinforcement Learning (RL) comes with the promise of automating network management. However, due to its trial-and-error learning approach, model-based RL (MBRL) is not applicable in some network management scenarios. This paper explores the potential of using Automated Planning (AP) to achieve this MBRL in the functional areas of network management. In addition, a comparison of several integration strategies of AP and RL is depicted. We also describe an architecture that realizes a cognitive management control loop by combining AP and RL. Our experiments evaluate on a simulated environment evidence that the combination proposed improves model-free RL but demonstrates lower performance than Deep RL regarding the reward and convergence time metrics. Nonetheless, AP-based MBRL is useful when the prediction model needs to be understood and when the high computational complexity of Deep RL can not be used.

Modern robots are increasingly capable of performing “basic” activities such as localization, navigation, and motion planning. However, for a robot to be considered intelligent, we would like it to be able to automatically combine these capabilities in order to achieve a high-level goal. The field of automated planning (sometimes called AI planning) deals with automatically synthesizing plans that combine basic actions to achieve a high-level goal. In this article, we focus on the intersection of automated planning and robotics and discuss some of the challenges and tools available to employ automated planning in controlling robots. We review different types of planning formalisms and discuss their advantages and limitations, especially in the context of planning robot actions. We conclude with a brief guide aimed at helping roboticists choose the right planning model to endow a robot with planning capabilities.

The widespread implementation of intelligent decision support systems (IDSS) is hampered by the lack of methods and technologies for automatically filling the knowledge base during the operation of such systems. This problem is especially acute in the medical field. Its solution lies in the application of automatic planning technologies. The methods and algorithms developed in this field for estimation the optimal strategy for solving problems, which are strictly formulated in terms of predicate logic, allow numerically evaluating the usefulness of new messages and thus ranking information by importance and automatically selecting essential information for entering it into the knowledge base. The paper proposes the architecture of a medical IDSS that implements this approach, substantiates the applicability of the Markov approximation for the formalization of automatic planning tasks in the medical field, shows the effectiveness of the proposed approach using the example of an informed choice of serum for influenza vaccination.

Applied Sciences 12(5), 2319 (2022). doi:10.3390/app12052319, Published by MDPI, Basel

Personalized sequencing and recommendation of pedagogical actions in virtual learning environments are relevant aspects in promoting an effective learning process with computer-aided support. Hence, this work investigates the use of automated planning to sequence these actions according to student profiles. Actions are modeled to correspond to the cognitive process described by Bloom’s Taxonomy, and the student profile is set using the Revised Approaches to Studying Inventory. Both models share theoretical foundations linked to the cognitive process, and the mapping of these two theories is one of the contributions merged into this study. In planning, through use of a genetic algorithm and the problem formulation as an optimization problem, one can correctly manage the search for good solutions, as demonstrated in this work. Through use of Digital Bloom’s Taxonomy, one arrives at a recommend set of actions. Experiments were performed using 41 students. The results were promising and demonstrate the viability of the proposal.

Background To assess the feasibility of CBCT-based adaptive intensity modulated proton therapy (IMPT) using automated planning for treatment of head and neck (HN) cancers. Methods Twenty HN cancer patients treated with IMPT and had daily CBCTs were included. Initial IMPT plans were created using automated planning software for all patients. Synthetic CTs (sCT) were created by deforming planning CT (pCT) to CBCTs. rCTs were deformed to CBCT obtained on the same day to create deformed rCT (rCTdef) as gold standard. Doses recalculated on sCT and rCTdef with the were compared using gamma analysis. The dosimetric parameters were assessed based on rCTdef, sCT with deformably propagated contours or with physician-corrected contours. Weekly sCTs were then created for all patients. For non-adaptive group, dose was directly recalculated on weekly sCTs. For adaptive group, adaptive IMPT plans were created on weekly sCT using the automated planning software. The non-adapted and adapted dose-volume parameters on weekly sCTs were evaluated. The weekly doses were accumulated back to the pCT for both groups, and dosimetric parameters were compared in between. Results High dosimetric agreement was found between sCT and rCTdef with high gamma passing rate of 97.4%±1.6% using 3mm/3% criteria. With contour correction on sCT by physician, the uncertainty range of using sCT to estimate mean dose for organ at risk (OARs) can be reduced to (-2.37%, 2.19%), while for V95 of primary or secondary CTVs, the uncertainty can be controlled within (-1.09%, 0.29%). For non-adapted treatments, 15.7%, 34% and 55.7% of the fractions didn’t meet the V95 > 98% constraint for primary, secondary and tertiary CTVs respectively while all adaptive fractions met the constraint. In the accumulated dose, adaptive planning significantly reduced mean dose to constrictors (-1.42Gy ± 2.79Gy) and larynx (-2.58Gy ± 3.09Gy) compared to non-adaptive group, resulting in significantly reduction on the normal tissue complication probability (NTCP) of larynx edema by 7.52%± 13.59%. Conclusion sCT can be a powerful tool for accurate proton dose calculation. Physician contour correction is recommended to reduce the uncertainty for dose evaluation. Daily adaptation resulted in better CTV coverage, OAR sparing and lower NTCP for some OARs as compared with non-adaptive IMPT.

Mención Internacional en el título de doctor Automated planning deals with the task of finding a sequence of actions, namely a plan, which achieves a goal from a given initial state. Most planning research consider goals are provided by a external user, and agents just have to find a plan to achieve them. However, there exist many real world domains where agents should not only reason about their actions but also about their goals, generating new ones or changing them according to the perceived environment. In this thesis we aim at broadening the goal reasoning capabilities of planningbased agents, both when acting in isolation and when operating in the same environment as other agents. In single-agent settings, we firstly explore a special type of planning tasks where we aim at discovering states that fulfill certain cost-based requirements with respect to a given set of goals. By computing these states, agents are able to solve interesting tasks such as find escape plans that move agents in to safe places, hide their true goal to a potential observer, or anticipate dynamically arriving goals. We also show how learning the environment’s dynamics may help agents to solve some of these tasks. Experimental results show that these states can be quickly found in practice, making agents able to solve new planning tasks and helping them in solving some existing ones. In multi-agent settings, we study the automated generation of goals based on other agents’ behavior. We focus on competitive scenarios, where we are interested in computing counterplans that prevent opponents from achieving their goals. We frame these tasks as counterplanning, providing theoretical properties of the counterplans that solve them. We also show how agents can benefit from computing some of the states we propose in the single-agent setting to anticipate their opponent’s movements, thus increasing the odds of blocking them. Experimental results show how counterplans can be found in different environments ranging from competitive planning domains to real-time strategy games. Programa de Doctorado en Ciencia y Tecnología Informática por la Universidad Carlos III de Madrid Presidenta: Eva Onaindía de la Rivaherrera.- Secretario: Ángel García Olaya.- Vocal: Mark Roberts

Software architecture design usually needs to be migrated to new architectural styles when new technologies and principles are adopted to enhance the qualities of the software system. The architectural migration is an evolution process, which the system is gradually and incrementally changed while the functionalities are still preserved. Planning the migration towards a new design is an important and challenging task. This paper presents an automated planning approach for architectural migration by applying AI planning and model checking technique. Our approach can automatically generate migration plans that can be used to find evolution path towards the new architecture designs. We have demonstrated our approach with a real-world system and found that it works effectively.

The development of efficient propositional satisfiability problem solving algorithms (SAT solvers) in the past two decades has made automated planning using SAT-solvers an established AI planning approach. Modern SAT solvers can accommodate a wide variety of planning problems with a large number of variables. However, fast computing of reasonably long plans proves challenging for planning as satisfiability. In order to address this challenge, we present a compositional approach based on abstraction refinement that iteratively generates, solves and composes partial solutions from a parameterized planning problem. We show that this approach decomposes the monolithic planning problem into smaller problems and thus significantly speeds up plan calculation, at least for a class of tested planning problems.

Determine the dosimetric quality and the planning time reduction when utilizing a template-based automated planning application.A software application integrated through the treatment planning system application programing interface, QuickPlan, was developed to facilitate automated planning using configurable templates for contouring, knowledge-based planning structure matching, field design, and algorithm settings. Validations are performed at various levels of the planning procedure and assist in the evaluation of readiness of the CT image, structure set, and plan layout for automated planning. QuickPlan is evaluated dosimetrically against 22 hippocampal-avoidance whole brain radiotherapy patients. The required times to treatment plan generation are compared for the validations set as well as 10 prospective patients whose plans have been automated by QuickPlan.The generations of 22 automated treatment plans are compared against a manual replanning using an identical process, resulting in dosimetric differences of minor clinical significance. The target dose to 2% volume and homogeneity index result in significantly decreased values for automated plans, whereas other dose metric evaluations are nonsignificant. The time to generate the treatment plans is reduced for all automated plans with a median difference of 9' 50″ ± 4' 33″.Template-based automated planning allows for reduced treatment planning time with consistent optimization structure creation, treatment field creation, plan optimization, and dose calculation with similar dosimetric quality. This process has potential expansion to numerous disease sites.

Automated planning for problems without an explicit model is an elusive research challenge. However, if tackled, it could provide a general approach to problems in real-world unstructured environments. There are currently two strong research directions in the area of artificial intelligence (AI), namely machine learning and symbolic AI. The former provides techniques to learn models of unstructured data but does not provide further problem solving capabilities on such models. The latter provides efficient algorithms for general problem solving, but requires a model to work with. Creating the model can itself be a bottleneck of many problem domains. Complicated problems require an explicit description that can be very costly or even impossible to create. In this paper, we propose a combination of the two areas, namely deep learning and classical planning, to form a planning system that works without a human-encoded model for variably scaled problems. The deep learning part extracts the model in the form of a transition system and a goal-distance heuristic estimator; the classical planning part uses such a model to efficiently solve the planning problem. Both networks in the planning system, we introduced, work with a problem in its graphic form and there is no need for any additional information to create the state transition system or to estimate a heuristic value. We proposed three different architectures for the heuristic estimator to compare different characteristics of well- known deep learning techniques. Besides the design of such planning systems, we provide experimental evaluation comparing the implemented techniques to classical model-based methods.

Design and evaluate a knowledge-based model using commercially available artificial intelligence tools for automated treatment planning to efficiently generate clinically acceptable hippocampal avoidance prophylactic cranial irradiation (HA-PCI) plans in patients with small-cell lung cancer.Data from 44 patients with different grades of head flexion (range 45°) were used as the training datasets. A Rapid Plan knowledge-based planning (KB) routine was applied for a prescription of 25 Gy in 10 fractions using two volumetric modulated arc therapy (VMAT) arcs. The 9 plans used to validate the initial model were added to generate a second version of the RP model (Hippo-MARv2). Automated plans (AP) were compared with manual plans (MP) according to the dose-volume objectives of the PREMER trial. Optimization time and model quality were assessed using 10 patients who were not included in the first 44 datasets.A 55% reduction in average optimization time was observed for AP compared to MP. (15 vs 33 min; p = 0.001).Statistically significant differences in favor of AP were found for D98% (22.6 vs 20.9 Gy), Homogeneity Index (17.6 vs 23.0) and Hippocampus D mean (11.0 vs 11.7 Gy). The AP met the proposed objectives without significant deviations, while in the case of the MP, significant deviations from the proposed target values were found in 2 cases.The KB model allows automated planning for HA-PCI. Automation of radiotherapy planning improves efficiency, safety, and quality and could facilitate access to new techniques.

Rapidly-exploring random trees (RRTs) are data structures and search algorithms designed to be used in continuous path planning problems. They are one of the most successful state-of-the-art techniques as they offer a great degree of flexibility and reliability. However, their use in other search domains has not been thoroughly analyzed. In this work we propose the use of RRTs as a search algorithm for automated planning. We analyze the advantages that this approach has over previously used search algorithms and the challenges of adapting RRTs for implicit and discrete search spaces.

Modern industrial production requires the improvement of assembly processes, and thus increase the level of automated intelligent sequence planning. Therefore, researches in the field of automation of the sequence of assembly of products in industries are relevant at this time. In today's world there is a need to develop complex, accurate products. Problems are created in industries due to the reduction of the life cycle of products. There is a need to study the problem of assembly planning to achieve the goal of practical implementation and standardization of assembly plans. Creating graphs of the addition process is one of the problems. The assembly planning system can reduce human intervention in the process and reduce computational effort. The finished assembly contains many components that can be assembled using many sequences. A review of the methods from the literature showed that although these methods increase the automation level, they still cannot be applied to actual production because they do not take into account the experience and knowledge that can play a major role in planning and are of great value. Assembly planning, relationship charts, priority charts. Improving the assembly planning system to create a communication schedule and an assembly priority schedule was proposed. The advanced system will be used to generate possible assembly sequences with subassembly identification. A system has been developed to create alternative possible assembly sequences that can be used by component part / product designers in the early stages. A system capable of generating assembly sequences for simultaneous assembly of multiple parts has been proposed. Conclusions and work results can be applied used and improved for more productive product development by designers in the early stages and faster assembly of products in enterprises. The paper did not consider practical limitations (gravity) and irreversible assembly operations, such as permanent fastening, welding etc. Кey words: assembly, blocking graph, relation graph, sequence

We show how reactive synthesis and automated planning can be leveraged effectively to find nonmaximal solutions to deterministic supervisory control problems of discrete event systems. To do so, we propose efficient translations of the supervisory control problem into the reactive synthesis and planning frameworks. Notably, our translation methods capture the compositional and reactive nature of control specifications, avoiding a potential exponential explosion found in alternative translation approaches. Additionally, we report on experimental results comparing the efficacy of different tools from the three disciplines, for a particular supervisory control benchmark.

Background Previous automated planning approach studies for Raystation were limited to a specific anatomical site cancer or a single treatment technique. The purpose of this study is to develop an automated planning approach in Raystation and evaluate its feasibility and performance in multiple clinical application scenarios. Methods Sixty patients, including 20 nasopharyngeal carcinoma (NPC), 20 esophageal carcinoma (ESCA) and 20 rectal cancer (RECA), who were treated with volumetric-modulated arc therapy for NPC and RECA and intensity-modulated radiotherapy for ESCA, were retrospectively enrolled in this study. An automated planning approach (Ruiplan), consisting of five key modules: prescription and OAR identification module, auxiliary structure generation module, dose prediction and objectives setting module, beam configuration module, plan fine-turning module, was developed by using the scripting platform of Raystation. Radiotherapy plans were re-generated both automatically by using Ruiplan and manually by experienced physicists. Target coverage, organs at risk (OARs) sparing, and planning efficiency of the automated plans (APs) and manual plans (MPs) were statistically compared using paired student t-test. Results For target coverage, APs yielded superior dose homogeneity in NPC and RECA, compared to MPs, while maintaining similar dose conformity for all studied anatomical sites. For OARs sparing, APs led to significant improvement in most OARs sparing, compared to MPs. The max dose of the lens, eyes and optic nerves in NPC, the V20 and mean dose of lungs, the V30, V40 and mean dose of heart in ESCA, the V30, V50 of bowel and V30 of femoral heads in CRCA were significantly decreased on average in APs compared to MPs (P

Purpose To develop and validate a robust template for VMAT SBRT of lung lesions, using the multicriterial optimization (MCO) of a commercial treatment planning system. Methods The template was established and refined on 10 lung SBRT patients planned for 55 Gy/5 fr. To improve gradient and conformity a ring structure around the planning target volume (PTV) was set in the list of objectives. Ideal fluence optimization was conducted giving priority to organs at risk (OARs) and using the MCO, which further pushes OARs doses. Segmentation was conducted giving priority to PTV coverage. Two different templates were produced with different degrees of modulation, by setting the Fluence Smoothing parameter to Medium (MFS) and High (HFS). Each template was applied on 20 further patients. Automatic and manual plans were compared in terms of dosimetric parameters, delivery time, and complexity. Statistical significance of differences was evaluated using paired two-sided Wilcoxon signed-rank test. Results No statistically significant differences in PTV coverage and maximum dose were observed, while an improvement was observed in gradient and conformity. A general improvement in dose to OARs was seen, which resulted to be significant for chest wall V30 Gy , total lung V20 Gy , and spinal cord D0.1 cc . MFS plans are characterized by a higher modulation and longer delivery time than manual plans. HFS plans have a modulation and a delivery time comparable to manual plans, but still present an advantage in terms of gradient. Conclusion The automation of the planning process for lung SBRT using robust templates and MCO was demonstrated to be feasible and more efficient.

PurposeThis paper proposes an innovative intelligent simulation-based construction planning framework that introduces a new approach to simulation-based construction planning.Design/methodology/approachIn this approach, the authors developed an ontological inference engine as an integrated part of a constraint-based simulation system that configures the construction processes, defines activities and manages resources considering a variety of requirements and constraints during the simulation. It allows for the incorporation of the latest project information and a deep level of construction planning knowledge in the planning. The construction planning knowledge is represented by an ontology and several semantic rules. Also, the proposed framework uses the project building information model (BIM) to extract information regarding the construction product and the relations between elements. The extracted information is then converted to an ontological format to be useable by the framework.FindingsThe authors implemented the framework in a case study project and tested its usefulness and capabilities. It successfully generated the construction processes, activities and required resources based on the construction product, available resources and the planning rules. It also allowed for a variety of analyses regarding different construction strategies and resource planning. Moreover, 4D BIM models that provide a very good understanding of the construction plan can be automatically generated using the proposed framework.Originality/valueThe active integration between BIM, discrete-event simulation (DES) and ontological knowledge base and inference engine defines a new class of construction simulation with expandable applications.

Properly planned single isocenter volumetric modulated arc therapy (VMAT) radiosurgery plans exhibit high quality and efficiency. We report here the largest clinical experience to date, to our knowledge, comparing manual planning with a new automated platform designed to standardize and simplify radiosurgery planning and delivery processes.We treated 693 patients with single isocenter VMAT radiosurgical plans generated by either our conventional manual (mVMAT) or a recently implemented automated (HyperArcThe median Radiation Therapy Oncology Group (RTOG) conformity index was 1.14 and was not different between the 2 techniques. The median Paddick gradient index was 5.42 for HyperArc versus 7.09 for mVMAT (P.001). The median mean brain doses were 4.6% and 5.1% for HyperArc and mVMAT, respectively (P = .04). The PSQA for both techniques met clinical criteria, but 97% of the HyperArc plans satisfied the gamma tolerance limit recommended by the American Association of Physicists in Medicine Task Group No. 218, compared with 94% of the mVMAT plans (P = .02). The median treatment-planning times were not significantly different. The median treatment times were 10.5 and 11.4 minutes for HyperArc and mVMAT, respectively (P.001). The Kaplan-Meier estimate of local control was 90.1% at 1 year.HyperArc produces high-quality radiosurgical plans that are at least as good as mVMAT plans created by an expert manual planner with easier planning and more efficient delivery workflow. A less experienced planner can produce very high-quality radiosurgical plans even for patients with more than 10 targets. The use of a single-isocenter technique for multiple targets with no PTV margin did not compromise clinical outcomes, and 1-year local control for treated targets remained congruent with historical series.

Purpose The purpose of this study was to develop automated planning for whole‐brain radiation therapy (WBRT) using a U‐net‐based deep‐learning model for predicting the multileaf collimator (MLC) shape bypassing the contouring processes. Methods A dataset of 55 cases, including 40 training sets, five validation sets, and 10 test sets, was used to predict the static MLC shape. The digitally reconstructed radiograph (DRR) reconstructed from planning CT images as an input layer and the MLC shape as an output layer are connected one‐to‐one via the U‐net modeling. The Dice similarity coefficient (DSC) was used as the loss function in the training and ninefold cross‐validation. Dose‐volume‐histogram (DVH) curves were constructed for assessing the automatic MLC shaping performance. Deep‐learning (DL) and manually optimized (MO) approaches were compared based on the DVH curves and dose distributions. Results The ninefold cross‐validation ensemble test results were consistent with DSC values of 94.6 ± 0.4 and 94.7 ± 0.9 in training and validation learnings, respectively. The dose coverages of 95% target volume were (98.0 ± 0.7)% and (98.3 ± 0.8)%, and the maximum doses for the lens as critical organ‐at‐risk were 2.9 Gy and 3.9 Gy for DL and MO, respectively. The DL technique shows the consistent results in terms of the DVH parameter except for MLC shaping prediction for dose saving of small organs such as lens. Conclusions Comparable with the MO plan result, the WBRT plan quality obtained using the DL approach is clinically acceptable. Moreover, the DL approach enables WBRT auto‐planning without the time‐consuming manual MLC shaping and target contouring.

A planning domain, as any model, is never “complete” and inevitably makes assumptions on the environment's dynamic. By allowing the specification of just one domain model, the knowledge engineer is only able to make one set of assumptions, and to specify a single objective-goal. Borrowing from work in Software Engineering, we propose a multi-tier framework for planning that allows the specification of different sets of assumptions, and of different corresponding objectives. The framework aims to support the synthesis of adaptive behavior so as to mitigate the intrinsic risk in any planning modeling task. After defining the multi-tier planning task and its solution concept, we show how to solve problem instances by a succinct compilation to a form of non-deterministic planning. In doing so, our technique justifies the applicability of planning with both fair and unfair actions, and the need for more efforts in developing planning systems supporting dual fairness assumptions.

The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. These trends are occurring in the context of concerns around environmental issues of poor air quality and transport related carbon dioxide emissions. One out of several ways to help meet these challenges is in the intelligent routing of road traffic through congested urban areas. Our goal is to show the feasibility of using automated planning to perform this routing, taking into account a knowledge of vehicle types, vehicle emissions, route maps, air quality zones, etc. Specifically focusing on air quality concerns, in this paper we investigate the problem where the goals are to minimise overall vehicle delay while utilising network capacity fully, and respecting air quality limits. We introduce an automated planning approach for the routing of traffic to address these areas. The approach has been evaluated on micro-simulation models that use real-world data supplied by our industrial partner. Results show the feasibility of using AI planning technology to deliver efficient routes for vehicles that avoid the breaking of air quality limits, and that balance traffic flow through the network.

Navigation and robotic systems have been increasingly applied to spinal instrumentation but dedicated screw planning is a time-consuming prerequisite to tap the full potential of these techniques.To develop and validate an automated planning tool for lumbosacral pedicle screw placement using a convolutional neural network (CNN) to facilitate the planning process.Retrospective analysis and processing of CT and screw planning data randomly selected from a consecutive registry of CT-navigated instrumentations from a single academic institution.Data from 179 cases was processed for CNN training and validation (155 for training, 24 for validation) leveraging a total of 1182 screws (1052 for training, 130 for validation).Quantitative and qualitative (Gertzbein-Robbins classification [GR]) validation via comparison of automatically and manually planned reference screws, inter-rater and intra-rater variability.Annotated data from CT-navigated instrumentation was used to train a CNN operating in a vertebra instance-based approach employing a state-of-the-art U-Net framework. Internal five-fold cross-validation and external validation on an independent cohort not previously involved in training was performed. Quantitative validation of automatically planned screws was performed in comparison to corresponding manually planned screws by calculating the minimal absolute difference (MAD) of screw head and tip points, length and diameter, screw direction and Dice coefficient. Results were evaluated in relation to inter-rater and intra-rater variability of manual screw planning.Automated screw planning was successful in all targeted 130 screws. Compared with manually planned screws as a reference, mean MAD of automatically planned screws was 4.61±2.27 mm for screw head, 3.96±2.19 mm for tip points and 5.51±3.64° for screw direction. These differences were either statistically comparable or significantly smaller when compared with interrater variability of manual screw planning (p.99 for head point and direction, p=.004 for tip point, respectively). Mean Dice coefficient of 0.61±0.16 indicated significantly greater agreement of automatic screws with the manual reference compared with interrater agreement (Dice 0.56±0.18, p.001). Automatically planned screws were marginally shorter (MAD 3.4±3.2 mm) and thinner (MAD mean 0.3±0.6 mm) compared with the manual reference, but with statistical significance (p.0001, respectively). Automatically planned screws were GR grade A in 96.2% in qualitative validation. Planning time was significantly shorter with the automatic approach (0:41 min vs. 6:41 min, p.0001).We derived and validated a fully automated planning tool for lumbosacral pedicle screws using a CNN. Our validation showed noninferiority to manual screw planning and provided sufficient accuracy to facilitate and expedite the screw planning process. These results offer a high potential to improve workflows in spine surgery when integrated into navigation or robotic assistance systems.

Constructing and adapting process models is highly relevant in today’s business world, but time-consuming and error-prone. Several approaches address these issues by manual tasks or making use of automation in the past years. Especially the research field Automated Planning envisions a (semi-)automated construction of process models by using semantic annotations and planning techniques. We aim at an empirical analysis of the influence of Automated Planning on the task performance of process modelers compared to the task performance when using common process modeling tools. We analyze the invested effort in terms of the required time for modeling tasks and the outcome in terms of the quality of the constructed process models by means of a laboratory experiment. Our findings indicate that Automated Planning significantly improves the task performance. The quality of constructed process models is increased, and especially for larger process models, the required time for modeling tasks could be decreased.

The compatible work is considered and the obtained results of the known algorithms generating unobstructed trajectories of different length and smoothness are investigated. Their operation is performed within the framework of the developed software product LSTr. The use of the analyzed set of these algorithms on the set of considered sections of the generated trajectories according to the obtained results allows a differentiated approach to the use of different algorithms on different sections of trajectories, determined by the accepted criteria of length and / or smoothness. The scientific novelty of the work and its practical significance in this area of research are determined.

Additional file 1. Details of our automated planning platform and machine-learning pipeline.

November 22-23, 2018, Madrid, Spain Comprehensive Geriatric Assessment is a medical procedure to evaluate the physical, social and psychological status of elder patients. One of its phases consists of performing different tests to the patient or relatives. In this paper we present the challenges to apply Automated Planning to control an autonomous robot helping the clinician to perform such tests. On the one hand the paper focuses on the modelling decisions taken, from an initial approach where each test was encoded using slightly different domains, to the final unified domain allowing any test to be represented. On the other hand, the paper deals with practical issues arisen when executing the plans. Preliminary tests performed with real users show that the proposed approach is able to seamlessly handle the patient-robot interaction in real time, recovering from unexpected events and adapting to the users' preferred input method, while being able to gather all the information needed by the clinician. This work has been partially funded by the European Union ECHORD++ project (FP7-ICT-601116) and the TIN2015-65686-C5 Spanish Ministerio de Economía y Competitividad project. Javier García is partially supported by the Comunidad de Madrid (Spain) funds under the project 2016-T2/TIC-1712.

The application of intelligent systems in industrial environments is still restricted, although autonomous systems based on artificial intelligence AI techniques have been under development for over 50 years and spreading into several areas since the last decade. Such integration goes against cultural and technical factors found on the shop floor and its project is often challenging. Classical industrial systems make use of programmable logic controllers PLCs, which centralise control by using a simple and low-level language. Automated planning solutions use a formal language called planning domain definition language PDDL to address specific problems, with predefined initial and target scenarios. Such feature seems to be interesting in some cases, since the generic domain models cannot predict all possible scenarios in a domain. Therefore, the applicability of intelligent systems in industrial cases is directly linked to the development of applications that allow integrating different languages, thus ensuring the access to PLCs and analysing specific situations. The current paper presents an application that integrates automated planning solution and PLCs as well as analyses such integrations’ functionality. Preliminary results are shown by using object process control OPC and TCP/IP client/server approaches. A comparison with classical approaches was presented for a specific case study.

Introduction. Given the ongoing digitalization of public administration, the Soviet experience in introducing computer-aided planning warrants more research with regard to overcoming departmentalism in creating supra-institutional (national) information systems. Based on the Russian State Archive of the Economy funds, interviews with the planners and Soviet economics literature, this paper examines the reasons behind the creation of the Automated Planning System which was meant to serve as a necessary intermediate step toward the National Information System (NACS). Materials and Methods. Through the lens of the institutional economics and actor-network theory, this research explores the inter-institutional struggle for the right to supervise the creation of the new instrument for the national economic planning. Results. A vast body of Soviet literature on the Automated Planning System and the archival documents from the Russian State Archive of the Economy was compiled and analyzed alongside with the interviews conducted with the chairmen of the Main Computing Centre of the Gosplan (V. B. Bezrukov, V. V. Kossov, Y. M. Urinson) and its other employees. It enabled the author to reconstruct the history of the ASPR, describe its architecture (key blocks and functions) and trace the political struggles over the computerization of the nationwide planning system. Discussion and Conclusions. This research improves upon the historiographic narrative on the NACS as a completely unimplemented project and offers an explanatory model for the Gosplan tactics which proved most effective in the competition for the right to run the nationwide administration system. ASPR is regarded as an interim solution crucial for suppressing the bureaucratic opposition. As the Gosplan institutional system, it allowed for the exclusion of other institutions from the creation process while the conceptual shift from a single system to a unified one turned all the opponents aspiring to have their information systems into observers. At the later stage, when ASPR had been launched, the Gosplan used the obtained results to insist on linking up other systems to build the OGAS with the ASPR at its core.

Purpose To develop a knowledge-based automated planning pipeline that generates treatment plans without feature engineering, using deep neural network architectures for predicting three-dimensional (3D) dose. Methods Our knowledge-based automated planning (KBAP) pipeline consisted of a knowledge-based planning (KBP) method that predicts dose for a contoured computed tomography (CT) image followed by two optimization models that learn objective function weights and generate fluence-based plans, respectively. We developed a novel generative adversarial network (GAN)-based KBP approach, a 3D GAN model, which predicts dose for the full 3D CT image at once and accounts for correlations between adjacent CT slices. Baseline comparisons were made against two state-of-the-art deep learning-based KBP methods from the literature. We also developed an additional benchmark, a two-dimensional (2D) GAN model which predicts dose to each axial slice independently. For all models, we investigated the impact of multiplicatively scaling the predictions before optimization, such that the predicted dose distributions achieved all target clinical criteria. Each KBP model was trained on 130 previously delivered oropharyngeal treatment plans. Performance was tested on 87 out-of-sample previously delivered treatment plans. All KBAP plans were evaluated using clinical planning criteria and compared to their corresponding clinical plans. KBP prediction quality was assessed using dose-volume histogram (DVH) differences from the corresponding clinical plans. Results The best performing KBAP plans were generated using predictions from the 3D GAN model that were multiplicatively scaled. These plans satisfied 77% of all clinical criteria, compared to the clinical plans, which satisfied 67% of all criteria. In general, multiplicatively scaling predictions prior to optimization increased the fraction of clinical criteria satisfaction by 11% relative to the plans generated with nonscaled predictions. Additionally, these KBAP plans satisfied the same criteria as the clinical plans 84% and 8% more frequently as compared to the two benchmark methods, respectively. Conclusions We developed the first knowledge-based automated planning framework using a 3D generative adversarial network for prediction. Our results, based on 217 oropharyngeal cancer treatment plans, demonstrated superior performance in satisfying clinical criteria and generated more realistic plans as compared to the previous state-of-the-art approaches.

Surgical planning for StereoElectroEncephaloGraphy (SEEG) is a complex and patient specific task, where the experience and medical workflow of each institution may influence the final planning choices. To account for this variability, we developed a data-based Computer Assisted Planning (CAP) solution able to exploit the knowledge extracted by past cases. By the analysis of retrospective patients' data sets, our system proposes a pool of trajectories commonly used by the institution, which can be selected to initialize a new patient plan. An optimization framework adapts those to the patient's anatomy by optimizing clinical requirements (e.g. distance from vessel, gray matter recording and insertion angle), and adapting its strategy based on the trajectory type selected.The system has been customized based on the data of a single institution. Two neurosurgeons, working in a high-volume hospital, have validated it by using 15 retrospective patient data sets, with more than 200 trajectories reviewed. Both surgeons considered ~81% of the optimized trajectories as clinically feasible (75% inter-rater reliability). Quantitative comparison of distance from vessels, insertion angle and gray matter recording index showed that the optimized trajectories reached superior or comparable values with respect to the original manual plans. The results suggest that a tailored center-based solution could increase the acceptance rate of the automated trajectories proposed.

One of the common challenges in delivering complex healthcare procedures such as radiation oncology is the organization and sharing of information in ways that facilitate workflow and prevent treatment delays. Within the major vendors of Oncology Information Systems (OIS) is a lack of tools and displays to assist in task timing and workflow processes. To address this issue, we developed an electronic whiteboard integrated with a local OIS to track, record, and evaluate time frames associated with clinical radiation oncology treatment planning processes.We developed software using an R environment hosted on a local web-server at Seattle Cancer Care Alliance (SCCA) in 2017. The planning process was divided into stages, and time-stamped moves between planning stages were recorded automatically via Mosaiq (Elekta, Sweden) Quality Check Lists (QCLs). Whiteboard logs were merged with Mosaiq-extracted diagnostic factors and evaluated for significance. Interventional changes to task time expectations were evaluated for 6 months in 2021 and compared with 6 month periods in 2018 and 2019.Whiteboard/Mosaiq data from the SCCA show that treatment intent, number of prescriptions, and nodal involvement were main factors influencing overall time to plan completion. Contouring and Planning times were improved by 2.6 days (p10This report establishes the utility of real-time task tracking tools in a radiotherapy planning process. The whiteboard results provide data-driven evidence to add justification for practice change implementations.