Search

Cranial vault remodelling for craniosynostosis aims to increase intracranial volume to facilitate brain growth, avoid the development of raised intracranial pressure and address cosmesis. The extent of vault expansion is predominantly limited by scalp closure and reconstruction technique. Virtual surgical planning tools have been developed to predict post-operative changes and guide expansion. We present a validation study of a novel 'Dura-based Automated Vault Expansion-Remodeling' (DAVE-R) model to guide pre-operative planning for fronto-orbital advancement and remodelling (FOAR). Methods: Patients with trigonocephaly who underwent FOAR with pre- and post-operative imaging from 2018 to 2020 were identified from a prospectively maintained database. Post-operative scans, normative atlas and whole brain parcellation were registered to the pre-operative images to quantify the change in intracranial volume and morphology (utilising measurement of fronto-orbital advancement and bifrontozygomatic distance) compared to that predicted by the DAVE-R model. Results: Ten patients were included. The DAVE-R model predicted bifrontozygomatic distances of 92.0 + / − 5.14 mm (mean + /SD), which closely matched the post-operative results of 92.7 + / − 6.02 mm (mean + / − SD); (t(d.f. 9) = -0.306, p = 0.77). The fronto-orbital advancement predicted by the DAVE-R method was 11.5 + / − 1.96 mm (mean + / − SD) which was significantly greater than 8.6 + / − 2.94 mm (mean ± SD); (t(d.f. 9) = 3.137, p = 0.01) achieved post-operatively. Conclusions: We demonstrate that the DAVE-R model provides an objective means of extracting realistic surgical goals in patients undergoing FOAR for trigonocephaly that closely correlates with post-operative outcomes. The normative dural model warrants further study and validation for other forms of craniosynostosis correction. [ABSTRACT FROM AUTHOR]

High product diversity, dynamic market conditions, and a lack of skilled workers are current challenges in manufacturing. Industrial robots autonomously planning and completing upcoming production tasks can help companies address these challenges. In this publication, we focus on autonomous task planning within industrial robotics and investigate how to facilitate the use of automated planning techniques from the field of artificial intelligence for this purpose. First, we present a novel methodology to automatically adapt abstractly modeled planning domains to the characteristics of individual application cases a user intends to implement. A planning domain is a formalized representation of the robot's working environment that builds the basis for automated planning. Second, we integrate this approach into the procedure for developing skills-based industrial robotic applications to enable them to perform autonomous task planning. Finally, we demonstrate the use of the methodology within the application field kitting in two reference scenarios with a mobile robot and a stationary robot cell. Using our methodology, persons without expertise in automated planning can enable a robot for autonomous task planning without much extra effort. [ABSTRACT FROM AUTHOR]

Collaborative Problem-Solving Skills (CPS) have become increasingly important. Research into the development of CPS is still scarce, but there are several approaches that may be useful for its development. Specifically, providing feedback in collaborative contexts is key. In this paper, we study and develop a feedback system that uses Automated Planning techniques to promote communication among students. Our system is designed to be used in a real-world educational setting, considering the underpinning theory of when and how to give feedback. The system's frontend is a video game, which presents tasks that can only be solved when students collaborate. In the backend, the system computes the solution to the task in a partial-order plan using an automated planning engine. While it monitors the plan and provides feedback to students. We describe an experimental study involving 42 students aged between 10 and 13, in which we explore the effectiveness of the feedback that was given. We show that the feedback allowed the students to perform better in the game, improve their communication, and develop their collaborative problem-solving skills. We also describe a novel approach to monitoring multi-agent partial-order plans, specifically designed for plans with so-called independent chains, that is more efficient than previous approaches and therefore requires fewer computational resources in the classroom. This paper contributes to the literature in two ways. First, we propose a novel monitoring algorithm for partial-order plans that is better suited to educational settings. Second, we show that feedback extracted from a plan can promote reflection about collaborative problem-solving during a multi-agent activity. [ABSTRACT FROM AUTHOR]

Cold spraying has emerged as a promising technique for the repair of metallic components. Manipulating the cold spray gun by industrial robots, referred to as robot-guided cold spraying, enables flexible and controlled material deposition. This work proposes a concept for automated planning of robotic cold spray paths and trajectories, enabling effective and efficient material deposition at specified repair locations. The concept incorporates predefined cold spray parameterizations and boundary conditions to provide the best possible material deposition for the individual repair application. The concept begins with the extraction of the volume to be filled. This volume is then sliced into suitable adaptively curved layers and converted into point clouds for path planning. Subsequently, the cold spray path is converted into a trajectory by adding a calculated spray velocity profile to produce the required locally varying layer thicknesses. In addition, simulation of the material deposition and a kinematic analysis of the simulated trajectory are performed. These are utilized as performance indicators for assessing deposit quality and material efficiency, enabling the validation and improvement of the parameterized trajectory. Finally, the implementation of the entire concept is demonstrated by representative use cases. The results demonstrate successful automated path and trajectory planning by the proposed concept, contributing to the overall goal of automated repair of damaged components by cold spraying. [ABSTRACT FROM AUTHOR]

Nonlinear Model Predictive Control (NMPC) is effective for local planning of automated vehicles, especially when there exist dynamical objects and multipe requirements. But it requires many computation resources for numerical optimization, which limits its practical application becase of the limited power of onboard unit. To extend the application range of the NMPC based local planner, the coupled nonlinear vehicle dynamics model is adopted based on the numerical analysis, which conversely requires much more discretization poits for acceptable accuracy. For better computation efficiency, Lagrange polynomials are used to discretize the vehicle dynamics model and objective function with less points and fine numerical accuracy. Furthermore, an adaptive strategy is designed to determine the order of Lagrange polynomials according to running state by numerical analysis of discretization error. Both acceleration effect and performance of the local planner designed by NMPC are validated by experimental tests under scenarios with multiple dynamical obstacles. The test results show that compared with the original one the accuracy and efficiency are improved by 74% and 60%, respectively. [ABSTRACT FROM AUTHOR]

Purpose: The goal of this study was to propose a knowledge-based planning system which could automatically design plans for lung cancer patients treated with intensity-modulated radiotherapy (IMRT). Methods and materials: From May 2018 to June 2020, 612 IMRT treatment plans of lung cancer patients were retrospectively selected to construct a planning database. Knowledge-based planning (KBP) architecture named αDiar was proposed in this study. It consisted of two parts separated by a firewall. One was the in-hospital workstation, and the other was the search engine in the cloud. Based on our previous study, A‑Net in the in-hospital workstation was used to generate predicted virtual dose images. A search engine including a three-dimensional convolutional neural network (3D CNN) was constructed to derive the feature vectors of dose images. By comparing the similarity of the features between virtual dose images and the clinical dose images in the database, the most similar feature was found. The optimization parameters (OPs) of the treatment plan corresponding to the most similar feature were assigned to the new plan, and the design of a new treatment plan was automatically completed. After αDiar was developed, we performed two studies. The first retrospective study was conducted to validate whether this architecture was qualified for clinical practice and involved 96 patients. The second comparative study was performed to investigate whether αDiar could assist dosimetrists in improving the quality of planning for the patients. Two dosimetrists were involved and designed plans for only one trial with and without αDiar; 26 patients were involved in this study. Results: The first study showed that about 54% (52/96) of the automatically generated plans would achieve the dosimetric constraints of the Radiation Therapy Oncology Group (RTOG) and about 93% (89/96) of the automatically generated plans would achieve the dosimetric constraints of the National Comprehensive Cancer Network (NCCN). The second study showed that the quality of treatment planning designed by junior dosimetrists was improved with the help of αDiar. Conclusions: Our results showed that αDiar was an effective tool to improve planning quality. Over half of the patients' plans could be designed automatically. For the remaining patients, although the automatically designed plans did not fully meet the clinical requirements, their quality was also better than that of manual plans. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The main goal of Nearest Prototype Classification is to reduce storage space and retrieval time of classical Instance-Based Learning (IBL) algorithms. This motivation is higher in relational data since relational distance metrics are much more expensive to compute than classical distances like Euclidean distance. In this paper, we present an algorithm to build Relational Nearest Prototype Classifiers (RNPCs). When compared with Relational Instance-Based Learning (Relational IBL or RIBL) approaches, the algorithm is able to dramatically reduce the number of instances by selecting the most relevant prototypes, maintaining similar accuracy. The number of prototypes is obtained automatically by the algorithm, although it can also be bound by the user. In this work, we also show an application of RNPC for automated planning. Specifically, we describe a modeling task where a relational policy is built following an IBL approach. This approach uses the decisions taken by a planning system as learning examples. We show that when the number of learning examples is reduced with RNPC, the resulting policy is able to scale up better than the original planning system. [ABSTRACT FROM AUTHOR]

To ensure sufficient repair of a metal structure damaged from, e.g., corrosion or wear by wire arc additive manufacturing (WAAM), appropriate toolpath planning and prediction of material deposition for the welding process are required. In the current work, a planner employing combined contour and raster pattern paths based on a sliced surface scan of the damage was developed. To extend existing empirical models for material deposition during welding to the two-dimensional paths used in WAAM, a paraboloid deposition function was used. Realistic deposition rates for uneven substrates were ensured by continuously adjusting the vertex height of the paraboloid in closely timed deposition events along the path. The deposition prediction can be used to assess if additional layers of repair welding are needed to fill a damage. For a repair with a build height of around 13 mm, the damage was sufficiently filled after following the generated toolpath plan, and a minimal amount of voids were observed. Errors in the material deposition prediction were within ± 1 mm in most of the repair. Errors in the predicted deposition were higher in the start/stop regions of weld beads, presumably because the ignition procedure in the welding machine was not accounted for. [ABSTRACT FROM AUTHOR]

Testing concurrent programs is a challenging problem due to interleaving explosion: even for a fixed set of inputs, there is a huge number of concurrent runs that need to be tested to account for scheduler behavior. Testing all possible schedules is not practical. Consequently, most effective testing algorithms only test a select subset of runs. For example, limiting testing to runs that contain data races or atomicity violations has been shown to capture a large proportion of concurrency bugs. In this paper we present a general approach to concurrent program testing that is based on techniques from artificial intelligence (AI) automated planning. We propose a framework for predicting concurrent program runs that violate a collection of generic correctness specifications for concurrent programs, namely runs that contain data races, atomicity violations, or null-pointer dereferences. Our prediction is based on observing an arbitrary run of the program, and using information collected from this run to model the behavior of the program, and to predict new runs that contain bugs with one of the above noted violation patterns. We characterize the problem of predicting such new runs as an AI sequential planning problem with the temporally extended goal of achieving a particular violation pattern. In contrast to many state-of-the-art approaches, in our approach feasibility of the predicted runs is guaranteed and, therefore, all generated runs are fully usable for testing. Moreover, our planning-based approach has the merit that it can easily accommodate a variety of violation patterns which serve as the selection criteria for guiding search in the state space of concurrent runs. This is achieved by simply modifying the planning goal. We have implemented our approach using state-of-the-art AI planning techniques and tested it within the Penelope concurrent program testing framework []. Nevertheless, the approach is general and is amenable to a variety of program testing frameworks. Our experiments with a benchmark suite showed that our approach is very fast and highly effective, finding all known bugs. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Purpose: Reaction databases are a key resource for a wide variety of applications in computational chemistry and biochemistry, including Computer-aided Synthesis Planning (CASP) and the large-scale analysis of metabolic networks. The full potential of these resources can only be realized if datasets are accurate and complete. Missing co-reactants and co-products, i.e., unbalanced reactions, however, are the rule rather than the exception. The curation and correction of such incomplete entries is thus an urgent need. Methods: The SynRBL framework addresses this issue with a dual-strategy: a rule-based method for non-carbon compounds, using atomic symbols and counts for prediction, alongside a Maximum Common Subgraph (MCS)-based technique for carbon compounds, aimed at aligning reactants and products to infer missing entities. Results: The rule-based method exceeded 99% accuracy, while MCS-based accuracy varied from 81.19 to 99.33%, depending on reaction properties. Furthermore, an applicability domain and a machine learning scoring function were devised to quantify prediction confidence. The overall efficacy of this framework was delineated through its success rate and accuracy metrics, which spanned from 89.83 to 99.75% and 90.85 to 99.05%, respectively. Conclusion: The SynRBL framework offers a novel solution for recalibrating chemical reactions, significantly enhancing reaction completeness. With rigorous validation, it achieved groundbreaking accuracy in reaction rebalancing. This sets the stage for future improvement in particular of atom-atom mapping techniques as well as of downstream tasks such as automated synthesis planning. Scientific Contribution: SynRBL features a novel computational approach to correcting unbalanced entries in chemical reaction databases. By combining heuristic rules for inferring non-carbon compounds and common subgraph searches to address carbon unbalance, SynRBL successfully addresses most instances of this problem, which affects the majority of data in most large-scale resources. Compared to alternative solutions, SynRBL achieves a dramatic increase in both success rate and accurary, and provides the first freely available open source solution for this problem. [ABSTRACT FROM AUTHOR]

The core of graphical programming for sheet-metal bending is operation planning based on parameter identification, which can directly determine the bending quality and efficiency. Given this, the proposed graphical programming system and method can predict the inner arc radius of bending oriented to programming demands and optimize multi-step bending operations. At first, a neural network model based on multi-layer perceptron (MLP) was established, considering the number of neurons and hidden layers. In the bending process a fitness function was defined, and the discrete particle swarm optimization (DPSO) was improved using the adaptive inertia weight and the genetic algorithm (GA). Finally, the operation planning of 10-step and 20-step bending was simulated, and bending tests were conducted on sheet-metal workpieces for verification. The results show that the algorithm's maximum positive error and minimum negative error in predicting the arc radius are 0.12 mm and − 0.16 mm, respectively. When there are 10 bending steps, the particle swarm optimization-genetic algorithm (PSO-GA) converges after only ten evolutions; when the bending steps increase to 20, the fitness value finally stabilizes at 1.31. The optimal operations of the experimental six-step bending part are 6 → 5 → 4 → 3 → 1 → 2. This result indicates that the workpiece is turned over three times and turned around once in the sheet-metal bending process, which is consistent with the simulation, thus verifying the bending efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Goal Recognition is the task of discerning the intended goal that an agent aims to achieve, given a set of goal hypotheses, a domain model, and a sequence of observations (i.e., a sample of the plan executed in the environment). Existing approaches assume that goal hypotheses comprise a single conjunctive formula over a single final state and that the environment dynamics are deterministic, preventing the recognition of temporally extended goals in more complex settings. In this paper, we expand goal recognition to temporally extended goals in Fully Observable Non-Deterministic (fond) planning domain models, focusing on goals on finite traces expressed in Linear Temporal Logic (ltl f ) and Pure-Past Linear Temporal Logic (ppltl). We develop the first approach capable of recognizing goals in such settings and evaluate it using different ltl f and ppltl goals over six fond planning domain models. Empirical results show that our approach is accurate in recognizing temporally extended goals in different recognition settings. [ABSTRACT FROM AUTHOR]

Background: Anterior closing wedge osteotomies (ACWO) are performed in revision anterior cruciate ligament (ACL) surgery to correct an excessive posterior tibial slope (PTS). Purpose: With the help of automated planning software, this study investigates the assumption that 1mm of wedge height gives 1° of slope correction (1:1). Methods: Fifty patients underwent ACWO, with the wedge height calculated using the 1:1 formula. Pre- and postosteotomy PTS were measured manually, and the achieved post-operative PTS was compared with the target PTS of 5.3° ± 1.9. The X-ray analysis was repeated virtually with the automated software, which also recommended a resection height. These parameters were then compared with the manually obtained parameters. Results: Using a 1:1 formula, wedge heights of 8.5mm ± 2.3 was resected to achieve a PTS of 4.2° ± 0.32. This showed an overcorrection of 1.6° ± 0.8 from the target slope. This was consistent with the data from the automated software, which recommended a lower wedge height of 7.7mm ± 2.9. Conclusion: In trans-tubercle ACW, using a wedge height (mm) to slope correction (°) ratio of 1:1 can lead to slight over-correction. Automated software planning is useful for planning correction osteotomies in the sagittal plane. [ABSTRACT FROM AUTHOR]

Introduction: Radiographic stress shielding is a common finding in uncemented convertible short-stem shoulder arthroplasty (UCSSSA). The distal filling ratio (DFR) has been described as a predictor for the occurrence of stress shielding. A DFR > 70% was mentioned as a risk factor for the occurrence of stress shielding for some UCSSSA. However, measurements were only performed on conventional radiographs and no validation exists for 3D automated planning tools. Methods: DFR was manually measured on postoperative true ap radiographs of 76 shoulder arthroplasties using a standardized protocol and were compared to preoperative CT scans with an automated calculation of the DFR after virtual implantation of the stem. Results: The mean DFR measured on X-rays was 75.9% (SD = 8.7; 95% CI = 74–78) vs. 78.9% (SD = 9.1; 95% CI = 76.8–83) automatically measured on CT scans. This difference was significant (p < 0.001). In 7 out of 76 cases (9%) the difference between manual measurement on radiographs and computerized measurement on CT scans was > 10%. Conclusion: Manual measurement of the DFR is underestimated on conventional radiographs compared to automated calculation on CT scans be a mean of 3%. Therefore, automated measurement of the DFR on CT scans seems to be beneficial, especially in cases with osteopenic cortices. Manual measurement of the DFR on conventional ap radiographs in cases without CT scans, however, is still a viable alternative. Level of evidence: Level IV, retrospective study. [ABSTRACT FROM AUTHOR]

Metal additive manufacturing has revolutionized the manufacturing industry due to its capability of building complex parts without any part-specific tooling. Wire arc metal additive manufacturing is a process that uses the arc welding technique to build parts layer by layer. Robotic manipulators equipped with arc welding hardware can perform wire arc additive manufacturing and build complex geometries. In addition, the manipulator's flexibility expands the capabilities of the additive manufacturing process. However, the geometries of the parts are limited by the flat substrate used for this process. This research aims to overcome this limitation by exploring a conformal substrate for wire arc additive manufacturing. Along with exploring the conformal substrate, this research will close the gap of the technical advancements and experimental validation required to build conformal metal parts. A conformal substrate makes the process planning complex. We address this complexity by making five novel contributions: (1) exploratory experiments with copper and iron as conformal substrate materials to determine if they are appropriate for the build material; (2) development of a corner accumulation detection algorithm for bead defect detection; (3) development of a process-specific tool-path planning algorithm to avoid molten metal from flowing under gravity; (4) development of a substrate placement planning algorithm to fit the trajectory in the manipulator's workspace; (5) building and characterization of the built parts' mechanical properties. Five truss-like parts are built using our process planning approach. Three of the truss-like parts are planar, and two truss-like parts are conformal. The parts are characterized to understand the effects of conformal substrate on the microstructure, microhardness, and T-peel strength. [ABSTRACT FROM AUTHOR]

Purpose/objectives: The complex planning and quality assurance required for spine SBRT are a barrier to implementation in time-sensitive or limited resource clinical situations. We developed and validated an automated inverse planning algorithm designed to streamline planning and allow rapid delivery of conformal single fraction spine SBRT using widely available technology. Materials/methods: The Rapid Spine (RaSp) automated script successfully generated single fraction SBRT plans for fourteen complex spinal lesions previously treated at a single high-volume institution. Automated RaSp plans were limited to 5 beams with a total of 15 segments (allowing calculation-based verification) and optimized based on RTOG 0631 objectives. Standard single fraction (16 Gy) stereotactic IMRT plans were generated for the same set of complex spinal lesions and used for comparison. A conservative 2 mm posterior isocenter shift was used to simulate minor set-up error. Results: Automated plans were generated in under 5 min from target definition and had a mean dose to the PTV of 1663 cGy (SD 131.5), a dose to 90 % of PTV (D90) of 1358 cGy (SD 111.0), and a maximum point dose (Dmax) to the PTV of 2055 cGy (SD 195.2) on average. IMRT plans took longer to generate but yielded more favorable dose escalation with a mean dose to the PTV of 1891 cGy (SD 117.6), D90 of 1731 cGy (SD 126.5), and Dmax of 2218 cGy (SD 195.7). A 2 mm posterior shift resulted in a 20 % (SD 10.5 %) increase in cord dose for IMRT plans and a 10 % (SD 5.3 %) increase for RaSp plans. The 2 mm perturbation caused 3 cord dose violations for the IMRT plans and 1 violation for corresponding RaSp plans. Conclusion: The Rapid Spine plan method yields timely and dosimetrically reasonable SBRT plans which meet RTOG 0631 objectives and are suitable for rapid yet robust pretreatment quality assurance followed by expedited treatment delivery. RaSp plans reduce the tradeoff between rapid treatment and optimal dosimetry in urgent cases and limited resource situations. [ABSTRACT FROM AUTHOR]

Purpose: 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. Materials and methods: 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. Results: 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. Conclusion: 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. [ABSTRACT FROM AUTHOR]

Predictive management of power consumption during static scheduling of outfitting automatic transportation equipment is very difficult. In addition, dynamic scheduling has poor response ability to sudden failures and emergency order insertion. To solve this problem, this paper proposes a scheduling approach for AGVs (automatic guided vehicles) in intelligent outfitting warehouses based on periodic driving and event triggering and integrating electricity power management. First, a power consumption model for AGVs is established and used to calculate the charging time of AGVs in initial scheduling. The charging time can be preplanned to avoid disturbance to the scheduling process. Second, considering the dynamic nature of transportation tasks, a periodically driven scheduling method is established to cope with uncertain emergency transportation tasks. In addition, considering the issue of sudden AGV failures, an event-triggered strategy is established to reduce the impact of sudden AGV failures on the scheduling process. Finally, an optimization algorithm based on power consumption and failure maintenance for outfitting vehicle scheduling is developed to solve the optimization model in a specific case. The proposed method can preplan the charging time according to the vehicle power consumption. Rescheduling is carried out for sudden failure and emergency tasks to improve the dynamic response capability of outfitting transport vehicles. [ABSTRACT FROM AUTHOR]

This study aimed to evaluate the robustness against geometric uncertainties in the hybrid intensity-modulated radiation therapy (IMRT) plans generated by commercially available software for automated breast planning (ABP). The ABP plans were compared with commonly used forward-planned field-in-field (FIF) technique plans. The planning computed tomography datasets of 20 patients who received left-sided breast-conserving surgery were used for both the ABP and FIF plans. Geometric uncertainties were simulated by shifting beam isocenters by 2, 3, 5, and 10 mm in the six directions: anterior/posterior, left/right, and superior/inferior. A total of 500 plans (20 patients and 25 scenarios, including the original plan) were created for each of the ABP and FIF plans. The homogeneity index of the target volume in the ABP plans was significantly better (p < 0.001) than the value in the FIF plans in the scenarios of shifting beam isocenters by 2, 3, and 5 mm. Mean heart dose and percentage volume of lungs receiving a dose more than 20 Gy were clinically acceptable in all scenarios. The hybrid IMRT plans generated by commercially available ABP software provided better robustness against geometric uncertainties than forward-planned FIF plans. [ABSTRACT FROM AUTHOR]

Inspection planning approaches so far have focused on automatically obtaining an optimal set of viewpoints required to cover a given object. While research has provided interesting results, the automatic inspection planning has still not been made a part of the everyday inspection system development process. This is mostly because the plans are difficult to verify and it is impossible to compare them to laboratory-developed plans. In this work, we give an overview of available generate-and-test approaches, evaluate their results for various objects and finally compare them to plans created by inspection system development experts. The comparison emphasizes both benefits and downsides of automated approaches and highlights problems which need to be tackled in the future in order to make the automated inspection planning more applicable. [ABSTRACT FROM AUTHOR]

Although the notion of task similarity is potentially interesting in a wide range of areas such as curriculum learning or automated planning, it has mostly been tied to transfer learning. Transfer is based on the idea of reusing the knowledge acquired in the learning of a set of source tasks to a new learning process in a target task, assuming that the target and source tasks are close enough. In recent years, transfer learning has succeeded in making reinforcement learning (RL) algorithms more efficient (e.g., by reducing the number of samples needed to achieve (near-)optimal performance). Transfer in RL is based on the core concept of similarity: whenever the tasks are similar, the transferred knowledge can be reused to solve the target task and significantly improve the learning performance. Therefore, the selection of good metrics to measure these similarities is a critical aspect when building transfer RL algorithms, especially when this knowledge is transferred from simulation to the real world. In the literature, there are many metrics to measure the similarity between MDPs, hence, many definitions of similarity or its complement distance have been considered. In this paper, we propose a categorization of these metrics and analyze the definitions of similarity proposed so far, taking into account such categorization. We also follow this taxonomy to survey the existing literature, as well as suggesting future directions for the construction of new metrics. [ABSTRACT FROM AUTHOR]

Numerical simulation is an efficient tool for evaluation and prediction of material properties and behavior in many industrial domains such as the development of novel materials and medicines. For numerical studies of complex processes or systems with high fidelity, various data processing tools, modeling and simulation programs are typically involved, desiring an integrated platform that can effectively manage the collaboration of such software resources and the execution of the underlying simulation workflow for efficiency purpose. Such a platform could be practically built with a scientific computing workflow engine that focuses on the automatic scheduling and execution of a batch of interrelated computing tasks. In this work, the main procedures on construction of a specialized integrated simulation platform for material research based on a general purpose scientific computing workflow engine named HSWAP is introduced in detail, and its application to molecule screening process of energetic materials is demonstrated. Due to the flexibility and the extensibility of the platform, the work could be handily extended to the screening of other materials such as protein to find optimized protein structures or high entropy alloys to find the best configuration of component contents, as well as other application scenarios such as geometry optimizations of complex structures. [ABSTRACT FROM AUTHOR]

Task scheduling (TS) and multi-agent-path-finding (MAPF) are two cruxes of pickup-and-delivery in automated warehouses. In this paper, the two cruxes are optimized simultaneously. Firstly, the system model, task model, and path model are established, respectively. Then, a task scheduling algorithm based on enhanced HEFT, a heuristic MAPF algorithm and a TS- MAPF algorithm are proposed to solve this combinatorial optimization problem. In EHEFT, a novel rank priority rule is used to determine task sequencing and task allocation. In MAPF algorithm, a CBS algorithm with priority rules is designed for path search. Subsequently, the TS-MAPF algorithm which combines EHEFT and MAPF is proposed. Finally, the proposed algorithms are tested separately against relevant typical algorithms at different scales. The experimental results indicate that the proposed algorithms exhibited good performance. [ABSTRACT FROM AUTHOR]

Driving comfort significantly affects travel experiences. However, the most prevailing automated vehicle (AV) control strategies mainly focus on the safety and efficiency concerns, neglecting the comfort perspective. Moreover, pavement conditions, such as roughness and distress, cannot be directly detected by standard AV onboard sensors, although they are essential factors impacting driving comfort. This study aimed to present a vehicle-to-infrastructure system to adjust AV trajectories for alleviating the negative impacts of bumpy roads on comfort. The precollected lane-based roadway roughness information was used to optimally adjust the longitudinal and lateral AV trajectories. The method was validated by an eight-degree-of-freedom full-car simulation model. Specifically, the relationships among comfort, jerk, speed, and pavement parameters were revealed and applied to the adjustment process. The results showed that the trajectory adjustment approach improved the overall comfort level by 30 % in the numerical case. Furthermore, a framework was designed to facilitate data exchanges between vehicles and infrastructures in empirical scenarios. The proposed method had the potential to assist AVs in better-perceived driving quality. [ABSTRACT FROM AUTHOR]

Upcoming space missions are requiring a higher degree of on-board autonomy operations to increase quality science return, to minimize closed-loop space-ground decision making, and to enable new scenarios. Artificial Intelligence technologies like Machine Learning and Automated Planning are becoming more and more popular as they can support data analytics conducted directly on-board as input for the on-board decision making system that generates plans or updates them while being executed. This paper describes the planning and execution architecture under development at the European Space Agency to target this need of autonomy for the ops-sat mission. [ABSTRACT FROM AUTHOR]

The process of designing progressive dies can be complex, tedious, time-consuming, and error-prone, which can significantly impact the development period and design quality. This paper presents a systematic methodology that includes the planning design and automated design of die structure. A super process model (SPM) is presented as the output of the planning design of die structure and the input of the automated design of die structure. Subsequently, parametric template methodology based on deformation feature process geometry (DFPG) is proposed to automate the design of punches and dies. Lastly, a layout method based on layout space for standard parts is proposed to perform the automated layout of standard parts for die-sets, punches, and dies; additionally, a robust calculation method of layout space is introduced. This system is then implemented in two home appliance enterprises. Case studies and industrial applications have demonstrated the effectiveness of the developed system, which can improve the design efficiency by a minimum of 85% and reduce design error by an average of 50%. [ABSTRACT FROM AUTHOR]

The car of the future will be driven by software and offer a variety of customisation options. Enabling these customisation options forces modern automotive manufacturers to update their standardised scheduling concepts for testing and commissioning cars. A flexible scheduling concept means that every chosen customer configuration code must have its own testing procedure. This concept is essential to provide individual testing workflows where the time and resources are optimised for every car. Manual scheduling is complicated due to constraints on time, predecessor-successor relationships, mutual exclusion criteria, resources and status conditions on the car engineering and assembly line. Applied methods to handle the mathematical formulation for the corresponding industrial optimisation problem and its implementation are not yet available. This paper presents a procedure for automated and non-preemptive scheduling in the testing and commissioning of cars, which is built on a Boolean satisfiability problem on parallel and identical machines with temporal and resource constraints. The presented method is successfully implemented and evaluated on a variant assembly line of an automotive Original Equipment Manufacturer. This paper is the starting point for an automated workflow planning and scheduling process in automotive manufacturing. [ABSTRACT FROM AUTHOR]

A many-server asymptotic regime is obtained by scaling capacity: HT ht , as HT ht ( HT ht is the resulting occupancy). We interpret the function I h i in two ways: I Target (soft capacity): i I X i is a G/G/ HT ht process, which depends on HT ht (deterministic) but not on I h i ; it is random due to service durations. I Capacity: i I X i is G/G/ HT ht , with arrivals HT ht and number-of-available servers HT ht (hence I X i depends on both HT ht and I h i ). [Extracted from the article]

Radiotherapy (RT) is one of the main treatment strategies of breast cancer. It is challenging to design RT plans that can completely cover the target area while protecting organs at risk (OAR). The Plan-IQ feasibility tool can estimate the best sparing dose of OAR before optimizing the Plan. A systematic quantitative evaluation of the quality change of intensity-modulated radiation therapy (IMRT) using the Plan-IQ feasibility tool was performed for modified radical mastectomy in this study. We selected 50 patients with breast cancer treated with IMRT. All patients received the same dose in the planning target volume (PTV). The plans are categorized into two groups, with each patient having one plan in each group: the clinically accepted normal plan group (NP group) and the repeat plan group (RP group). An automated planning strategy was generated using a Plan-IQ feasibility dose volume histogram (FDVH) in RP group. These plans were assessed according to the dosimetry parameters. A detailed scoring strategy was based on the RTOG9804 report and 2018 National Comprehensive Cancer Network guidelines, combined with clinical experience. PTV coverage in both groups was achieved at 100% of the prescribed dose. Except for the thyroid coverage, the dose limit of organs at risk (OAR) in RP group was significantly better than that in NP group. In the scoring analysis, the total scores of RP group decreased compared to that of NP group (P < 0.05), and the individual scores of PTV and OAR significantly changed. PTV scores in RP group decreased (P < 0.01); however, OAR scores improved (P < 0.01). The Plan-IQ FDVH was useful for evaluating a class solution for IMRT planning. Plan-IQ can automatically help physicians design the best OAR protection plan, which sacrifices part of PTV, but still meets clinical requirements. [ABSTRACT FROM AUTHOR]

Traditional urban planning demands urban experts to spend much time producing an optimal urban plan under many architectural constraints. The remarkable imaginative ability of deep generative learning provides hope for renovating this domain. Existing works are constrained by: (1) neglecting human requirements; (2) omitting spatial hierarchies, and (3) lacking urban plan samples. We propose a novel, deep human-instructed urban planner to fill these gaps and implement two practical frameworks. In the preliminary version, we formulate the task into an encoder–decoder paradigm. The encoder is to learn the information distribution of surrounding contexts, human instructions, and land-use configuration. The decoder is to reconstruct the land-use configuration and the associated urban functional zones. Although it has achieved good results, the generation performance is still unstable due to the complex optimization directions of the decoder. Thus, we propose a cascading deep generative adversarial network (GAN) in this paper, inspired by the workflow of urban experts. The first GAN is to build urban functional zones based on human instructions and surrounding contexts. The second GAN will produce the land-use configuration by considering the built urban functional zones. Finally, we conducted extensive experiments and case studies to validate the effectiveness and superiority of our work. [ABSTRACT FROM AUTHOR]

Inefficient management of resources and waiting lists for high-risk ophthalmology patients can contribute to sight loss. The aim was to develop a decision support tool which determines an optimal patient schedule for ophthalmology patients. Our approach considers available booking slots as well as patient-specific factors. Using standard software (Microsoft Excel and OpenSolver), an operations research approach was used to formulate a mathematical model. Given a set of patients and clinic capacities, the model objective was to schedule patients efficiently depending on eyecare measure risk factors, referral-to-treatment times and targets, patient locations and slot availabilities over a pre-defined planning horizon. Our decision support tool can feedback whether or not a patient is scheduled. If a patient is scheduled, the tool determines the optimal date and location to book the patients' appointments, with a score provided to show the associated value of the decisions made. Our dataset from 519 patients showed optimal prioritization based on location, risk of serious vision loss/damage and the referral-to-treatment time. Given the constraints of available slots, managers can input hospital-specific parameters such as demand and capacity into our model. The model can be applied and implemented immediately, without the need for additional software, to generate an optimized patient schedule. [ABSTRACT FROM AUTHOR]

Model checking provides a way to automatically explore the state space of a finite state system based on desired properties, whereas planning is to produce a sequence of actions that leads from the initial state to the target goal states. Previous research in this field proposed a number of approaches for connecting model checking with planning problem solving. In this paper, we investigate the feasibility of using an established model checking framework, Process Analysis Toolkit (PAT), as a planning solution provider for upper layer applications. To achieve this, we first carry out a number of experiments on different model checking tools in order to compare their performance and capabilities on planning problem solving. Our experimental results suggest that solving planning problems using model checkers is not only possible but also practical. We then propose a formal semantic mapping from the standard Planning Domain Description Language (PDDL) to the Labeled Transition System (LTS), based on which a planning module was implemented as a part of the PAT framework. Lastly, we demonstrate and evaluate the approach of using PAT as planning service via a case study on a public transportation management system. [ABSTRACT FROM AUTHOR]

Background: Published treatment technique comparisons for postoperative left-sided whole breast irradiation (WBI) with deep-inspiration breath-hold (DIBH) are scarce, small, and inconclusive. In this study, fully automated multi-criterial plan optimization, generating a single high-quality, Pareto-optimal plan per patient and treatment technique, was used to compare for a large patient cohort 1) intensity modulated radiotherapy (IMRT) with two tangential fields and 2) volumetric modulated arc therapy (VMAT) with two small tangential subarcs. Materials and methods: Forty-eight randomly selected patients recently treated with DIBH and 16 × 2.66 Gy were included. The optimizer was configured for the clinical planning protocol. Comparisons between IMRT and VMAT included dosimetric plan parameters, estimated excess relative risks (ERR) for toxicities, delivery times, MUs, and deliverability accuracy at a linac. Results: The automatically generated IMRT and VMAT plans applied in this study were similar or higher in quality than the manually generated clinical plans. For equal PTVin V95% (98.4 ± 0.9%), VMAT had significant advantages compared to IMRT regarding breast dose homogeneity and doses in heart and ipsilateral lung, at the cost of some minor deteriorations for contralateral breast (few cases with larger deteriorations) and lung. Conformality improved from 1.38 to 1.18 (p < 0.001). With VMAT, ERR for major coronary events and ipsilateral lung tumors were reduced by 3% (range: −1–12%) and 16% (range: −3–38%), respectively. MUs and delivery times were higher for VMAT. There were no statistical differences in γ passing rates. Conclusion: For WBI in conservative therapy of left-sided breast patients treated with DIBH, VMAT with two tangential subarcs was generally dosimetrically superior to IMRT with two tangential static fields. Results need confirmation by robustness analyses. [ABSTRACT FROM AUTHOR]

Modern astrophysics research has heavily relied on data measured from telescopes. Reasonable observational scheduling brings into play action on the output of highly sensitive data and utilization of telescopes. However, most existing observational scheduling methods aim to solve medium- to long-term problems with proposals as scheduled objects. Nevertheless, the Yunnan 40 m Radio Telescope (YRT40) has the requirements of short-term scheduling within a few days. In this paper, we present a time-dependent short-term observational scheduling method based on a genetic algorithm to achieve automatic scheduling of observation targets. We established a mathematical model of a multi-objective optimization with time dependence and the constraints of telescope hardware conditions with the aim of minimizing the slew time of the telescope and maximizing the scientific values of the targets. In the experiments, we adopted the actual observational targets of YRT40. The results from tests on the runtime of the telescope demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The main issue in multi-agent planning (MAP) is the agents' coordination process that is a computationally hard problem. Thus, many works focus on the planning strategy considering the computational process, agents' distribution roles, information privacy, and the resources coupling level. But domain-independent models that explore the balance between coordination process and privacy leading to efficient execution are missing. In this manuscript, we present a Lightweight Coordination Multi-agent Planning (LCMAP), a domain-independent model that balances the coordination process and privacy through three independent phases: (i) verification—each agent verifies its capabilities of reaching the goals; (ii) transformation—the coordinator selects agents through their capabilities and distributes the goals, transforming the original problem into single-agent problems; and (iii) validation—each plan is validated to check whether it can be parallel. LCMAP was compared to the state-of-the-art models to evaluate time efficiency and plan length during the problem-solving process using loosely and tightly coupled domains with specific evaluation metrics inherited from planning competitions. Furthermore, we conducted experiments to evaluate the execution efficiency regarding different configurations concerning planning time and plan length of the models, when LCMAP execution proves to be efficient. [ABSTRACT FROM AUTHOR]

This article presents a novel approach for the automated 3D-layout planning of multi-station assembly lines. The planning method is based on a comprehensive model of the used production resources, including their geometry, kinematic properties, and general characteristics. Different resource types can be included in the planning system. A genetic algorithm generates and optimizes possible layouts for a line. The optimization aims to minimize the line's area and the costs for assembling the line while simultaneously optimizing the resources' positioning to perform their tasks. The line's cycle time is considered as a boundary condition. For the evaluation of different layout alternatives, a multi-body simulation is performed. A parameter study is used to set the algorithm's parameters. Afterward, the algorithm is applied to three increasingly complex examples to validate and evaluate its functionality. The approach is promising for industrial applications as it allows the integration of various resource types and individualization of the optimization function. [ABSTRACT FROM AUTHOR]

Minimizing the setup costs caused by color changes is one of the main concerns for paint shop scheduling in the automotive industry. Yet, finding an optimized color sequence is a very challenging task, as a large number of exterior systems for car manufacturing need to be painted in a variety of different colors. Therefore, there is a strong need for efficient automated scheduling solutions in this area. Previously, exact and metaheuristic approaches for creating efficient paint shop schedules in the automotive supply industry have been proposed and evaluated on a publicly available set of real-life benchmark instances. However, optimal solutions are still unknown for many of the benchmark instances, and there is still a potential of reducing color change costs for large instances. In this paper, we propose a novel large neighborhood search approach for the paint shop scheduling problem. We introduce innovative exact and heuristic solution methods that are utilized within the large neighborhood search and show that our approach leads to improved results for large real-life problem instances compared to existing techniques. Furthermore, we provide previously unknown upper bounds for 14 benchmark instances using the proposed method. [ABSTRACT FROM AUTHOR]

The CIRCA planning system automatically creates reactive plans and uses formal verification techniques to prove that those plans will preserve system safety. CIRCA's timed automata verification system is highly efficient, yet can display pathologically bad behavior when reasoning about reaction loops, a particular form of interacting cycles of states. In this paper, we describe a loop acceleration technique that recognizes these state-space structures during the verification process and bypasses the process of expanding an arbitrarily large cycle of states, effectively compressing loops of arbitrary size into a compact, finite set of states. The resulting performance improvement can be very dramatic: in domains where tight loops of short-duration transitions interact with long-duration transitions, our new loop acceleration methods can reduce verification time (and hence planning time) from hours to below a second. [ABSTRACT FROM AUTHOR]

Many of today's most successful planners perform a forward heuristic search. The accuracy of the heuristic estimates and the cost of their computation determine the performance of the planner. Thanks to the efforts of researchers in the area of heuristic search planning, modern algorithms are able to generate high-quality estimates. In this paper we propose to learn heuristic functions using artificial neural networks and support vector machines. This approach can be used to learn standalone heuristic functions but also to improve standard planning heuristics. One of the most famous and successful variants for heuristic search planning is used by the Fast-Forward (FF) planner. We analyze the performance of standalone learned heuristics based on nature-inspired machine learning techniques and employ a comparison to the standard FF heuristic and other heuristic learning approaches. In the conducted experiments artificial neural networks and support vector machines were able to produce standalone heuristics of superior accuracy. Also, the resulting heuristics are computationally much more performant than related ones. [ABSTRACT FROM AUTHOR]

In this paper, we propose a domain learning process build on a machine learning-based process that, starting from plan traces with (partially known) intermediate states, returns a planning domain with numeric predicates, and expressive logical/arithmetic relations between domain predicates written in the planning domain definition language (PDDL). The novelty of our approach is that it can discover relations with little information about the ontology of the target domain to be learned. This is achieved by applying a selection of preprocessing, regression, and classification techniques to infer information from the input plan traces. These techniques are used to prepare the planning data, discover relational/numeric expressions, or extract the preconditions and effects of the domain's actions. Our solution was evaluated using several metrics from the literature, taking as experimental data plan traces obtained from several domains from the International Planning Competition. The experiments demonstrate that our proposal—even with high levels of incompleteness—correctly learns a wide variety of domains discovering relational/arithmetic expressions, showing F-Score values above 0.85 and obtaining valid domains in most of the experiments. [ABSTRACT FROM AUTHOR]

The ability to express derived predicates in the formalization of a planning domain is both practically and theoretically important. In this paper, we propose an approach to planning with derived predicates where the search space consists of 'Rule-Action Graphs', particular graphs of actions and rules representing derived predicates. We propose some techniques for representing such rules and reasoning with them, which are integrated into a framework for planning through local search and rule-action graphs. We also present some heuristics for guiding the search of a rule-action graph representing a valid plan. Finally, we analyze our approach through an extensive experimental study aimed at evaluating the importance of some specific techniques for the performance of the approach. The results of our experiments also show that our planner performs quite well compared to other state-of-the-art planners handling derived predicates. [ABSTRACT FROM AUTHOR]

Automatic scheduling techniques are becoming a crucial tool for the efficient planning of large astronomical surveys. A specific scheduling method is being designed and developed for the Atmospheric Remote-sensing Infrared Exoplanet Large-survey (Ariel) mission planning based on a hybrid meta-heuristic algorithm with global optimization capability to ensure obtaining satisfying results fulfilling all mission constraints. We used this method to simulate the Ariel mission plan, to assess the feasibility of its scientific goals, and to study the outcome of different science scenarios. We conclude that Ariel will be able to fulfill the scientific objectives, i.e. characterizing ∼ 1000 exoplanet atmospheres, with a total exposure time representing about 75–80% of the mission lifetime. We demonstrate that it is possible to include phase curve observations for a sample of targets or to increase the number of studied exoplanets within the mission lifetime. Finally, around 12–15% of the time can still be used for non-time constrained observations. [ABSTRACT FROM AUTHOR]

Wooden pallets are commonly used as load carriers in many industrial and logistic applications. This article investigates and formalizes the production planning for a highly automated but customized pallet production and provides a solution approach. For completing a specific pallet, the required boards must be cut and stacked in advance to meet the demand at the assembly line. The arising planning problem for producing the required boards consists of both a cutting stock and a constraining open stack problem. Further, both the changeover of raw material at the cutting process and the number of fully automated internal storages, for stacked boards, are restricted. The proposed solution heuristic aims at minimizing the cutting waste. Additionally, feasibility with regard to the buffers is tested using discrete event simulation. Different approaches to generate, select and sequence the cutting patterns are investigated. [ABSTRACT FROM AUTHOR]

Establishing a healthy lifestyle has become a very important aspect in people's lives. The latter requires maintaining a healthy nutrition by considering the nature and quantity of foods being consumed, allowing to regulate one's intake and consumption of calories and nutrients. As a result, people reach out for nutrition experts which services are costly, time-consuming, and not readily available. While various e-solutions have been developed to perform meal planning, yet most of them lack a completely automated process and require domain expert intervention at different stages of the recommendation process (e.g., identifying macronutrient distribution, providing pre-defined meal plans, or combining recommended foods into meal structures). In addition, most solutions focus on fulfilling the patients' nutrition requirements (in terms of caloric intake and macronutrients) while disregarding other relevant factors such as patient food preferences, food variety, food-meal compatibility, and inter-food compatibility. Hence, there is a need for an automated solution to produce a full-fledged meal plan from scratch, based on a recommended caloric intake and considering multiple factors. In this study, we introduce a novel solution titled MPG for automated Meal Plan Generation recommendations, designed based on an adaptation of the transportation optimization problem to simulate the "human thought process" involved in generating daily meal plans. MPG allows to: (i) generate plans which fulfill a recommended caloric intake, given a set of available foods, while (ii) personalizing the plans following patient chosen factors (e.g., food preferences, variety, and compatibility), and (iii) evaluating the relevance of the produced plans following patient preferences. We have conducted various experiments involving 9 human testers and 124 meal plans to test the performance of MPG. Results highlight MPG's effectiveness in producing "healthy" and personalized meal plans while complying with the testers' preferences. [ABSTRACT FROM AUTHOR]

Automated treatment planning may decrease the effort required in planning and promote increased routine clinical use of intensity-modulated radiation therapy (IMRT) for many breast cancer patients. The aim of this study was to evaluate a new commercial automated planning software for tangential breast IMRT by comparing it with clinical plans from whole-breast irradiation. We prospectively enrolled 150 patients with Stage 0–1 breast cancer who underwent breast-conserving surgery at our institution between September 2016 and August 2017. Total doses of 42.56 Gy in 16 fractions (n = 98) or 50 Gy in 25 fractions (n = 44) were used. All treatment plans were retrospectively re-planned using the automated breast planning (ABP) software. All automated plans generated clinically deliverable beam parameters with no patient body collision and no contralateral breast pass through. The mean homogeneity index of the automatically generated clinical target volume, percentage volume of lungs receiving dose more than 20 Gy, mean heart dose, and dose to the highest irradiated 2-cc volumes of the irradiated volume were 0.077 ± 0.019, 4.2% ± 1.2%, 142 ± 69 cGy, and 105.8% ± 1.7% (prescribed dose: 100%), respectively. The mean planning time was 4.8 ± 1.4 min. The ABP software demonstrated high clinical acceptability and treatment planning cost efficiency for tangential breast IMRT. The ABP software may be useful for delivering high-quality treatment to a majority of patients with early-stage breast cancer. [ABSTRACT FROM AUTHOR]