Execution Monitoring Research Articles

Optimizing mining projects: how business intelligence enhances data-driven decisions

The project management sector grapples with the challenge of handling a vast amount of information. Data compilation is essential to support effective decision-making processes by project managers. This paper emphasizes the significance of both project planning and execution monitoring. It concurrently explores the applicability of Business Intelligence (BI) software and its contributions to enhancing project management. The methodology employed a literature review combined with the authors' expertise in engineering projects. The findings reveal that BI offers substantial benefits. These include reducing the time required to transform large datasets into clear and concise graphical information that can be readily presented and dynamically adjusted to meet specific user needs. A study conducted in a mining company demonstrated a significant reduction in project management activities. By utilizing Power BI software, they achieved a 50% reduction in total time dedicated to project management activities. Additionally, there was a remarkable 83% reduction in the time spent on report issuance and updates. This outcome enables that project team members are aligned with consolidated information, facilitating real-time decision-making and fostering greater integration and productivity.

Interpersonal population diversity in the bank boardroom and corporate misconduct

PurposeThis research empirically establishes that the interpersonal population diversity of executive board members partly explains the differences in financial misconduct across US banks. It advances the hypothesis that heterogeneity in the composition of an interpersonal population and diverse traits of board members, originating from the prehistoric course of the exodus of Homo sapiens from East Africa tens of thousands of years ago, is an important factor explaining the effectiveness of executive board monitoring with respect to a bank engaging in financial misconduct. The underlying intuition is that population-fragmented societies, characterized by mistrust, preference heterogeneity and corruption, find it difficult to sustain collective integrity action.Design/methodology/approachEmploying a panel of US banks from 1998 to 2019 we find that adding directors from countries with different levels of interpersonal population diversity is positively associated with financial misconduct as measured by enforcement and class action litigation against banks by the main regulatory agencies. Furthermore, we document that the more population-diverse bank boards are more likely to commit misconduct, consistent with a mechanism of inter-generational transmission of cultural norms of mistrust and non-cooperation.FindingsWe find that adding directors from countries with different levels of interpersonal population diversity is positively associated with financial misconduct as measured by enforcement and class action litigation against banks by the main regulatory agencies. These results are robust to controlling for bank-specific variables, including other board characteristics, and to the use of instrumental variables.Practical implicationsThe findings suggest that reducing financial misconduct by banks likely requires reducing the interpersonal population diversity of banks’ executive boards.Originality/valueWe show how bank boards with different interpersonal population diversity impact the likelihood of engaging in misconduct provides evidence of the microeconomic effects of interpersonal population diversity. We show the negative results of diversity that they can have on the management of a firm given that populated diverse boards are more likely to lead to higher levels of misconduct. Our evidence reveals that banks having interpersonal population fragmented boards are more likely to commit misconduct given the cultural norms of mistrust and the lack of societal cohesiveness.

Monitoring Intensity, Institutional Shareholders, and Earnings Manipulation Engendered Accounting Scandal: The South African Perspective

This study determines the extent to which loosening institutional shareholder monitoring intensity induces earnings management, thereby leading to accounting scandals. When there is intense monitoring of the corporate executives, their opportunistic tendencies are prevented, and corporate decisions align with the value-creation target. The study postulates that institutional shareholders' relaxed monitoring role positively and significantly impacts earnings management. The more robust Two-Step System GMM was used to analyse the collected data of companies listed on the Johannesburg Stock Exchange (JSE) for 15 years from 2004 to 2019. The finding revealed that slack institutional shareholders' control affects earnings management positively.

Abstract 4959: Immunopipe: A comprehensive and flexible scRNA-seq and scTCR-seq data analysis pipeline

Abstract Introduction: Single-cell RNA-sequencing (scRNA-seq) pairing with single-cell T-Cell-Receptor-sequencing (scTCR-seq) enables profiling of gene expression and TCR repertoires in individual T cells, elevating our understanding of T-cell-mediated immunity. Here, we present immunopipe, a comprehensive and flexible pipeline (https://github.com/pwwang/immunopipe) for analyzing the paired data. Besides the command-line tool, it offers a user-friendly web interface that allows users with varying programming expertise to configure, initiate, and monitor the pipeline. By combining extensive functionality with ease of use, immunopipe empowers users to unlock valuable insights from the data, which notably advances our understanding of immune response and fosters the development of innovative immunotherapies. Results: Immunopipe is a comprehensive analytical pipeline for scRNA-seq and scTCR-seq data, offering various modules leveraging existing tools and novel methods to ensure data quality and enable downstream analytics. It performs quality control for scRNA-seq data, clusters cells based on gene expression to facilitate the identification of cell populations and provides insights into T-cell heterogeneity and functional diversity through T-cell selection and clustering. Enrichment analysis identifies markers and pathways for T-cell characterization. Our automated T-cell annotation tool annotates cell types accurately and hierarchically. For scTCR-seq data, immunopipe analyzes TCR clones, including clonality, diversity, gene usage, and repertoire overlap. Clone residency analysis examines the presence of clones across samples. Integrative analyses combine scRNA-seq and scTCR-seq data, providing a comprehensive understanding of the cellular landscape. Immunopipe incorporates diverse cell group information to analyze T-cell populations, which enables granular perspectives of the data for comprehensive insights. Immunopipe offers a flexible platform, allowing users to customize the analyses as needed. It supports both core and optional analyses through configuration, where users have control over the adjustable parameters. The pipeline relies on cell grouping information that can be referenced from metadata or modified to generate new variables for analysis and data filtering. Immunopipe can be executed locally or on scheduler platforms, and a docker image is provided for compatibility and simplified installation. It also offers a web interface that facilitates configuration, execution monitoring, and access to results. Conclusion: Immunopipe is a flexible and user-friendly pipeline for analyzing scRNA-seq and scTCR-seq data. It empowers researchers to gain valuable insights that could enhance the understanding of immune responses and facilitate the development of innovative immunotherapies. Citation Format: Panwen Wang, Haidong Dong, Yue Yu, Shuwen Zhang, Zhifu Sun, Jean-Pierre A. Kocher, Junwen Wang, Lin Yi, Ying Li. Immunopipe: A comprehensive and flexible scRNA-seq and scTCR-seq data analysis pipeline [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4959.

Scrutinizing the adoption of smart contracts in the MENA Region’s Construction Industry

ABSTRACT The construction industry embodies a paramount role in the economic growth of various nations, including the Middle East and North Africa (MENA) region. Despite its significance, the industry faces construction disputes and payment issues, inducing financial losses and project postponements. Consequently, the construction industry has mutated smart contracts to enhance operational efficiency, which automates contract management tasks and offers perks, including transparency and efficiency. However, the adoption of smart contracts in the MENA construction sector remains limited, and the region lacks thorough research on this topic. This study addresses this gap by examining the level of cognizance and apprehension of smart contracts among construction industry stakeholders in the MENA region. The research employs Structural Equation Modeling (SEM) to analyze the relative importance of implementing smart contracts within different project lifecycle phases and relevant practices and identify the hindrances impacting MENA’s smart contract deployment. A practical implementation of smart contract-based tendering employing the Trakti platform is paraded. The findings unveiled the infancy of smart contract adoption in the MENA construction sector. They revealed the substantial importance of implementing smart contracts in the Project Execution Phase, Project Closure, and Monitoring and Control Phase, attaining relative weights of 23.23%, 21.62%, and 20.50%, respectively.

Parsing state mindfulness effects on neurobehavioral markers of cognitive control: A within-subject comparison of focused attention and open monitoring.

Over the past two decades, scientific interest in understanding the relationship between mindfulness and cognition has accelerated. However, despite considerable investigative efforts, pervasive methodological inconsistencies within the literature preclude a thorough understanding of whether or how mindfulness influences core cognitive functions. The purpose of the current study is to provide an initial "proof-of-concept" demonstration of a new research strategy and methodological approach designed to address previous limitations. Specifically, we implemented a novel fully within-subject state induction protocol to elucidate the neurobehavioral influence of discrete mindfulness states-focused attention (FA) and open monitoring (OM), compared against an active control-on well-established behavioral and ERP indices of executive attention and error monitoring assessed during the Eriksen flanker task. Bayesian mixed modeling was used to test preregistered hypotheses pertaining to FA and OM effects on flanker interference, the stimulus-locked P3, and the response-locked ERN and Pe. Results yielded strong but unexpected evidence that OM selectively produced a more cautious and intentional response style, characterized by higher accuracy, slower RTs, and reduced P3 amplitude. Follow-up exploratory analyses revealed that trait mindfulness moderated the influence of OM, such that individuals with greater trait mindfulness responded more cautiously and exhibited higher trial accuracy and smaller P3s. Neither FA nor OM modulated the ERN or Pe. Taken together, our findings support the promise of our approach, demonstrating that theoretically distinct mindfulness states are functionally dissociable among mindfulness-naive participants and that interactive variability associated with different operational facets of mindfulness (i.e., state vs. trait) can be modeled directly.

An enhanced state-aware model learning approach for security analysis in lightweight protocol implementations

Owing to the emergence and rapid advances of new-generation information and digitalization technologies, the concept of model-driven digital twin has received widespread attentions and is developing vigorously. Driven by data and simulators, the digital twin can create the virtual twins of physical objects to perform monitoring, simulation, prediction, optimization, and so on. Hence, the application of digital twin can increase efficiency and security of systems by providing reliable model and decision supports. In this paper, we propose a state-aware model learning method to simulate and analyze the lightweight protocol implementations in edge/cloud environments. We introduce the data flow of program execution and network interaction inputs/outputs (I/O) into the extended finite state machine (EFSM) to expand the modeling scope and insight. We aim to calibrate the states and construct an accurate state-machine model using a digital twin based layered approach to reasonably reflect the correlation of a device’s external behavior and internal data. This, in turn, improves our ability to verify the logic and evaluate the security for protocol implementations. This method firstly involves instrumenting the target device to monitor variable activity during its execution. We then employ learning algorithms to produce multiple rounds of message queries. Both the I/O data corresponding to these query sequences and the state calibration information derived from filtered memory variables are obtained through the mapper and execution monitor, respectively. These two aspects of information are combined to dynamically and incrementally construct the protocol’s state machine. We apply this method to develop SALearn and evaluate the effectiveness of SALearn on two lightweight protocol implementations. Our experimental results indicate that SALearn outperforms existing protocol model learning tools, achieving higher learning efficiency and uncovering more interesting states and security issues. In total, we identified two violation scenarios of rekey logic. These situations also reflect the differences in details between different implementations.

Penerapan Konsep Hybrid Contracts dalam Pembiayaan Rahn di Pegadaian Syariah

Islamic financing has become an increasingly popular option for individuals and businesses looking to meet their financial needs in accordance with Islamic principles. One of the prominent innovations in Islamic financing is the concept of Hybrid Contracts, which allows combining several types of Islamic contracts in one financing product. This article explores the role and benefits of the concept of Hybrid Contracts in financing rahn at Pegadaian Syariah. We also explain the detailed implementation steps, which include customer identification, risk evaluation, determination of sharia contract type, application submission, feasibility review, contract signing, transaction execution, and financing monitoring. The concept of Hybrid Contracts helps increase flexibility, inclusivity, and compliance with sharia principles in rahn financing, opening the door to broader sharia-based economic development.

INTERCONNECTION OF DIVERSIFICATION AND VALUE BASED MANAGEMENT IN SMALL WHOLESALE BUSINESS

In the paper, we found out types of diversification suitable for small wholesale business in Ukraine in wartime. The most suitable types of diversification are: service, product, financial and geographic diversification. Also, horizontal, vertical, conglomerate and concentric types of diversification can be applied, taking into account their benefits and potential pitfalls defined in this paper.We also considered diversification as a value-creating strategy, outlined its main benefits and pitfalls. It offers several benefits, such as risk reduction by spreading investments across industries, thus reducing dependence on one market. It allows for synergies in related diversification through shared resources and expertise, enhancing efficiency and profitability. Additionally, diversification enables portfolio optimization, balancing performance across various sectors. However, it entails challenges like integration difficulties, potential overextension, and the risk of not realizing expected synergies. Effective diversification requires a clear strategic rationale, meticulous execution, and continuous monitoring, with willingness to divest from underperforming areas to sustain value creation.We suggested using Value Chain Analysis for choosing the most effective strategy of diversification for small wholesale business and developed Value Chain of a Small Wholesale Business (particularly, with heating equipment wholesale as a main type of activity).By understanding how each activity affects customer value, businesses can tailor their strategies to enhance customer satisfaction and loyalty. This might involve improving product quality, customer service, or any other activity directly impacting the customer experience.Value Chain Analysis is a strategic lens through which a business can view its activities and make informed decisions about where to focus its resources to maximize value creation.The next step of choosing the most effective value-creating strategy is building a Value Drivers Tree for each strategy considered and choosing the one creating the highest value of business.

A Novel Control Architecture Based on Behavior Trees for an Omni-Directional Mobile Robot

Robotic systems are increasingly present in dynamic environments. This paper proposes a hierarchical control structure wherein a behavior tree (BT) is used to improve the flexibility and adaptability of an omni-directional mobile robot for point stabilization. Flexibility and adaptability are crucial at each level of the sense–plan–act loop to implement robust and effective robotic solutions in dynamic environments. The proposed BT combines high-level decision making and continuous execution monitoring while applying non-linear model predictive control (NMPC) for the point stabilization of an omni-directional mobile robot. The proposed control architecture can guide the mobile robot to any configuration within the workspace while satisfying state constraints (e.g., obstacle avoidance) and input constraints (e.g., motor limits). The effectiveness of the controller was validated through a set of realistic simulation scenarios and experiments in a real environment, where an industrial omni-directional mobile robot performed a point stabilization task with obstacle avoidance in a workspace.

Role of Infrared Thermography in Planning and Monitoring of Head and Neck Microvascular Flap Reconstruction.

Reconstruction using microvascular free flaps has become the standard of care in head and neck cancer surgery, and their success lies in appropriate planning, adequate revascularization, and early detection of flap compromise so that prompt salvage is possible. This study evaluates the role of infrared thermography in the planning, execution, and postoperative monitoring of microvascular flaps in head and neck reconstructions. This is a single institutional, prospective observational study conducted at a tertiary care hospital in South India for 13 months. Twenty patients were included, and their thermographic images were captured in the preoperative, intraoperative, and postoperative settings using the infrared camera FLIR T400. These images were analyzed along with the Doppler, and clinical monitoring findings in all the settings and the temperature difference were calculated postoperatively. Hotspot perforator marking was made using infrared camera, and perforator marking was made using hand-held Doppler preoperatively, which correlated in 93% of cases. Intraoperatively, flap rewarming was successfully demonstrated in 19 of 20 cases. Postoperatively, flap compromise was observed on infrared thermography during the first 24 hours but not on clinical monitoring in three cases. The temperature difference values recorded were 5.4°C, 2.4°C, and 4.9°C. The mean of temperature difference of the healthy flaps was 1.0°C (range 0.1°C-1.8°C). Infrared thermography provides simple and reliable imaging, which can be used in perforator marking and flap designing preoperatively and checking the flap perfusion and vascular anastomosis patency intra- and postoperatively.

Probabilistic Programs as an Action Description Language

Actions description languages (ADLs), such as STRIPS, PDDL, and RDDL specify the input format for planning algorithms. Unfortunately, their syntax is familiar to planning experts only, and not to potential users of planning technology. Moreover, this syntax limits the ability to describe complex and large domains. We argue that programming languages (PLs), and more specifically, probabilistic programming languages (PPLs), provide a more suitable alternative. PLs are familiar to all programmers, support complex data types and rich libraries for their manipulation, and have powerful constructs, such as loops, sub-routines, and local variables with which complex, realistic models and complex objectives can be simply and naturally specified. PPLs, specifically, make it easy to specify distributions, which is essential for stochastic models. The natural objection to this proposal is that PLs are opaque and too expressive, making reasoning about them difficult. However, PPLs also come with efficient inference algorithms, which, coupled with a growing body of work on sampling-based and gradient-based planning, imply that planning and execution monitoring can be carried out efficiently in practice. In this paper, we expand on this proposal, illustrating its potential with examples.

Prospective memory: the combined impact of cognitive load and task focality

Prospective Memory (PM) entails a set of executive processes primarily associated with the activation of frontal and parietal regions. Both the number of PM-targets to be monitored (i.e. task load) and the relationship between the type of PM-targets and the ongoing (ONG) task (i.e. task focality) can impact executive monitoring and PM performance. In the present imaging study, we manipulated load and focality of an event-based PM task to test the hypothesis that common resources engage in situations requiring high levels of cognitive control: that is, in high-load (i.e. monitor multiple PM-targets) and non-focal conditions (i.e. monitor at the same time letters’ identity and color). We investigated monitoring-related and detection-related processes by assessing behavior and brain activity separately for ONG trials (monitoring) and PM-targets (detection). At the behavioral level, we found a significant interaction between load and focality during detection, with slowest reaction times for focal, high-load PM-targets. The imaging analyses of the detection phase revealed the activation of the left intraparietal sulcus in the high-load conditions. Both in the monitoring and the detection phases, we found overlapping effects of non-focality and low-load in the fusiform gyrus. Our results suggest that under low-load conditions, cognitive control operates via early selection mechanisms in the ventral occipito-temporal cortex. By contrast, high-load conditions entail control at later processing stages within the dorsal parietal cortex. We conclude that load and focality operate via different mechanisms, with the level of task load largely determining how cognitive control selects the most relevant information.

Regulation of work execution processes in railway construction using neural network technologies

The article presents the theoretical provisions and practical possibilities of regulating the technological process implementation of construction railway track entity using an artificial neural network. Railway construction as a complex dynamic system requires certain resources for its maintenance. Under these conditions, effective control over the technology of work execution performed during the railway track entity construction is of decisive importance. This can be achieved by improving the existing system of engineering and technical support for railway construction through the introduction of a subsystem for engineering and intellectual support of technological processes for the railway entities construction. One of the subsystem’s tasks is the effective use of automation tools with artificial intelligence elements. The appearance of deviations from planned requirements during construction work, due to the stochastic nature of railway construction, leads to technology violations, an increase in labor costs, prime cost, an increase in duration and, as a result, a deterioration in the railway entity operational characteristics. To avoid such a development of events, a prompt review of the adopted technological solutions is necessary. To this end, as part of the methodology formation for technological processes engineering and intellectual support of railway construction, a system has been developed for regulating the technological processes implementation for the railway entity construction. The process regulation is based on the work execution monitoring results. Adjusting the technological process to changing work execution conditions flexibility in the railway track entity construction. This is achieved by choosing regulatory solutions using the artificial neural network capabilities and then adjusting the work progress. Based on the theoretical study results, the article presents the practical aspects of the work execution processes regulation implementation in railway construction using neural network technologies on the example of a flooded railway roadbed subgrade construction. The results presented in the article were obtained in the course of a dissertation research carried out by the author.

Does high cash compensation compromise the independence of outside directors? Evidence from directors' dissenting votes in China

Using data on directors' voting behaviour in board meetings in China, we examine whether high cash compensation compromises outside directors' independence in markets with weak investor protection. The results show that highly paid outside directors are more likely to vote against proposals sponsored by executives, particularly in firms with weaker monitoring of executives. Highly paid outside directors are also positively associated with cash dividends and future firm performance. Overall, the evidence suggests that high cash compensation reflects the market value of reputable outside directors and reputation concerns motivate outside directors to maintain their independence and challenge executives in board meetings.

Detection of Vulnerabilities by Incorrect Use of Variable Using Machine Learning

Common Weakness Enumeration (CWE) refers to a list of faults caused from software or hardware. The CWE includes the faults related to programming language and security. We propose a technique to detect the vulnerabilities from incorrect use of a variable in C language. There are various static/dynamic methods to detect the variable vulnerabilities. However, when analyzing the vulnerabilities, a static technique causes a lot of false alarms, meaning that there is no fault in the actual implementation. When monitoring the variable via the static analysis, there is a great overhead during execution, so its application is not easy in a real environment. In this paper, we propose a method to reduce false alarms and detect vulnerabilities by performing static analysis and dynamic verification using machine learning. Our method extracts information on variables through static analysis and detects defects through static analysis results and execution monitoring of the variables. In this process, it is determined whether the currently used variable values are valid and whether the variables are used in the correct order by learning the initial values and permissible range of the variables using machine learning techniques. We implemented our method as VVDUM (Variable Vulnerability Detector Using Machine learning). We conducted the comparative experiment with the existing static/dynamic analysis tools. As a result, compared with other tools with the rate of variable vulnerability detection between 9.17~18.5%, ours had that of 89.5%. In particular, VVDUM detects ‘defects out of the range of valid’ that are difficult to detect with existing methods, and the overhead due to defect detection is small. In addition, there were a few overheads at run time that were caused during data collection for detection of a fault.

Evolution of Solid Waste Management System in Lahore: A Step towards Sustainability of the Sector in Pakistan

Solid Waste Management (SWM) is a technical subject which requires comprehensive planning, execution, and effective operational monitoring under cost-effective modes compatible with environmentally sound technologies. The policymakers made some enormous efforts for the sustainability of this sector as well as setting a benchmark for other municipalities and Waste Management Companies (WMCs) in the country. Provincial Government prioritizes its focus on SWM, i.e., waste collection, transportation, treatment, and final disposal. The waste management sector in Lahore has achieved sustainability in waste collection and haulage components by gaining experience from international outsourcing and, now, sharing its knowledge with other municipalities to strengthen the sector in the country. Lahore has emerged with the highest collection efficiency (84%) in SAARC countries and placed fifth in rank in comparison to 54 low–middle-income countries/cities worldwide. The sectorial interventions in Lahore reveal an aspiration for the sustainability of the SWM sector in Pakistan. However, there is an urgent need to focus and invest in waste-related infrastructure development, i.e., permanent/mobile transfer stations, semi-underground containers for commercial and planned areas, material recovery facilities (MRF), and landfill. Environmental and economic sustainability in this sector can be achieved through public–private partnership (PPP) modality in compost, anaerobic digestion, recycling, and refuse-derived fuel (RDF) as it is a more feasible option to strengthen the industry in the country.

A digital twin based framework for detection, diagnosis, and improvement of throughput bottlenecks

Digitalization through Industry 4.0 technologies is one of the essential steps for the complete collaboration, communication, and integration of heterogeneous resources in a manufacturing organization towards improving manufacturing performance. One of the ways is to measure the effective utilization of critical resources, also known as bottlenecks. Finding such critical resources in a manufacturing system has been a significant focus of manufacturing research for several decades. However, finding a bottleneck in a complex manufacturing system is difficult due to the interdependencies and interactions of many resources. In this work, a digital twin framework is developed to detect, diagnose, and improve bottleneck resources using utilization-based bottleneck analysis, process mining, and diagnostic analytics. Unlike existing bottleneck detection methods, this novel approach is capable of directly utilizing enterprise data from multiple levels, namely production planning, process execution, and asset monitoring, to generate event-log which can be fed into a digital twin. This enables not only the detection and diagnosis of bottleneck resources, but also validation of various what-if improvement scenarios. The digital twin itself is generated through process mining techniques, which can extract the main process map from a complex system. The results show that the utilization can detect both sole and shifting bottlenecks in a complex manufacturing system. Diagnosing and managing bottleneck resources through the proposed approach yielded a minimum throughput improvement of 10% in a real factory setting. The concept of a custom digital twin for a specific context and goal opens many new possibilities for studying the strong interaction of multi-source data and decision-making in a manufacturing system. This methodology also has the potential to be exploited for multi-objective optimization of bottleneck resources.

The Role of Executive Functions in Reading Comprehension by Adolescents with ADHD

The present study explored (a) whether differences between students with and without ADHD in reading comprehension are explained by their executive functions, and (b) the unique and shared contribution of the various executive functions to reading comprehension ability. To address these questions, ninety-six adolescents with and without ADHD completed open-ended question tests following the reading of two expository texts, and a series of tasks to assess five EF—planning, cognitive flexibility, updating, inhibition, and monitoring. Findings demonstrated significantly lower performance on reading comprehension tests and executive function tasks, including planning, cognitive flexibility, updating, and monitoring for the ADHD group relative to the control. Critically, these four executive functions, separately, were also found as significant mediators of the difference observed in the reading comprehension ability between groups. When analyzed jointly, only monitoring remained a significant mediator over and above all others. Contrary to expectations, inhibition skill did not differ between groups, nor was it found to be a significant mediator, separately or jointly with other executive functions. These findings support the importance of executive functions in general and monitoring skill in particular for reading comprehension ability. Moreover, they suggest implications for the development of effective reading comprehension training and strategies suited to students with ADHD.

Explainable Robotic Plan Execution Monitoring Under Partial Observability

Successful plan generation for autonomous systems is necessary but not sufficient to guarantee reaching a goal state by an execution of a plan. Various discrepancies between an expected state and the observed state may occur during the plan execution (e.g., due to unexpected exogenous events, changes in the goals, or failure of robot parts) and these discrepancies may lead to plan failures. For that reason, autonomous systems should be equipped with execution monitoring algorithms so that they can autonomously recover from such discrepancies. We introduce a plan execution monitoring algorithm that operates under partial observability. This algorithm relies on novel formal methods for hybrid prediction, diagnosis and explanation generation, and planning. The prediction module generates an expected state after the execution of a part of the plan from an incomplete state to check for discrepancies. The diagnostic reasoning module generates meaningful hypotheses to explain failures of robot parts. Unlike the existing diagnosis methods, the previous hypotheses can be revised, based on new partial observations, increasing the accuracy of explanations as further information becomes available. The replanning module considers these explanations while computing a new plan that would avoid such failures. All these reasoning modules are hybrid in that they combine high-level logical reasoning with low-level feasibility checks based on probabilistic methods. We experimentally show that these hybrid formal reasoning modules improve the performance of plan execution monitoring.