Search

Partially Observable Monte Carlo Planning (POMCP) is a powerful online algorithm that can generate approximate policies for large Partially Observable Markov Decision Processes. The online nature of this method supports scalability by avoiding complete policy representation. However, the lack of an explicit policy representation hinders interpretability and a proper evaluation of the risks an agent may incur. In this work, we propose a methodology based on Maximum Satisfiability Modulo Theory (MAX-SMT) for analyzing POMCP policies by inspecting their traces, namely, sequences of belief-action pairs generated by the algorithm. The proposed method explores local properties of the policy to build a compact and informative summary of the policy behaviour. Moreover, we introduce a rich and formal language that a domain expert can use to describe the expected behaviour of a policy. In more detail, we present a formulation that directly computes the risk involved in taking actions by considering the high-level elements specified by the expert. The final formula can identify risky decisions taken by POMCP that violate the expert indications. We show that this identification process can be used offline (to improve the policy's explainability and identify anomalous behaviours) or online (to shield the risky decisions of the POMCP algorithm). We present an extended evaluation of our approach on four domains: the well-known tiger and rocksample benchmarks, a problem of velocity regulation in mobile robots, and a problem of battery management in mobile robots. We test the methodology against a state-of-the-art anomaly detection algorithm to show that our approach can be used to identify anomalous behaviours in faulty POMCP. We also show, comparing the performance of shielded and unshielded POMCP, that the shielding mechanism can improve the system's performance. We provide an open-source implementation of the proposed methodologies at https://github.com/GiuMaz/XPOMCP. [ABSTRACT FROM AUTHOR]

In this paper, we propose the use of subspace clustering to detect the states of dynamical systems from sequences of observations. In particular, we generate sparse and interpretable models that relate the states of aquatic drones involved in autonomous water monitoring to the properties (e.g., statistical distribution) of data collected by drone sensors. The subspace clustering algorithm used is called SubCMedians. A quantitative experimental analysis is performed to investigate the connections between i) learning parameters and performance, ii) noise in the data and performance. The clustering obtained with this analysis outperforms those generated by previous approaches. [ABSTRACT FROM AUTHOR]

Metabolic P systems are a modeling framework for metabolic, regulatory and signaling processes. The key point of MP systems are flux regulation functions, which determine the evolution of a system from a given initial state. This paper presents important improvements to a technique, based on genetic algorithms and multiple linear regression, for inferring regulation functions that reproduce observed behaviors (time series datasets). An accurate analysis of three case studies, namely the mitotic oscillator in early amphibian embryos, the Lodka-Volterra predator-prey model and the chaotic logistic map show that this methodology can provide, from observed data, significant knowledge about the regulation mechanisms underlying biological processes. [ABSTRACT FROM AUTHOR]

Motivated by an interest to understand how information is organized within genomes, and how genes communicate between each other in the transcription process, in this paper we propose a novel network based methodology for genomic sequence analysis, specifically applied to three organisms: Nanoarchaeum equitans, Escherichia coli, and Saccaromyces cerevisiae. A dictionary based approach previously introduced is here continued through a repeat analysis in genic and intergenic regions. Key results of this work have been found in a biological and computational analysis of novel parametrized gene networks, defined by means of motifs of fixed length occurring inside multiple genes. Cliques emerge as groups of genes sharing a long repeat with a clear biological interpretation, while a (complete, paralog) cluster analysis has outlined some unexpected regularity. Repeat sharing gene networks may be applied in contexts of comparative genomics, as an investigation methodology for a comprehension of evolutional and functional properties of genes. [ABSTRACT FROM AUTHOR]

Background: In the post-genomic era several methods of computational genomics are emerging to understand how the whole information is structured within genomes. Literature of last five years accounts for several alignment-free methods, arisen as alternative metrics for dissimilarity of biological sequences. Among the others, recent approaches are based on empirical frequencies of DNA k-mers in whole genomes. Results: Any set of words (factors) occurring in a genome provides a genomic dictionary. About sixty genomes were analyzed by means of informational indexes based on genomic dictionaries, where a systemic view replaces a local sequence analysis. A software prototype applying a methodology here outlined carried out some computations on genomic data. We computed informational indexes, built the genomic dictionaries with different sizes, along with frequency distributions. The software performed three main tasks: computation of informational indexes, storage of these in a database, index analysis and visualization. The validation was done by investigating genomes of various organisms. A systematic analysis of genomic repeats of several lengths, which is of vivid interest in biology (for example to compute excessively represented functional sequences, such as promoters), was discussed, and suggested a method to define synthetic genetic networks. Conclusions: We introduced a methodology based on dictionaries, and an efficient motif-finding software application for comparative genomics. This approach could be extended along many investigation lines, namely exported in other contexts of computational genomics, as a basis for discrimination of genomic pathologies [ABSTRACT FROM AUTHOR]

workflow for data analysis is introduced to synthesize flux regulation maps of a Metabolic P system from time series of data observed in laboratory. The procedure is successfully tested on a significant case study, the photosynthetic phenomenon called NPQ, which determines plant accommodation to environmental light. A previously introduced MP model of such a photosynthetic process has been improved, by providing an MP system with a simpler regulative network that reproduces the observed behaviors of the natural system. Two regression techniques were employed to find out the regulation maps, and interesting experimental results came out in the context of their residual analysis for model validation. [ABSTRACT FROM AUTHOR]

In this work we give a formalization of Hybrid Functional Petri Nets, shortly HFPN, an extension of Petri Nets for biopathways modelling, and we compare them with Metabolic P Systems. An introduction to both the formalisms is given, together with highlights about respective similarities and differences. Their equivalence is thus proved by means of a theorem which holds under quite general hypotheses. The case study of the lac operon gene regulatory mechanism in the glycolytic pathway of Escherichia coli is modeled by an MP system which provides the same dynamics of an equivalent HFPN model. [ABSTRACT FROM AUTHOR]

Autonomous mobile robots employed in industrial applications often operate in complex and uncertain environments. In this paper we propose an approach based on an extension of Partially Observable Monte Carlo Planning (POMCP) for robot velocity regulation in industrial-like environments characterized by uncertain motion difficulties. The velocity selected by POMCP is used by a standard engine controller which deals with path planning. This two-layer approach allows POMCP to exploit prior knowledge on the relationships between task similarities to improve performance in terms of time spent to traverse a path with obstacles. We also propose three measures to support human-understanding of the strategy used by POMCP to improve the performance. The overall architecture is tested on a Turtlebot3 in two environments, a rectangular path and a realistic production line in a research lab. Tests performed on a C++ simulator confirm the capability of the proposed approach to profitably use prior knowledge, achieving a performance improvement from 0.7% to 3.1% depending on the complexity of the path. Experiments on a Unity simulator show that the proposed two-layer approach outperforms also single-layer approaches based only on the engine controller (i.e., without the POMCP layer). In this case the performance improvement is up to 37% comparing to a state-of-the-art deep reinforcement learning engine controller, and up to 51% comparing to the standard ROS engine controller. Finally, experiments in a real-world testing arena confirm the possibility to run the approach on real robots. [ABSTRACT FROM AUTHOR]

Summary: MP-GeneticSynth is a Java tool for discovering the logic and regulation mechanisms responsible for observed biological dynamics in terms of finite difference recurrent equations. The software makes use of: (i) metabolic P systems as a modeling framework, (ii) an evolutionary approach to discover flux regulation functions as linear combinations of given primitive functions, (iii) a suitable reformulation of the least squares method to estimate function parameters considering simultaneously all the reactions involved in complex dynamics. The tool is available as a plugin for the virtual laboratory MetaPlab. It has graphical and interactive interfaces for data preparation, a priori knowledge integration, and flux regulator analysis.Availability and implemention: Source code, binaries, documentation (including quick start guide and videos) and case studies are freely available at http://mplab.sci.univr.it/plugins/mpgs/index.html.Contact: castellini@mpimp-golm.mpg.de [ABSTRACT FROM PUBLISHER]

Autonomous surface vessels are becoming increasingly important for water monitoring. Their aim is to navigate rivers and lakes with limited intervention of human operators, to collect real-time data about water parameters. To reach this goal, these intelligent systems must interact with the environment and act according to the situations they face. In this work we propose a framework based on the integration of recent time-series clustering/segmentation methods and cluster validity indices, for detecting, modeling and evaluating aquatic drone states. The approach is completely data-driven and unsupervised. It takes unlabeled multivariate time series of sensor traces and returns both a set of statistically significant state-models (generated by different mathematical approaches) and a related segmentation of the dataset. We test the approach on a real dataset containing data of six campaigns, two in rivers and four in lakes, in different countries for about 5.6 h of navigation. Results show that the methodology is able to recognize known states and to discover unknown states, enabling novelty detection. The approach is therefore an easy-to-use tool for discovering and interpreting significant states in sensor data, that enables improved data analysis and drone autonomy. [ABSTRACT FROM AUTHOR]