Polynomial-time probabilistic observability analysis of sampled-data piecewise affine systems

This paper proposes a polynomial-time probabilistic approach to solve the observability problem of sampled-data piecewise affine systems. First, an algebraic characterization for the system to be observable is derived. Next, based on the characterization, we propose a randomized algorithm that can determine if the system is observable in a probabilistic sense or the system is not observable in a deterministic sense. Finally, it is shown with some examples, for which it is hopeless to check the observability in a deterministic way, that the proposed algorithm is very useful.     

Motion strategies for exploration and map building under uncertainty with multiple heterogeneous robots

In this paper, we present a multi-robot exploration strategy for map building. We consider an indoor structured environment and a team of robots with different sensing and motion capabilities. We combine geometric and probabilistic reasoning to propose a solution to our problem. We formalize the proposed solution using stochastic dynamic programming (SDP) in states with imperfect information. Our modeling can be considered as a partially observable Markov decision process (POMDP), which is optimized using SDP. We apply the dynamic programming technique in a reduced search space that allows us to incrementally explore the environment. We propose realistic sensor models and provide a method to compute the probability of the next observation given the current state of the team of robots based on a Bayesian approach. We also propose a probabilistic motion model, which allows us to take into account errors (noise) on the velocities applied to each robot. This modeling also allows us to simulate imperfect robot motions, and to estimate the probability of reaching the next state given the current state. We have implemented all our algorithms and simulations results are presented.     

Learning-based symbolic assume-guarantee reasoning for Markov decision process by using interval Markov process

Many real-life critical systems are described with large models and exhibit both probabilistic and non-deterministic behaviour. Verification of such systems requires techniques to avoid the state space explosion problem. Symbolic model checking and compositional verification such as assume-guarantee reasoning are two promising techniques to overcome this barrier. In this paper, we propose a probabilistic symbolic compositional verification approach (PSCV) to verify probabilistic systems where each component is a Markov decision process (MDP). PSCV starts by encoding implicitly the system components using compact data structures. To establish the symbolic compositional verification process, we propose a sound and complete symbolic assume-guarantee reasoning rule. To attain completeness of the symbolic assume-guarantee reasoning rule, we propose to model assumptions using interval MDP. In addition, we give a symbolic MTBDD-learning algorithm to generate automatically the symbolic assumptions. Moreover, we propose to use causality to generate small counterexamples in order to refine the conjecture assumptions. Experimental results suggest promising outlooks for our probabilistic symbolic compositional approach.     

A model‐based development approach for the verification of real‐time Java code

Many real‐time systems are safety‐and security‐critical systems and, as a result, tools and techniques for verifying them are extremely important. Simulation and testing such systems can be exceedingly time‐consuming and these techniques provide only probabilistic measures of correctness. There are a number of model‐checking tools for real‐time systems. Although they provide formal verification for models, we still need to implement these models. To increase the confidence in real‐time programs written in real‐time Java, this paper proposes a model‐based approach to the development of such programs. First, models can be mechanically verified, to check whether they satisfy particular properties, by using current real‐time model‐checking tools. Then, programs can be derived from the model by following a systematic approach. We introduce a timed automata to RTSJ Tool (TART), a prototype tool to automatically generate real‐time Java code from the model. Finally, we show the applicability of our approach by means of four examples: a gear controller, an audio/video protocol, a producer/consumer and the Fischer protocol. Copyright © 2011 John Wiley & Sons, Ltd.     

Toward finding hidden communities based on user profile

We consider the community detection problem from a partially observable network structure where some edges are not observable. Previous community detection methods are often based solely on the observed connectivity relation and the above situation is not explicitly considered. Even when the connectivity relation is partially observable, if some profile data about the vertices in the network is available, it can be exploited as auxiliary or additional information. We propose to utilize a graph structure (called a profile graph) which is constructed via the profile data, and propose a simple model to utilize both the observed connectivity relation and the profile graph. Furthermore, instead of a hierarchical approach, based on the modularity matrix of the network structure, we propose an embedding approach which utilizes the regularization via the profile graph. Various experiments are conducted over two social network datasets and comparison with several state-of-the-art methods is reported. The results are encouraging and indicate that it is promising to pursue this line of research.     

Interactive POMDPs with finite-state models of other agents

We consider an autonomous agent facing a stochastic, partially observable, multiagent environment. In order to compute an optimal plan, the agent must accurately predict the actions of the other agents, since they influence the state of the environment and ultimately the agent’s utility. To do so, we propose a special case of interactive partially observable Markov decision process, in which the agent does not explicitly model the other agents’ beliefs and preferences, and instead represents them as stochastic processes implemented by probabilistic deterministic finite state controllers (PDFCs). The agent maintains a probability distribution over the PDFC models of the other agents, and updates this belief using Bayesian inference. Since the number of nodes of these PDFCs is unknown and unbounded, the agent places a Bayesian nonparametric prior distribution over the infinitely dimensional set of PDFCs. This allows the size of the learned models to adapt to the complexity of the observed behavior. Deriving the posterior distribution is in this case too complex to be amenable to analytical computation; therefore, we provide a Markov chain Monte Carlo algorithm that approximates the posterior beliefs over the other agents’ PDFCs, given a sequence of (possibly imperfect) observations about their behavior. Experimental results show that the learned models converge behaviorally to the true ones. We consider two settings, one in which the agent first learns, then interacts with other agents, and one in which learning and planning are interleaved. We show that the agent’s performance increases as a result of learning in both situations. Moreover, we analyze the dynamics that ensue when two agents are simultaneously learning about each other while interacting, showing in an example environment that coordination emerges naturally from our approach. Furthermore, we demonstrate how an agent can exploit the learned models to perform indirect inference over the state of the environment via the modeled agent’s actions.     

Diagnosing time-varying misbehavior: an approach based on model decomposition

The analysis of time-varying systems is attracting a lot of attention in the model-based diagnosis community. In this paper we propose an approach to the diagnosis of such systems, relying on a component-oriented model; we provide separately a behavioral model, that is, knowledge about the consequences of differentbehavioral modes of the components, and a model of the possible temporal evolution of such modes (mode transition graphs). In the basic approach, we assume that the consequences of behavioral modes are instantaneous with respect to the transition between two modes; this allows us to decompose the solution of a temporal diagnostic problem into two subtasks: determining solutions of atemporal problems in different time points and assembling the solution of the temporal problem from those of the atemporal ones. Most of the definitions and machinery developed for static diagnosis can be re-used in such a framework. We then consider the consequences of some extensions. Even allowing for very simple temporal relations in the behavioral model leads to a more complex interference between reasoning on the behavioral models and the consistency check with respect to possible temporal evolutions. We also briefly analyze the case of adding quantitative temporal knowledge or probabilistic knowledge to the mode transition graphs.This work was partially supported by CNR under grants 91.00916.PF69 and 91.02351.CT12.     

Quantitative and qualitative analysis of SysML activity diagrams

Model-driven engineering refers to a range of approaches that uses models throughout systems and software development life cycle. Towards sustaining such a successful approach in practice, we present a model-based verification framework that supports the quantitative and qualitative analysis of SysML activity diagrams. To this end, we propose an algorithm that maps SysML activity diagrams into Markov decision processes expressed using the language of the probabilistic symbolic model checker PRISM. Furthermore, we elaborate on the correctness of our translation algorithm by proving its soundness with respect to a SysML activity diagrams operational semantics that we also present in this work. The generated models can be verified against a set of properties expressed in the probabilistic computation tree logic. To automate our approach, we developed a prototype tool that interfaces a modeling environment and the probabilistic model checker. We also show how to leverage adversary generation to provide the developer with a useful counterexample/witness as a feedback on the verified properties. Finally, the established theoretical foundations are complemented with an illustrative case study that demonstrates the usability and benefit of such a framework.     

Probabilistic robust design with linear quadratic regulators

In this paper, we study robust design of uncertain systems in a probabilistic setting by means of linear quadratic regulators (LQR). We consider systems affected by random bounded nonlinear uncertainty so that classical optimization methods based on linear matrix inequalities cannot be used without conservatism. The approach followed here is a blend of randomization techniques for the uncertainty together with convex optimization for the controller parameters. In particular, we propose an iterative algorithm for designing a controller which is based upon subgradient iterations. At each step of the sequence, we first generate a random sample and then we perform a subgradient step for a convex constraint defined by the LQR problem. The main result of the paper is to prove that this iterative algorithm provides a controller which quadratically stabilizes the uncertain system with probability one in a finite number of steps. In addition, at a fixed step, we compute a lower bound of the probability that a quadratically stabilizing controller is found.     

Effective learning system techniques for human–robot interaction in service environment

HRI (Human–Robot Interaction) is often frequent and intense in assistive service environment and it is known that realizing human-friendly interaction is a very difficult task because of human presence as a subsystem of the interaction process. After briefly discussing typical HRI models and characteristics of human, we point out that learning aspect would play an important role for designing the interaction process of the human-in-the loop system. We then show that the soft computing toolbox approach, especially with fuzzy set-based learning techniques, can be effectively adopted for modeling human behavior patterns as well as for processing human bio-signals including facial expressions, hand/ body gestures, EMG and so forth. Two project works are briefly described to illustrate how the fuzzy logic-based learning techniques and the soft computing toolbox approach are successfully applied for human-friendly HRI systems. Next, we observe that probabilistic fuzzy rules can handle inconsistent data patterns originated from human, and show that combination of fuzzy logic, fuzzy clustering, and probabilistic reasoning in a single frame leads to an algorithm of iterative fuzzy clustering with supervision. Further, we discuss a possibility of using the algorithm for inductively constructing probabilistic fuzzy rule base in a learning system of a smart home. Finally, we propose a life-long learning system architecture for the HRI type of human-in-the-loop systems.     

Optimal control of infinite horizon partially observable decision processes modelled as generators of probabilistic regular languages

Decision processes with incomplete state feedback have been traditionally modelled as partially observable Markov decision processes. In this article, we present an alternative formulation based on probabilistic regular languages. The proposed approach generalises the recently reported work on language measure theoretic optimal control for perfectly observable situations and shows that such a framework is far more computationally tractable to the classical alternative. In particular, we show that the infinite horizon decision problem under partial observation, modelled in the proposed framework, is λ-approximable and, in general, is not harder to solve compared to the fully observable case. The approach is illustrated via two simple examples.     

A new approach to adaptive control: no nonlinearities

In adaptive control the goal is to design a controller to control an uncertain system whose parameters may be changing with time. Typically the controller consists of an identifier (or tuner) which is used to adjust the parameters of a linear time-invariant (LTI) compensator, and under suitable assumptions on the plant model uncertainty it is proven that good asymptotic behaviour is achieved, such as model matching (for minimum phase systems) or stability. However, a typical adaptive controller does not track time-varying parameters very well, and it is often highly nonlinear, which can result in undesirable behaviour, such as large transients or a large control signal. Furthermore, most adaptive controllers provide only asymptotic tracking, with no ability to design for a pre-specified settling time.Here we propose an alternative approach, which yields a linear periodic controller. Rather than estimating the plant or compensator parameters, instead we estimate what the control signal would be if the plant parameters were known. In this paper we argue the utility of this approach and then examine the first order case in detail, including a simulation. We also explore the benefits and limitations of the approach.     

Formal modeling and synthesis of programmable logic controllers

Programmable logic controllers (PLCs) are complex cyber-physical systems which are widely used in industry. This paper presents a robust approach to design and implement PLC-based embedded systems. Timed automata are used to model the controller and its environment. We validate the design model with resort to model checking techniques. We propose an algorithm to generate PLC code from timed automata and implement this algorithm with a prototype tool. This method can condense the developing process and guarantee the correctness of PLC programs. A case study demonstrates the effectiveness of the method.     

Incremental online sparsification for model learning in real-time robot control

For many applications such as compliant, accurate robot tracking control, dynamics models learned from data can help to achieve both compliant control performance as well as high tracking quality. Online learning of these dynamics models allows the robot controller to adapt itself to changes in the dynamics (e.g., due to time-variant nonlinearities or unforeseen loads). However, online learning in real-time applications - as required in control - cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for fast real-time model learning. The proposed approach employs a sparsification method based on an independence measure. In combination with an incremental learning approach such as incremental Gaussian process regression, we obtain a model approximation method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real Barrett WAM robot demonstrates the applicability of the approach in real-time online model learning for real world systems.     

一类非线性系统的间接自适应模糊滑模控制

基于启发式知识的模糊控制是一种解决非线性系统控制问题的有效方法。然而其设计缺乏系统性,并且系统的稳定性和鲁棒性难以保证。本文利用滑模控制的概念和Lyapunov综合方法提出一种针对一类非线性系统的间接自适应模糊滑模控制（IAFSMC）方法。仿真研究表明即使在缺少系统先验知识和不确定性干扰的情况下,系统性能也十分理想。     

A formal verification framework for SysML activity diagrams

SysML activity diagrams are OMG/INCOSE standard diagrams used for modeling and specifying probabilistic systems. They support systems composition by call behavior and send/receive artifacts. For verification, the existing approaches dedicated to these diagrams are limited to a restricted set of artifacts. In this paper, we propose a formal verification framework for these diagrams that supports the most important artifacts. It is based on mapping a composition of SysML activity diagrams to the input language of the probabilistic symbolic model checker called “PRISM”. To prove the soundness of our mapping approach, we capture the underlying semantics of both the SysML activity diagrams and their generated PRISM code. We found that the probabilistic equivalence relation between both semantics preserve the satisfaction of the system requirements. Finally, we demonstrate the effectiveness of our approach by presenting real case studies.     

Collaborative user modeling for enhanced content filtering in recommender systems

Recommender systems, which have emerged in response to the problem of information overload, provide users with recommendations of content suited to their needs. To provide proper recommendations to users, personalized recommender systems require accurate user models of characteristics, preferences and needs. In this study, we propose a collaborative approach to user modeling for enhancing personalized recommendations to users. Our approach first discovers useful and meaningful user patterns, and then enriches the personal model with collaboration from other similar users. In order to evaluate the performance of our approach, we compare experimental results with those of a probabilistic learning model, a user model based on collaborative filtering approaches, and a vector space model. We present experimental results that show how our model performs better than existing alternatives.     

Evaluating design proposals for complex systems with work domain analysis

In this paper we propose a new framework for evaluating designs based on work domain analysis, the first phase of cognitive work analysis. We develop a rationale for a new approach to evaluation by describing the unique characteristics of complex systems and by showing that systems engineering techniques only partially accommodate these characteristics. We then present work domain analysis as a complementary framework for evaluation. We explain this technique by example by showing how the Australian Defence Force used work domain analysis to evaluate design proposals for a new system called Airborne Early Warning and Control. This case study also demonstrates that work domain analysis is a useful and feasible approach that complements standard techniques for evaluation and that promotes a central role for human factors professionals early in the system design and development process. Actual or potential applications of this research include the evaluation of designs for complex systems.