In this article, we address the problem of realizing a complete efficient system for automated management of fleets of autonomous ground vehicles in industrial sites. We elicit from current industrial practice and the scientific state of the art the key challenges related to autonomous transport vehicles in industrial environments and relate them to enabling techniques in perception, task allocation, motion planning, coordination, collision prediction, and control. We propose a modular approach based on least commitment, which integrates all modules through a uniform constraint-based paradigm. We describe an instantiation of this system and present a summary of the results, showing evidence of increased flexibility at the control level to adapt to contingencies.
We consider the analysis and design of three different types of nonlinear observers for dynamic Takagi-Sugeno fuzzy systems. Our approach is based on extending existing nonlinear observer schemes, namely Thau-Luenberger and sliding mode observers, to the case of interpolated multiple local affine linear models. Then linear matrix inequality based techniques are used for observer analysis and design.
We focus on the analysis and design of two different sliding mode observers for dynamic Takagi-Sugeno (TS) fuzzy systems. A nonlinear system of this class is composed of multiple affine local linear models that are smoothly interpolated by weighting functions resulting from a fuzzy partitioning of the state space of a given nonlinear system subject to observation. The Takagi-Sugeno fuzzy system is then an accurate approximation of the original nonlinear system. Our approach to the analysis and design of observers for Takagi-Sugeno fuzzy systems is based on extending sliding mode observer schemes to the case of interpolated multiple local affine linear models. Thus, our main contribution is nonlinear observer analysis and design methods that can effectively deal with model/plant mismatches. Furthermore, we consider the difficult case when the weighting functions in the Takagi-Sugeno fuzzy system depend on the estimated state
An intelligent physical agent must incorporate motor and perceptual processes to interface with the physical world, and abstract cognitive processes to reason about the world and the options available. One crucial aspect of incorporating cognitive processes into a physically embedded reasoning system is the integration between the symbols used by the reasoning processes to denote physical objects, and the perceptual data corresponding to these objects. We treat this integration aspect by proposing a fuzzy computational theory of anchoring. Anchoring is the process of creating and maintaining the correspondence between symbols and percepts that refer to the same physical objects. Modeling this process using fuzzy set-theoretic notions enables dealing with perceptual data that can be affected by uncertainty/imprecision and imprecise/vague linguistic descriptions of objects
We consider the possibility of generalizing the notion of a fuzzy If-Then rule to take into account its context dependent nature. We interpret fuzzy rules as modeling a forward directed causal relationship between the antecedent and the conclusion, which applies in most contexts, but on occasion breaks down in exceptional contexts. The default nature of the rule is modeled by augmenting the original If-Then rule with an exception part. We then consider the proper semantic correlate to such an addition and propose a ternary relation which satisfies a number of intuitive constraints described in terms of a number of inference rules. In the rest of the paper, we consider implementational issues arising from the unless extension and propose the use of reason maintenance systems, in particular TMS's, where a fuzzy If-Then-Unless rule is encoded into a dependency net. We verify that the net satisfies the constraints stated in the inference schemes and conclude with a discussion concerning the integration of qualitative IN-OUT labelings of the TMS with quantitative degree of membership labelings for the variables in question.
The aim of the present paper is to outline a formal framework for dealing with the problem of decision making with multiple interdependent goals. The approach uses the idea of aspiration levels in order to bridge the gap between the prescriptive and the descriptive approaches thus allowing the problems of evaluation, choice and generation of alternatives to be treated in a coherent formal framework. On the other hand the approach recognizes the existance of interdependent and very often conflicting goals and suggests that in the case when the relationships between the goals can not be modelled by means of mathematical equations one should employ some techniques for knowledge representation based on fuzzy production rules and basic concepts from the theory of approximate reasoning.
The objective of the present article is twofold: first, to provide ways for eliciting consistent a priori and conditional probabilities for a set of events representing pieces of evidence and hypotheses in the context of a rule based expert system. Then an algorithm is proposed which uses the least possible number of a prior and conditional probabilities as its input and which computes the lower and upper bounds for higher order conditional and joint probabilities, so that these be consistent with the input probabilities provided. In the case, when inconsistent lower and upper bounds are obtained, it is suggested how the latter can be turned into consistent ones, by changing the values of only these input probabilities which are directly represented in the higher order probability under consideration. Secondly, a number of typical cases with respect to the problems of aggregation and propagation of uncertainty in expert systems is considered. It is shown how these can be treated by using higher order joint probabilities. For this purpose no global assumptions for independence of evidence and for mutual exclu-siveness of hypotheses are required, since the presence of independent and/or dependent pieces of evidence, as well as the presence of mutually exclusive hypotheses, is explicitly encoded in the input probabilities and thus, such a presence is automatically detected by the algorithm when computing higher order joint probabilities.
In a previous article we introduced extended logical operators, based on the Dubois family of T-norms and their dual T-conorms, to induce a semantics for a language involving and, or, and negation. Thus, given these logical operators and an arbitrary set-up S (a mapping from atomic formulas into a set of truth-values), we extended S to a mapping of all formulas into a set of truth-values defined as belief/disbelief pairs. Then using a particular partial order between belief/disbelief pairs to define entailment we were able to derive a many-valued variant of the so-called relevance logic. Here we introduce the notion of the so-called information lattice built upon another type of partial order between belief/disbelief pairs. Furthermore, we introduce specific meet and join operations and use them to provide answers to three fundamental questions: How does the reasoning machine represent belief and/or disbelief in the validity of the constituents of a complex formula when it is supplied with belief and/or disbelief in the validity of this complex formula as a whole; how does it determine the amount of belief and/or disbelief to be assigned to complex formulas in an epistemic state, that is, a collection of set-ups; and finally, how does it change its present belief and/or disbelief in the validity of formulas already in its data base, when provided with an input bringing in new belief and/or disbelief in the validity of these formulas.
The intended purpose of the present article is two-fold: first, introducing an interval-like representation of uncertainty that is an adequate summary of the following two items of information: a report on how strongly the validity of a proposition is supported by a body of evidence and a report on how strongly the validity of its negation is supported. A representation of this type is called a beliefinterval and is introduced as a subinterval of a certain verbal scale consisting of nine linguistic estimates expressing the amount of support provided for the validity of a proposition and/or its negation; each linguistic estimate is represented as a fuzzy number in the interval [0,1]. A belief-interval is bounded from below by an estimate indicating the so-called degree of support and from above by an estimate indicating the so-called degree of plauibility. The latter is defined as the difference between a fuzzy number representing the maximal degree of support that might be provided for a proposition in general and a fuzzy number expressing the degree of support provided for the validity of the negation of the proposition under consideration. The so-introduced degrees of support and plausibility of a proposition are subjective measurements provided by the expert on the basis of some negative and/or positive evidence available to him. Thus, these two notions do not have the same measure-based origins as do the set-theoretic measures of support and plausibility proposed by G. Shafer, neither do they coincide with the possibility and necessity measures proposed by L. Zadeh. The main difference is that in our case the degree of plausibility might be, in cases of contradictory beliefs, less than its corresponding degree of support. Three types of belief-intervals are identified on the basis of the different amounts of support that might be provided for the validity of a proposition and/or its negation, namely balanced, unbalanced, and contradictory belief-intervals. The second objective of this article is to propose a calculus for the belief-intervals by extending the usual logical connectives and, or, negation, and implies. Thus, conjunctive and disjunctive operators are introduced using the Dubois' parametrized family of T-norms and their dual T-conorms. The parameter Q characterizing the latter is being interpreted as a measure of the strength of these connectives and further interpretation of the notion of strength is done in the cases of independent and dependent evidence. This leads to the introduction of specific conjunctive and disjunctive operators to be used separately in each of the latter two cases. A negation operator is proposed with the main purpose of determining the belief-interval to be assigned to the negation of a particular proposition, given the belief-interval of the proposition alone. A so-called aggregation operator is introduced with the purpose of aggregating multiple belief-intervals assigned to one and the same proposition into a total belief-interval for this particular proposition. Detachment operators are proposed for determining the belief-interval of a conclusion given the belief-interval of the premise and the one that represents the amount of belief commited to the validity of the inference rule itself. Two different detachment operators are constructed for use in cases when: (1) the presence of the negation of the premise suggests the presence of the negation of the conclusion, and (2) when the presence of the negation of the premise does not tell anything at all with respect to the validity of the conclusion to be drawn.
Fuzzy controllers are a class of knowledge based controllers using artificial intelligence techniques with origins in fuzzy logic. They can be found either as stand-alone control elements or as integral parts of a wide range of industrial process control systems and consumer products. Applications of fuzzy controllers are an established practice for Japanese manufacturers, and are spreading in Europe and America. The main aim of this book is to show that fuzzy control is not totally ad hoc, that there exist formal techniques for the analysis of a fuzzy controller, and that fuzzy control can be implemented even when no expert knowledge is available. The book is mainly oriented to control engineers and theorists, although parts can be read without any knowledge of control theory and may interest AI people. This 2nd, revised edition incorporates suggestions from numerous reviewers and updates and reorganizes some of the material.
The problem of chaining of fuzzy IF-THEN rules has so far received a rather theoretic treatment in the literature on approximate reasoning. In particular, different types of composition operators, fuzzy implication operators, etc., have been identified such that the conclusion obtained via a chain of fuzzy rules coincides with the conclusion derived from the “abbreviated” version of the same chain. This “abbreviated” version is a single fuzzy rule which the rule-antecedent is the rule-antecedent of the first rule in the chain, and its rule-consequent is the rule-consequent of the last rule in the chain. However, in the case of more than one chain of rules and when the fuzzy sets defining the meaning of the rule-antecedents and rule-consequents from different chains overlap, then the above theoretical results do not hold in general. In the present paper we identify two major problems with the chaining of fuzzy rules in the case of more than one chain and overlapping rule-antecedents and rule-consequents that belong to different chains
Unless-rules are intended to deal with problems of reasoning with incomplete information and/or resource constraints. An unless-rule is proposed to be of the form `if X is A then Y is B unless Z is C'. Such rules are employed in situations in which the conditional statement if X is A then Y is B usually holds and the assertion Z is C holds rarely. Thus, using a rule of this type the exception condition can be ignored when the resources needed to establish its presence are tight or there simply is no information available as to whether it holds or does not hold. In this case of incomplete information, since it is the case that if X is A then Y is B usually holds, one may be willing to jump to the conclusion Y is B given that X is A because no information as to whether Z is C holds is available
The standard computation taking place in a fuzzy logic controller proceeds from crisp inputs and via the consecutive steps of fuzzification, inference, and defuzzification computes a crisp control output. However, this computational practice simplifies to an extent the actual developments taking place in the closed loop. In reality, the knowledge about the current values of the controller input is very often available via sensory measurements. In this case, one has to take into account the negative side effects that come up with the use of sensors, in particular the presence of noisy measurements. In the paper the authors consider one particular way of dealing with noisy controller inputs, namely transforming the noise-distribution into a fuzzy set and then feeding back the so obtained fuzzy signal to the controller input. Adopting this approach requires that the shape of the input fuzzy signal should be reflected as much as possible in the output fuzzy signal so that important noise characteristics are preserved. In the paper the authors describe the requirements on the shape of the fuzzy output signal given a certain fuzzy input signal and show that the existing semantics for fuzzy IF-THEN rules do not satisfy these requirements. The authors propose new semantics for such rules which together with max-min composition produces the desired results.
The paper deals with the analysis of local fuzzy observers for nonlinear plants. The plant is approximated by a TS fuzzy model for which a local linear fuzzy observer is designed. This type of fuzzy observer reconstructs the non-measurable states if the parameters of the locally linearized plant are given. Matched uncertainties in the plant model can be eliminated by an additional nonlinear fuzzy sliding mode observer. Conditions are given under which the combination of the linear and the nonlinear observer lead to a reconstruction of non-measurable states
In the present paper we describe the design of a fuzzy gain scheduler for tracking a reference trajectory of a nonlinear autonomous system. The proposed fuzzy gain scheduling method has two major advantages over the existing crisp gain scheduling methods. First, it provides a general and formally motivated method for the interpolation of available local control laws into a global gain scheduling control law. Second, the method for determining the weights of the local control laws in the global gain scheduling control law is general and computationally efficient. It is shown that a fuzzy gain scheduler can be designed such that robust asymptotic stability is met. Finally, an LQR control design based method is presented
The goal of autonomous mobile robotics is to build and control physical systems which can move purposefully and without human intervention in real-world environments which have not been specifically engineered for the robot. The development of techniques for autonomous mobile robot operation constitutes one of the major trends in the current research and practice in modern robotics. This volume presents a variety of fuzzy logic techniques which address the challenges posed by autonomous robot navigation. The focus is on four major problems: how to design robust behavior-producing control modules; how to use data from sensors for the purpose of environment modeling; and how to integrate high-level reasoning and low-level behavior execution. In this volume state-of-the-art fuzzy logic solutions are presented and their pros and cons are discussed in detail based on extensive experimentation on real mobile robots.
There is a growing trend to use object-based implementations and modeling in industrial control applications. However, the object-based approach imposes new theoretical and practical problems. Those problems are due to a higher abstraction level that is achievable with objects as compared to the more traditional, state-based fault detection and isolation methods (FDI) approaches. This paper presents a description of the problems and solutions to them in the framework of a discrete FDI method referred to as ontological control. The results are also relevant in respect to domain-independent failure recovery methods... (Fodor et al., 1997)
This paper presents an approach to complex system recovery based on a fuzzy specification method. The method can be applied when controllers of different types and makes are connected in a common control architecture. The method allows a controller B to trigger a recovery operation on a controller A when B has the recovery specification of A. The approach has important potential applications in industry, e.g. as a possible complement to PLC standards such as IEC1131, and to the design of hybrid and complex control systems
The current trend of using object based design for real time control systems has the implication that traditional state based fault detection and recovery methods cannot be used directly. This problem is even more difficult for domain independent fault detection and recovery since most such methods are based on a formal analysis of the global state set. The paper presents a domain independent fault isolation, detection and recovery method for object based control systems based on constraints of the object architecture. Variations of the control behavior from normal cases are detected using a fuzzy state machine approach
A programmable logic controller (PC) carries out a control algorithm under violations of theontological assumptions (VOA) when the plant does not meet one or more unstated but essential assumptions used in the design of the control algorithm. This paper presents a recovery technique based on the theory of Fuzzy State Fuzzy Output Finite State Machines (FSFO-FSM). The appeal of this approach is that the only known recovery results today are for fuzzy controllers. A common drawback of most linguistic models is that they are essentially static and thus not suitable to model the sequential behavior of a PC program. A FSFO-FSM can act as a sequentialmachine during the normal course of control, yet it possesses all the required linguistic properties during a VOA. This approach can enhance substantially the safety and operational range of existing PC and embedded control applications. This paper describes the control problem, presents results based on simulations, and show architectural constraints when applying this principle to real-world application.
The solution to the problem of application-independent fault recovery of autonomous agents requires a specification method for the agent's capacity to act outside of its normal operational limits. This paper presents a recovery method based upon the theory of a fuzzy finite state machine. A fuzzy specification is given for the bounds within which an autonomous agent is capable to recover after an unexpected situation has occurred in its environment. It has been shown that the three main components of the recovery problem: fault detection, fault recovery, and the properties of the actuator/sensor gear of an autonomous agent are interrelated. The suggested method can be implemented either by an application-independent software algorithm, or by fuzzy logic hardware
This paper introduces a hybrid fuzzy-Boolean finite state machine (HFB FSM) model for ontological control. Ontological control is a novel type supervisory control that deals with the problems of error detection and recovery in complex control systems. The HFB FSM is used as a specification method for the problem of recovery when an autonomous control system encounters unexpected changes in its environment. The method allows a controller B (the ontological controller) to trigger a recovery operation on controller A when B has the recovery specification of A. The approach has important potential applications in industry
This carefully edited volume presents a collection of recent works in fuzzy model identification. It opens the field of fuzzy identification to conventional control theorists as a complement to existing approaches, provides practicing control engineers with the algorithmic and practical aspects of a set of new identification techniques, and emphasizes opportunities for a more systematic and coherent theory of fuzzy identification by bringing together methods based on different techniques but aiming at the identification of the same types of fuzzy models. In control engineering, mathematical models are often constructed, for example based on differential or difference equations or derived from physical laws without using system data (white-box models) or using data but no insight (black-box models). In this volume the authors choose a combination of these models from types of structures that are known to be flexible and successful in applications. They consider Mamdani, Takagi-Sugeno, and singleton models, employing such identification methods as clustering, neural networks, genetic algorithms, and classical learning. All authors use the same notation and terminology, and each describes the model to be identified and the identification technique with algorithms that will help the reader to apply the presented methods in his or her own environment to solve real-world problems. Furthermore, each author gives a practical example to show how the presented method works, and deals with the issues of prior knowledge, model complexity, robustness of the identification method, and real-world applications.
The work reported in the paper is aimed at achieving aggressive manoeuvrability for an unmanned helicopter APID MK-III by Scandicraft AB in Sweden. The manoeuvrability problem is treated at the level of attitude (pitch, roll, yaw) and the aim is to achieve stabilization of the attitude angles within much larger ranges than currently available. We present a fuzzy gain scheduling control approach based on two different types of Iinearization of the original nonlinear APID MK-III model. The performance of the fuzzy gain scheduled controllers is evaluated in simulation and shows that they are effective means for achieving the desired robust manoeuvrability.
In this paper we address the design of a fuzzy flight controller that achieves stable and robust -aggressive- manoeuvrability for an unmanned helicopter. The fuzzy flight controller proposed consists of a combination of a fuzzy gain scheduler and linguistic (Mamdani-type) controller. The fuzzy gain scheduler is used for stable and robust altitude, roll, pitch, and yaw control. The linguistic controller is used to compute the inputs to the fuzzy gain scheduler, i.e., desired values for roll, pitch, and yaw at given desired altitude and horizontal velocities. The flight controller is obtained and tested in simulation using a realistic nonlinear MIMO model of a real unmanned helicopter platform, the APID-MK
In this paper, we address the design of an attitude controller that achieves stable, and robust aggressive maneuverability for an unmanned helicopter. The controller proposed is in the form of a fuzzy gain-scheduler, and is used for stable and robust altitude, roll, pitch, and yaw control. The controller is obtained from a realistic nonlinear multiple-input-multiple-output model of a real unmanned helicopter platform, the APID-MK3. The results of this work are illustrated by extensive simulation, showing that the objective of aggressive, and robust maneuverability has been achieved.
The paper presents the design of a horizontal velocity controller for the unmanned helicopter APID MK-III developed by Scandicraft AB in Sweden. The controller is able of regulating high horizontal velocities via stabilization of the attitude angles within much larger ranges than currently available. We use a novel approach to the design consisting of two steps: 1) a Mamdani-type of a fuzzy rules are used to compute for each desired horizontal velocity the corresponding desired values for the attitude angles and the main rotor collective pitch; and 2) using a nonlinear model of the altitude and attitude dynamics, a Takagi-Sugeno controller is used to regulate the attitude angles so that the helicopter achieves its desired horizontal velocities at a desired altitude. According to our knowledge this is the first time when a combination of linguistic and model-based fuzzy control is used for the control of a complicated plant such as an autonomous helicopter. The performance of the combined linguistic/model-based controllers is evaluated in simulation and shows that the proposed design method achieves its intended purpose
This work presents a horizontal velocity controller for the unmanned helicopter APID MK-III developed by Scandicraft AB in Sweden. We use a novel approach to the design consisting of two steps: 1) Mamdani-type of fuzzy rules to compute each of the desired horizontal velocity corresponding to the desired values for the attitude angles and the main rotor collective pitch; and 2) a Takagi-Sugeno controller is used to regulate the attitude angles so that the helicopter achieves its desired horizontal velocities at a desired altitude. The performance of the combined linguistic/model-based controller is evaluated in simulation and shows that the proposed design method achieves its intended purpose
This paper addresses the robust fuzzy control problem for discrete-time nonlinear systems in the presence of sampling time uncertainties. The case of the discrete T-S fuzzy system with sampling-time uncertainty is considered and a robust controller design method is proposed. The sufficient conditions and the design procedure are formulated in the form of linear matrix inequalities (LMI). The effectiveness of the proposed controller design methodology is demonstrated of a visual-servoing control problem.
Fuzzy gain schedulers are designed on the basis of a conventional modeling of the nonlinear controlled system and the division of the state space into a finite number of fuzzy regions. Linearization of the nonlinear system at the center of each fuzzy region leads to the design of a set of linear control laws that locally stabilize the linearized system, and consequently the original nonlinear system at the corresponding operating point. Gain scheduling control of the original nonlinear system can be therefore realized along an a priori unknown, but slowly time varying desired trajectory. In this paper we analyze the stability and robustness of the gain-scheduled closed-loop system by adopting ideas from sliding mode control. It is shown that gain scheduling control of the original nonlinear system can be realized along an a priori unknown, but slowly time-varying desired trajectory. It is shown how the advantages of the sliding mode types of analysis of a fuzzy gain scheduler can also be used for its design. © 2001 Elsevier Science B.V.
Obstacle avoidance is an important issue for off-line path planning and on-line reaction to unforeseen appearance of obstacles during motion of a non-holonomic mobile robot along apredefined trajectory. Possible trajectories for obstacle avoidance are modeled by the velocity potential using a uniform flow plus a doublet representing a cylindrical obstacle. In the case of an appearance of an obstacle in the sensor cone of the robot a set of streamlines is computed from which a streamline is selected that guarantees a smooth transition from/to the planned trajectory. To avoid collisions with other robots a combination of velocity potential and force potential and/or the change of streamlines during operation (lane hopping) are discussed.
The combination of hybrid systems and fuzzy multiple model systems is described. Further, a hierarchical identification of the resulting fuzzy switched hybrid system is outlined. The behavior of the discrete component is identified by black box fuzzy clustering and subsequent parameter identification taking into account some prior-knowledge about the discrete states. The identification of the continuous models for each discrete state is done based on local linear fuzzy models
The fundamental issue in gain scheduling along a desired reference trajectory is the question of guaranteed stability of the overall gain-scheduled closed-loop system. Since the gain-scheduled design is based on linear-time-invariant approximation of the open-loop system, and since this system is actually nonlinear, the design guarantees only local stability. This requires a further restriction, namely that the desired reference trajectory should vary slowly. The design of a fuzzy gain scheduler requires a conventional model of the nonlinear system under control and a partition of the state space into a ®nite number of fuzzy regions. The nonlinear system is Lyapunov-linearized at the center of each fuzzy region. Then linear controllers intended to locally stabilize the linearized system, and consequently the original nonlinear system, at the center of a fuzzy region are designed. In that way, gain-scheduling control of the original nonlinear system can be designed to cope with any (unknown in advance) slowly time-varying desired trajectory. This paper shows how the stability and robustness analysis of the gainscheduled closed-loop sysem in terms of sliding-mode control techniques can be used for the design of a supervisory system which avoids unstable behavior outside the region in which local stability is guaranteed.
The use of the velocity potential of an incompressible fluid is an important and elegant tool for obstacle avoidance of mobile robots. Obstacles are modeled as cylindrical objects - combinations of cylinders can also form super obstacles. Possible trajectories of a vehicle are given by a set of streamlines around the obstacle computed by the velocity potential. Because of the number of streamlines and of data points involved therein, models of sets of streamlines for different sizes of obstacles are created first using dataset models and finally fuzzy models of streamlines. Once an obstacle appears in the sensor cone of the robot the set of streamlines is computed from which that streamline is selected that guarantees a smooth transition from/to the planned trajectory. Collisions with other robots are avoided by a combination of velocity potential and force potential and/or the change of streamlines during operation (lane hopping).
Model Based Fuzzy Control uses a given conventional or fuzzy open loop model of the plant under control to derive the set of fuzzy rules for the fuzzy controller. Of central interest are the stability, performance, and robustness of the resulting closed loop system. The major objective of model based fuzzy control is to use the full range of linear and nonlinear design and analysis methods to design such fuzzy controllers with better stability, performance, and robustness properties than non-fuzzy controllers designed using the same techniques. This objective has already been achieved for fuzzy sliding mode controllers and fuzzy gain schedulers - the main topics of this book. The primary aim of the book is to serve as a guide for the practitioner and to provide introductory material for courses in control theory.
Robot skills are low-level motion and/or grasping capabilities that constitute the basic building blocks from which tasks are built. Teaching and recognition of such skills can be done by Programming-by-Demonstration approach. A human operator demonstrates certain skills while his motions are recorded by a data-capturing device and modeled in our case via fuzzy clustering and Takagi-Sugeno modeling technique. The resulting skill models use the time as input and the operator's actions and reactions as outputs. Given a test skill by the human operator the robot control system recognizes the individual phases of skills and generates the type of skill shown by the operator.
We describe our initial steps toward the realization of a robotic system for assisting fire-fighting and rescue services. The system implements the concept of shared autonomy between the robot and the human operator: the mobile robot performs local navigation, sensing and mapping, while the operator interprets the sensor data and provides strategic navigation goals.
The highly percipient nature of human mind in avoiding sensory overload is a crucial factor which gives human vision an advantage over machine vision, the latter has otherwise powerful computational resources at its disposal given today’s technology. This stresses the need to focus on methods which extract a concise representation of the environment inorder to approach a complex problem such as visual mapping. This article is an attempt of creating a mapping system, which proposes an architecture that combines task-specific and saliency driven approaches. The proposed method is implemented on a warehouse robot. The proposed solution provide a priority framework which enables an industrial robot to build a concise visual representation of the environment. The method is evaluated on data collected by a RGBD sensor mounted on a fork-lift robot and shows promise for addressing visual mapping problems in industrial environments.
In the present paper a multi-sensor system is considered wlicre the sensors comprising it utilize the principles of huinan olfactory sensing and the processing of the sensor iiicasurcnients is done by a fuzzy sensor fusion technique. 'l'hc enipliasis of the paper is on the fuzzy fusion technique used for the classification of the numerical measurements of a quality characteristic in different fuzzy quality profiles.
sensor system for the measurement of air quality is presented and evaluated. It is based on the approach of mimicking the advantages of human olfactory sensing, using gas sensor measurements and fuzzy sensor fusion. Signals from four sensitive metal - oxide - semiconductor field-effect transistors (MOSFET), each with a unique selectivity profile, are used. Each sensor exhibits information which is extracted by signal analysis and used to determine a crisp air-quality profile. The resulting crisp profile is unique, representing a distinct air quality and serves as a basis for the determining of a fuzzy quality profile. A fuzzy measurement profile is then matched pair-wise to the different fuzzy quality profiles. The matches are processed with help of a fuzzy fusion technique to determine the most representative crisp air-quality profile. Preliminary experiments show that the performance of the proposed fuzzy sensor clustering system is very promising. Environmental air-quality tests inside and outside a car driving in different cities during different seasons resulted in an artificial system determining air-quality opinions. The sensor opinions are classified with reference to three air-quality references (clean, medium and polluted air) and appear to be in accordance with human opinions obtained simultaneously.