The MOVE System: Monitoring of waste collecting vehicles

Telmo Cunha, Phillip Tomé
2003
Article de conférence

Résumé

Nowadays, efficiency and productivity are fundamental concepts, in any kind of business. Although one can easily accept this as a known fact, one cannot easily identify which steps must be taken to achieve these goals. One approach consists of taking full advantage of the assets already available in the company, be they manpower or equipment. One kind of business that is strongly exposed to this problem concerns urban waste collecting. In this case, the productivity of the company can increase substantially if good fleet management policies are followed. Being aware of this fact, GEONAV has developed a fleet management system, named MOVE (Vehicle Monitoring), which is based on GPS. Each vehicle is equipped with a small onboard computer that includes, in the less complex model, a 12 channel GPS receiver and a GSM module. To cope with the problems usually affecting GPS in urban environments, such as having few satellites in view and multipath due to urban canyons, the system can incorporate information from low cost dead-reckoning sensors, such as the vehicle odometer and a gyroscope. Furthermore, other features can be added to the system, by using information from sensors readily available in the vehicle or that are installed specifically for the task intended. For instance, through a keypad unit, the driver can identity itself, by inserting a specific code or input the amount of fuel supplied to the vehicle. In addition, the system can automatically count the number of waste bins emptied, the number of times the vehicle has disposed of its waste in the wasteland or determine in real-time the vehicle’s weight. All information is sent to a Control Center using GSM or is stored in the computer’s memory, for a later download. In this case, an alternative means of transmission besides GSM can be used, namely a short range radio. Since no costs are involved when using this radio system, the exploitation costs of the MOVE system are greatly reduced. The Control Center software is based on a client/server architecture. The server application is responsible for controlling the communications between the Control Center and the vehicles and for storing all data received in a central database. The client applications connect to the server application, using the intranet, and are based on the GIS ArcView 8.x platform. Using a client application, an operator can visually determine the fleet status over a map or other type of visual representation. To reduce exploitation costs of the system, the status of the fleet is obtained by using SMS messages to exchange data between the vehicles and the Control Center. However, the option to follow a particular vehicle, by establishing a GSM call, is also possible. In this case, the position of the vehicle is updated at 1 Hz. The information that is stored in the database is organized in such a way as to allow the calculus of several statistical parameters that are useful to the management and control of the fleet. For example, one can determine the amount of kilometers driven, the time to complete a particular waste collection circuit, the fuel consumption, the number of waste bins emptied and their location, the number of times the vehicle was emptied of its waste, the vehicle’s weight, etc. This information can be used to establish new and better policies to enhance the fleet’s productivity and to present a better service to the end customer. This paper describes in detail the architecture of the MOVE system and its functionalities, including both the equipment installed onboard the vehicles and the Control Center’s software. Emphasis is given to the system’s flexibility to be used in different case scenarios, besides the monitoring of waste collection vehicles.

Official source

https://infoscience.epfl.ch/record/63831?ln=fr

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

Telmo Cunha, Phillip Tomé
2003
Article de conférence

Résumé

Official source

https://infoscience.epfl.ch/record/63831?ln=fr

À propos de ce résultat

Concepts associés (23)

Concepts associés

Chargement

Publications associées (57)

Chargement

Afficher plus

Publications associées

Chargement

Publications associées (57)

Error handling in multimodal voice-enabled interfaces of tour-guide robots using graphical models

Plamen Prodanov

Mobile service robots are going to play an increasing role in the society of humans. Voice-enabled interaction with service robots becomes very important, if such robots are to be deployed in real-world environments and accepted by the vast majority of potential human users. The research presented in this thesis addresses the problem of speech recognition integration in an interactive voice-enabled interface of a service robot, in particular a tour-guide robot. The task of a tour-guide robot is to engage visitors to mass exhibitions (users) in dialogue providing the services it is designed for (e.g. exhibit presentations) within a limited time. In managing tour-guide dialogues, extracting the user goal (intention) for requesting a particular service at each dialogue state is the key issue. In mass exhibition conditions speech recognition errors are inevitable because of noisy speech and uncooperative users of robots with no prior experience in robotics. They can jeopardize the user goal identification. Wrongly identified user goals can lead to communication failures. Therefore, to reduce the risk of such failures, methods for detecting and compensating for communication failures in human-robot dialogue are needed. During the short-term interaction with visitors, the interpretation of the user goal at each dialogue state can be improved by combining speech recognition in the speech modality with information from other available robot modalities. The methods presented in this thesis exploit probabilistic models for fusing information from speech and auxiliary modalities of the robot for user goal identification and communication failure detection. To compensate for the detected communication failures we investigate multimodal methods for recovery from communication failures. To model the process of modality fusion, taking into account the uncertainties in the information extracted from each input modality during human-robot interaction, we use the probabilistic framework of Bayesian networks. Bayesian networks are graphical models that represent a joint probability function over a set of random variables. They are used to model the dependencies among variables associated with the user goals, modality related events (e.g. the event of user presence that is inferred from the laser scanner modality of the robot), and observed modality features providing evidence in favor of these modality events. Bayesian networks are used to calculate posterior probabilities over the possible user goals at each dialogue state. These probabilities serve as a base in deciding if the user goal is valid, i.e. if it can be mapped into a tour-guide service (e.g. exhibit presentation) or is undefined – signaling a possible communication failure. The Bayesian network can be also used to elicit probabilities over the modality events revealing information about the possible cause for a communication failure. Introducing new user goal aspects (e.g. new modality events and related features) that provide auxiliary information for detecting communication failures makes the design process cumbersome, calling for a systematic approach in the Bayesian network modelling. Generally, introducing new variables for user goal identification in the Bayesian networks can lead to complex and computationally expensive models. In order to make the design process more systematic and modular, we adapt principles from the theory of grounding in human communication. When people communicate, they resolve understanding problems in a collaborative joint effort of providing evidence of common shared knowledge (grounding). We use Bayesian network topologies, tailored to limited computational resources, to model a state-based grounding model fusing information from three different input modalities (laser, video and speech) to infer possible grounding states. These grounding states are associated with modality events showing if the user is present in range for communication, if the user is attending to the interaction, whether the speech modality is reliable, and if the user goal is valid. The state-based grounding model is used to compute probabilities that intermediary grounding states have been reached. This serves as a base for detecting if the the user has reached the final grounding state, or wether a repair dialogue sequence is needed. In the case of a repair dialogue sequence, the tour-guide robot can exploit the multiple available modalities along with speech. For example, if the user has failed to reach the grounding state related to her/his presence in range for communication, the robot can use its move modality to search and attract the attention of the visitors. In the case when speech recognition is detected to be unreliable, the robot can offer the alternative use of the buttons modality in the repair sequence. Given the probability of each grounding state, and the dialogue sequence that can be executed in the next dialogue state, a tour-guide robot has different preferences on the possible dialogue continuation. If the possible dialogue sequences at each dialogue state are defined as actions, the introduced principle of maximum expected utility (MEU) provides an explicit way of action selection, based on the action utility, given the evidence about the user goal at each dialogue state. Decision networks, constructed as graphical models based on Bayesian networks are proposed to perform MEU-based decisions, incorporating the utility of the actions to be chosen at each dialogue state by the tour-guide robot. These action utilities are defined taking into account the tour-guide task requirements. The proposed graphical models for user goal identification and dialogue error handling in human-robot dialogue are evaluated in experiments with multimodal data. These data were collected during the operation of the tour-guide robot RoboX at the Autonomous System Lab of EPFL and at the Swiss National Exhibition in 2002 (Expo.02). The evaluation experiments use component and system level metrics for technical (objective) and user-based (subjective) evaluation. On the component level, the technical evaluation is done by calculating accuracies, as objective measures of the performance of the grounding model, and the resulting performance of the user goal identification in dialogue. The benefit of the proposed error handling framework is demonstrated comparing the accuracy of a baseline interactive system, employing only speech recognition for user goal identification, and a system equipped with multimodal grounding models for error handling.

EPFL2006

Chargement

This work presents a synthesis method that leads to the preliminary design of industrial energy systems. Such systems are composed of several technologies that transform, through a set of physical unit operations, raw materials and energy into products and energy services. The purpose of the preliminary synthesis is to define which technologies form the system, to calculate their technical characteristics, their operating conditions and their interactions, based on performance indicators such as for example the cost of the system or its environmental impact. This area is studied since a long time and many synthesis approaches are available. However, these methods have significant limitations, particularly in their ability to face the study of more and more complex systems. The main goal of the method presented in this work is to enable the study of large systems and promote the use of the experience gained from previous studies in the form of models and methodological approaches. The synthesis method of industrial energy systems is based on the overall system optimization using a model that is obtained by assembling several modules, representing each a set of physical unit operations and whose equations are formulated with the black box technique, and an integration model that can represent the possible interactions within the system. Optimization is performed using a multi-objective evolutionary algorithm, whose objective functions are defined on the basis of calculation of several performance indicators based on the model of the system. To simplify the resolution of this complex system, the optimization problem is decomposed into a master problem, responsible for calculating the characteristics of the units and their operating conditions, and an optimization slave subproblem, which selects the units being part of the system and their interconnections. To ensure its robustness, the slave subproblem is formulated as a mixed-integer linear optimization problem. The slave subproblem is formulated by using process integration techniques, which are extended in this work to allow the synthesis of multiple heat and mass transfer networks. The synthesis problem can thus be defined using an explicit superstructure or by one generated automatically, either implicit or explicit. This work also introduces a technique that greatly reduces the number of degrees of freedom of the integration model. Instead of separately optimizing each ΔTmin/2 associated with heat streams, a formula is applied to calculate their value from a reference case. The ΔTmin/2 optimization is thus reduced to the optimization of a single decision variable related to the reference case, regardless of the size of the problem. The proposed method uses a set of heterogeneous elements, including flowsheeting software for modeling physical unit operations, mathematical programming tools for the formulation of the integration problem, methods for calculating performance indicators and calculation tools such as the optimization algorithm. This work introduces new tools developed to systematically apply the proposed methodology and to automate recurring operations of data transfer and the call of the various used software. In particular, a syntax description is defined as an abstraction layer to describe and to structure the exchanged information. A computing platform has been created to support the application of the method and to ensure the data transfer between its components. Two case studies are presented to illustrate the various aspects of the synthesis method. A first case, involving the synthesis of two combined cycles, has been chosen to illustrate the different application stages of the method and to show the potential reuse of certain modules. Through the integration techniques, it has been possible to identify potential heat recovery that can increase the performance of one of the cycles beyond what had been expected by experts using conventional simulation techniques. The second case study is about the treatment of waste generated by an industrial site active in the field of fine chemicals. Waste treatment can recover different materials and energy services useful for process units, thereby reducing the quantities purchased in the market. The model of multi-network integration can easily solve the complexity of the problem of waste management in developing strategies for allocating waste to the various treatments available for different objective functions related to operating costs and environmental impact.

EPFL2010

Chargement

A system for resource efficient process planning for wire EDM

Sandeep Dhanik, Ricardo Pérez Suárez, Paul Xirouchakis

Efficient utilization of available resources for a particular machine tool technology is an important aspect of sustainable manufacturing. The objective of this paper is to present a method for efficient resource process planning for a Wire EDM Machine Tool System. For a given part information (required surface finish and workpiece height), the developed program automatically selects the feasible wires and generates the operation sequence and corresponding cutting conditions. The system then presents a multi objective framework consisting of both ecological criteria (waste generation, electricity consumption) and economic criteria (different costs and machining time) to suggest the wire which provides the best compromise solution for the considered criteria.

2011

Chargement

Afficher plus

Error handling in multimodal voice-enabled interfaces of tour-guide robots using graphical models

Plamen Prodanov

EPFL2006

EPFL2010