Dario Di Nocera

Agent Negotiation for Different Needs in Smart Parking Allocation

Smart Cities are experiencing a growing interest from different research areas. One of the challenges of Smart Cities is the design of an effective City Parking System that may contribute to improve the city life in terms of gas emission and air pollution in city centers, but also the everyday life of city dwellers by facilitating to park with the support of automatic parking services. In this work, an investigation on the use of software agents negotiation to accommodate both user and vendor requirements on a parking space is carried out. It is shown that agent negotiation allows to assign parking spaces in an automatic and intelligent manner by taking into account that users have their own needs regarding parking location and price, while parking vendors have their own needs regarding efficient allocation of parking spaces, and city regulations.

The role of intrinsic motivations in attention allocation and shifting

The concepts of attention and intrinsic motivations are of great interest within adaptive robotic systems, and can be exploited in order to guide, activate, and coordinate multiple concurrent behaviors. Attention allocation strategies represent key capabilities of human beings, which are strictly connected with action selection and execution mechanisms, while intrinsic motivations directly affect the allocation of attentional resources. In this paper we propose a model of Reinforcement Learning (RL), where both these capabilities are involved. RL is deployed to learn how to allocate attentional resources in a behavior-based robotic system, while action selection is obtained as a side effect of the resulting motivated attentional behaviors. Moreover, the influence of intrinsic motivations in attention orientation is obtained by introducing rewards associated with curiosity drives. In this way, the learning process is affected not only by goal-specific rewards, but also by intrinsic motivations.

Attentional Action Selection Using Reinforcement Learning

Reinforcement learning is typically used to model and optimize action selection strategies, in this work we deploy it to optimize attentional allocation strategies while action selection is obtained as a side effect. We present a reinforcement learning approach to attentional allocation and action selection in a behavior-based robotic systems. We detail our attentional allocation mechanisms describing the reinforcement learning problem and analysing its performance in a survival domain.

A Multiagent Approach Using Model-Based Predictive Control for an Irrigation Canal

Software negotiation is gaining an increased popularity as a viable approach to establish agreements between service providers and consumers of QoS-aware Service-Based Applications (SBA) composed of services provided by different agents. In most cases, QoS preferences are expressed as end-to-end quality requirements on the whole application, and different service agents have to provide services with QoS values that, once aggregated, have to meet them. In the present work we analyze the properties of a hybrid iterative negotiation mechanism occurring among a composer agent and service provider agents on the QoS attributes of the required SBA. The proposed negotiation relies on normal probability distributions to model service provider agents, and it allows to model single-issue and multi-issue negotiation within the same negotiation framework in terms of adopted concession strategy, utility and protocol.

A Market-Based Coordinated Negotiation for QoS-Aware Service Selection

The provision of Service-Based Applications (SBAs) will be driven by market-oriented mechanisms, and the market value of an application will depend not only on its functionality, but also on the value of “Quality of Service” (QoS) parameters affecting its performance. These parameters are not static properties since they may vary according to the provision strategies of providers as well as the demand of users having their own preferences on the application QoS values. In this paper we propose a market-based negotiation mechanism among service providers and a user requesting a QoS-aware SBA. It allows to take into account the variability of service QoS attribute values typical of the future market of services, as well as to dynamically set the length of the negotiation process that is usually very time-consuming especially in the context of SBAs.

Evaluating the Social Benefit of a Negotiation–Based Parking Allocation

Smart parking systems usually support drivers to select parking spaces according to their preferences among competitive alternatives, which are well known in advance to the decision maker, but without considering also the needs of a city. In this paper a decision support system for selecting and reserving optimal parking spaces to drivers is presented, where the concept of optimality is related to the city social welfare including the level of satisfaction of both drivers and the city. It relies on an automated software agent negotiation to accommodate the different needs coming from the different actors involved in the parking allocation process. A simulator of such a system is evaluated with respect to a case of complete information sharing among agents, and a case of no shared information. Different metrics to evaluate the social benefit of the parking allocation in terms of both agents utilities, and allocation efficiency are considered.

Using Negotiation for Parking Selection in Smart Cities

Parking in urban areas is becoming a big concern for its environmental and economic implications. Smart parking systems are considered essential to improve both city life in terms of gas emission and air pollution, and motorists life by making it easier to park. Supporting technologies are emerging at the industrial level to easily locate available parking spaces, to automate parking payments, and to collect useful data on consumer demand. Most of the research projects concerning smart parking systems focus on ways to collect and publish live parking information and many companies are developing electronic parking systems allowing for a wide variety of available payment methods.

Using Reference Points for Competitive Negotiations in Service Composition

In a market of services, it is likely that the number of service implementations that exhibit similar functionalities with varying Quality of Service (QoS) will significantly increase. In this context, the provision of a QoS-aware SBA becomes a decision problem on how to select the appropriate services. The approach adopted in the present work is to model both service providers and customers as software agents, and to use automated agent negotiation to dynamically select a set of provider agents whose services QoSs satisfy the customer’s requirements. The main features that an automated agent negotiation process should satisfy in order to be applied in service composition are discussed concluding that a multi-issue one-to-many negotiation should be used. In such a setting, we show that using reference points for trading off when different provider agents compete to provide the same service, allows to find (near) Pareto optimal agreements if they exist.

Attentional Shifting and Curiosity: a Reinforcement Learning Approach

Attention allocation strategies represent key capabilities of human beings, which are strictly connected with action selection and execution mechanisms, while intrinsic motivations directly affect the allocation of attentional resources. In this paper we propose a model of Reinforcement Learning (RL), where both these capabilities are involved. RL is deployed to learn how to allocate attentional resources in a behavior-based robotic system, while action selection is obtained as a side effect of the resulting motivated attentional behaviors. Moreover, the influence of intrinsic motivations in attention orientation is obtained by introducing internal rewards associated with curiosity drives. In this way, the learning process is affected not only by goalspecific rewards, but also by intrinsic motivations depending on the internal state of the system.

Gaussian-Based Bidding Strategies for Service Composition Simulations

Service composition plays a crucial role in service–oriented computing allowing to deliver complex distributed applications obtained by aggregating autonomous and independent component services characterized by a given functionality and a Quality of Service. Automated negotiation is a viable approach to select component services according to their QoS values so to meet the end–to–end quality requirements of users requesting the application. This paper discusses the use of Gaussian probability functions to model negotiation strategies of service providers, and how the properties of these functions can be used to model multiple negotiations necessary for service composition as a single multi–issue negotiation. A numerical analysis shows comparable negotiation trends for the different representations of the service composition problem.