Maria Gini

• Universita' di Milano, Italy
• Professor (Full) at University of Minnesota

Airline ticket purchase timing is a strategic problem that requires both historical data and domain knowledge to solve consistently. Even with some historical information (often a feature of modern travel reservation web sites), it is difficult for consumers to make true cost-minimizing decisions. To address this problem, we introduce an automated...

We present empirical results of an auction-based algorithm for dynamic allocation of tasks to robots. The results have been obtained both in simulation and using real robots. A distinctive feature of our algorithm is its robustness to uncertainties and to robot malfunctions that happen during task execution, when unexpected obstacles, loss of commu...

Most map building methods employed by mobile robots are based on the assumption that an estimate of robot poses can be obtained from odometry readings or from observing landmarks or other robots. In this paper we propose methods to build a global geometric map by integrating scans collected by laser range scanners without using any knowledge about...

We present a testbed for multi-agent negotiation, implemented as a generalized market architecture called MAGNET (Multi AGent NEgotiation Testbed). In contrast with other approaches to multi-agent negotiation, we introduce an explicit intermediary into the negotiation process. We show how this approach helps in controlling fraud and discouraging co...

Wildlife-induced crop damage, particularly from deer, threatens agricultural productivity. Traditional deterrence methods often fall short in scalability, responsiveness, and adaptability to diverse farmland environments. This paper presents an integrated unmanned aerial vehicle (UAV) system designed for autonomous wildlife deterrence, developed as...

Conversational agents (CAs) are one of the most promising technologies for helping older adults maintain independence longer by augmenting their support and social networks. Voice-based technology in particular is especially powerful in this regard due to its accessibility and ease of use. There is also a growing body of evidence supporting the pot...

Social media has become a crucial open-access platform for individuals to express opinions and share experiences. However, leveraging low-resource language data from Twitter is challenging due to scarce, poor-quality content and the major variations in language use, such as slang and code-switching. Identifying tweets in these languages can be diff...

Social media has become a crucial open-access platform for individuals to express opinions and share experiences. However, leveraging low-resource language data from Twitter is challenging due to scarce, poor-quality content and the major variations in language use, such as slang and code-switching. Identifying tweets in these languages can be diff...

Recent research explores the potential of captioning withinvirtual environments. However, the effects of prolonged exposure to cap-tioning in these environments have received scant attention. This studydelves into the impacts of extended exposure to captions in a virtual real-ity (VR) setting, utilizing Head-Mounted Displays (HMDs). Its objec-tive...

There is a large class of real-world problems, such as warehouse transport, at different scales, swarm densities, etc., that can be characterized as Central Place Foraging Problems (CPFPs). We contribute to swarm engineering by designing an Ordinary Differential Equation (ODE) model that strives to capture the underlying behavioral dynamics of the...

In healthcare, the ability to care for oneself is reflected in the "Activities of Daily Living (ADL)," which serve as a measure of functional ability (functioning). A lack of functioning may lead to poor living conditions requiring personal care and assistance. To accurately identify those in need of support, assistance programs continuously evalua...

Healthcare in Africa is a complex issue influenced by many factors including poverty, lack of infrastructure, and inadequate funding. However, Artificial intelligence (AI) applied to healthcare, has the potential to transform healthcare in Africa by improving the accuracy and efficiency of diagnosis, enabling earlier detection of diseases, and supp...

Multi-robot systems are frequently used for tasks involving searching, so it is important to be able to estimate the searching time. Yet, simulation approaches and real-world experiments to determine searching time can be cumbersome and even impractical. In this work, we propose a correlated-random-walk based model to efficiently approximate hittin...

Modal verbs, such as "can", "may", and "must", are commonly used in daily communication to convey the speaker's perspective related to the likelihood and/or mode of the proposition. They can differ greatly in meaning depending on how they're used and the context of a sentence (e.g. "They 'must' help each other out." vs. "They 'must' have helped eac...

Modern intelligent systems researchers form hypotheses about system behavior and then run experiments using one or more independent variables to test their hypotheses. We present SIERRA, a novel framework structured around that idea for accelerating research development and improving reproducibility of results. SIERRA accelerates research by automa...

Modern intelligent systems researchers employ the scientific method: they form hypotheses about system behavior, and then run experiments using one or more independent variables to test their hypotheses. We present SIERRA, a novel framework structured around that idea for accelerating research developments and improving reproducibility of results....

Conversational agent (CA) technology is rapidly becoming ubiquitous. Understanding how CAs impact users on multiple levels, including physiology, thus becomes increasingly important. In this study, we examined the effects of a CA interaction on naive users’ physiological markers of stress i.e. heart rate (HR) and electrodermal activity (EDA). Parti...

The exploration time for a swarm of robots doing object gathering depends on the specific task, environment, number of objects, and number of robots. Hence, it is important to understand how different properties affect the exploration time. To address this practical challenge, we present a theoretical analysis of the expected exploration time for a...

We study the limits of linear modeling of swarm behavior by characterizing the inflection point beyond which linear models of swarm collective behavior break down. The problem we consider is a central place object gathering task. We design a linear model which strives to capture the underlying dynamics of object gathering in robot swarms from first...

The 2021 edition of AAMAS, the International Conference on Autonomous Agents and Multiagent Systems, took place from the 3rd to 7th of May 2021 (aamas2021.soton.ac.uk). This year it was organized in the form of a virtual event and attracted over 1,000 registered participants. As every year, the conference featured an exciting programme of contribut...

Spatiotemporal reasoning is a fundamental contributor to effective problem solving. In an effort to design better problem-solving agents, we examined and evaluated the strategies that humans use to solve Tower Defense puzzles, a complex and popular class of real-time strategy games. A consistent and unexpected finding was that humans frequently tre...

Growing interest in applications of AI in healthcare has led to a similarly elevated interest in fully integrated smart systems in which disparate technologies, such as biometric sensors and conversational agents, are combined to address health problems like medical event detection and response. Here we describe an ongoing project to develop a supp...

Monte Carlo Tree Search (MCTS) is being effectively used in many domains, but acquiring good results from building larger trees takes time that can in many cases be impractical. In this paper we show that parallelizing the tree building process using multiple independent trees (root parallelization) can improve results when limited time is availabl...

Robotics has the potential to magnify the skilled workforce of the nation by complementing our workforce with automation: teams of people and robots will be able to do more than either could alone. The economic engine of the U.S. runs on the productivity of our people. The rise of automation offers new opportunities to enhance the work of our citiz...

When designing swarm-robotic systems, systematic comparison of swarm control algorithms is necessary to determine which can scale up to handle the target problem size and operating conditions. Qualitative predictions of performance based on algorithm descriptions are often incorrect, and can lead to costly design processes for swarm-robotic systems...

Since computer-controlled robots were introduced, the methodology of robotprogramming has seen a great deal of development (Blume and Jakob, 1986;Brady et al. , 1982; Craig, 1986; Paul, 1981). Two completely differentapproaches to robot programming have been considered in the past. On oneside within the artificial intelligence (AI) community a lot...

In crowded multi-agent navigation, the motion of the agents is significantly constrained by the motion of the nearby agents. This makes planning paths very difficult and leads to inefficient global motion. To address this problem, we propose a distributed approach, which we call C-Nav, that introduces politeness into multi agent navigation. With ou...

The interest towards spoken dialogue systems has been rapidly growing in the last few years, including the field of health care. There is a growing need for automated systems that can do more than order airline and movie tickets, find restaurants and hotels, or find information on the internet. Eliciting information from patients about their curren...

When designing swarm-robotic systems, system- atic comparison of algorithms from different do- mains is necessary to determine which is capa- ble of scaling up to handle the target problem size and target operating conditions. We propose a set of quantitative metrics for scalability, flexibility, and emergence which are capable of addressing these...

When designing swarm-robotic systems, systematic comparison of algorithms from different domains is necessary to determine which is capable of scaling up to handle the target problem size and target operating conditions. We propose a set of quantitative metrics for scalability, flexibility, and emergence which are capable of addressing these needs...

Miniaturization and cost, two of the main attractive factors of swarm robotics, have motivated its use as a solution in object collecting tasks, search & rescue missions, and other applications. However, in the current literature only a few papers consider energy allocation efficiency within a swarm. Generally, robots recharge to their maximum leve...

Localized communication in swarms has been shown to increase swarm effectiveness in some situations by allowing for additional opportunities for cooperation. However, communication and utilization of potentially outdated information is also a concern. We present an explicit non-directional goal-based communication model and message accept/reject sc...

Localized communication in swarms has been shown to increase swarm effectiveness in some situations by allowing for additional opportunities for cooperation. However, communication and utilization of potentially outdated information is also a concern. We present an explicit non-directional goal-based communication model and message accept/reject sc...

Understanding the needs of a variety of distinct user groups is vital in designing effective, desirable dialogue systems that will be adopted by the largest possible segment of the population. Despite the increasing popularity of dialogue systems in both mobile and home formats, user studies remain relatively infrequent and often sample a segment o...

We propose a method for task allocation to multiple physical agents that works when tasks have temporal and spatial constraints and agents have different capacities. Assuming that the problem is over-constrained, we need to find allocations that maximize the number of tasks that can be done without violating any of the constraints. The contribution...

When agents in a multi-robot system move, they need to adapt their paths to account for potential collisions with other agents and with static obstacles. Existing distributed navigation methods compute motions that are optimal locally but do not account for the aggregate motions of all the agents. When there are many agents that move in a crowded s...

We propose a model for the allocation of agents to tasks when the tasks have a cost which grows over time. Our model accounts for both the natural growth of tasks and the effort of the agents at containing such growth. The objective is to produce solutions that minimize the growth of tasks (potentially stopping such growth) by efficiently coordinat...

Living with memory loss presents many challenges for patients and caregivers alike. Intelligent assistive technology can help address care gaps. Our core objective is to develop an assistive device that can be used at home by individuals experiencing memory impairment. We propose an assistant, based on existing and widely used voice activated consu...

Every day we read in the scientific and popular press about advances in AI and how AI is changing our lives. Things are moving at a fast pace, with no obvious end in sight.

Electricity disaggregation identifies individual appliances from one or more aggregate data streams and has immense potential to reduce residential and commercial electrical waste. Since supervised learning methods rely on meticulously labeled training samples that are expensive to obtain, unsupervised methods show the most promise for wide-spread...

Exploring an unknown environment comes with risks and complications, and in some cases an environment may be too dangerous for humans to explore, but immediate exploration is critical, as in the aftermath of an earthquake. Robots, however, can be deployed to seek out points of interest and report back to the waiting human operators. One aspect of a...

We present an auction-based method for a team of robots to allocate and execute tasks that have temporal and precedence constraints. Temporal constraints are expressed as time windows, within which a task must be executed. The robots use our priority-based iterated sequential single-item auction algorithm to allocate tasks among themselves and keep...

In multi-agent navigation, agents need to move towards their goal locations while avoiding collisions with other agents and static obstacles, often without communication with each other. Existing methods compute motions that are optimal locally but do not account for the aggregated motions of all agents, producing inefficient global behavior especi...

The AAAI-17 workshop program included 17 workshops covering a wide range of topics in AI. Workshops were held Sunday and Monday, February 4-5, 2017 at the Hilton San Francisco Union Square in San Francisco, California, USA. This report contains summaries of 12 of the workshops, and brief abstracts of the remaining 5.

Task allocation is ubiquitous in computer science and robotics, yet some problems have received limited attention in the computer science and AI community. Specifically, we will focus on multi-robot task allocation problems when tasks have time windows or ordering constraints. We will outline the main lines ofresearch and open problems.

We present a novel decentralized approach to allocate agents to tasks whose costs increase over time. Our model accounts for both the natural growth of the tasks and the effort of the agents at containing such growth. The objective is to minimize the increase in task costs. We show how a distributed coordination algorithm, which is based on max-sum...

We propose an auction-based method for a team of robots to allocate and execute tasks that have temporal and precedence constraints. The robots use our priority-based iterated sequential single-item auction algorithm to allocate tasks among themselves and keep track of their individual schedules. The key idea is to decouple precedence constraints f...

Previous work on assigning tasks to robots has proposed extensive categorizations of allocation of tasks with and without constraints. The main contribution of this paper is a specific categorization of problems that have temporal and ordering constraints. We propose a novel taxonomy that emphasizes the differences between temporal and ordering con...

Multi-robot teams are effective in a variety of task allocation domains such as warehouse automation and surveillance. Robots in such domains have to perform tasks at given locations and specific times. Tasks have to be allocated to optimize given team objectives, such as minimizing the total distance travelled. We propose an efficient, satisficing...

Multi-robot teams are useful in a variety of task allocation domains such as warehouse automation and surveillance. Robots in such domains perform tasks at given locations and specific times, and are allocated tasks to optimize given team objectives. We propose an efficient, satisficing and centralized Monte Carlo TreeSearch based algorithm exploit...

In crowded multi-agent navigation environments, the motion of the agents is significantly constrained by the motion of the nearby agents. This makes planning paths very difficult and leads to inefficient global motion. To address this problem, we propose a new distributed approach to coordinate the motions of agents in crowded environments. With ou...

These are boom times for AI. Articles celebrating the success of AI research appear frequently in the international press. Every day, millions of people routinely use AI-based systems that the founders of the field would hail as miraculous. And there is a palpable sense of excitement about impending applications of AI technologies.

Multi-robot teams are useful in a variety of task allocation domains such as warehouse automation and surveillance. Robots in such domains perform tasks at given locations and specific times, and are allocated tasks to optimize given team objectives. We propose an efficient, satisficing and centralized Monte Carlo Tree Search based algorithm exploi...

In this paper, we define a time-extended multi-robot task allocation problem and propose heuristics to tackle the problem complexity in computational resource constrained settings. The agents (or robots) can perform a limited amount of work per unit of time, while the tasks have durations and deadlines by which they must be completed. These constr...

Iterated local search (ILS) is a metaheuristic that proved to be effective on many intractable combinatorial optimization problems. However, as for most metaheuristics, evaluating and tuning ILS is not straightforward and can sometimes be misleading. In this paper, we suggest that any well-tuned ILS should at least be evaluated against two baseline...

Proper timing of the purchase of airline tickets is difficult even when historical ticket prices and some domain knowledge are available. To address this problem, we introduce an algorithm that optimizes purchase timing on behalf of customers and provides performance estimates of its computed action policy. Given a desired flight route and travel d...

Preface, table of contents, and author list. For the full text of the proceedings go to https://books.google.com/books/abou//Intelligent_Autonomous_Systems_7.html?id=39pdmU7v0sUC

We propose coordination mechanisms for multiple heterogeneous physical agents that operate in city-scale disaster scenarios, where they need to find and rescue people and extinguish fires. Large-scale disasters are characterized by limited and unreliable communications; dangerous events that may disable agents; uncertainty about the location, durat...

We propose an auction algorithm to allocate tasks that have temporal constraints to cooperative robots. Temporal constraints are expressed as time windows, within which a task must be executed. There are no restrictions on the time windows, which are allowed to overlap. Robots model their temporal constraints using a simple temporal network, enabli...

In multi-robot systems, efficiently navigating in a a partially-known environment is an ubiquitous but challenging task, as each robot must account for the uncertainty introduced, for example, by other moving robots. This uncertainty makes pre-computed plans not always applicable, and often hinders the desired efficient use of the robot's resources...

We propose a novel framework for predicting the paths of vehicles that move on a road network. The framework leverages global and local patterns in spatio-temporal data. From a large corpus of GPS trajectories, we predict the subsequent path of an in-progress vehicle trajectory using only spatio-temporal features from the data. Our framework consis...

We model a transportation network where agents of different types operate with conflicting objectives: drivers want to drive at high speeds to reach their destinations faster, while police units want to prevent unlawful speeding. Police units have to efficiently allocate their limited resources to monitor roads and catch speeders, who try to avoid...

To efficiently complete tasks whose completion costs change predictably over time requires agents that can take into account these changes. When there are more agents than tasks the problem is how to coordinate the allocation of agents to prevent tasks from growing so much that they become unsolvable. This work focuses on a subset of cost functions...

An agent must learn and adapt quickly when playing against other agents. This process is challenging in particular when playing in stochastic environments against other learning agents. In this paper, we introduce a fast and adaptive learning algorithm for repeated stochastic games (FAL-SG). FAL-SG utilizes lossy game abstraction to reduce the stat...

Dispersing a team of robots into an unknown and dangerous environment, such as a collapsed building, can provide information about structural damage and locations of survivors and help rescuers plan their actions. We propose a rolling dispersion algorithm, which makes use of a small number of robots and achieves full exploration. The robots dispers...

Buying airline tickets is an ubiquitous task in which it is difficult for humans to minimize cost due to insufficient information. Even with historical data available for inspection (a recent addition to some travel reservation websites), it is difficult to assess how purchase timing translates into changes in expected cost. To address this problem...

This work explores “big data” analysis in the context of supply chain management. Specifically we propose the use of agent-based competitive simulation as a tool to develop complex decision making strategies and to stress test them under a variety of market conditions. We propose an extensive set of business key performance indicators (KPIs) and ap...

We address the construction of a prediction model from data available in a complex environment. We first present a data extraction method that is able to leverage information contained in the movements of all variables in recent observations. This improved data extraction is then used with a common multivariate regression technique: Partial Least S...

In multi robot task allocation, a set of tasks has to be allocated to a group of robots while optimizing some measure (for example, fuel or time). In order to find the optimal allocation, an exponential number of possibilities must be explored. In this work, we extend the Consensus Based Bundle Algorithm, to improve its support for tasks with time...

We study how two self-interested agents that play a sequence of randomly generated normal form games, each game played once, can achieve cooperation without being exploited. The agent learns if the opponent is willing to cooperate by tracking the attitude of its opponent, which tells how much the opponent values its own payoff relative to the agent...

We propose eigen-based and Markov-based methods to explore the global and local structure of patterns in real-world GPS taxi trajectories. Our primary goal is to predict the subsequent path of an in-progress taxi trajectory. The exploration of global and local structure in the data differentiates this work from the state-of-the-art literature in tr...

This case study concerns the use of software agent advisors to improve efficiency and quality in issue tracking activities of development teams at the world's largest medical device manufacturer. Each software agent monitors, interacts with, and learns from its environment and user, recognizing when and how to provide different kinds of advice and...

"The better the team mental model, the better the teamwork", or so is said, in which better model refers to the extent to which the model is shared by the team members. This paper argues that according to circumstances, some components of that model are more relevant with respect to team performance than others. Circumstances change with the dynami...

This work investigates allocation of tasks to multi-robots when tasks are spatially distributed and constrained to be executed within assigned time windows. Our work explores the interaction between scheduling and optimal routing. We propose the Time-Sensitive Sequential Single-Item Auction algorithm as a method to allocate tasks with time windows...

In this paper, we consider the problem of environmental constraints on teams and examine how the constraints impact teamwork. We simulate a realistic problem for teams in the physical world by implementing a limit on the range of communication among agents. Using BlocksWorld for Teams from Delft University of Technology, we build teams of 3-4 agent...

This paper introduces a domain-specific language for programming mobile robots that is based on hierarchical state machines. Following Brooks, we refer to states as behaviors. A novelty of this language is that behaviors are treated as first class objects in the language and thus they can be passed as arguments to other parameterized behaviors. The...

Spatiotemporal reasoning is a fundamental contributor to effective problem solving. In an effort to design better problem-solving agents, we examined and evaluated the strategies that humans use to solve Tower Defense puzzles, a complex and popular class of real-time strategy games. A consistent and unexpected finding was that humans frequently tre...

Situational awareness is critical in many human tasks, especially in cases where humans have to make decisions fast and where the result of their decisions might affect their life. This paper addresses the problem of learning optimal values for the parameters of a situational awareness model. The model is a complex network with nodes connected by l...

We present an algorithm that maintains coverage of an open polyline patrolled by a team of robots. While previous work has focused on the uniformity of patrolling, we focus on ensuring the longevity of the system in the face of robot failures. A central control tower monitors the battery levels of the robots, and recalls them when they are low on p...

Many enterprises that participate in dynamic markets need to make product pricing and inventory resource utilization decisions in real-time. We describe a family of statistical models that address these needs by combining characterization of the economic environment with the ability to predict future economic conditions to make tactical (short-term...

We study the problem of achieving cooperation between two self-interested agents that play a sequence of different randomly generated normal form games. The agent learns how much the opponent is willing to cooperate and reciprocates. We present empirical results that show that both agents benefit from cooperation and that a small number of games is...

The deregulation of the electricity markets produced significant economic benefits. Improving their efficiency is a prominent scientific challenge. We focus on wholesale electricity markets, in which generators sell electricity to a public agency by ...

We describe the decision processes of agents in the Robocup Rescue Agent Simulation. Agents have to rescue civilians trapped in buildings and extin-guish fires in a city which has been struck by an earthquake. Lack of information and limited communications hamper the rescue process. We examine how effec-tive our strategies and algorithms are and co...

We examine how robots using only laser range data and the ability to communicate within a certain radius may disperse in a complex unknown environment. We demonstrate an algorithm which attempts to maximize coverage while minimizing loss of connectivity during deployment. We demonstrate using Player/Stage that this algorithm can reliably achieve si...

When agents participate in an auction, either as buyers or sellers, it is important to be able to verify compliance to auction protocols and correctness of auction clearing. We propose a method for such a verification which is based on analyzing execution traces of the auction. Our method has the advantage that it does not require access to the int...

This paper deals with large scale information retrieval aiming at contributing to web searching. The collections of documents considered are huge and not obvious to tackle with classical approaches. The greater the number of documents belonging to the ...

We present a graph-based semi-supervised approach for learn- ing user-preferred travel schedules. Assuming a setting in which a user provides a small number of labeled travel sched- ules, we classify schedules into desirable and non-desirable. This task is non-trivial since only a small number of labeled points is available. It is further complicat...

An autonomous trading agent is a complex piece of software that must operate in a competitive economic environment. We identify the problem of decision coordination as a crucial element in the design of an agent for TAC SCM, and we review the published literature on agent design to discover a wide variety of approaches to this problem. We believe t...