Alberto Finzi

IROS Conference 2024 Conference Paper

Incremental Learning of Robotic Manipulation Tasks through Virtual Reality Demonstrations

• Giuseppe Rauso
• Riccardo Caccavale
• Alberto Finzi

We propose an incremental, modular, and extensible method for learning robotic manipulation tasks using a limited number of demonstrations provided in Virtual Reality, while assuming minimal prior information about the objects to be manipulated. The developed framework enables an incremental training process in which the operator first demonstrates specialized tasks to the robotic system, and subsequently more complex tasks, exploiting the skills learned during the previous phases. We illustrate and discuss the method at work considering picking tasks performed by manipulators equipped with multi-fingered sensorized hands. The experimental evaluation highlights the feasibility and advantage of the proposed method, particularly in terms of modularity, low number of demonstrations, and reliability of the trained system.

ECAI Conference 2020 Conference Paper

Rapidly Finding the Best Arm Using Variance

• Marco Faella
• Alberto Finzi
• Luigi Sauro

We address the problem of identifying the best arm in a pure-exploration multi-armed bandit problem. In this setting, the agent repeatedly pulls arms in order to identify the one associated with the maximum expected reward. We focus on the fixed-budget version of the problem in which the agent tries to find the best arm given a fixed number of arm pulls. We propose a novel sequential elimination method exploiting the empirical variance of the arms. We detail and analyse the overall approach providing theoretical and empirical results. The experimental evaluation shows the advantage of our variance-based rejection method in heterogeneous test settings, considering both identification accuracy and execution time.

ICAPS Conference 2015 Conference Paper

Mixed-Initiative Planning and Execution for Multiple Drones in Search and Rescue Missions

• Giuseppe Bevacqua
• Jonathan Cacace
• Alberto Finzi
• Vincenzo Lippiello

We present a mixed-initiative planning and execution system for human multi-drones interaction during search and rescue missions. The proposed system should allow a single operator to supervise and orchestrate the operations of a set of UAVs by means of a natural multimodal communication. In particular, we consider the task of searching for missing persons in a real-world alpine scenario. In this context, we assume that the human operator is an alpine rescuer, involved in the scene and co-located with the drones, hence not fully dedicated to the robotic platforms, but only able to provide sparse and sketchy interventions. This scenario requires a framework that supports adjustable autonomy, from explicit teleoperation to a complete autonomy, and an effective and natural mixed-initiative interaction between the human and the robotic team. In this paper, we illustrate the domain and the overall framework discussing the system at work in a simulated case study.

IROS Conference 2014 Conference Paper

A mixed-initiative control system for an Aerial Service Vehicle supported by force feedback

• Jonathan Cacace
• Alberto Finzi
• Vincenzo Lippiello

We present an approach to mixed initiative control for unmanned aerial vehicles (UAVs) where sliding autonomy is supported by mixed-initiative planning and haptic feedback. In the proposed framework, we assume that an autonomous system can plan and execute robotic tasks while a human operator can provide interventions when necessary receiving a force feedback. The haptic feedback is associated with the sensation about how the system is diverging from the planned operations. We tested the system at work in virtual and real environments considering simple navigation tasks. We compared the performance of human operators with or without the assistance of the force feedback. The collected results support the hypothesis that the proposed approach enables effective and intuitive mixed-initiative control.

ICRA Conference 2014 Conference Paper

Continuous gesture recognition for flexible human-robot interaction

• Salvatore Iengo
• Silvia Rossi 0002
• Mariacarla Staffa
• Alberto Finzi

In this work, we present a reliable and continuous gesture recognition method that supports a natural and flexible interaction between the human and the robot. The aim is to provide a system that can be trained online with few samples and can cope with intra user variability during the gesture execution. The proposed approach relies on the generation of an ad-hoc Hidden Markov Model (HMM) for each gesture exploiting a direct estimation of the parameters. Each model represents the best prototype candidate from the associated gesture training set. The generated models are then employed within a continuous recognition process that provides the probability of each gesture at each step. The proposed method is evaluated in two case studies: a hand-performed letters recognizer and a natural gesture recognizer. Finally, we show the overall system at work in a simple human-robot interaction scenario.

IROS Conference 2013 Conference Paper

An extensible architecture for robust multimodal human-robot communication

• Silvia Rossi 0002
• Enrico Leone
• Michelangelo Fiore
• Alberto Finzi
• Francesco Cutugno

Human safety and effective human-robot communication are main concerns in HRI applications. In order to achieve such goals, a system should be very robust, allowing little chance for misunderstanding the user's commands. Moreover, the system should permit natural interaction reducing the time and the effort needed to achieve tasks. The main purpose of this work is to develop a general framework for flexible and multimodal human-robot communication. The proposed architecture should be easy to modify and expand, adding or modifying input channels and changing the multimodal fusion strategies. In this paper, we introduce our general approach and provide a case study with two modalities (gesture and speech).

ECAI Conference 2010 Conference Paper

Analyzing Flexible Timeline-based Plans

• Amedeo Cesta
• Alberto Finzi
• Simone Fratini
• Andrea Orlandini
• Enrico Tronci

Timeline-based planners have been shown quite successful in addressing real world problems. Nevertheless they are considered as a niche technology in AI P&S research as an application synthesis with such techniques is still considered a sort of "black art". Authors are currently developing a knowledge engineering tool around a timeline-based problem solving environment; in this framework we aim at integrating verification and validation methods. This work presents a verification process suitable for a timeline-based planner. It shows how a problem of flexible temporal plan verification can be cast as model-checking on timed game automata. Additionally it provides formal properties and checks the effectiveness of the proposed approach with a detailed experimental analysis.

KER Journal 2010 Journal Article

Validation and verification issues in a timeline-based planning system

• Amedeo Cesta
• Alberto Finzi
• Simone Fratini
• Andrea Orlandini
• Enrico Tronci

Abstract To foster effective use of artificial intelligence planning and scheduling ( P & S) systems in the real world, it is of great importance to both (a) broaden direct access to the technology for the end users and (b) significantly increase their trust in such technology. Automated P & S systems often bring solutions to the users that are neither ‘obvious’ nor immediately acceptable to them. This is because these tools directly reason on causal, temporal, and resource constraints; moreover, they employ resolution processes designed to optimize the solution with respect to non-trivial evaluation functions. Knowledge engineering environments aim at simplifying direct access to the technology for people other than the original system designers, while the integration of validation and verification ( V & V ) capabilities in such environments may potentially enhance the users’ trust in the technology. Somehow, V & V techniques may represent a complementary technology, with respect to P & S, that contributes to developing richer software environments to synthesize a new generation of robust problem-solving applications. The integration of V & V and P & S techniques in a knowledge engineering environment is the topic of this paper. In particular, it analyzes the use of state-of-the-art V & V technology to support knowledge engineering for a timeline-based planning system called MrSPOCK. The paper presents the application domain for which the automated solver has been developed, introduces the timeline-based planning ideas, and then describes the different possibilities to apply V & V to planning. Hence, it continues by describing the step of adding V & V functionalities around the specialized planner, MrSPOCK. New functionalities have been added to perform both model validation and plan verification. Lastly, a specific section describes the benefits as well as the performance of such functionalities.

IJCAI Conference 2007 Conference Paper

• Alessandro Farinelli
• Alberto Finzi
• Thomas Lukasiewicz

In this paper, we present the agent programming language TeamGolog, which is a novel approach to programming a team of cooperative agents under partial observability. Every agent is associated with a partial control program in Golog, which is completed by the TeamGolog interpreter in an optimal way by assuming a decision-theoretic semantics. The approach is based on the key concepts of a synchronization state and a communication state, which allow the agents to passively resp. actively coordinate their behavior, while keeping their belief states, observations, and activities invisible to the other agents. We show the usefulness of the approach in a rescue simulated domain.

ECAI Conference 2006 Conference Paper

Adaptive Multi-Agent Programming in GTGolog

• Alberto Finzi
• Thomas Lukasiewicz

We present a novel approach to adaptive multi-agent programming, which is based on an integration of the agent programming language GTGolog with adaptive dynamic programming techniques. GTGolog combines explicit agent programming in Golog with game-theoretic multi-agent planning in stochastic games. In GTGolog, the transition probabilities and reward values of the domain must be provided with the model. The adaptive generalization of GTGolog proposed here is directed towards letting the agents themselves explore and adapt these data. We use high-level programs for the generation of both abstract states and optimal policies.

IROS Conference 2005 Conference Paper

Augmenting situation awareness via model-based control in rescue robots

• Andrea Carbone
• Alberto Finzi
• Andrea Orlandini
• Fiora Pirri
• Giorgio Ugazio

In this work we describe a model-based approach to the executive control of a rescue rover. We show how this control architecture naturally supports human-robot interaction in the diverse activities needed in rescue and search. We illustrate the approach by considering human-robot interaction in the domain of the RoboCup rescue competition. We discuss the implementation and tests done both during RoboCup contests and in the laboratory, to show performances according to different working modalities such as fully operated, supervised, fully autonomous.

AAMAS Conference 2005 Conference Paper

Game Theoretic Golog under Partial Observability

• Alberto Finzi
• Thomas Lukasiewicz

IJCAI Conference 2005 Conference Paper

Representing Flexible Temporal Behaviors in the Situation Calculus

• Alberto Finzi
• Fiora

In this paper we present an approach to representing and managing temporally-flexible behaviors in the Situation Calculus based on a model of time and concurrent situations. We define a new hybrid framework combining temporal constraint reasoning and reasoning about actions. We show that the Constraint Based Interval Planning approach can be imported into the Situation Calculus by defining a temporal and concurrent extension of the basic action theory. Finally, we provide a version of the Golog interpreter suitable for managing flexible plans on multiple timelines.

ECAI Conference 2004 Conference Paper

Game-Theoretic Agent Programming in Golog

• Alberto Finzi
• Thomas Lukasiewicz

IROS Conference 2004 Conference Paper

Model-based executive control through reactive planning for autonomous rovers

• Alberto Finzi
• Félix Ingrand
• Nicola Muscettola

This paper reports on the design and implementation of a real-time executive for a mobile rover that uses a model-based, declarative approach. The control system is based on the intelligent distributed execution architecture (IDEA), an approach to planning and execution that provides a unified representational and computational framework for an autonomous agent. The basic hypothesis of IDEA is that a large control system can be structured as a collection of interacting agents, each with the same fundamental structure. We show that planning and real-time response are compatible if the executive minimizes the size of the planning problem. We detail the implementation of this approach on an 'exploration rover (Gromit, an RWI ATRV Junior at NASA Ames) presenting different IDEA controllers of the same domain and comparing them with more classical approaches. We demonstrate that the approach is scalable to complex coordination of functional modules needed for autonomous navigation and exploration.

JELIA Conference 2004 Conference Paper

Relational Markov Games

• Alberto Finzi
• Thomas Lukasiewicz

Abstract Towards a compact and elaboration-tolerant first-order representation of Markov games, we introduce relational Markov games, which combine standard Markov games with first-order action descriptions in a stochastic variant of the situation calculus. We focus on the zero-sum two-agent case, where we have two agents with diametrically opposed goals. We also present a symbolic value iteration algorithm for computing Nash policy pairs in this framework.

UAI Conference 2003 Conference Paper

Structure-Based Causes and Explanations in the Independent Choice Logic

• Alberto Finzi
• Thomas Lukasiewicz

This paper is directed towards combining Pearl's structural-model approach to causal reasoning with high-level formalisms for reasoning about actions. More precisely, we present a combination of Pearl's structural-model approach with Poole's independent choice logic. We show how probabilistic theories in the independent choice logic can be mapped to probabilistic causal models. This mapping provides the independent choice logic with appealing concepts of causality and explanation from the structural-model approach. We illustrate this along Halpern and Pearl's sophisticated notions of actual cause, explanation, and partial explanation. This mapping also adds first-order modeling capabilities and explicit actions to the structural-model approach.

NMR Workshop 2002 Conference Paper

Explanatory diagnosing and meaningful perception

• Alberto Finzi
• Fiora Pirri

In this paper we focus on the problem of sensing data interpretations in the context of a dynamic system accounting for both control and sensing actions failures. The execution of a sequence of actions mentioning sensing actions can lead to a misalignment between the observed status and the expected one. We introduce a model for failures and explanatory diagnosis to produce a plausible revision of the actions’ history, one in which all actions leading to a misalignments are avoided. The revised history serves also as an explanation of the plausible/actual state of the agent. In connection with this revision we get an interpretation of what has been perceived.