A5028729032- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Optimization and Search Problems
- Modular Robots and Swarm Intelligence
- Multi-Agent Systems and Negotiation
- Robotics and Automated Systems
- Logic, Reasoning, and Knowledge
- Distributed Control Multi-Agent Systems
- AI-based Problem Solving and Planning
- Semantic Web and Ontologies
- Advanced Image and Video Retrieval Techniques
- Mobile Agent-Based Network Management
- 3D Surveying and Cultural Heritage
- Auction Theory and Applications
- Infrastructure Resilience and Vulnerability Analysis
- Robot Manipulation and Learning
- Energy Efficient Wireless Sensor Networks
- Reinforcement Learning in Robotics
- Data Management and Algorithms
- Target Tracking and Data Fusion in Sensor Networks
- Water resources management and optimization
- Indoor and Outdoor Localization Technologies
- Anomaly Detection Techniques and Applications
- Artificial Intelligence in Games
- Computability, Logic, AI Algorithms
Politecnico di Milano
2015-2024
Université Paris Sciences et Lettres
2021
ParisTech
2021
Institute of Electrical and Electronics Engineers
2017-2018
Gorgias Press (United States)
2018
Vrije Universiteit Brussel
2018
Intelligent Systems Research (United States)
2017
IEEE Computer Society
2017
Consorzio di Bioingegneria e Informatica Medica
2015
University of Lisbon
2014
Game theoretic approaches to patrolling have become a topic of increasing interest in the very last years. They mainly refer mobile robot that preserves an environment from intrusions. These allow for development strategies consider possible actions intruder deciding where should move. Usually, it is supposed can hide and observe patroller before intervening. This leads adoption leader-follower solution concept. In this paper, mostly theoretical its nature, we propose approach determine...
Exploration of initially unknown environments is an online task in which autonomous mobile robots coordinate themselves to efficiently discover free spaces and obstacles. Several efforts have been devoted study coordinated multirobot exploration assuming that communication possible between any two locations. The problem developing systems for effective the presence constraints, despite its remarkable practical relevance, comparably much less studied. authors provide a taxonomy field...
Scientific experiments and robotic competitions share some common traits that can put the debate about developing better experimental methodologies replicability of results in robotics research on more solid ground. In this context, Robot Competitions Kick Innovation Cognitive Systems Robotics (RoCKIn) project aims to develop come close scientific experiments, providing an objective performance evaluation robot systems under controlled replicable conditions. article, by further articulating...
The most tight intractability results for graph-based Multirobot Path Planning (MPP), proven recently, state that time-optimal and distance-optimal MPP problems are NP-hard on planar graphs. In this letter, we go one step further what concerns the objectives, prove such remain when restricting graph to a 2D grid with holes, which is discretization widely used in robotics. Our reduction (from Boolean satisfiability problem) cannot be easily modified whose hardness remains an open problem.
The ability of building maps environments where they operate is one the main requirements for autonomous mobile robots. An efficient map process based on a good exploration strategy that determines most convenient observation positions in partially known environment order to incrementally it. Several strategies have been proposed literature but their comparative evaluations are rare. In this paper, we experimentally compare some contribute assess strengths and weaknesses.
The development of ambient intelligence (AmI) applications that effectively adapt to the needs users and environments requires, among other things, presence planning mechanisms for goal-oriented behavior. Planning is intended as ability an AmI system build a course actions that, when carried out by devices in environment, achieve given goal. problem has not yet been adequately explored literature. We propose applications, based on hierarchical task network (HTN) approach called distributed...
Patrolling environments by means of autonomous mobile robots has received an increasing attention in the last few years. The interest agent community is mainly development effective patrolling strategies. Approaches based on game theory have been demonstrated to be very effective. They model situation as a two-player leader-follower game, where patroller leader and intruder follower. These models present several limitations that prevent their use realistic settings. In this paper, we extend...
Many water resources systems include multiple, independent, and distributed decision makers representing different conflicting interests. In much of the literature, operation these is studied assuming a fully cooperative attitude by parties involved maximizing global efficiency at system-level. However, presence social planner might be questionable when multiple institutions are involved, particularly in transboundary systems. At other extreme, totally uncoordinated strategies among...
In multirobot exploration under centralized control, communication plays an important role in constraining the team strategy. Recurrent connectivity is a way to define constraints for which robots must connect base station only when making new observations. This paper studies effective strategies recurrent by considering and asynchronous planning framework. We formalize problem of selecting optimal set locations should reach, provide exact formulation solve it, devise approximation algorithm...
Exploration strategies are used to guide mobile robots in building maps of environments. Usually, exploration work greedily by evaluating a number candidate observation positions on the basis utility function and selecting best one. The functions defined an ad hoc manner as compositionof values measuring different features position, such travelling cost estimated information gain. In this paper, we propose more general way define strategy through multi-objective optimization. our approach,...
Detection of anomalies and faults is a crucial ability for fully autonomous robots. This letter proposes new deep learning-based minimally supervised method detecting in We contribute Variational Auto-Encoder architecture able to model very long multivariate sensor logs exploiting incremental training method, which induces progress-based latent space that can be used detect both at runtime offline. While most existing approaches are trained semi-supervised fashion require big batches nominal...
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 observing landmarks other robots. In this paper we propose to build a global geometric integrating scans collected laser range scanners without using any knowledge about robots' poses. We consider collections line segments. Our approach increases flexibility in data collection, since do not need see each during mapping, and multiple single...
Using autonomous mobile robots to patrol environments for detecting intruders is a topic of increasing relevance its possible applications. A large part strategies patrolling proposed so far adopt some kind random movements. Although these are unpredictable an intruder, they not always efficient in getting the patroller expected utility. In this paper we propose approach that considers model adversary game theoretic framework find optimally-efficient strategies. We show our extends those...