Maurizio Di Rocco

Development of a Socially Believable Multi-Robot Solution from Town to Home

Abstract Technological advances in the robotic and ICT fields represent an effective solution to address specific societal problems to support ageing and independent life. One of the key factors for these technologies is that they have to be socially acceptable and believable to the end-users. This paper aimed to present some technological aspects that have been faced to develop the Robot-Era system, a multi-robotic system that is able to act in a socially believable way in the environments daily inhabited by humans, such as urban areas, buildings and homes. In particular, this paper focuses on two services—shopping delivery and garbage collection—showing preliminary results on experiments conducted with 35 elderly people. The analysis adopts an end-user-oriented perspective, considering some of the main attributes of acceptability: usability, attitude, anxiety, trust and quality of life.

Robotic Ubiquitous Cognitive Ecology for Smart Homes

Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them both autonomous and adaptive, so as to reduce the amount of preparation, pre-programming and human supervision that they require in real world applications. The project RUBICON develops learning solutions which yield cheaper, adaptive and efficient coordination of robotic ecologies. The approach we pursue builds upon a unique combination of methods from cognitive robotics, machine learning, planning and agent-based control, and wireless sensor networks. This paper illustrates the innovations advanced by RUBICON in each of these fronts before describing how the resulting techniques have been integrated and applied to a proof of concept smart home scenario. The resulting system is able to provide useful services and pro-actively assist the users in their activities. RUBICON learns through an incremental and progressive approach driven by the feedback received from its own activities and from the user, while also self-organizing the manner in which it uses available sensors, actuators and other functional components in the process. This paper summarises some of the lessons learned by adopting such an approach and outlines promising directions for future work.

When robots are late: Configuration planning for multiple robots with dynamic goals

Unexpected contingencies in robot execution may induce a cascade of effects, especially when multiple robots are involved. In order to effectively adapt to this, robots need the ability to reason along multiple dimensions at execution time. We propose an approach to closed-loop planning capable of generating configuration plans, i.e., action plans for multirobot systems which specify the causal, temporal, resource and information dependencies between individual sensing, computation, and actuation components. The key feature which enables closed loop performance is that configuration plans are represented as constraint networks, which are shared between the planner and the executor and are continuously updated during execution. We report experiments run both in simulation and on real robots, in which a fault in one robot is compensated through different types of plan modifications at run time.

Learning context-aware mobile robot navigation in home environments

We present an approach to make planning adaptive in order to enable context-aware mobile robot navigation. We integrate a model-based planner with a distributed learning system based on reservoir computing, to yield personalized planning and resource allocations that account for user preferences and environmental changes. We demonstrate our approach in a real robot ecology, and show that the learning system can effectively exploit historical data about navigation performance to modify the models in the planner, without any prior information oncerning the phenomenon being modeled. The plans produced by the adapted CL fail more rarely than the ones generated by a non-adaptive planner. The distributed learning system handles the new learning task autonomously, and is able to automatically identify the sensorial information most relevant for the task, thus reducing the communication and computational overhead of the predictive task.

A cognitive robotic ecology approach to self-configuring and evolving AAL systems

Robotic ecologies are systems made out of several robotic devices, including mobile robots, wireless sensors and effectors embedded in everyday environments, where they cooperate to achieve complex tasks. This paper demonstrates how endowing robotic ecologies with information processing algorithms such as perception, learning, planning, and novelty detection can make these systems able to deliver modular, flexible, manageable and dependable Ambient Assisted Living (AAL) solutions. Specifically, we show how the integrated and self-organising cognitive solutions implemented within the EU project RUBICON (Robotic UBIquitous Cognitive Network) can reduce the need of costly pre-programming and maintenance of robotic ecologies. We illustrate how these solutions can be harnessed to (i) deliver a range of assistive services by coordinating the sensing & acting capabilities of heterogeneous devices, (ii) adapt and tune the overall behaviour of the ecology to the preferences and behaviour of its inhabitants, and also (iii) deal with novel events, due to the occurrence of new users activities and changing users habits.

Stigmergic algorithms for multiple minimalistic robots on an RFID floor

Stigmergy is a powerful principle in nature, which has been shown to have interesting applications to robotic systems. By leveraging the ability to store information in the environment, robots with minimal sensing, memory, and computational capabilities can solve complex problems like global path planning. In this paper, we discuss the use of stigmergy in minimalist multi-robot systems, in which robots do not need to use any internal model, long-range sensing, or position awareness. We illustrate our discussion with three case studies: building a globally optimal navigation map, building a gradient map of a sensed feature, and updating the above maps dynamically. All case studies have been implemented in a real environment with multiple ePuck robots, using a floor with 1,500 embedded radio frequency identification tags as the stigmergic medium. Results collected from tens of hours of real experiments and thousands of simulated runs demonstrate the effectiveness of our approach.

Gas source localization in indoor environments using multiple inexpensive robots and stigmergy

Environmental monitoring is a rather new field in robotics. One of the main appealing tasks is gas mapping, i.e., the characterization of the chemical properties (concentration, dispersion, etc.) of the air within an environment. Current approaches rely on a robot using standard localization and mapping techniques to fuse gas measures with spatial features. These approaches require sophisticated sensors and/or high computational resources. We propose a minimalistic approach, in which one or multiple low-cost robots exploit the ability to store information in the environment, or “stigmergy”, to effectively compute an artificial potential leading toward the likely location of the gas source, as indicated by a highest gas concentration or fluctuation. The potential is computed and stored directly on an array of RFID tags buried under the floor. Our approach has been validated in extensive experiments performed on real robots in a domestic environment.

A distributed Transferable Belief Model for collaborative topological map-building in multi-robot systems

In this paper the problem of multi-robot collaborative topological map-building is addressed. In this framework, a team of robots is supposed to move in an indoor office-like environment. Each robot, after building a local map by using infrared range-finders, achieves a topological representation of the environment by extracting the most significant features via the Hough transform and comparing them with a set of predefined environmental patterns. The local view of each robot which is significantly constrained by its limited sensing capabilities is then strengthened by a collaborative aggregation schema based on the Transferable Belief Model (TBM). In this way, a better representation of the environment is achieved by each robot with a minimal exchange of information. A preliminary experimental validation carried out by exploiting data collected from a self-made team of robots is proposed.

An experimental validation of a low-cost indoor relative position localizing system for mobile robotic networks

In this work, an experimental validation of a low-cost indoor relative position localizing system for mobile robotic networks is described. In our framework, each robot is assumed to be equipped with a light emitter along with a camera, both pointing to the ceiling. In this way, each robot can see on the ceiling a constellation with its own position at the azimuth and the (relative) positions of its neighbors falling in its visual field. This allows to measure the relative distance and orientation among robots. The proposed localizing system can be thought as a convenient tool to validate, among the others, the efficacy of cooperative control algorithms. Several experiments are provided to show the effectiveness of the proposed localizing system for typical multi-robot tasks, such as rendezvous or formation control.

A networked transferable belief model approach for distributed data aggregation - Dynamic version

This paper investigates the data aggregation problem for a multi-agent system. In this framework, agents are assumed to be independent reliable sources which collect data and collaborate to reach a common knowledge. In particular, agents are assumed to dynamically gather data over time, i.e., a dynamic scenario. A protocol for distributed data aggregation which is proved to converge to the basic belief assignment (BBA) given by a centralized aggregation based on the Transferable Belief Model (TBM) is provided.