Unlocking the full societal potential of artificial intelligence demands a fundamental shift towards responsible and reproducible research. Understanding that PhD students are pivotal in conducting and reproducing experiments, we investigated the challenges of 28 AI PhD candidates from 13 European countries. We identify three critical areas where current practices fall short: (1) the findability and quality of AI resources such as datasets, models, and experiments; (2) the difficulties in replicating the experiments in AI papers; (3) and the lack of trustworthiness and interdisciplinarity. After uncovering some of the underlying reasons behind the challenges, we propose a combination of social and technical recommendations to overcome the identified challenges and foster a more transparent and reliable AI research ecosystem. Socially, we recommend the general adoption of reproducibility initiatives in AI conferences and journals, as well as improved interdisciplinary scientific collaboration, especially in data governance practices. On the technical front, we call for enhanced tools to better support versioning control of datasets and code, and a computing infrastructure that facilitates the sharing and discovery of AI resources, as well as the sharing, execution, and verification of experiments.

Tackling many of humanity's contemporary challenges requires individuals to cooperate in so-called collective risk dilemmas, i.e. scenarios where cooperation is costly yet required to reach collective targets and prevent catastrophic outcomes. It remains a scientific challenge to understand which external incentives enable cooperation and whether that can be facilitated through socially interactive agents. In this paper, we evaluate human cooperation in the presence of an artificial virtual agent. We developed a game called The Pest Control, in which five players attempt to maximize their earnings while avoiding being infested by a spreading pest. Controlling the pest requires costly public good contributions, yet free-riding on the efforts of others leads to maximum individual payoffs. We conducted an online experiment and analyzed the data of 265 participants, where we manipulated the feedback strategy of the virtual agent in a between-subject design. Our results suggest that feedback highlighting salient elements of the game increases participants' cooperation, while feedback regarding the consequences of actions slightly promotes selfish behaviors. Our study provides insight into how future artificial agents and AI systems could be designed to promote cooperation in complex social dilemmas by leveraging different strategies.

In this position paper, we argue for the need for deliberation in communication for artificial agents that perform tasks together with humans. Existing works use a set of terms and concepts with different meanings, resulting in ambiguity which does not allow for a general framework. As an initial step towards such a framework, we propose the notion of deliberative communication, clarify the necessary concepts and terminology, highlight the capabilities required in using deliberation for agents that communicate with human users, and discuss the main challenges.

In many robotic applications, especially those involving humans and the environment, linguistic and visual information must be processed jointly and bound together. Existing works either encode the image or the language into a subsymbolic space, like the CLIP model, or create a symbolic space of extracted information, like the object detection models. In this paper, we propose to describe images by nouns and modifiers and introduce a new embedded binding space where the linguistic and visual cues can effectively be bound. We investigate how state-of-the-art models perform in recognizing nouns and modifiers from images, and propose our method by introducing a dataset and CLIP-like recognition techniques based on transfer learning and metric learning. We show real-world experiments that demonstrate the practical applicability of our approach to robotics applications. Our results indicate that our method can surpass the state-of-the-art in recognizing nouns and modifiers from images. Interestingly, our method exhibits a language characteristic related to context sensitivity.

In traditional decision-theoretic planning, information gathering is a means to a goal. The agent receives information about its environment (state or observation) and uses it as a way to optimize a state-based reward function. Recent works, however, have focused on application domains in which information gathering is not only the mean but the goal itself. The agent must optimize its knowledge of the environment. However, traditional Markov-based decision-theoretic models cannot account for rewarding the agent based on its knowledge, which leads to the development of many approaches to overcome this limitation. We survey recent approaches for using decision-theoretic models in information-gathering scenarios, highlighting common practices and existing generic models, and show that existing methods can be categorized into three classes: reactive sensing , single-agent active sensing , and multi-agent active sensing . Finally, we highlight potential research gaps and suggest directions for future research.

In this paper, we propose a system that stems from the integration of an autonomous mobile robot with an IoT-based monitoring system to provide monitoring, assistance, and stimulation to older adults living alone in their own houses. The creation of an Internet of Robotics Things (IoRT) based on the interplay between pervasive smart objects and autonomous robotic systems is claimed to enable the creation of innovative services conceived for assisting the final user, especially in elderly care. The synergy between IoT and a Socially Assistive Robot (SAR) was conceived to offer robustness, reconfiguration, heterogeneity, and scalability, by bringing a strong added value to both the current SAR and IoT technologies. First, we propose a method to achieve the synergy and integration between the IoT system and the robot; then, we show how our method increases the performance and effectiveness of both to provide long-term support to the older adults. To do so, we present a case-study, where we focus on the detection of signs of the frailty syndrome, a set of vulnerabilities typically conveyed by a cognitive and physical decline in older people that concur in amplifying the risks of major diseases hindering the capabilities of independent living. Experimental evaluation is performed in both controlled settings and in a long-term real-world pilot study with 9 older adults in their own apartments, where the system was deployed autonomously for, on average, 12 weeks.

Behavior Trees (BTs) are a formalism increasingly used to control the execution of robotic systems. The strength of BTs resides in their compact, hierarchical and transparent representation. However, when used in practical applications transparency is often hindered by the introduction of implicit runtime relations between nodes, e.g., because of data dependencies or hardware-related ordering constraints. Manually verifying the correctness of a BT with respect to these hidden relations is a tedious and error-prone task. This paper presents a modular planning-based approach for automatically testing BTs offline at design time, to identify possible executions that may violate given data and ordering constraints and to exhibit traces of these executions to help debugging. Our approach supports both basic and advanced BT node types, e.g., supporting parallel behaviors, and can be extended with other node types as needed. We evaluate our approach on BTs used in a commercially deployed robotics system and on a large set of randomly generated trees showing that our approach scales to realistic sizes of more than 3000 nodes.

The integration of Ambient Assisted Living (AAL) frameworks with Socially Assistive Robots (SARs) has proven useful for monitoring and assisting older adults in their own home. However, the difficulties associated with long-term deployments in real-world complex environments are still highly under-explored. In this work, we first present the MoveCare system, an unobtrusive platform that, through the integration of a SAR into an AAL framework, aimed to monitor, assist and provide social, cognitive, and physical stimulation in the own houses of elders living alone and at risk of falling into frailty. We then focus on the evaluation and analysis of a long-term pilot campaign of more than 300 weeks of usages. We evaluated the system's acceptability and feasibility through various questionnaires and empirically assessed the impact of the presence of an assistive robot by deploying the system with and without it. Our results provide strong empirical evidence that Socially Assistive Robots integrated with monitoring and stimulation platforms can be successfully used for long-term support to older adults. We describe how the robot's presence significantly incentivised the use of the system, but slightly lowered the system's overall acceptability. Finally, we emphasise that real-world long-term deployment of SARs introduces a significant technical, organisational, and logistical overhead that should not be neglected nor underestimated in the pursuit of long-term robust systems. We hope that the findings and lessons learned from our work can bring value towards future long-term real-world and widespread use of SARs.

In an ageing society, the at-home use of Socially Assistive Robots (SARs) could provide remote monitoring of their users’ well-being, together with physical and psychological support. However, private home environments are particularly challenging for SARs, due to their unstructured and dynamic nature which often contributes to robots’ failures. For this reason, even though several prototypes of SARs for elderly care have been developed, their commercialisation and wide-spread at-home use are yet to be effective. In this paper, we analyse how including the end users’ feedback impacts the SARs reliability and acceptance. To do so, we introduce a Monitoring and Logging System (MLS) for remote supervision, which increases the explainability of SAR-based systems deployed in older adults’ apartments, while also allowing the exchange of feedback between caregivers, technicians, and older adults. We then present an extensive field study showing how long-term deployment of autonomous SARs can be accomplished by relying on such a feedback loop to address any potential issue. To this end, we provide the results obtained in a 130-week long study where autonomous SARs were deployed in the apartments of 10 older adults, with the aim of possibly serving and assisting future practitioners, with the knowledge collected from this extensive experimental campaign, to fill the gap that currently exists for the widespread adoption of SARs.

As Europe sees its population aging dramatically, Assisted Daily Living for the elderly becomes a more and more important and relevant research topic. The Movecare Project focuses on this topic by integrating a robotic platform, an IoT system, and an activity center to provide assistance, suggestions of activities and transparent monitoring to users at home. In this paper, we describe the Virtual Caregiver, a software component of the Movecare platform, that is responsible for analyzing the data from the various modules and generating suggestions tailored to the user’s state and needs. A preliminary study has been carried on over 2 months with 15 users. This study suggests that the presence of the Virtual Caregiver encourages people to use the Movecare platform more consistently, which in turn could result in better monitoring and prevention of cognitive and physical decline.

Context-aware reasoning systems allow drawing sophisticated inferences about users' behaviour and physiological condition, by aggregating data from seemingly unrelated sources. We conducted a general population online survey to evaluate users' concern about the privacy of data gathered by these systems. We found that people are more concerned about third parties accessing data gathered by environmental sensors as compared to physiological sensors. Participants also indicated greater concern about unfamiliar third parties (e.g., private companies) as opposed to familiar third parties (e.g., relatives). We further found that these concerns are predicted and (to a lesser degree) causally affected by people's beliefs about how much can be inferred from these types of data, as well as by their background in computer science.

We consider the problem of communication planning for human-machine cooperation in stochastic and partially observable environments. Partially Observable Markov Decision Processes with Information Rewards (POMDPs-IR) form a powerful framework for information-gathering tasks in such environments. We propose an extension of the POMDP-IR model, called a Communicating POMDP-IR (com-POMDP-IR), that allows an agent to proactively plan its communication actions by using an approximation of the human’s beliefs. We experimentally demonstrate the capability of our com-POMDPIR agent to limit its communication to relevant information and its robustness to lost messages.

As research in smart homes and activity recognition is increasing, it is of ever increasing importance to have benchmarks systems and data upon which researchers can compare methods. While synthetic data can be useful for certain method developments, real data sets that are open and shared are equally as important. This paper presents the E-care@home system, its installation in a real home setting, and a series of data sets that were collected using the E-care@home system. Our first contribution, the E-care@home system, is a collection of software modules for data collection, labeling, and various reasoning tasks such as activity recognition, person counting, and configuration planning. It supports a heterogeneous set of sensors that can be extended easily and connects collected sensor data to higher-level Artificial Intelligence (AI) reasoning modules. Our second contribution is a series of open data sets which can be used to recognize activities of daily living. In addition to these data sets, we describe the technical infrastructure that we have developed to collect the data and the physical environment. Each data set is annotated with ground-truth information, making it relevant for researchers interested in benchmarking different algorithms for activity recognition.

Concerning frailty, the use of home-based technology able to continuously and transparently monitor the independent elder may represent a useful tool to support the traditional geriatric assessment in the identification of elderly people at risk of frailty, with the final aim of guiding the development of early preventive interventions. To this aim, the European MoveCare project develops an ICT platform to support the independent living of the elder at home. Here, we describe how home-based monitoring of frailty is addressed within MoveCare, specifically for the five Fried criteria. The platform leverages a net of heterogeneous sensors a service robot, and the use of gamification to achieve ecological monitoring of frailty through quantitative measurements transparently recorded during common daily-life activities. The indicators collected over time are fed to the reasoning entity of the platform to provide informal caregivers with relevant information on the elder's status.

Smart home environments equipped with distributed sensor networks are capable of helping people by providing services related to health, emergency detection or daily routine management. A backbone to these systems relies often on the system's ability to track and detect activities performed by the users in their home. Despite the continuous progress in the area of activity recognition in smart homes, many systems make a strong underlying assumption that the number of occupants in the home at any given moment of time is always known. Estimating the number of persons in a Smart Home at each time step remains a challenge nowadays. Indeed, unlike most (crowd) counting solution which are based on computer vision techniques, the sensors considered in a Smart Home are often very simple and do not offer individually a good overview of the situation. The data gathered needs therefore to be fused in order to infer useful information. This paper aims at addressing this challenge and presents a probabilistic approach able to estimate the number of persons in the environment at each time step. This approach works in two steps: first, an estimate of the number of persons present in the environment is done using a Constraint Satisfaction Problem solver, based on the topology of the sensor network and the sensor activation pattern at this time point. Then, a Hidden Markov Model refines this estimate by considering the uncertainty related to the sensors. Using both simulated and real data, our method has been tested and validated on two smart homes of different sizes and configuration and demonstrates the ability to accurately estimate the number of inhabitants.

Addressing the lack of social, cognitive, and physical stimuli among elders is a key factor to contrast Mild Cognitive Impairment (MCI) that can arise during the third age. Against such background, agent-based technology has been applied to different application domains related to the assistance of elders. In this demo, we introduce an application of this kind: an activity center featuring social, cognitive, and physical activities targeted for elders. This activity center interacts with an autonomous agent, called Virtual Caregiver, residing in the cloud and generating interventions based on users' data. We show how the user experience can be enriched with an adaptive configuration encouraging socialization and cognitive training.

Smart Homes are currently one of the hottest topics in the area of Internet of Things or Augmented Living. In order to provide high-level intelligent solutions, algorithms for identifying which activities the inhabitants intend to perform are necessary. Sensor data plays here an essential role, for testing, for learning underlying rules, for classifying and connecting sensor patterns and to inhabitant activities, etc. However, only few and limited data sets are currently available. We present concepts and solutions for generating high-quality data using a flexible agent-based simulation tool. The basic idea is to integrate the simulation of a sensorised apartment with human behaviour modelling based on constraint-based planning that produces a sequence of daily activities. The overall set-up is shown to generate data that exhibits the same relevant properties as data from a comparable real-world apartment.

Context-recognition and activity recognition systems in multi-user environments such as smart homes, usually assume to know the number of occupants in the environment. However, being able to count ...