Francesco Rea

Carlo Mazzola, Marta Romeo, Francesco Rea et al.

Communicating shapes our social word. For a robot to be considered social and being consequently integrated in our social environment it is fundamental to understand some of the dynamics that rule human-human communication. In this work, we tackle the problem of Addressee Estimation, the ability to understand an utterance's addressee, by interpreting and exploiting non-verbal bodily cues from the speaker. We do so by implementing an hybrid deep learning model composed of convolutional layers and LSTM cells taking as input images portraying the face of the speaker and 2D vectors of the speaker's body posture. Our implementation choices were guided by the aim to develop a model that could be deployed on social robots and be efficient in ecological scenarios. We demonstrate that our model is able to solve the Addressee Estimation problem in terms of addressee localisation in space, from a robot ego-centric point of view.

Linda Lastrico, Luca Garello, Francesco Rea et al.

Humans have an extraordinary ability to communicate and read the properties of objects by simply watching them being carried by someone else. This level of communicative skills and interpretation, available to humans, is essential for collaborative robots if they are to interact naturally and effectively. For example, suppose a robot is handing over a fragile object. In that case, the human who receives it should be informed of its fragility in advance, through an immediate and implicit message, i.e., by the direct modulation of the robot's action. This work investigates the perception of object manipulations performed with a communicative intent by two robots with different embodiments (an iCub humanoid robot and a Baxter robot). We designed the robots' movements to communicate carefulness or not during the transportation of objects. We found that not only this feature is correctly perceived by human observers, but it can elicit as well a form of motor adaptation in subsequent human object manipulations. In addition, we get an insight into which motion features may induce to manipulate an object more or less carefully.

Carlo Mazzola, Francesco Rea, Alessandra Sciutti

Addressee Estimation is the ability to understand to whom a person is talking, a skill essential for social robots to interact smoothly with humans. In this sense, it is one of the problems that must be tackled to develop effective conversational agents in multi-party and unstructured scenarios. As humans, one of the channels that mainly lead us to such estimation is the non-verbal behavior of speakers: first of all, their gaze and body pose. Inspired by human perceptual skills, in the present work, a deep-learning model for Addressee Estimation relying on these two non-verbal features is designed, trained, and deployed on an iCub robot. The study presents the procedure of such implementation and the performance of the model deployed in real-time human-robot interaction compared to previous tests on the dataset used for the training.

Doreen Jirak, Alessandra Sciutti, Pablo Barros et al.

Human-robot interaction (HRI) benefits greatly from advances in the machine learning field as it allows researchers to employ high-performance models for perceptual tasks like detection and recognition. Especially deep learning models, either pre-trained for feature extraction or used for classification, are now established methods to characterize human behaviors in HRI scenarios and to have social robots that understand better those behaviors. As HRI experiments are usually small-scale and constrained to particular lab environments, the questions are how well can deep learning models generalize to specific interaction scenarios, and further, how good is their robustness towards environmental changes? These questions are important to address if the HRI field wishes to put social robotic companions into real environments acting consistently, i.e. changing lighting conditions or moving people should still produce the same recognition results. In this paper, we study the impact of different image conditions on the recognition of arousal and valence from human facial expressions using the FaceChannel framework \cite{Barro20}. Our results show how the interpretation of human affective states can differ greatly in either the positive or negative direction even when changing only slightly the image properties. We conclude the paper with important points to consider when employing deep learning models to ensure sound interpretation of HRI experiments.

Luca Garello, Linda Lastrico, Alessandra Sciutti et al.

Object manipulation is a natural activity we perform every day. How humans handle objects can communicate not only the willfulness of the acting, or key aspects of the context where we operate, but also the properties of the objects involved, without any need for explicit verbal description. Since human intelligence comprises the ability to read the context, allowing robots to perform actions that intuitively convey this kind of information would greatly facilitate collaboration. In this work, we focus on how to transfer on two different robotic platforms the same kinematics modulation that humans adopt when manipulating delicate objects, aiming to endow robots with the capability to show carefulness in their movements. We choose to modulate the velocity profile adopted by the robots' end-effector, inspired by what humans do when transporting objects with different characteristics. We exploit a novel Generative Adversarial Network architecture, trained with human kinematics examples, to generalize over them and generate new and meaningful velocity profiles, either associated with careful or not careful attitudes. This approach would allow next generation robots to select the most appropriate style of movement, depending on the perceived context, and autonomously generate their motor action execution.

Marco Matarese, Francesco Rea, Alessandra Sciutti

There is an increasing consensus about the effectiveness of user-centred approaches in the explainable artificial intelligence (XAI) field. Indeed, the number and complexity of personalised and user-centred approaches to XAI have rapidly grown in recent years. Often, these works have a two-fold objective: (1) proposing novel XAI techniques able to consider the users and (2) assessing the \textit{goodness} of such techniques with respect to others. From these new works, it emerged that user-centred approaches to XAI positively affect the interaction between users and systems. However, so far, the goodness of XAI systems has been measured through indirect measures, such as performance. In this paper, we propose an assessment task to objectively and quantitatively measure the goodness of XAI systems in terms of their \textit{information power}, which we intended as the amount of information the system provides to the users during the interaction. Moreover, we plan to use our task to objectively compare two XAI techniques in a human-robot decision-making task to understand deeper whether user-centred approaches are more informative than classical ones.

Marco Matarese, Francesco Rea, Katharina J. Rohlfing et al.

Collaborative decision-making with artificial intelligence (AI) agents presents opportunities and challenges. While human-AI performance often surpasses that of individuals, the impact of such technology on human behavior remains insufficiently understood, primarily when AI agents can provide justifiable explanations for their suggestions. This study compares the effects of classic vs. partner-aware explanations on human behavior and performance during a learning-by-doing task. Three participant groups were involved: one interacting with a computer, another with a humanoid robot, and a third one without assistance. Results indicated that partner-aware explanations influenced participants differently based on the type of artificial agents involved. With the computer, participants enhanced their task completion times. At the same time, those interacting with the humanoid robot were more inclined to follow its suggestions, although they did not reduce their timing. Interestingly, participants autonomously performing the learning-by-doing task demonstrated superior knowledge acquisition than those assisted by explainable AI (XAI). These findings raise profound questions and have significant implications for automated tutoring and human-AI collaboration.

Marco Matarese, Francesco Rea, Alessandra Sciutti

State of the art Artificial Intelligence (AI) techniques have reached an impressive complexity. Consequently, researchers are discovering more and more methods to use them in real-world applications. However, the complexity of such systems requires the introduction of methods that make those transparent to the human user. The AI community is trying to overcome the problem by introducing the Explainable AI (XAI) field, which is tentative to make AI algorithms less opaque. However, in recent years, it became clearer that XAI is much more than a computer science problem: since it is about communication, XAI is also a Human-Agent Interaction problem. Moreover, AI came out of the laboratories to be used in real life. This implies the need for XAI solutions tailored to non-expert users. Hence, we propose a user-centred framework for XAI that focuses on its social-interactive aspect taking inspiration from cognitive and social sciences' theories and findings. The framework aims to provide a structure for interactive XAI solutions thought for non-expert users.

Linda Lastrico, Alessandro Carfì, Francesco Rea et al.

When manipulating objects, humans finely adapt their motions to the characteristics of what they are handling. Thus, an attentive observer can foresee hidden properties of the manipulated object, such as its weight, temperature, and even whether it requires special care in manipulation. This study is a step towards endowing a humanoid robot with this last capability. Specifically, we study how a robot can infer online, from vision alone, whether or not the human partner is careful when moving an object. We demonstrated that a humanoid robot could perform this inference with high accuracy (up to 81.3%) even with a low-resolution camera. Only for short movements without obstacles, carefulness recognition was insufficient. The prompt recognition of movement carefulness from observing the partner's action will allow robots to adapt their actions on the object to show the same degree of care as their human partners.

Jonas Gonzalez-Billandon, Giulia Belgiovine, Alessandra Sciutti et al.

The ability to recognize human partners is an important social skill to build personalized and long-term human-robot interactions, especially in scenarios like education, care-giving, and rehabilitation. Faces and voices constitute two important sources of information to enable artificial systems to reliably recognize individuals. Deep learning networks have achieved state-of-the-art results and demonstrated to be suitable tools to address such a task. However, when those networks are applied to different and unprecedented scenarios not included in the training set, they can suffer a drop in performance. For example, with robotic platforms in ever-changing and realistic environments, where always new sensory evidence is acquired, the performance of those models degrades. One solution is to make robots learn from their first-hand sensory data with self-supervision. This allows coping with the inherent variability of the data gathered in realistic and interactive contexts. To this aim, we propose a cognitive architecture integrating low-level perceptual processes with a spatial working memory mechanism. The architecture autonomously organizes the robot's sensory experience into a structured dataset suitable for human recognition. Our results demonstrate the effectiveness of our architecture and show that it is a promising solution in the quest of making robots more autonomous in their learning process.

Jonas Gonzalez-Billandon, Lukas Grasse, Matthew Tata et al.

In the future robots will interact more and more with humans and will have to communicate naturally and efficiently. Automatic speech recognition systems (ASR) will play an important role in creating natural interactions and making robots better companions. Humans excel in speech recognition in noisy environments and are able to filter out noise. Looking at a person's face is one of the mechanisms that humans rely on when it comes to filtering speech in such noisy environments. Having a robot that can look toward a speaker could benefit ASR performance in challenging environments. To this aims, we propose a self-supervised reinforcement learning-based framework inspired by the early development of humans to allow the robot to autonomously create a dataset that is later used to learn to localize speakers with a deep learning network.

Vipul Nair, Paul Hemeren, Alessia Vignolo et al.

Understanding which features humans rely on -- in visually recognizing action similarity is a crucial step towards a clearer picture of human action perception from a learning and developmental perspective. In the present work, we investigate to which extent a computational model based on kinematics can determine action similarity and how its performance relates to human similarity judgments of the same actions. To this aim, twelve participants perform an action similarity task, and their performances are compared to that of a computational model solving the same task. The chosen model has its roots in developmental robotics and performs action classification based on learned kinematic primitives. The comparative experiment results show that both the model and human participants can reliably identify whether two actions are the same or not. However, the model produces more false hits and has a greater selection bias than human participants. A possible reason for this is the particular sensitivity of the model towards kinematic primitives of the presented actions. In a second experiment, human participants' performance on an action identification task indicated that they relied solely on kinematic information rather than on action semantics. The results show that both the model and human performance are highly accurate in an action similarity task based on kinematic-level features, which can provide an essential basis for classifying human actions.

Marco Matarese, Silvia Rossi, Alessandra Sciutti et al.

The high request for autonomous and flexible HRI implies the necessity of deploying Machine Learning (ML) mechanisms in the robot control. Indeed, the use of ML techniques, such as Reinforcement Learning (RL), makes the robot behaviour, during the learning process, not transparent to the observing user. In this work, we proposed an emotional model to improve the transparency in RL tasks for human-robot collaborative scenarios. The architecture we propose supports the RL algorithm with an emotional model able to both receive human feedback and exhibit emotional responses based on the learning process. The model is entirely based on the Temporal Difference (TD) error. The architecture was tested in an isolated laboratory with a simple setup. The results highlight that showing its internal state through an emotional response is enough to make a robot transparent to its human teacher. People also prefer to interact with a responsive robot because they are used to understand their intentions via emotions and social signals.