
Mohamed ChetouaniSorbonne University | UPMC
Mohamed Chetouani
About
357
Publications
102,960
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
8,347
Citations
Introduction
Additional affiliations
September 2013 - present
January 2007 - present
January 2006 - December 2011
Publications
Publications (357)
This paper introduces User-VLM, a novel approach for constructing VLMs through LLM contextualization with multimodal pre-trained user models. The proposed model is not merely beneficial but essential for effective human-robot interactions that inherently require multimodal understanding the ability to perceive, interpret, and respond to human visua...
One of the significant challenges to generating value-aligned behavior is to not only account for the specified user objectives but also any implicit or unspecified user requirements. The existence of such implicit requirements could be particularly common in settings where the user's understanding of the task model may differ from the agent's esti...
In this paper, we propose hardware and software enhancements for the Pepper robot to improve its human-robot interaction capabilities. This includes the integration of an NVIDIA Jetson GPU to enhance computational capabilities and execute real time algorithms, and a RealSense D435i camera to capture depth images, as well as the computer vision algo...
Emergent states are temporal group phenomena that arise from collective affective, behavioral, and cognitive processes shared among the group's members during their interactions. Cohesion is one such state, mainly conceptualized by scholars as affective in nature, and frequently distinguished into the two dimensions social and task cohesion. Wherea...
Social robotics continues to expand as a prominent area of research due to the increasing use of robots in settings involving social interactions. In this paper we study the social dimension of human robot interaction during a posture imitation game. We discuss how human personality traits influence a learning robot. A neural architecture is used t...
Neurodevelopmental disorders (NDD) are a group of conditions affecting children’s neurodevelopment with consequences on personal, social, and educational functioning. Social robots have been used in the rehabilitation of children with NDD with encouraging results on learning outcomes. This study aims at understanding how a social robot should act t...
Logistics and service operations involving parcel preparation, delivery, and unpacking from a supply point to a user’s home could be carried out completely by robots in the near future, taking advantage of the capabilities of the different robot morphologies for the logistics, outdoor, and domestic environments. The use of robots for parcel deliver...
Social interactions are fundamental to human life. Accurately identifying and interpreting verbal and non-verbal cues is essential for analyzing human behavior and human-machine interactions. The complexity of these interactions, along with the different communication signals, and their varying frequencies is a challenge that Deep Neural Networks c...
Phone calls are an essential communication channel in today’s contact centers, but they are more difficult to analyze than written or form-based interactions. To that end, companies have traditionally used surveys to gather feedback and gauge customer satisfaction. In this work, we study the relationship between self-reported customer satisfaction...
Perceiving the environment from another person's perspective, in other words, being in someone else's shoes spatially, is not always an easy task. Perspective-taking can be even more challenging when working with a robot as a collaborator. The study reported here aims at investigating humans' level 2 spatial perspective-taking performance when inte...
We introduce a novel category of GC-agents capable of functioning as both teachers and learners. Leveraging action-based demonstrations and language-based instructions, these agents enhance communication efficiency. We investigate the incorporation of pedagogy and pragmatism, essential elements in human communication and goal achievement, enhancing...
How do people teach robots tasks? Here, we focus on main methods and models enabling humans to teach embodied social agents such as social robots, using natural interaction. Humans guide the learning process of such agents by providing various teaching signals, which could take the form of feedback, demonstrations and instructions. This overview de...
Human-centered AI mobilizes several disciplines such as AI, human-machine interaction, philosophy, ethics, law and social sciences. In such a context, being introduced to the basic concepts of Human-centered AI is challenging. In this chapter, we describe the learning objectives of the Advanced Course on AI organized in 2021 with a focus on Human-c...
Understanding the impact of robot errors in child-robot-interactions (CRI) is critical, as current technological systems are still limited and may randomly present a variety of mistakes during interactions with children. In this study we manipulate a task-based error of a NAO robot during a semi-autonomous computational thinking task implemented wi...
In this paper, we speculate about the use of social robots as convenient tools for improving learning in an educational scenario. We introduce an experimental setup in which students listen a story read by a storyteller while their attention levels are monitored through electrophysiological and behavioral measures: if the participants are judged in...
The use of Information and Communication Technologies (ICTs) for people with Neurodevelopmental Disorders (NDD) is increasing; however, it is currently hard to assess its quality as there are issues regarding the lack of consensus on how to design these technologies. Here, using a Delphi method, we built a trans-ICTs inventory named the Design ICT...
Engagement is the process by which participants establish, maintain, and end their perceived connection. Automatic engagement inference is one of the tasks required to develop successful human-centered HMI applications. Engagement is a multi-faceted multimodal construct requiring high accuracy in interpretating contextual, verbal and non-verbal cue...
We present a new neuro-inspired reinforcement learning architecture for robot online learning and decision-making during both social and non-social scenarios. The goal is to take inspiration from the way humans dynamically and autonomously adapt their behavior according to variations in their own performance while minimizing cognitive effort. Follo...
We present SLOT-V, a novel supervised learning framework that learns observer models (human preferences) from robot motion trajectories in a legibility context. Legibility measures how easily a (human) observer can infer the robot's goal from a robot motion trajectory. When generating such trajectories, existing planners often rely on an observer m...
An integral part of seamless human-human communication is engagement, the process by which two or more participants establish, maintain, and end their perceived connection. Therefore, to develop successful human-centered human-machine interaction applications, automatic engagement inference is one of the tasks required to achieve engaging interacti...
This paper investigates how unitizing affects external observers' annotation of group cohesion. We compared unitizing techniques belonging to these categories: interval coding, continuous coding, and a technique inspired by a cognitive theory on event perception. We applied such techniques for sampling coding units from a set of recordings of socia...
Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation. When a teacher provides an instruction to a learner about an object by referring to its features, the learner can misunderstand the teacher's intentions, for instance if the instruction ambiguously refer to features of the object,...
We present SLOT-V, a novel supervised learning framework that learns observer models (human preferences) from robot motion trajectories in a legibility context. Legibility measures how easily a (human) observer can infer the robot's goal from a robot motion trajectory. When generating such trajectories, existing planners often rely on an observer m...
Robots sharing their space with humans need to be proactive to be helpful. Proactive robots can act on their own initiatives in an anticipatory way to benefit humans. In this work, we investigate two ways to make robots proactive. One way is to recognize human intentions and to act to fulfill them, like opening the door that you are about to cross....
Clinician-patient communication is essential to successful care and treatment. However, health training programs do not provide sufficient clinical exposure to practice communication skills that are pivotal when interacting with patients exhibiting mental health or age-related disorders. Recently, virtual reality has been used to develop simulation...
Learning from demonstration methods usually leverage close to optimal demonstrations to accelerate training. By contrast, when demonstrating a task, human teachers deviate from optimal demonstrations and pedagogically modify their behavior by giving demonstrations that best disambiguate the goal they want to demonstrate. Analogously, human learners...
Multi-modal behavior for social robots is crucial for the robot’s perceived social intelligence, ability to communicate nonverbally, and the extent to which the robot can be trusted. However, most of the research conducted so far has been with only one modality, thus there is still a lack of understanding of the effect of each modality when perform...
Robots sharing their space with humans need to be proactive in order to be helpful. Proactive robots are able to act on their own initiative in an anticipatory way to benefit humans. In this work, we investigate two ways to make robots proactive. One way is to recognize humans' intentions and to act to fulfill them, like opening the door that you a...
Résumé
Depuis une dizaine d’années, psychiatrie, psychologie, et intelligence artificielle (IA) ont ouvert un dialogue fécond. Dans le domaine des interactions sociales et du traitement des signaux sociaux, de nombreux travaux multidisciplinaires concourent à mieux appréhender la complexité de certains phénomènes psychologiques et à faire progresse...
In this paper we propose a new parameterization algorithm based on nonlinear prediction, which is an extension of the classical LPC parameters. The parameters performances are estimated by two different methods: the Arithmetic-Harmonic Sphericity (AHS) and the Auto-Regressive Vector Model (ARVM). Two different methods are proposed for the parameter...
Our research effort takes inspiration from human social learning mechanisms to focus on situations in which an expert guides a learner through explanations. The proposed approach incorporates explanations into maximum likelihood inverse reinforcement learning. We computationally evaluate explanations against other teaching signals (reward, demonstr...
When demonstrating a task, human tutors pedagogically modify their behavior by either "showing" the task rather than just "doing" it (exaggerating on relevant parts of the demonstration) or by giving demonstrations that best disambiguate the communicated goal. Analogously, human learners pragmatically infer the communicative intent of the tutor: th...
Collective risk dilemmas (CRDs) are a class of n-player games that represent societal challenges where groups need to coordinate to avoid the risk of a disastrous outcome. Multi-agent systems incurring such dilemmas face difficulties achieving cooperation and often converge to sub-optimal, risk-dominant solutions where everyone defects. In this pap...
Robots that share an environment with humans may communicate their intent using a variety of different channels. Movement is one of these channels and, particularly in manipulation tasks, intent communication via movement is called legibility. It alters a robot's trajectory to make it intent expressive. Here we propose a novel evaluation method tha...
Autism spectrum disorder (ASD) is mainly described as a disorder of communication and socialization. However, motor abnormalities are also common in ASD. New technologies may offer quantitative and automatic metrics to measure movement difficulties. We sought to identify computational methods to automatize the assessment of motor impairments in ASD...
In educational HRI, it is generally believed that a robots behavior has a direct effect on the engagement of a user with the robot, the task at hand and also their partner in case of a collaborative activity. Increasing this engagement is then held responsible for increased learning and productivity. The state of the art usually investigates the re...
Autonomous discovery and direct instruction are two distinct sources of learning in children but education sciences demonstrate that mixed approaches such as assisted discovery or guided play result in improved skill acquisition. In the field of Artificial Intelligence (AI), these extremes respectively map to autonomous agents learning from their o...
Creativity, in one sense, can be seen as an effort or action to bring novelty. Following this, we explore how a robot can be creative by bringing novelty in a human–robot interaction (HRI) scenario. Studies suggest that proactivity is closely linked with creativity. Proactivity can be defined as acting or interacting by anticipating future needs or...
In this paper, we present a study aimed at understanding whether the embodiment and humanlikeness of an artificial agent can affect people’s spontaneous and instructed mimicry of its facial expressions. The study followed a mixed experimental design and revolved around an emotion recognition task. Participants were randomly assigned to one level of...
Today it seems even more evident that social robots will have a more integral role to play in the real-world scenarios and need to participate in the full richness of human society. Central to the success of robots being socially intelligent agents is insuring effective interactions between humans and robots. In order to achieve that goal, research...
With more social robots entering different industries such as educational systems, health-care facilities, and even airports, it is important to tackle problems that may hinder high quality interactions in a wild setting including group conversations. This paper presents an autonomous group conversational role coordinator system based on the proxem...
In this paper, we provide an overview of the existing methods for integrating human advice into a reinforcement learning process. We first propose a taxonomy of the different forms of advice that can be provided to a learning agent. We then describe the methods that can be used for interpreting advice when its meaning is not determined beforehand....
Autonomous discovery and direct instruction are two extreme sources of learning in children, but educational sciences have shown that intermediate approaches such as assisted discovery or guided play resulted in better acquisition of skills. When turning to Artificial Intelligence, the above dichotomy is translated into the distinction between auto...
In this paper, we present a study aimed at understanding whether the embodiment and humanlikeness of an artificial agent can affect people's spontaneous and instructed mimicry of its facial expressions. The study followed a mixed experimental design and revolved around an emotion recognition task. Participants were randomly assigned to one level of...
Introduction: Motherese, or emotional infant directed speech (IDS), is the specific form of speech used by parents to address their infants. The prosody of IDS has affective properties, expresses caregiver involvement, is a marker of caregiver-infant interaction quality. IDS prosodic characteristics can be detected with automatic analysis. We aimed...
The issue of how to make embodied agents explainable has experienced a surge of interest over the past 3 years, and there are many terms that refer to this concept, such as transparency and legibility. One reason for this high variance in terminology is the unique array of social cues that embodied agents can access in contrast to that accessed by...
Writing disorders are frequent and impairing. However, social robots may help to improve children's motivation and to propose enjoyable and tailored activities. Here, we have used the Co-writer scenario in which a child is asked to teach a robot how to write via demonstration on a tablet, combined with a series of games we developed to train specif...
We discuss the relationship between explainability and knowledge transfer in reinforcement learning. We argue that explainability methods, in particular methods that use counterfactuals, might help increasing sample efficiency. For this, we present a computational approach to optimize the learner’s performance using explanations of another agent an...
Depression is a common and serious mood disorder that negatively affects the patient’s capacity of functioning normally in daily tasks. Speech is proven to be a vigorous tool in depression diagnosis. Research in psychiatry concentrated on performing fine-grained analysis on word-level speech components contributing to the manifestation of depressio...
Previous research has highlighted age-related differences in social perception, in particular emotional expression processing. To date, such studies have largely focused on approaches that use static emotional stimuli that the participant has to identify passively without the possibility of any interaction. In this study, we propose an interactive...
Depression is a common and serious mood disorder that negatively affects the patient's capacity of functioning normally in daily tasks. Speech is proven to be a vigorous tool in depression diagnosis. Research in psychiatry concentrated on performing fine-grained analysis on word-level speech components contributing to the manifestation of depressio...