The French National Research Agency Projects for science

Voir cette page en français

ANR funded project

(DS0704)
Edition 2016


JointAction4HRI


Joint Action for Human Robot Interaction

JointAction4HRI
Joint Action for Human-Robot Interaction
What matters to us are the key components and mechanisms underlying joint action, their informational content and how they are linked together, temporarily, hierarchically and meaningfully. Our ambition is to contribute, at the most fundamental level, to the identification and characterization of the ingredients required for the successful realization of a collaborative task in a human-human and a human-robot contexts.

In the framework of joint action, our objectives are: to identify elements of mutual understanding, to model the notion of commitment, to develop a robotics architecture
JointAction4HRI project objectives are:
1) Identifying the elements (and their interaction) that allow the establishment and maintenance of mutual understanding between a human and a robot in a collaborative task.
2) Modeling the notion of commitment that structures the relationship between two agents during interaction.
3) Elaborate and test robotics architecture design for collaboration with humans
Our first objective is to study the necessary elements for mutual understanding between agents in the context of human-robot interactions. When we interact with another person, and especially in a collaborative context, we produce and perceive a number of indices, sometimes without even realizing it: e.g., visual back and forth between two individuals, gaze alternation between the two partners and the subject/object of collaboration, change in posture, etc.
Our second objective is to characterize in detail the nature and role of commitments in joint action in order to model their functioning in joint action. When they engage in a collaborative task, agent are committed to pursuing together a common goal. The coordination among agents also involves commitments with respect to the means to be deployed in pursuit of this goal, the division of labour among participants and the sharing of information relevant to the successful performance of the task. What is exactly the nature of these commitments and what are their functions? How should we model the processes involved in forming, implementing and sustaining commitments?
Finally, our third objective is to elaborate and experiment (through the implementation of human-robot collaborative objects manipulation tasks involving a human and a laboratory robot) a robotic control architecture enabled for joint action. A complementary objective will be to instantiate a “proof of concept” and to implement on a robot in order to effectively exhibit in a comprehensive and explicit manner the ingredients for human-robot joint action.

Methods/Approach
The project is organized into four tasks; there will be one leader by task but partners will be involved in all the tasks:
Task 1: Elements of Mutual Understanding (resp: CLLE): In charge of the first objective, namely identifying the elements (and their interaction) that allow the establishment and maintenance of mutual understanding between a human and a robot in a collaborative task
Task 2: Commitment Management (resp: Institut Jean Nicod) : In charge of the second objective, namely characterizing the nature and functions of commitments in order to model their functioning in joint action
Task 3: Robotic architecture (resp: LAAS) : In charge of the third objective: Elaborate and test a robot architecture design for collaboration with humans
Task 4: Management, dissemination and prospective (resp: LAAS)

and the timing of these tasks will be organized through four milestones:
M1: Challenges and requirements for a robotic architecture enabled for joint action
M2: Fundamental research about human-human joint action done, Models of joint action ready, first robotics architecture enabled for joint action design ready
M3: A first instance of the robotics architecture implemented
M4: Fundamental research about human-robot joint action done ?M5: A second iteration of the robotics architecture implemented

Results

Task 1: Elements of Mutual Understanding
Work on the theoretical contribution of developmental psychology for the project : development of joint attention and joint action, feeling of dealing with a social agent to improve the success of collaborative tasks, proposition to deal with HRI complexity on 3 dimensions (motor precision, coordination, anticipatory planning), necessity of considering multimodal communication and analyze separately its forms and functions [3].
A collaboration with the H2020 MuMMER project has been setup to study route description task (seen as a joint action) [2][10].

Task 2: Commitment Management
Task 2.1.1 Typology and functions of commitments has been handled before T0+13, it defines Motivational uncertainty, Instrumental uncertainty, Common ground uncertainty. Task 2.1.2 is now on the way, the proposition is that to solve the credibility problem one needs to appeal to a basic motivational factor (the need to belong) that scaffolds more sophisticated motivational mechanisms (reputation management and social emotion), that in turn back up the social normativity and practical rationality that make commitments efficient for reducing uncertainty [8][9].

Task 3: Robotic Architecture
We have chosen to study and develop robot abilities for several tasks considered as joint actions: (1) Building stack tasks, (2) Navigating in narrow spaces populated with humans and (3) Providing route directions.
We have contributed through a refined study of human-robot shared plans execution [4]. We have proposed and used the PERDITA questionnaire [1] to assess the pertinence of robot decisions.

Task 4: Management, dissemination and prospective
A bibliography has been setup: https://www.zotero.org/groups/jointaction4hri-openbiblio
We have pursued our effort consisting in organizing workshops on joint action with roboticists, psychologists and philosophers fja.sciencesconf.org.

Outlook

Far beyond the «simplistic« anthropomorphic appearance or the «naive« human-mimicry that we could implement to the machine, what matters to us here are the key components and mechanisms underlying joint action, their informational content (relatively to the common ground in terms of general knowledge, acquired previously and during the task itself), and how they are linked together, temporarily, hierarchically and meaningfully. Our ambition is to contribute, at the most fundamental level, to the identification and characterization of the ingredients required for the successful realization of a collaborative task.
JointAction4HRI project proposes an original consortium composed of researchers from a philosophy laboratory (Institut Jean Nicod), a psychology laboratory (CLLE), and a robotics laboratory (LAAS). Each has contributed in their respective discipline and for several years to research in the joint action domain. By bringing their complementary expertise together, JointAction4HRI will foster the development of an integrated theoretical framework.
Expected benefits are obvious from the perspective of service or entertainment robotics development. But we can envision broader benefits. Thus, we expect that joint attention modeling will give us cues to help the evaluation and support of children with developmental disorders (e.g. autistic children). Confronting the roles of commitments in human-human interaction and in human-robot interaction should also shed new light on the current philosophical debate about commitments in joint action, helping to identify more precisely their essential properties as well as the nature of the social norms and emotions that ensure their efficiency. Finally, our research should lead to a precise characterization of the elements necessary to manage mutual understanding between agents in cooperative situations.

Scientific outputs and patents

1. Devin S., Vrignaud C., Belhassein K., Clodic A., Carreras O., Alami R., « Evaluating the Pertinence of Robot Decisions in a Human-Robot Joint Action Context: The PeRDITA Questionnaire » IEEE RO-MAN’18
2. Belhassein K., Clodic A., Cochet H., Niemela¨ M., Heikkila¨ P., et al.. « Human-Human Guidance Study. » Rapport LAAS n° 17596. 2017. 4. Devin, S., Clodic, A., & Alami, R. (2017). « About Decisions During Human-Robot Shared Plan Achievement: Who Should Act and How? » Social Robotics, Springer International Publishing. https://doi.org/10.1007/978-3-319-70022-9_45
5. Pacherie E. « Common beliefs, solution thinking and team reasoning«, Symposium: Guala on Understanding Institutions, Fifth Conference of the European Network on Social Ontology, University of Lund, Sweden, August 30 - September 1, 2017
6. Clodic A., Vazquez Salceda J., Dignum F., Mascarenhas S., Dignum V., Augello A., Gentile M., Alami R. (2018) « On the pertinence of Social Practices for Social Robotics » Robo- philosophy’18 Conference
7. Dignum V., Dignum F., Vazquez Salceda J., Clodic A., Gentile M., Mascarenhas S., Augello A., (2018) « Design for Values for Social Robot Architectures » Robo-philosophy’18 Conference
8. Pacherie E. «Joint action, commitments and need to belong» Layers of Collective Intentionality. Vienna (Austria) 16th-18th August 2018.
9. Fernandez-Castro V., Pacherie E. «Commitments in joint action: the credibility problem» 3rd DFG Workshop Methodological issues relevant to testing and measuring Theory of Mind, empathy and related social behaviours. Dresden (Germany)13th-14th September 2018
10. Heikkila¨ P., Lammi H, Belhassein K. «Where Can I Find a Pharmacy? - Human-Driven Design of a Service Robot’s Guidance Behaviour» - 4th Workshop on Public Space Human- Robot Interaction (PubRob 2018)

Partners

CNRS/CLLE CNRS/Cognition, Langues, Langage, Ergonomie

CNRS/LAAS Centre National de la Recherche Scientifique/LAAS

IJN Institut Jean Nicod

ANR grant: 369 256 euros
Beginning and duration: mars 2017 - 48 mois

Submission abstract

In a foreseeable future, humans and robots are set to act together and even to collaborate. Service, assistant or teammate
robots are actively considered as possible applications. Collaborating shall then not be tied to one single, specific interaction, since all the agents concerned, both the human AND the robot, will then have to build and to maintain, co- constructively, and as long as necessary, the collaborative process and relationship that come along with the task, thus allowing its joint execution. Such a process must be flexible, adaptable enough, so any of the agents, human or (even) robots, could make mistakes, fail locally, speed up or slow down, change their "mind", modify their decisions, etc., along the way, without undermining the interaction. In order to make it possible, all those elements have to be recognized just for what they are.
Considerable work is currently ongoing, addressing those points and contributing to make this interaction easier and smoother; and we take part of it. We envision this work as a first step on which the project JointAction4HRI will be able to build a solid and comprehensive theoretical framework to help human-robot interaction design.
This is the way we are aiming to orient our research. We strongly believe that a human agent should be able to engage into an interaction with a robot in a natural way, with some social references she is familiar with, that she knows how to use and to deal with, and that are those she would use in a usual interaction with another human. Systematically identifying these references, understanding how they work together, adapting and integrating these social skills to the robot are the root constituents of the project JointAction4HRI.
Far beyond the "simplistic" anthropomorphic appearance or the "naive" human-mimicry that we could implement to the machine, what matters to us here are the key components and mechanisms underlying joint action, their informational content (relatively to the common ground in terms of general knowledge, acquired previously and during the task itself), and how they are linked together, temporarily, hierarchically and meaningfully. Our ambition is to contribute, at the most fundamental level, to the identification and characterization of the ingredients required for the successful realization of a collaborative task.
The JointAction4HRI project will address this goal through three objectives:
(1) Identifying the elements (and their interaction) that allow the establishment and maintenance of mutual understanding between a human and a robot in a collaborative task
(2) Modeling the notion of commitment that structures the relationship between two agents during interaction
(3) Elaborate and test robotics architecture design for collaboration with humans.
It proposes an original consortium composed of researchers from a philosophy laboratory (Institut Jean Nicod), a psychology laboratory (CLLE), and a robotics laboratory (LAAS). Each has contributed in their respective discipline and for several years to research in the joint action domain. By bringing their complementary expertise together, JointAction4HRI will foster the development of an integrated theoretical framework.
Expected benefits are obvious from the perspective of service or entertainment robotics development. But we can envision broader benefits. Thus, we expect that joint attention modeling will give us cues to help the evaluation and support of children with developmental disorders (e.g. autistic children). Confronting the roles of commitments in human-human interaction and in human-robot interaction should also shed new light on the current philosophical debate about commitments in joint action, helping to identify more precisely their essential properties as well as the nature of the social norms and emotions that ensure their efficiency.

 

ANR Programme: (DS0704) 2016

Project ID: ANR-16-CE33-0017

Project coordinator:
Monsieur Rachid Alami (Centre National de la Recherche Scientifique/LAAS)

Project web site: https://jointaction4hri.laas.fr/

 

Back to the previous page

 

The project coordinator is the author of this abstract and is therefore responsible for the content of the summary. The ANR disclaims all responsibility in connection with its content.