Studying the co-construction of interaction protocols in collaborative tasks with humans

Vollmer, Anna-Lisa; Grizou, Jonathan; Lopes, Manuel; Rohlfing, Katharina J.; Oudeyer, Pierre-Yves

doi:10.1109/devlrn.2014.6982983

Cited by 3 publications

(6 citation statements)

References 22 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This assumes that, if the architect were to act in the environment instead of the builder, it would be able to quickly figure out how to solve the task. This assumption is compatible with the CoCo game experiment (Vollmer et al, 2014) where humans participants, and in particular the architects, are known to have such world models.…”

Section: Problem Definitionsupporting

confidence: 52%

“…This work is inspired by experimental semiotics (Galantucci & Garrod, 2011) and in particular Vollmer et al (2014) that studied the CoCo game with human subjects as a key step towards understanding the underlying mechanisms of the emergence of communication. Here we take a complementary approach by defining and investigating solutions to the Architect-Builder Problem (ABP), a general formulation of the CoCo game where both agents are AIs.…”

Section: Related Workmentioning

confidence: 99%

“…Experimental Semiotics (Galantucci & Garrod, 2011), a line of work that studies the forms of communication that people develop when they cannot use pre-established ones, reveals that humans can even teach and learn without direct reinforcement signal, demonstrations or a shared communication protocol. Vollmer et al (2014) for example investigate a co-construction (CoCo) game experiment where an architect must rely only on arbitrary instructions to guide a builder toward constructing a structure. In this experiment, both the task of building the structure and the meanings of the instructions -through which the architect guides the builder -are simultaneously learned throughout interactions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning to Guide and to Be Guided in the Architect-Builder Problem

Barde¹,

Karch²,

Nowrouzezahrai³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We are interested in interactive agents that learn to coordinate, namely, a builder -which performs actions but ignores the goal of the task -and an architect which guides the builder towards the goal of the task. We define and explore a formal setting where artificial agents are equipped with mechanisms that allow them to simultaneously learn a task while at the same time evolving a shared communication protocol. Ideally, such learning should only rely on high-level communication priors and be able to handle a large variety of tasks and meanings while deriving communication protocols that can be reused across tasks. The field of Experimental Semiotics has shown the extent of human proficiency at learning from a priori unknown instructions meanings. Therefore, we take inspiration from it and present the Architect-Builder Problem (ABP): an asymmetrical setting in which an architect must learn to guide a builder towards constructing a specific structure. The architect knows the target structure but cannot act in the environment and can only send arbitrary messages to the builder. The builder on the other hand can act in the environment but has no knowledge about the task at hand and must learn to solve it relying only on the messages sent by the architect. Crucially, the meaning of messages is initially not defined nor shared between the agents but must be negotiated throughout learning. Under these constraints, we propose Architect-Builder Iterated Guiding (ABIG), a solution to the Architect-Builder Problem where the architect leverages a learned model of the builder to guide it while the builder uses self-imitation learning to reinforce its guided behavior. To palliate to the non-stationarity induced by the two agents concurrently learning, ABIG structures the sequence of interactions between the agents into interaction frames. We analyze the key learning mechanisms of ABIG and test it in a 2-dimensional instantiation of the ABP where tasks involve grasping cubes, placing them at a given location, or building various shapes. In this environment, ABIG results in a low-level, high-frequency, guiding communication protocol that not only enables an architect-builder pair to solve the task at hand, but that can also generalize to unseen tasks. * Equal contribution.† Work conducted while at Inria.

show abstract

Section: Problem Definitionsupporting

confidence: 52%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Guide and to Be Guided in the Architect-Builder Problem

Barde¹,

Karch²,

Nowrouzezahrai³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is likely however that children make use of the repertoire of frame they dispose of to understand new structures. This phenomenon becomes visible in adults (Vollmer et al, 2014 ). Thus, further adult–child experiments on interaction within new frames should shed light on this matter.…”

Section: Perspectives and Challenges For Future Researchmentioning

confidence: 99%

Pragmatic Frames for Teaching and Learning in Human–Robot Interaction: Review and Challenges

et al. 2016

Self Cite

View full text Add to dashboard Cite

One of the big challenges in robotics today is to learn from human users that are inexperienced in interacting with robots but yet are often used to teach skills flexibly to other humans and to children in particular. A potential route toward natural and efficient learning and teaching in Human-Robot Interaction (HRI) is to leverage the social competences of humans and the underlying interactional mechanisms. In this perspective, this article discusses the importance of pragmatic frames as flexible interaction protocols that provide important contextual cues to enable learners to infer new action or language skills and teachers to convey these cues. After defining and discussing the concept of pragmatic frames, grounded in decades of research in developmental psychology, we study a selection of HRI work in the literature which has focused on learning–teaching interaction and analyze the interactional and learning mechanisms that were used in the light of pragmatic frames. This allows us to show that many of the works have already used in practice, but not always explicitly, basic elements of the pragmatic frames machinery. However, we also show that pragmatic frames have so far been used in a very restricted way as compared to how they are used in human–human interaction and argue that this has been an obstacle preventing robust natural multi-task learning and teaching in HRI. In particular, we explain that two central features of human pragmatic frames, mostly absent of existing HRI studies, are that (1) social peers use rich repertoires of frames, potentially combined together, to convey and infer multiple kinds of cues; (2) new frames can be learnt continually, building on existing ones, and guiding the interaction toward higher levels of complexity and expressivity. To conclude, we give an outlook on the future research direction describing the relevant key challenges that need to be solved for leveraging pragmatic frames for robot learning and teaching.

show abstract

“…Parts Robot actions [19] manufacturing -pick, place [20] load sharing -collaborative hold [21], [22] buttons 3 press button [23] warehouse -pick, hold [24] sweeping -move [25] set table -pick, place [26] kitchen, set table -- [27] assembly 10 pick, pass [28] kitchen, set table -pick, place [29] assembly 5 (2) hold, pass [30] virtual -pick, place [31] assembly 40 (20) - [32] assembly -pick, place [33] warehouse -pick, place [34] manufacturing -pick, place [35] manufacturing -collaborative hold [4] assembly 5 (2) hold [2], [3] assembly 5 (4) pick, assemble [36] assembly 14 (6) - [37] assembly 8 - [38] assembly 14 (3) pick, place [39] assembly 12 (6) - [40] diaper change 2 pick, pass [41] manufacturing -hold [42] kitchen -pick, pass [43] assembly 3 - [44] assembly 5 pick, pass, hold [1], [45] assembly 4 (4) pick, place, pass, hold robotics [10], [11] or human-robot teamwork [12]. Further, a number of robotic platforms have been designed with the specific purpose of mitigating the issue by fostering robotics research on shared hardware (e.g.…”

Section: Domainmentioning

confidence: 99%

The HRC Model Set for Human-Robot Collaboration Research

Zeylikman

Widder

Roncone

et al. 2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

In this paper, we present a model set for designing human-robot collaboration (HRC) experiments. It targets a common scenario in HRC, which is the collaborative assembly of furniture, and it consists of a combination of standard components and custom designs. With this work, we aim at reducing the amount of work required to set up and reproduce HRC experiments, and we provide a unified framework to facilitate the comparison and integration of contributions to the field. The model set is designed to be modular, extendable, and easy to distribute. Importantly, it covers the majority of relevant research in HRC, and it allows tuning of a number of experimental variables that are particularly valuable to the field. Additionally, we provide a set of software libraries for perception, control and interaction, with the goal of encouraging other researchers to proactively contribute to our work.

show abstract

Studying the co-construction of interaction protocols in collaborative tasks with humans

Cited by 3 publications

References 22 publications

Learning to Guide and to Be Guided in the Architect-Builder Problem

Learning to Guide and to Be Guided in the Architect-Builder Problem

Pragmatic Frames for Teaching and Learning in Human–Robot Interaction: Review and Challenges

The HRC Model Set for Human-Robot Collaboration Research

Contact Info

Product

Resources

About