On Studying Human Teaching Behavior with Robots: a Review

Vollmer, Anna-Lisa; Schillingmann, Lars

doi:10.1007/s13164-017-0353-4

Cited by 14 publications

(9 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As was already the case for research on Reinforcement Learning (RL) for computational neurosciences Daw & Doya (2006), research on teachable autonomous agents from an AI perspective could be turned into research on computational modelling of developmental psychology and educational sciences phenomena. As put forward in Vollmer & Schillingmann (2018), using teachable agents or robots would help a lot performing studies about tutoring processes with strictly controlled experimental conditions from the side of the learner, which is not easy with children. However, for such studies to provide useful models of natural teaching between a tutor and a child, the robot or agent has to be a convincing model of a human learner.…”

Section: Prospects On Developmental Psychology and Educationmentioning

confidence: 99%

“…Finally, a teachable autonomous agent could be of interest in the context of practical education when embodied into a robot. Children are often fond of robots and a robotic teacher is a tool of interest for many reasons Vollmer & Schillingmann (2018). But a robotic learner can also be of interest for practical education in the context of learning by teaching, which as been shown to provide the best level of retention in children Leelawong & Biswas (2008); Biswas et al (2005); Zhu et al (2018); Gargot et al (2021).…”

Section: Prospects On Developmental Psychology and Educationmentioning

confidence: 99%

“…In order to ground our investigation in developmental science, we start from a classical work about the normal teaching of a child, namely "The role of tutoring in problem solving" Wood et al (1976). As put forward in Vollmer & Schillingmann (2018), there are numerous theories and guidelines on optimal teaching, but studies such as Wood et al (1976) on how teaching is done naturally are relatively scarce.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards Teachable Autotelic Agents

Sigaud¹,

Akakzia²,

Caselles-Dupré³

et al. 2021

Preprint

View full text Add to dashboard Cite

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 can be translated into the distinction between autonomous agents, which learn in isolation from their own signals, and interactive learning agents which can be taught by social partners but generally lack autonomy. In between should stand teachable autonomous agents: agents that learn from both internal and teaching signals to benefit from the higher efficiency of assisted discovery processes. Designing such agents could result in progress in two ways. First, very concretely, it would offer a way to non-expert users in the real world to drive the learning behavior of agents towards their expectations. Second, more fundamentally, it might be a key step to endow agents with the necessary capabilities to reach general intelligence. The purpose of this paper is to elucidate the key obstacles standing in the way towards the design of such agents. We proceed in four steps. First, we build on a seminal work of Bruner to extract relevant features of the assisted discovery processes happening between a child and a tutor. Second, we highlight how current research on intrinsically motivated agents is paving the way towards teachable and autonomous agents. In particular, we focus on autotelic agents, i.e. agents equipped with forms of intrinsic motivations that enable them to represent, self-generate and pursue their own goals. We argue that such autotelic capabilities from the learner side are key in the discovery process. Third, we adopt a social learning perspective on the interaction between a tutor and a learner to highlight some components that are currently missing to these agents before they can be taught by ordinary people using natural pedagogy. Finally, we provide a list of specific research questions that emerge from the perspective of extending these agents with assisted learning capabilities.

show abstract

Section: Prospects On Developmental Psychology and Educationmentioning

confidence: 99%

Section: Prospects On Developmental Psychology and Educationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Teachable Autotelic Agents

Sigaud¹,

Akakzia²,

Caselles-Dupré³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This need of an intuitive human-robot interaction can be approached from different directions. In current research, this problem is often approached by developing robotic systems simulating real humans' response and behavior and for example convincing users to have emotions (Breazeal et al, 2016;Vollmer & Schillingmann, 2018). While this approach reduces the cognitive load for users and at the same time increases the satisfaction on the user's side, it also raises problems (Breazeal et al, 2016;Duffy, 2006;Hegel et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Why robots should be technical: Correcting mental models through technical architecture concepts

Hindemith,

Vollmer,

Göpfert

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Research in social robotics is commonly focused on designing robots that imitate human behavior. While this might increase a user's satisfaction and acceptance of robots at first glance, it does not automatically aid a non-expert user in naturally interacting with robots, and might actually hurt their ability to correctly anticipate a robot's capabilities. We argue that a faulty mental model, that the user has of the robot, is one of the main sources of confusion. In this work we investigate how communicating technical concepts of robotic systems to users affects their mental models, and how this can increase the quality of human-robot interaction. We conducted an online study and investigated possible ways of improving users' mental models. Our results underline that communicating technical concepts can form an improved mental model. Consequently, we show the importance of consciously designing robots that express their capabilities and limitations.

show abstract

“…Here, we briefly review studies of human-robot-learning scenarios with real naive human users. Some related HRI studies test machine learning algorithms with humans users and examine how naive users naturally teach robots and how the robot's behavior impacts human teaching strategies (see Vollmer and Schillingmann, 2017 , for a review). In the area of concept learning for example, Cakmak and Thomaz ( 2010 ) and Khan et al ( 2011 ) studied how humans teach a novel concept to a robot.…”

Section: Introductionmentioning

confidence: 99%

A User Study on Robot Skill Learning Without a Cost Function: Optimization of Dynamic Movement Primitives via Naive User Feedback

Vollmer

Hemion

2018

Front. Robot. AI

Self Cite

View full text Add to dashboard Cite

Enabling users to teach their robots new tasks at home is a major challenge for research in personal robotics. This work presents a user study in which participants were asked to teach the robot Pepper a game of skill. The robot was equipped with a state-of-the-art skill learning method, based on dynamic movement primitives (DMPs). The only feedback participants could give was a discrete rating after each of Pepper's movement executions ("very good," "good," "average," "not so good," "not good at all"). We compare the learning performance of the robot when applying user-provided feedback with a version of the learning where an objectively determined cost via hand-coded cost function and external tracking system is applied. Our findings suggest that (a) an intuitive graphical user interface for providing discrete feedback can be used for robot learning of complex movement skills when using DMP-based optimization, making the tedious definition of a cost function obsolete; and (b) un-experienced users with no knowledge about the learning algorithm naturally tend to apply a working rating strategy, leading to similar learning performance as when using the objectively determined cost. We discuss insights about difficulties when learning from user provided feedback, and make suggestions how learning continuous movement skills from non-expert humans could be improved.

show abstract

On Studying Human Teaching Behavior with Robots: a Review

Cited by 14 publications

References 51 publications

Towards Teachable Autotelic Agents

Towards Teachable Autotelic Agents

Why robots should be technical: Correcting mental models through technical architecture concepts

A User Study on Robot Skill Learning Without a Cost Function: Optimization of Dynamic Movement Primitives via Naive User Feedback

Contact Info

Product

Resources

About